NeurIPS 2026 spotlights

Best rated first.

92%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightTsinghua Xiaomi Corporation Peking Institute of Automation, Chinese The Hong Kong University of Scie Vision-language-action models

Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation

Embodied chain-of-thought improves generalization when grounded in action guidance, and ERVLA uses reasoning-dropout supervision to avoid unstable autoregressive reasoning at inference, achieving state-of-the-art robot manipulation results.

Nan Sun, Yuan Zhang, Yongkun Yang, Wentao Zhao and 9 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

19/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 19 of 20 reviewers recommend it

lenient 5/5

medium 10/10

strict 4/5

92%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightOsnabrueck Osnabrück Universität Osnabrück U Osnabrück Bergische Universität Wuppertal Object detection

Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty

Re-annotation reveals object detection benchmarks miss up to 60% of objects due to incomplete labels, and current detectors remain misaligned with human perception.

Sarina Penquitt, Jonathan Klees, Antonia van Betteray, Parssa Jashnieh and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

19/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

91%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightMicrosoft U Wisconsin-Madison RL for LLMs

ECHO: Terminal Agents Learn World Models for Free

ECHO trains terminal agents to predict environment responses for dense supervision, doubling GRPO pass@1 on TerminalBench-2.0.

Vaishnavi Shrivastava, Ahmed Awadallah, Dimitris Papailiopoulos

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 7 on Hugging Face

– ReadersNo votes yet. 1 from authors or colleagues not counted

18/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 18 of 20 reviewers recommend it

lenient 5/5

medium 10/10

strict 3/5

91%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Toronto / Vector Institute Cornell BlankBio Memorial Sloan Kettering Cancer U Toronto Genomics & single-cell

mRNABench: A curated benchmark for mature mRNA property and function prediction

mRNABench benchmarks mature mRNA property predictions across 59 tasks and 135K experiments, revealing synergies between self-supervised objectives that yield a compact state-of-the-art Mamba model using 700x fewer parameters.

Ruian (Ian) Shi, Taykhoom Dalal, Philip Fradkin, Divya Koyyalagunta and 9 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

18/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

91%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightHunan U Hong Kong Mechanistic interpretability

CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models

CRAFT localizes arbitration and brake failure in medical vision-language models to disjoint attention head sets, enabling targeted interventions that reduce misleading text influence and restore abstention without retraining.

Chunzheng Zhu, Jiaqi Zeng, Hongbo Zhao, Yihang Chen and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

18/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

91%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Neuchatel U Neuchâtel Delft University of Technology IBM Research U Turin AI oversight & deception

Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails

LLaDA-Guard uses masked diffusion to score responses under each safety label and classify by difference, improving calibration, reducing over-defense, and enabling token-level risk localization with 60.7% prompt rewriting success.

Gert Lek, Abele Mălan, Chaoyi Zhu, Pin-Yu Chen and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

17/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

91%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightMicrosoft AI Microsoft RL for LLMs

Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use

CARL assigns segment-level reinforcement learning credit at tool-use boundaries to teach models when external tools are needed, improving accuracy by up to 9.7 points while cutting unnecessary calls by 53%.

Abhijit Kumar, Zoey WU, Mohit Suley

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

17/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

91%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightSUN YAT-SEN UNIVERSITY Shenzhen Shenzhen Institutes of Advanced Alibaba Group Shenzhen MSU-BIT Segmentation

SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization

SIGMA uses semantic feature differencing with instruction-guided spatial priors to generate manipulation masks from edited images, producing a 1.1M training set that improves detectors by +18.34% F1.

Peiyu Zhuang, Jianquan Yang, Haodong Li, Zhuoying Cai and 5 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

17/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

89%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Melbourne U Wisconsin-Madison AI oversight & deception

Combating Data Laundering in LLM Training

Data laundering transforms proprietary data to hide LLM training traces, and Synthesis Data Reversion restores detection by synthesizing likely transformed queries via goal-detail abstraction.

Muxing Li, Zesheng Ye, Sharon Li, Feng Liu

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 2/5

89%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightGoogle DeepMind U California, San Diego U Waterloo Stanford; Noeri AI Tencent LLM agents & planning

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Direct corpus interaction uses terminal tools to search raw corpora directly, bypassing fixed retrieval interfaces and substantially outperforming sparse, dense, and reranking baselines on agentic search benchmarks.

Zhuofeng Li, Haoxiang Zhang, Cong Wei, Pan Lu and 14 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 125 on Hugging Face · Code ★ 408

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 2/5

89%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightUK AI Security Institute Anthropic Alan Turing Institute U Oxford The Alan Turing Institute Backdoors & data poisoning

Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

Poisoning LLM pretraining requires only ~250 malicious documents regardless of dataset or model scale, revealing constant-cost backdoor injection risks for large models.

Alexandra Souly, Javier Rando, Ed Chapman, Xander Davies and 9 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 5 on Hugging Face

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 4/5

89%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightNanyang Technological Shanghai Jiaotong Microsoft Shanghai Jiao Tong College of Computing and Data Sc Pose & motion

The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction

ViDiHand leverages pretrained video diffusion models to reconstruct 4D hand poses directly from full egocentric video without detectors, substantially outperforming prior methods on ARCTIC, HOT3D, and HOI4D.

Yuxi Wang, Chengkai Jin, Yufei Liu, Wenqi Ouyang and 5 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 9 on Hugging Face · Code ★ 187

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

89%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Cambridge Diffusion models

Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization

Recursive diffusion training converges geometrically to a unique Gaussian-smoothed mixture limit via early-stopping drift, attenuating high-order spectral modes, with annealed truncation schedules asymptotically preventing collapse.

Nail B Khelifa, Richard Turner, Ramji Venkataramanan

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

89%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightAnhui Polytechnic SUN YAT-SEN UNIVERSITY Nanyang Technological Nanyang Technology University, S Vision-language models

Text as Partial Constraint: Core–Residual Alignment for Robust Vision–Language Learning

TPC treats captions as partial constraints, aligning vision-language representations to a consensus semantic core while penalizing dependence on unsaid residuals, yielding robust zero-shot recognition and improved LVLM grounding.

Chengzhen Yu, Canran Xiao, SiYuan Ma, Yang Liu

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Chicago Princeton Web & GUI agents

Mecha-nudges for Machines

Mecha-nudging changes online choice environments to systematically influence AI agents without harming human usability, and Etsy listings show a 0.143-bit rise in machine-usable information after ChatGPT's release.

Giulio Frey, Kawin Ethayarajh

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 1 on Hugging Face

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 15 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 3/5

88%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightThe Cyprus Institute NCSR Demokritos U Oxford U Athens & Archimedes AI, At Cyprus Institute Sparse autoencoders

fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery

Standard crosscoders learn layer-localized features; fmxcoders use factorized weights and layer masking to recover cross-layer features, improving coherence and reconstruction across four LLMs.

Andreas D Demou, Panagiotis Koromilas, James Oldfield, Yannis Panagakis and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 15 of 20 reviewers recommend it

lenient 3/5

medium 9/10

strict 3/5

88%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Cambridge Alignment & preference optimization

Don't Lose Focus: Activation Steering via Key-Orthogonal Projections

SKOP constrains harmful attention rerouting by preserving focus-token attention during steering, reducing utility degradation 5-7x at over 95% steering efficacy.

Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightCzech Technical University of Pr Czech Technical Univeresity in P Czech Technical Univeresity in P Czech Techical Datasets & benchmarks

Doomed to Re-Annotate, Forever: The ImageNet Story

ReImageNet reveals ~12% of ImageNet-1k labels are wrong and reannotation boosts top-1 accuracy up to 1.2% for supervised models and 5, 6% for MLLMs.

Illia Volkov, Nikita Kisel, Tetiana Mishkina, Klara Janouskova and 1 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026 · ▲ 3 on Hugging Face

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightCenter of Computational Neurosci New York Harvard Google DeepMind Training dynamics

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent

A representation-readout decomposition attributes grokking and double descent to competing encoder and classifier dynamics, showing delayed generalization stems from gradual representation learning rather than lazy-to-rich transitions.

Chi-Ning Chou, Oscar Uzdelewicz, Neng-Chun Chiu, Yao-Yuan Yang and 1 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Bristol Mila/École de technologie supéri Microsoft Research McGill U Calgary Probing & representation analysis

The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show

Video diffusion transformers encode physical plausibility linearly in latent states around 81% accuracy despite lacking predictive training, emerging inside the denoiser rather than the VAE.

Parsa Esmati, Somjit Nath, Katja Hofmann, Derek Nowrouzezahrai and 2 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 1 on Hugging Face

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightPeking Microsoft Research, New England LLM evaluation & benchmarks

Calibration without Ground Truth

A label-free framework improves miscalibrated models using better-calibrated references, guaranteeing strict loss reduction without ground-truth labels via Bregman projection.

Yuqing Kong, Mingyu Song, Yizhou Wang, Yifan Wu

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightThe Hong Kong Polytechnic The Hong Kong University of Scie U California, Berkeley Hong Kong Polytechnic ByteDance Inc.LLM agents & planning

VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries

VisInteract introduces interactive text-to-visualization with imperfect queries via VisInteract-Bench and Vis-MCTS, boosting success by over 13% versus interactive baselines.

Wenxin XU, Jinwei Lu, Hwanhee Kim, Chen J Zhang and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightUC San Diego Shanghai Jiaotong U Science and Technology of Chin JD.com Zhejiang Video-language models

AdaCodec: A Predictive Visual Code for Video MLLMs

AdaCodec uses predictive visual codes to send full reference frames only when unpredictable, cutting video MLLM tokens by 7x while improving long-video benchmark scores and reducing latency.

Haowen Hou, Zhen Huang, Zheming Liang, Qingyi Si and 7 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 7 on Hugging Face

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightNanyang Technological HKUST The Hong Kong University of Scie Segmentation

AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation

AdapToPASS is a bio-inspired spherical transformer that adaptively models contextual and geometric ambiguities to achieve robust panoramic semantic segmentation, outperforming state-of-the-art methods by up to 18.77% relative mIoU under unseen spherical transformations.

Soumyaratna Debnath, weiming zhang, Shriram Damodaran, Dingwen Xiao and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

NeurIPS 2026SpotlightTechnion Technion - Israel Institute of T Electrical Engineering Departmen Nvidia INRIA Unified multimodal models

MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image

MulTaBench benchmarks 40 multimodal tabular datasets and shows target-aware tuning of text and image embeddings improves predictive performance over frozen embeddings.

Alan Arazi, Eilam Shapira, Shoham Grunblat, Mor Ventura and 7 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026 · ▲ 142 on Hugging Face

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Only vote on papers you've read. Sign in with GitHub to vote.

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightJohns Hopkins Massachusetts Institute of Techn Harvard the Kempner Institute for the St Google Deepmind / Harvard Pose & motion

MoSE3: Learning World-Space SE(3) at Every Pixel

MoSE3 predicts dense per-pixel world-space SE(3) motion from monocular video via point tracks and rigidity embeddings, achieving state-of-the-art 6-DoF estimation and 3D tracking.

Jiahuan Cheng, Zhiyi Li, Tian Xia, Ruojin Cai and 2 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 1 on Hugging Face

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 14 of 20 reviewers recommend it

lenient 4/5

medium 7/10

strict 3/5

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightCMU, Carnegie Mellon Carnegie Mellon 3D vision & reconstruction

Point4D: Long-range 4D Motion Reconstruction

Point4D infers dense 3D point trajectories across multi-hundred-frame videos via a decoupled query-based motion decoder, outperforming prior short-window feed-forward 4D methods.

Minsik Jeon, Jay Karhade, Deva Ramanan, Shubham Tulsiani

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 14 of 20 reviewers recommend it

lenient 4/5

medium 9/10

strict 1/5

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightFudan Hong Kong University of Science Mila / Université de Montréal City University of Hong Kong Hong Kong University of Science Deep RL

Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions

Gaussian trust region reshaping replaces monotonic divergence penalties with bounded non-monotonic constraints, unlocking efficient behavior transitions in non-stationary reinforcement learning.

Bingxu Liu, Jiashun Liu, Johan Obando Ceron, Hao Wang and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 14 of 20 reviewers recommend it

lenient 4/5

medium 9/10

strict 1/5

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightNational Taiwan University / CyC National Taiwan University Appier National Taiwan Jailbreaks & red teaming

Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs

Expected Harm weights jailbreak severity by execution likelihood to reveal inverse risk calibration, where models over-refuse costly threats yet remain vulnerable to cheap, high-likelihood attacks that double jailbreak success.

Yen-Shan Chen, Zhi Rui Tam, Cheng-Kuang Wu, Yun-Nung (Vivian) Chen

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 21 on Hugging Face

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 14 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 2/5

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU California, Berkeley UC Berkeley, Transluce AI Multi-agent LLM systems

Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems

Simple norm enforcement for AI agents is exploited for competitive gain, but mechanisms tracking reliability with escalating penalties resist exploitation across multi-agent environments.

Yaowen Ye, Jacob Steinhardt

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 14 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 1/5

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightGenesis Molecular AI MIT Massachusetts Institute of Techn Genesis Therapeutics Genesis Molecular AI Flow matching

Few-Step Cofolding with All-Atom Flow Maps

DeCAF distills all-atom biomolecular cofolding diffusion models into few-step flow maps with SE(3)-aligned endpoint losses, improving accuracy and physical validity at strict inference budgets.

Gianluca Scarpellini, Ron Shprints, Peter Holderrieth, Juno Nam and 6 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightEPFL U Michigan, Ann Arbor USI TU Wien, AITHYRA, University of KAIST LLM reasoning & chain of thought

MUX: Continuous Reasoning via Multiplexed Tokens

MUX compresses reasoning into continuous multiplexed tokens via lossless superposition, accelerating reasoning and outperforming latent baselines across 32 settings.

Ayhan Suleymanzade, Halil Alperen Gozeten, Michael Bronstein, Ismail Ilkan Ceylan and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightSUN YAT-SEN UNIVERSITY Sun Yat-Sen Sun Yat-sen Zhejiang China University of Mining and T Time series classification & imputation

TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning

TSQAgent uses collaborative agent roles and external analytical tools to automatically identify relevant time series quality dimensions and perform quantitative comparisons, substantially improving LLM assessment and downstream data selection.

Shunyu Wu, Dan Li, Haozheng Ye, Weibin Feng and 5 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightApple Alignment & preference optimization

Theoretical Limits of Language Model Alignment

Optimal alignment gains follow a Jeffreys-divergence limit, best-of-N approaches it, and reward hacking grows with error while ensembling mitigates it.

Lucas Monteiro Paes, Natalie Mackraz, Barry-John Theobald, Federico Danieli

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightCMU, Carnegie Mellon Department of Computer Science, U Washington Google U North Carolina at Chapel Hill Pose & motion

MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction

MolmoMotion predicts goal-conditioned 3D point trajectories from visual history and language, outperforming baselines on PointMotionBench and improving robot manipulation and video synthesis.

Jianing Zhang, Chenhao Zheng, Yajun Yang, Rustin Soraki and 6 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 53 on Hugging Face · Code ★ 151

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightMcGill U Tennessee, Knoxville McGill & MBZUAI California Institute of Technolo MBZUAI Navigation & SLAM

GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning

GeoWind2Plan predicts mission-time 3D urban wind via neural operators to enable energy-efficient UAV planning in seconds, reducing energy by up to 12.7% versus wind-agnostic paths.

Shaoxiang Qin, Xiongye Xiao, Yucheng Zhao, Fuyuan Lyu and 5 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Zurich Ecole Polytechnique Paris / Tech Graz University of Technology Molecules & drug discovery

Generating Physically Consistent Molecules with Energy-Based Models

EBMol learns atom-additive scalar potentials via flow-inspired restoring field matching to generate physically consistent 3D molecules with state-of-the-art results.

Christoph Griesbacher, Lea Bogensperger, Andreas Habring, Thomas Pock

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

86%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightMassachusetts Institute of Techn MIT Diffusion models

The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler

Matching full posterior covariance in Gaussian DDPMs reduces path-KL error to O(1/T²), and the matrix-free Lanczos Gaussian sampler achieves this with exponentially decaying approximation error using only Jacobian-vector products.

Sahil Akhtar, Aymane El Gadarri, Vivek Farias, Adam Jozefiak

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightSoutheast Nanjing University of Informatio Ant Group Efficient inference & serving

TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding

TreeGraft combines small and large drafters with a scheduler to build shared draft trees, boosting speculative decoding by 15.1% over single-drafter methods.

Jiaming Fan, Daming Cao, Canchen Huang, Jiale Fu and 5 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightTechnion - Israel Institute of T Technion - Israel Institute of T IT University of Copenhagen Graph neural networks

Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them

For every k, k-WL fails to distinguish some non-isomorphic simple-spectrum graphs, so PRiSM provides the first complete canonicalization of their eigendecompositions to enable universal approximation.

Snir Hordan, Nadav Dym, Tim Seppelt

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightTelepath The Sequel Institute New York NYU Representation & contrastive learning

Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks

Prospective bottom-up inputs via two-tap updates mitigate depth-dependent gradient attenuation in deep continuous-time recurrent networks, boosting RQF accuracy on Speech Commands and Path-X.

Shivang Rawat, Mirko Morello, Flaviano Morone, David Heeger

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightKorea Advanced Institute of Scie KAIST KRAFTON U California, Los Angeles Stanford AutoML & architecture search

AMUSE: Anytime Muon with Stable Gradient Evaluation

AMUSE integrates Muon's rapid bulk progress with Schedule-Free averaging via time-varying interpolation to suppress oscillations, requiring no learning rate schedules and improving training efficiency across vision and LLM tasks.

Jueun Kim, Baekrok Shin, Jihun Yun, Beomhan Baek and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightHong Kong Polytechnic Department of Computer Science a Zhejiang U Technology Sydney The Hong Kong Polytechnic Model merging

FeatCal: Feature Calibration for Post-Merging Models

FeatCal reduces post-merging feature drift via layer-wise closed-form weight calibration without gradients, outperforming Surgery and ProbSurgery on CLIP and GLUE benchmarks.

Yanggan Gu, Shuo CAI, Zihao Wang, Wenjun Wang and 6 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Electronic Science and Technol Graph neural networks

Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting

Pre-trained GNNs exhibit spectral bias favoring large singular values, and SRP reverses this via spectral masking and null-space augmentation for state-of-the-art graph prompting.

Hanxu Yang, Yuhuan Zhao, Xiaodong He, Zhao Kang

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightZhejiang Efficient inference & serving

Beyond Selection: Token Parameterization for Extreme Visual Token Compression

Braco separates token compression into basis truncation and coordinate organization via coupled compressibility and learnability objectives, achieving 95.2% accuracy at up to 144x compression with 84-87% lower prefill FLOPs and up to 36% speedup.

Rui Zhong, YU LI, Zheyu Yan, Cheng Zhuo

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 7 on Hugging Face · Code ★ 2

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightStony Brook State University of New York at Adelaide Vision-language models

OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following

OmniGF unifies multi-person gaze following via dual-branch vision-language decoding with head embeddings, achieving state-of-the-art spatial, semantic, and social gaze reasoning.

Qiaomu Miao, Haoyu Wu, Jingyi Xu, Minh Hoai and 1 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 0/5

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightTechnion Technion and Google Research Technion - Israel Institute of T Technion -- Israel Institute of Learning theory

Strategic PAC Learnability via Geometric Definability

Strategic classification can make VC dimension 1 problems unlearnable, but geometric definability via first-order formulas over real exponentiation preserves learnability with controlled sample complexity.

Yuval Filmus, Shay Moran, Elizaveta Nesterova, Nir Rosenfeld and 1 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 3/5

medium 6/10

strict 3/5

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightUT Austin U Texas, Austin The University of Texas at Austi U Texas at Austin U.S. DEVCOM Army Research Labora Quantization

CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization

CoreQ proposes a learning-free post-training quantization framework using a geometric closed-form layer-adaptive mismatch correction coefficient and successive rounding to improve LLM quantization accuracy without hyperparameter tuning.

Seohyeon Cha, Huancheng Chen, Dongjun Kim, Haoran Zhang and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 0/5

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightMIT Google The Institute for Bird Populatio Automated scientific discovery

Targeted Review for AI-Assisted Biodiversity Surveys: Active Continuous-Score Occupancy Modeling

ACORN strategically selects ML predictions for expert review to optimize occupancy model inference, recovering ecological conclusions near fully human-labeled levels with far fewer reviews.

Timm Haucke, Lauren Harrell, Justin Kay, Mary K Clapp and 1 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 0/5

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Massachusetts Amherst Adobe Research Boston UMass Amherst U Massachusetts, Amherst Mechanistic interpretability

The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching

Activation patching's natural indirect effect embeds hidden interaction effects between components, which cause conditional importance to be invisible or inflated, explain faithfulness instability, scale with activation distance, and diagnose when greedy component ranking misses combinatorial mechan

Sankaran Vaidyanathan, David Arbour, Aaron Mueller, Scott Niekum and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 2/5

medium 7/10

strict 3/5

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightU Amsterdam Explainable AI

Hyperbolic Concept Bottleneck Models

HypCBM grounds concept bottlenecks in hyperbolic space via asymmetric geometric containment to yield sparse, hierarchy-aware activations and coherent interventions without extra supervision.

Daniel Uyterlinde, Swasti S Mishra, Pascal Mettes

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 0/5

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightShanghai Jiaotong California Institute of Technolo Representation & contrastive learning

Winfree Oscillatory Neural Network

Winfree Oscillatory Neural Network applies generalized synchronization dynamics to vision and reasoning tasks, scaling to ImageNet-1K and achieving 80.1% Maze-hard accuracy with 1% of prior parameters.

Jiawen Dai, Yue Song

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

NeurIPS 2026Spotlightnanjing university Tencent Youtu Lab Tencent YouTu Lab Youtu Lab, Tencent Nanjing Diffusion models

L2P: Unlocking Latent Potential for Pixel Generation

L2P transfers pre-trained latent diffusion models to pixel space via frozen intermediate layers and synthetic data, enabling efficient 4K generation with near-source performance.

Zhennan Chen, Junwei Zhu, Xu Chen, Jiangning Zhang and 6 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 36 on Hugging Face · Code ★ 195

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightHarvard Yonsei University Colleg Yonsei Cancer Center Zhejiang Mohamed bin Zayed University of Multi-agent LLM systems

CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support

CoMMa is a decentralized multi-agent oncology framework using partitioned data, specialized fine-tuning, and deterministic contribution-aware aggregation to enable interpretable, privacy-preserving decision support across diverse clinical settings.

Yichen WU, Yujin Oh, Sangjoon Park, Kailong Fan and 9 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightVirginia Polytechnic Institute a Washington University, Saint Lou AI policy & governance

Budgeting Discretion: Theory and Evidence on Street-Level Decision-Making

Formalizing discretion as a dynamic budget problem yields time-dependent override thresholds and shape-dependent spending rates, with homelessness data showing budget-constrained discretionary patterns.

Gaurab Pokharel, Sanmay Das, Patrick J Fowler

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightDeel, ANITI, Université Paul Sab Apple U Cambridge Massachusetts Institute of Techn Apple MLR Unified multimodal models

The Design Space of Tri-Modal Masked Diffusion Models

A tri-modal masked diffusion model pretrained from scratch on text, image-text, and audio-text data achieves strong cross-modal generation and introduces an SDE-based batch-size reparameterization.

Louis Bethune, Victor Guilherme Turrisi da Costa, Bruno Mlodozeniec, Pau Rodriguez and 20 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 4 on Hugging Face

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightDEEPNOID Inc.DEEPNOID Flow matching

STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation

STREAM applies Riemannian flow matching to histopathology VFM patch-token features on the hypersphere to avoid conditioning collapse, achieving state-of-the-art synthetic image generation via a stochastic bridge and anisotropic decoder.

Won June Cho, Daeky Jeong, Hyeongyeol Lim, Hongjun Yoon

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightHCP - Sun Yat-sen SUN YAT-SEN UNIVERSITY The Hong Kong University of Scie Pengcheng Laboratory U Technology Sydney Multimodal reasoning

Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains

SR-MCR aligns multimodal reasoning via intrinsic process rewards and a critic-free GRPO objective, achieving 81.4% average accuracy across visual benchmarks.

jusheng zhang, Ningyuan Liu, Kaitong Cai, Sidi Liu and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightHarvard Qube Research and Technologies American University of Beirut Privacy

Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy

For binary hypothesis testing under local differential privacy, optimal mechanisms sort inputs by likelihood ratio, partition into contiguous blocks, and apply randomized response to block labels, enabling exact O(k³)-time computation via dynamic programming.

Elena Ghazi, Jawad Nasser, Flavio Calmon, Ibrahim Issa

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightNew York Stanford Rutgers Amazon New York University, Meta Video generation

Solaris: Building a Multiplayer Video World Model in Minecraft

Solaris introduces a multiplayer video world model and automated data system for Minecraft, collecting 12.64M frames to enable consistent multi-agent simulation via staged training that outperforms single-player baselines.

Oscar Michel, Georgy Savva, Daohan Lu, Suppakit Waiwitlikhit and 6 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightKAIST AI UNIST Ewha Womans Learning theory

Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality

BROT estimates optimal transport maps via barycentric regression with deep networks, achieving minimax optimal convergence rates under Lipschitz conditions with stable training.

Kunwoong Kim, Insung Kong, Yongdai Kim

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightETH Zurich EPFL Technische Universität München Optimization

Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success

Muon achieves optimal heavy-tailed sample complexity with dimension-independent convergence for nuclear-norm stationarity, unlike Euclidean methods.

Florian Hübler, Thomas Pethick, Suvrit Sra

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it

lenient 3/5

medium 5/10

strict 3/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU Oxford Deep learning theory

Understanding Sample Efficiency in Predictive Coding

Predictive coding improves sample efficiency over backpropagation via higher target alignment, especially in deep, narrow, and pre-trained networks.

Gaspard Oliviers, Elene Lominadze, Rafal Bogacz

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it

lenient 4/5

medium 6/10

strict 1/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightBytedance Seed; The University o The Australian National Peking Renmin University of China Chinese University of Hong Kong LLM pretraining & scaling laws

Continuous Latent Diffusion Language Model

Cola DLM is a hierarchical latent diffusion language model using continuous latent priors and block-causal DiTs to achieve scalable non-autoregressive text generation. It demonstrates strong scaling behavior and quality competitive with matched autoregressive baselines across benchmarks.

Hongcan Guo, Qinyu Zhao, Yian Zhao, Shen Nie and 7 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 86 on Hugging Face · Code ★ 293

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it

lenient 3/5

medium 7/10

strict 1/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightMIT Massachusetts Institute of Techn Speech synthesis

Reconstructing the Vocal Tract with Differentiable Acoustic Simulation

A differentiable GPU acoustic simulator reconstructs vocal tract geometry from speech via gradient descent, enabling cross-lingual autoencoding and unpaired MRI reconstruction.

Eric Chen, Jin Woo Lee, Vincent Sitzmann

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it

lenient 5/5

medium 4/10

strict 2/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightUT Austin | Google DeepMind The University of Texas at Austi U Texas at Austin Google Nanyang Technological Multi-agent RL

ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork

ROTATE reformulates ad hoc teamwork as open-ended adversarial training between an agent and teammate generator to probe collaboration deficiencies, substantially improving generalization to unseen partners.

Caroline Wang, Muhammad Arrasy Rahman, Benjamin Nativi, Johnny Liu and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU California, Davis Mechanistic interpretability

OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting

OceanCBM is a concept bottleneck model that predicts ocean heat content through physically derived intermediate concepts, yielding consistent interpretable representations without sacrificing predictive skill.

Sanah Suri, Kieran Ringel, Maike Sonnewald

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Spotlight北京大学 Peking University/UT Southwester Peking Model-based RL

Planning as Dynamics Relaxation: Hippocampal Recurrent Network Realizes Optimal Goal-Directed Navigation

Hippocampal recurrent networks achieve optimal navigation via relaxation dynamics equivalent to linearly-solvable Markov decision processes.

宇航他, Junfeng Zuo, Tianhao Chu, Si Wu

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU Wisconsin-Madison U Wisconsin - Madison Learning theory

Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals

Multiclass linear classification under Gaussian marginals achieves polynomial-time robust learning via pairwise and localization frameworks, yielding near-optimal error bounds and exposing perceptron limitations.

Ilias Diakonikolas, Giannis Iakovidis, Mingchen Ma

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightHigher School of Economics Institute of Science and Technol IST Austria Aril Computer ETH Zurich Quantization

Grid Games: The Power Of Multiple Grids for Quantizing Large Language Models

Multiple grids per group improve 4-bit quantization by selecting better grids per group, consistently boosting accuracy over single-grid FP4 for weights and activations.

Vage Egiazarian, Erik Schultheis, Andrei Panferov, Earl Killian and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightUniversität Tübingen Universtity of Tübingen Eberhard-Karls-Universität Tübin U Tübingen Machine unlearning

Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs

JensUn uses Jensen-Shannon divergence to achieve stable, robust LLM unlearning with preserved utility and strong resistance to relearning.

Naman Deep Singh, Maximilian Mueller, Amit Peleg, Francesco Croce and 1 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightTélécom Paris CEA Sorbonne Université - Faculté de Diffusion models

Diff-CA: Separating Common and Salient Factors with Diffusion Models

Diff-CA conditions diffusion models to decompose image representations into common and salient factors via weak supervision, achieving high-fidelity contrastive generation and editing with provable factorization identifiability.

Michaël Soumm, Alexandre Fournier Montgieux, Yunlong HE, Pietro Gori and 1 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightKling AI ByteDance Inc.Canva Nanjing Kuaishou Technology Video generation

Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE

SplitMoE replaces uniform token-wise routing with split semantic and generic experts, improving video diffusion convergence, routing coherence, and generation quality over load-balanced MoEs.

Yu Xu, Yuxin Zhang, Xiao Yang, Haotian Yang and 6 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 6 on Hugging Face

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU California, Los Angeles Computer Science Department, Uni UCLA Bandits & online learning

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability

Forward-KL-regularized offline contextual bandits achieve epsilon^{-1} sample complexity under single-policy concentrability via pessimism, with matching lower bounds showing slow rates at weak regularization.

Qingyue Zhao, Kaixuan Ji, Heyang Zhao, Quanquan Gu

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightKAIST Mechanistic interpretability

FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping

FiTS introduces frequency-selective, temporally shaped spiking neurons that improve feedforward SNN accuracy on auditory tasks while yielding interpretable frequency and timing organization.

Jongmin Choi, Joon Son Chung

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightNew York Basis Sakana AI 3D generation

Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes

Dream-Cubed introduces a billion-scale Minecraft voxel dataset and diffusion models that generate interactive 3D worlds directly from block tokens with inpainting and outpainting support.

Tim Merino, Sam Earle, Ryunosuke Iwai, Julian Togelius and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it

lenient 5/5

medium 3/10

strict 2/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU Minnesota - Twin Cities U Minnesota Diffusion models

UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction

UDT is a U-Net diffusion transformer using data-adaptive token merging for downsampling and upsampling that outperforms existing U-Net DiTs, achieves comparable performance to REPA, and reaches FID 1.35 with faster convergence.

Junno Yun, Yasar Utku Alcalar, Mehmet Akcakaya

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it

lenient 2/5

medium 7/10

strict 1/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightPeking Computer Science and Technology,DeepSeek AI DeepSeek Tsinghua Multimodal reasoning

Thinking with Visual Primitives

Thinking with Visual Primitives interleaves spatial markers into chain-of-thought reasoning to close the reference gap, achieving frontier-level visual QA with extreme token efficiency.

Ruijie Lu, Yiyang Ma, Xiaokang Chen, Lingxiao Luo and 4 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it

lenient 4/5

medium 5/10

strict 1/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightTianjin Nanyang Technological Nanjing University of Aeronautic Vision-language models

Neural‑Visual Decoding via Cognitive‑guided Adaptive Blurring and Information‑Constrained Alignment

CAIA improves EEG visual decoding by cognitively guided adaptive blurring and information-constrained alignment, significantly boosting zero-shot brain-to-image retrieval accuracy.

Fan Yin, Chuhang Zheng, Peiliang Gong, Donghai Guan and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightXi'an Jiaotong Tencent Hunyuan SEA AI LAB Tencent Deep RL

Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models

Flow-DPPO replaces PPO ratio clipping with exact KL divergence constraints for flow matching models, improving reward, stability, and multi-objective alignment.

Bowen Ping, Xiangxin Zhou, Penghui Qi, Minnan Luo and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 42 on Hugging Face

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU Hong Kong South China University of Techno Nanyang Technological Tencent 3D generation

Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation

BDF transforms mesh connectivity into continuous surface signals for diffusion models, enabling higher-quality, scalable native 3D mesh generation.

Gaochao Song, Haohan Weng, Luo Zhang, Zibo Zhao and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightNankai Monash Shanghai Jiaotong Fudan Shanghai Jiao Tong LLM evaluation & benchmarks

IndustryCode: A Benchmark for Industry Code Generation

IndustryCode is a multi-domain, multi-language benchmark of 579 industrial coding sub-problems; Claude 3.5 Opus reaches 68.1% sub-problem and 42.5% main-problem accuracy.

Puyu Zeng, Zhaoxi Wang, Zhixu Duan, Liang Feng and 7 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightHSLU Learning theory

Nearly Optimal Robust Covariance and Scatter Matrix Estimation Beyond Gaussians

A polynomial-time algorithm robustly estimates elliptical scatter matrices with nearly optimal samples and error beyond Gaussians.

Gleb Novikov

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

76%Highly rated

NeurIPS 2026SpotlightInstitute of Information Enginer Institute of Information Enginee JD.com U the Chinese Academy of Science Institute of Information Enginee RL for LLMs

In high-compute, data-scarce pretraining, removing filters and using all data improves large models by letting them learn from nominally poor data.

Christopher Mohri, John Duchi, Tatsunori Hashimoto

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 1 on Hugging Face

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 9 of 20 reviewers recommend it

lenient 4/5

medium 4/10

strict 1/5

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU Oregon Google Purdue Adobe Research Test-time compute

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion

Orthrus unifies autoregressive and diffusion views in transformers to enable lossless parallel token generation with up to 7.8x speedup and O(1) memory overhead.

Van Chien Nguyen, Chaitra Hegde, Van-Cuong Pham, Ryan Rossi and 2 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 12 on Hugging Face · Code ★ 482

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU Washington U Texas at Dallas Hankuk University of Foreign Stu UW Unified multimodal models

SceneBind: Binding What and Where Across Vision, Audio, and Language

SceneBind binds vision, audio, and language via semantic-spatial entities and matching to achieve state-of-the-art cross-modal scene retrieval and spatial grounding.

Mingfei Chen, Zijun Cui, Ruoke Zhang, Hyeonggon Ryu and 1 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightZhejiang Harvard Electrical Engineering & Com U California, Berkeley Flow matching

World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories

World Motion Models unify dynamic 3D entities via sparse SE(3) trajectories and flow-matching, enabling any-to-any conditioning across prediction, control, and retargeting tasks.

Jiahui Lei, Qianqian Wang, Trevor Darrell, Angjoo Kanazawa

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightGoogle Research AGH University, Poland Optimization

Polynomial-Time Algorithm for Thiele Voting Rules with Voter Interval Preferences

A polynomial-time algorithm computes optimal Thiele committees for voter-interval preferences via a concavity theorem and Lagrangian relaxation.

Pasin Manurangsi, Krzysztof Sornat

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightCentral Institute of Mental Heal Ruprecht-Karls-Universität Heide IWR, Heidelberg Time series forecasting

Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction

DEER with generalized teacher forcing trains recurrent networks in parallel time to learn nonlinear dynamics on long sequences, outperforming linear state-space models for systems with long time scales.

Florian Hess, Florian Götz, Daniel Durstewitz

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightNagoya Nagoya University / RIKEN Optimization

Post-ADC Inference: Valid Inference After Active Data Collection

Post-ADC inference provides valid p-values and confidence intervals for data-dependent targets after active data collection by correcting adaptive sampling and selection biases without assuming the black-box function form.

Shuichi Nishino, Tomohiro Shiraishi, Teruyuki Katsuoka, Ichiro Takeuchi

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightColumbia Columbia University in the City Domain adaptation

Environment-Robust Representation Learning with Empirical Bayes

A Bayesian model with cross-environment balancing learns environment-robust latent representations that improve prediction across unseen settings.

Yuli Slavutsky, Matthew Shen, Bohan Wu, David Blei

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 8 of 20 reviewers recommend it

lenient 5/5

medium 2/10

strict 1/5

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightAmazon Seoul National Efficient attention & state-space models

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection

CompactAttention accelerates chunked prefill via block-union KV selection that builds minimal per-group block tables to eliminate KV copy overhead, achieving up to 2.72x attention speedup with near-dense accuracy on 128K contexts.

Jiwon Song, Dongwon Jo, Beomseok Kang, jae-joon kim

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 12 on Hugging Face · Code ★ 7

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU Wisconsin-Madison U Wisconsin - Madison UCSD Computer Science and Engineering Learning theory

Testable Learning of General Halfspaces under Massart Noise

A testable learning algorithm learns general Massart halfspaces under Gaussian marginals with quasi-polynomial complexity matching SQ lower bounds.

Ilias Diakonikolas, Giannis Iakovidis, Daniel Kane, Sihan Liu

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightNortheastern U Texas at Austin UT Austin Learning theory

Optimal Recalibration of an Online Predictor

An online algorithm achieves optimal ε-recalibration with ε² excess error in ε⁻³ rounds via Blackwell approachability, and yields simultaneous calibration and calibeating for smooth losses.

Lunjia Hu, Kevin Tian, Chutong Yang

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU Pennsylvania Sakana AI Northeastern Harvard Deep learning theory

Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves

A Hilbert bundle convolutional framework defines HilbNets for infinite-dimensional manifold signals, proving discrete versions converge to continuous architectures and transfer across samplings.

Kartik Tandon, Julian J Gould, Tanishq Bhatia, Francesca Dominici and 2 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightUniversity College London U Oxford Representation & contrastive learning

Normative Networks for Source Separation via Local Plasticity and Dendritic Computation

Predictive Entropy Maximization achieves blind source separation via local plasticity and dendritic error-driven rules with competitive robustness.

Bariscan Bozkurt, Efe Ali Gorguner, Francesco Innocenti, Rafal Bogacz

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightWashington University, Saint Lou U Virginia U Maryland, College Park U North Carolina at Chapel Hill Washington University in St. Lou Alignment & preference optimization

G-Zero: Self-Play for Open-Ended Generation from Zero Data

G-Zero uses intrinsic predictive-shift rewards in a verifier-free co-evolutionary framework that enables continuous LLM self-improvement across open-ended unverifiable domains without external judges.

Chengsong Huang, Haolin Liu, Tong Zheng, Runpeng(Leo) Dai and 6 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 17 on Hugging Face · Code ★ 30

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightCopenhagen U Copenhagen U Technology Nuremberg Worcester Polytechnic Institute Technion - Israel institue of Te Deep learning theory

On the Depth of Monotone ReLU Neural Networks and ICNNs

Monotone ReLU networks cannot compute or approximate maximum, ICNNs need depth n for it, and depth-k ICNNs cannot simulate some depth-2 ReLU networks.

Egor Bakaev, Florestan Brunck, Christoph Hertrich, Daniel Reichman and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU Michigan U Michigan - Ann Arbor The George Washington Bayesian & probabilistic methods

The Score Kalman Filter

Score Kalman Filter avoids partition functions by combining score matching with Stein's identity to propagate polynomial moments via linear algebra for nonlinear filtering up to 20 dimensions with lower RMSE than EKF, UKF, EnKF, and particle filters.

Kaito Iwasaki, Anthony Bloch, Taeyoung Lee, Maani Ghaffari

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightGoogle Google, Tel Aviv Research, Google Google DeepMind Technion - Israel Institute of T LLM evaluation & benchmarks

The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality

The FACTS Leaderboard benchmarks large language model factuality across multimodal, parametric, search, and grounding tasks via automated judges.

Aileen Cheng, Alon Jacovi, Amir Globerson, Ben Golan and 36 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 8 on Hugging Face

– ReadersNo votes yet

7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightBeijing Institute of Technology Fudan Shanghai Artificial Intelligence beijing institute of technology Tsinghua Vision-language models

ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder

ProCLIP progressively aligns CLIP image encoders with LLM-based embedders via curriculum distillation and contrastive tuning to support long multilingual texts without disrupting pretrained vision-language alignment.

Xiaoxing Hu, Kaicheng Yang, Ziqi Ye, Ziyang Gong and 6 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 11 on Hugging Face · Code ★ 27

– ReadersNo votes yet

7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightCISPA Helmholtz Center for Infor Privacy

Optimal Rates for Pure $\varepsilon$-Differentially Private Stochastic Convex Optimization with Heavy Tails

Pure ε-DP heavy-tailed stochastic convex optimization achieves minimax optimal excess risk via polynomial-time private Lipschitz extension optimization, including deterministic algorithms for structured losses with unbounded gradients.

Andrew Lowy

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightInstitute of Science and Technol CuspAI / University of Amsterdam ISTA Causal inference

Reconciling Causality and Non-Equilibrium Thermodynamics with Hamiltonian Causal Models

Hamiltonian Causal Models separate equations of motion from intervenable mechanisms and define causal effects as interventional path discrepancies, showing entropy production witnesses trajectory-level causal effects invisible to standard average treatment effects.

Dario Rancati, Max Welling, Francesco Locatello

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

6/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

70%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightTechnical University of Denmark Max Planck Institute for Mathem UCLA Deep learning theory

The Symmetries of Three-Layer ReLU Networks

This paper characterizes generic parameter fibers of three-layer ReLU bottleneck networks via semi-algebraic descriptions, yielding polynomial-time functional equivalence tests and analyzing symmetry-induced gradient flow conservation laws.

Johanna Marie Gegenfurtner, Moritz Grillo, Guido Montufar

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

5/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

70%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightNagoya LY Corporation Kernels & Gaussian processes

Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization

Parallel GP-BTS achieves batch-size-independent regret without initial uncertainty sampling, with stronger noiseless bounds than noisy.

Shion Takeno, Shogo Iwazaki

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

5/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

69%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightStanford Dartmouth College U California Los Angeles Mechanistic interpretability

A Mechanistic Investigation of Theory of Mind in a Large Language Model

Idil K Sahin, Steven M Frankland, Taylor Webb

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

3/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Spotlightkaist KAIST Korea Advanced Institute of Scie RL for LLMs

Imitation Dominates Reinforcement: Direct In-Context RL Is Closer to ICL Than RL

Minchan Kwon, Seunghee Koh, Sunghyun Baek, Minsung Bae and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it

lenient 1/5

medium 0/10

strict 1/5

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightWuhan Nanyang Technological Unified multimodal models

Complexity-Aware LoRA Aggregation for Modality-Heterogeneous Federated Person Re-identification

Kunyang Lv, Wenke Huang, Wenwen He, Bin Yang and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightNanjing Singapore Management AI oversight & deception

Are LLM Safety Judges Policy-Invariant? A Three-Principle Stress-Test

Shihao Weng, Yang Feng, Xiaofei Xie

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightGeorgia Tech Constellation Mila & Université de Montréa Georgia Institute of Technology U California, Davis On-device ML

FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices

Jonathan McCart, Pranav Deevi, Mehdi Azabou, Nanda H Krishna and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SpotlightU Technology Sydney Singapore Management U Wisconsin-Madison " University of Technology,Hallucination & factuality

CHORD: Cross-Model Hallucination Detection via Relational Graph Discrimination

Yongxin Deng, Zhen Fang, Guansong Pang, Sharon Li and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

Zhaowei Liu, zengyang zhang, HaitaoYang, Yao Shan and 2 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightPrinceton Princeton AI oversight & deception

Do Thinking Tokens Help with Safety?

Narutatsu Ri, Abhishek Panigrahi, Sanjeev Arora

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightTsinghua Microsoft U Toronto Massachusetts Institute of Techn Research, Microsoft Multi-agent LLM systems

STAR-Math: Multi-Agent Mathematical Reasoning under Persistent Meta-Strategic Supervision

Jiaao Wu, Xian Zhang, Hanzhang Liu, Sophia Zhang and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightFauna Robotics New York Amazon Meta Reality Labs Locomotion

Whole-Body Compliant Control via Learned Force-Regulation Modules

Diego Aldarondo, Aadhithya Iyer, Daniel Giebisch, Nina Mortensen and 3 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightNanjing Korea Advanced Institute of Scie Nanjing University of Science an Max Planck Institute for Informa Image restoration

Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement

Wei Zhu, Kai Zhang, Yu Zheng, Lei Luo and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightChinese Academy of Sciences, Ins ShanghaiTech National University of Singapore The Chinese University of Hong K Institute of Automation, Chinese Molecules & drug discovery

Binding Mode Matters: Hotspot-Aware Drug Discovery via Explorative Preferences

Dingshuo Chen, Hao Yang, Kuangqi Zhou, Zhixun Li and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightU Science and Technology of Chin Northeastern Time series forecasting

Beyond Linear Decoders: Dynamic Expert-Coupled Optimal Decoding for Time Series Forecasting

Binwu Wang, Zhipeng Liu, Zhengyang Zhou, Pengkun Wang and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightThe Hong Kong University of Scie Adobe Research Hong Kong University of Science Adobe Systems The Hong Kong University of Scie Diffusion models

UltraDiff:Transferring High-Fidelity Priors to Compressed Latent Spaces for High-resolution Image Generation

Jingjing Ren, Haitian Zheng, Haoyu Chen, Connelly Barnes and 4 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightU Waterloo 3D vision & reconstruction

Deformable 2D Gaussian Splatting

Huibin Li, Chul Min Yeum

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightFGV - EMAp Universidade Federal de Viçosa Avra FGV EMAp Universidade Federal Rural do Ri Graph neural networks

Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective

André Ribeiro Guimarães, Germano Barcelos, Amauri Souza, Diego Mesquita and 1 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightGerman Research Center for Artif German Research Center for AI Feature attribution

Weakly Supervised Concept Learning for Interpreting and Attributing LVLM Predictions

Md Abdul Kadir, Omair Shahzad Bhatti, Daniel Sonntag

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightSouthern Methodist University, S Northeastern MLCommons The University of Texas at Dalla Purdue Datasets & benchmarks

OTel: Open Telco AI Datasets, Benchmarks, and Models

Farbod Tavakkoli, Gregory Diamos, Kenneth Church, David Kanter and 14 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightSeoul National Vision-language models

Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs

Hoigi Seo, Byung Hyun Lee, Minjun Kim, Dohyun Mah and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightU Washington | Google U California, Berkeley Department of Computer Science, U Washington U California, San Diego Embodied agents

Embedded-Arena: Building Hardware-in-the-Loop Coding Agents to Run AI on Microcontrollers

Zhihan Zhang, Alexander Le Metzger, Jiuyang Lyu, Chun-Cheng Chang and 9 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightEast China Normal Xian Polytechnic Aalborg Time series forecasting

Rubato: Signature Attention for Irregular Multivariate Time Series Forecasting

Jintao Yang, Meng Wang, Chenjuan Guo, Bin Yang

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightGeorgia Tech Bilkent Distribution shift & OOD detection

Robust Satisficing Ensemble: Scalable Model Aggregation Under Distribution Shifts

Ahmet Faruk Cetinkaya, Enes Ağırman, Cem Tekin

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightUniversity College London Google Deepmind / UCL Bayesian & probabilistic methods

Learning Gaussian Conditional Distributions using Neural Ratio Estimation is Hard

Pierre Glaser, Arthur Gretton

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightNanjing University of Science an Nanjing Flow matching

Toward Semantically-Consistent Tuning-Free Customization for Rectified Flow Transformers

Jian Jin, Kai Zhang, Zhenyong Fu, Jian Yang

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightU the Chinese Academy of Science Institute of automation, Chinese , Institute of automation, Chine Beijing University of Aeronautic Institute of automation, Chinese Pose & motion

PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization

Hanqiao Ye, Yuzhou Liu, Mengqi Rong, Jian Liu and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightColumbia RWTH Aachen Mohamed bin Zayed University of Causal inference

Causal Discovery over Clusters of Variables in Non-Markovian Systems

Tara Anand, Adèle H Ribeiro, Jin Tian, George Hripcsak and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightYonsei Meta, transfer & few-shot learning

MT-CC: Multi-Group Temperature Scaling for Asymmetric Calibration Behavior in Class-Incremental Learning

Sungjun Yun, Yonghee Choi, Dong-Jun Han

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightSungkyunkwan Sung Kyun Kwan Korea Advanced Institute of Scie Vision-language models

VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph

Yuntae Jeon, Younho Jeon, Sujin Jin, Sungho Jo and 1 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightSun Yat-sen University & She The University of Sydney SUN YAT-SEN UNIVERSITY Tencent AI Lab Sun Yat-Sen Optimization

Sparse Updates Generalize Better Than Optimization: Stability Analysis for Randomized Subspace Descent

Yifei Liang, Yan Sun, Yifei Cheng, Haobo Fu and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightMILA / McGill EPFL ETHZ - ETH Zurich Apertus ETH Zürich McGill University / Mila Vision-language models

Scaling Laws for Multimodal Data Mixtures

Aditi Khandelwal, Ayush Kumar Tarun, Yixuan Xu, Imanol Schlag and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightHeidelberg Technical University of Munich U Heidelberg Image restoration

Do Image Editing Models Understand Lighting?

Tim Küchler, Johann-Friedrich Feiden, Matthias Niessner, Carsten Rother

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightMacau University of Science and Shanghai Artificial Intelligence Institute of Process Engineering Shanghai Jiao Tong Faculty of Electrical Engineerin Agent benchmarks & environments

BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories

Fei Lin, Tengchao Zhang, Ziyang Gong, Xiaotong Yu and 14 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

Luca Thiede, Andreas Burger, Alan Aspuru-Guzik

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightBeihang Zhejiang The University of Hong Kong Tsinghua Xiamen Flow matching

GenRM-Flow: Generators are Process-aware Reward Models in Flow Matching

Siming Fu, Zheming Fu, Ruizhe He, Zeyue Xue and 6 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightSeoul National Massachusetts General Hospital, RL for LLMs

Predicting Human-Gain Curves under Local Proxy Optimization from Repeated Ratings

Moonwon Choi, Kisung Nam, Seunggeun Lee

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightU Wisconsin-Madison University Of Wisconsin Madison UCSD Computer Science and Engineering U California San Diego Learning theory

(Strongly) Replicable Distribution Testers imply High Probability Distribution Testers

Ilias Diakonikolas, Jingyi Gao, Daniel Kane, Sihan Liu and 1 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightTexas A&M Texas A&M University - Colle Texas A&M university Vision-language models

Tune-Up Open-Weight CLIP: Optimization Framework for Self-Supervised Fine-tuning of CLIP

Anant Mehta, Xiyuan Wei, Xingyu Chen, Tianbao Yang

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightU Texas at Dallas New Jersey Institute of Technolo The University of Texas at Dalla UT Dallas UTDallas Optimization

Neural Dual Bounds: Valid-by-Construction JGLP Warm-Starts for MAP and Constrained MAP

Akshay Vyas, Shivvrat Arya, Brij Malhotra, Tahrima Rahman and 2 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightKing's College London King's College London, Univ Diffusion models

Improving the Diffusability of Motion Tokenizer

Guanhe Huang, Songqiao Han, Tangzheng Lian, Oya Celiktutan

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightEindhoven University of Technolo Eindhoven University of Technolo U Amsterdam Bayesian & probabilistic methods

On the Tightness and Computational Tractability of Higher-Dimensional Confidence Sequences

Fabian Denoodt, Sibylle Hess, Joaquin Vanschoren, Christian Andersson Naesseth

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightPeking Optimization

How Can SignSGD Outperform SGD? A Functional Scaling Law Perspective

Zilin Wang, Binghui Li, Jia-Nan Wang, Lean Wang and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightMorgan Stanley Université Grenoble Alpes Université de Toulouse CNRS and LJK CNRS and Archimedes, Athena Rese Learning theory

The Long-Run Distribution of Regularized Learning in Non-Concave Games: A Large Deviations Approach

Waïss Azizian, Pierre-Louis Cauvin, Franck Iutzeler, Jérôme Malick and 1 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightNew York Carnegie Mellon U Illinois at Urbana-Champaign CMU & MBZUAI Quantization

Requential Coding: Measuring Model Compressibility by Coding Data Instead of Parameters

Shikai Qiu, Marc Finzi, Yujia Zheng, Kun Zhang and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightBeijing Institute of Technology U Central Florida U Technology Sydney Time series forecasting

Paloma: Phase-Conditioned Residual Modulation for Time Series Forecasting

Jingru Fei, Kun Yi, Wei Fan, Qi Zhang and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightGeorgia Institute of Technology Computational neuroscience

MICE: Multi-animal Interaction Context Encoder — A Hierarchical Foundation Model for Mouse Behavior

Yen-Shuo Su, Weihan Li, Anqi Wu

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightU Cambridge Princeton Physics-informed ML & PDEs

Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivariance

Dongzhe Zheng, Christine Allen-Blanchette

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightCornell Department of Computer Science, Long-context modeling

Can 4D Foundation Models Remember?

Guangzhao He, Hadar Averbuch-Elor, Wei-Chiu Ma

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightKyoto Deep learning theory

Foundations of Categorical Equivariant Deep Learning

Yoshihiro Maruyama

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightU Houston Wayne State UC Riverside Privacy

Online Allocation with Differential Privacy

Jianyi Yang, Xingyu Zhou, Mostafa Mushsharat, Shaolei Ren

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightStanford LLM reasoning & chain of thought

Large language models suffer from a curse of ambiguity

Nicolas Zucchet, Hyun Dong Lee, Scott Linderman

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightSeoul National Deep RL

Distributionally Robust Domain Randomization with Learned Risk-Sensitive Dynamics Samplers

Sukchul Jeong, Insoon Yang

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightU Melbourne The University of Melbourne Southeast University, China Amazon Monash Vision-language models

Permute-then-Adapt: Weak-to-Strong Contrastive Image--Text Adaptation

Jinhao Li, Sarah Erfani, Lei Feng, Guangrui Li and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightTechnical University of Munich Technische Universität München HPI f. Digit. Engin. GGMBH LLM pretraining & scaling laws

How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models

Kristian Schwethelm, Daniel Rueckert, Georgios Kaissis

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightNanyang Technological The Institute of Statistical Mat Learning theory

Toward Minimal-dimensional Convex Calibrated Surrogate Losses for Classification with Rejection

Yuzhou Cao, Han Bao, Bo An

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightU Electronic Science and Technol Deep learning theory

Phase Kernel Lifts Capacity of Dense Associative Memory

Yifei Zhao, Ying Tang

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightWuhan National University of Singapore Renmin University of China China Three Gorges U California, San Diego Instruction tuning

Structure vs. Chaos: Asymmetric Entropic Optimization for Enforcing Instruction Hierarchy

Tianxiao Huang, Xinwei Liu, Zitong Shi, Yuxin Wu and 4 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightNortheastern Tsinghua Northeastern University, China U International Business and Eco Sichuan Graph neural networks

CLEAR: Complementary Tripartite Play with Bayesian Calibration for Semi-Supervised Edge Classification

Zhipeng Sun, Fanchun Meng, Jiazhen Huang, Yongpeng Zhang and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightSDSU South Dakota State Government of Manitoba Object detection

StomataBench: Measuring Taxonomic Generalization in Stomatal Detection

Sainath Reddy Gummi, Hankui K Zhang, Chulwoo Pack, Shyam Solanki and 1 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightApplied AI APPLIED-AI Applied AI Institute Higher School of Economics Skoltech Event sequences

Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective

Dmitry Osin, Egor Surkov, Petr Mokrov, Igor Udovichenko and 4 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightTsinghua Tsinghua University, Tsinghua , Tsinghua Beijing Houdu Technology Co., Lt Peng Cheng Laboratory LLM pretraining & scaling laws

Quantile Benchmarking Heterogeneous Web Corpora in Open LLM Pretraining

Kairong Luo, Zhenbo Sun, Xinyu Shi, Shengqi Chen and 8 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightTsinghua Tianjin Tsinghua University, Tsinghua LLM agents & planning

Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Tianyuan Yuan, Zibin Dong, Yicheng Liu, Hang Zhao

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightIndian Institute of Technology Adobe Indraprastha Institute of Inform EMBL IIITD; Adobe LLM agents & planning

ExperiGen: Agentic Hypothesis Discovery from Observational Data

Jishu Sen Gupta, Harini S I, Somesh K Singh, Mohamad Tawseeq Syed and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightU North Carolina at Chapel Hill U North Carolina, Chapel Hill Deep learning theory

What Makes a Good Path? Factoring Manifold Support and Path Geometry

Zhixuan Zhou, Tingting Dan, Guorong Wu

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightETHZ - ETH Zurich U Warsaw ETH Zurich Ideas NCBR, Polish Academy of Sc UC Berkeley & Amazon Deep RL

When Does Non-Uniform Replay Matter in Reinforcement Learning?

Michal Korniak, Mikołaj Czarnecki, Yarden As, Piotr Miłoś and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightShanghai Jiao Tong Shanghai Jiaotong AutoML & architecture search

NLD4CO: Neural Langevin Dynamics for Combinatorial Optimization

Jiale Ma, Wenzheng Pan, Binghao Cai, Xihe Zhang and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightDepartment of Computer Science, U Washington Allen Institute for AI, Universi Music

Rubato: Transcribing Piano Music with Timestamps

Nazif Tamer, Victoria Ebert, Guang Yang, Noah Smith

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightStanford U Washington RL for LLMs

Rethinking Visual Reasoning in Text-to-Image Reward Modeling

Shiye Su, Xiaohan Wang, Ludwig Schmidt, Serena Yeung-Levy

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightImperial College London Representation & contrastive learning

Casper: A Projection-Based Neurosymbolic Layer for Scalable & Guaranteed Constraint Satisfaction

Lohith Konathala, Luca Andolfi, Eleonora Giunchiglia

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightCollege of Computer Science and Tencent Youtu Lab Tencent Canva U the Chinese Academy of Science Text-to-image

PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

Yanjie Pan, Qingdong He, Zhengkai Jiang, Pengcheng Xu and 8 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightU Copenhagen Privacy

Optimal Rates for Adaptive Private $k$-PCA

Johanna Düngler, Amartya Sanyal

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightNanyang Technological Skywork AI RL for LLMs

Negative-Only Policy Optimization for One-Sided Verifiable Rewards

Jiacheng Xu, Shuo He, Fuxiang Zhang, Chaojie Wang and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightThe University of Hong Kong The University of Tokyo U Hong Kong U British Columbia LLM agents & planning

RAOP: Step-Level Resource Orchestration for LLM Agents across Edge and Cloud

Jinze Li, Xin Yang, Shuo Yang, Jinfeng Xu and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightShanghai Jiao Tong Northeastern National University of Singapore Vietnam Academy of Science and T LLM pretraining & scaling laws

First-Token Attraction in Mamba Dynamics

Trinh Nguyen, Duy-Tung Pham, Minh-Khoi Nguyen-Nhat, Hoang-Son Do and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightShanghai Jiao Tong DataCanvas Tsinghua Project Numina LLM, Xiaohongshu LLM pretraining & scaling laws

Decomposing and Reshaping Scaling Laws through Token Learning Times

Pingjie Wang, zechenhu, Peiru Yang, Jingtao Han and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightU California, San Diego UCSD Deep learning theory

Sharpness of Minima in Deep Matrix Factorization

Anıl Kamber, Rahul Parhi

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightKAIST Korea Advanced Institute of Scie UNIST Korea Advanced Institute of Scie Multi-agent RL

Addressing Exogenous Variability in Cooperative Multi-Agent Reinforcement Learning

Seongmin Kim, Woohyeon Byeon, Jiwon Jeon, Seungyul Han and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightU Houston Virginia Commonwealth U California, Riverside Watermarking & AI-text detection

UniReFP: Robust Unified Fingerprinting for Vision Models against Cross-Task Repurposing Attacks

Ziye Geng, Guang Yang, Yihang Chen, Lingfeng Yao and 4 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightMalanshan Audio&Video Labora Image restoration

Noise-Regularized Training for Learned Image Compression

Renjie Zou, Zhiwei Huang, Dong Jiang

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightNational University of Singapore Deep learning theory

Point-to-Manifold Geometry: Flexibly Overcoming the Curse of Dimensionality in Neural Computational Units

Rohan Ghosh, Mehul Motani

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightMassachusetts Institute of Techn MIT Information retrieval

Is Dimensionality a Barrier for Retrieval Models?

Kiril Bangachev, Guy Bresler, Jonathan Kogan, Yury Polyanskiy

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightINSAIT, Sofia University "S Woven by Toyota INSAIT, Sofia University, St. Kl Sofia Un. St. Kliment Ohridski INSAIT Sofia & ETH Zurich Visual grounding

P$^3$-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models

Anna-Maria Halacheva, Jan-Nico Zaech, Sombit Dey, Luc V Gool and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026SpotlightGoethe University Frankfurt am M Johann Wolfgang Goethe Universit Image recognition

How Far Is Too Far? Object Recognition Declines Monotonically with Semantic Distance

Domenic Bersch, Hai Van Tran, Gemma Roig

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.