Good Papers: read the good ones

Gen-Searcher trains a search-augmented image generation agent via supervised and reinforcement learning, yielding about 16-point gains on knowledge-intensive benchmarks.

Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin and 6 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 54 on Hugging Face · Code ★ 400

100% Readers1 of 1 upvoted

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.

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026ShanghaiTech Shanghai Jiao Tong The Chinese University of Hong K Shanghai Jiaotong Morphic Robotics Robot manipulation

Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry

IDP uses conditional expert geometry to implicitly enforce training-time drifting corrections, yielding a one-step generative policy that improves robot control speed while maintaining valid action manifolds.

Zemin Yang, Yaoyu He, Yiming Zhong, Yuhao Zhang and 4 more

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

AI panel: 7 of 20 reviewers recommend it

lenient 3/5

medium 4/10

strict 0/5

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Tsinghua The Chinese University of Hong K Hong Kong University of Science Duke Image restoration

PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing

PRISM proposes a unified physically structured framework for real-world dehazing via proximal scattering atmosphere reconstruction, online non-uniform haze synthesis, and selective self-distillation adaptation to achieve competitive restoration results.

Chengyu Fang, Chunming He, Yuelin Zhang, Chubin Chen and 5 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 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.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Columbia The Chinese University of Hong K Dartmouth College Microsoft Microsoft Research LLM agents & planning

Reinforcement World Model Learning for LLM-based Agents

RWML learns action-conditioned world models for LLM agents via self-supervised sim-to-real alignment, outperforming direct task-success RL by up to 6.9 points without expert data.

Xiao Yu, Baolin Peng, Ruize Xu, yelong shen and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 28 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.

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Tsinghua University, Tsinghua Hunan Dalian Martime The Chinese University of Hong K Tsinghua Unified multimodal models

DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization

DCVD jointly detects vulnerable functions and localizes vulnerable statements via dual-channel cross-modal fusion with explicit multi-granularity supervision, outperforming state-of-the-art baselines.

Wenxin Tang, Wenbin Li, Junliang Liu, Jingyu Xiao and 9 more

Sydney Poster Session 2, Tue, Dec 8, 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.

83%Must read

?Must readVote to see the score

NeurIPS 2026U Sydney The Chinese University of Hong K Shenzhen Institutes of Advanced INRIA Shanghai Artificial Intelligence Pruning & sparsity

PARE: Pruning and Adaptive Routing for Efficient Video Generation

PARE combines structure-aware width pruning and timestep-conditioned adaptive depth routing to cut video diffusion compute while preserving generation quality.

Yutong Wang, Yunke Wang, Tianfan Xue, Yu Qiao and 3 more

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.

86%Must read

?Must readVote to see the score

NeurIPS 2026Department of Computer Science a Chinese University of Hong Kong Stanford The Chinese University of Hong K Genomics & single-cell

Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images

CELLO predicts single-cell spatial transcriptomics from histology via grid sampling and distance-decay cross-attention, achieving 14x faster inference than DeepSpot2Cell without upstream segmentation.

Zijun Gao, Chunbin Gu, Xiangde Luo, Jinxi Xiang and 1 more

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.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026U Michigan The Chinese University of Hong K Test-time compute

Confidence-Based Decoding is Provably Efficient for Diffusion Language Models

Confidence-based decoding achieves ε-accurate diffusion language model sampling in Õ(H(X₀)/ε) iterations by adaptively unmasking tokens until cumulative entropy exceeds a threshold.

Changxiao Cai, Gen Li

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 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 2026The Chinese University of Hong K National University of Defense T City University of Hong Kong Hefei University of Technology The Education University of Hong Graph neural networks

DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation

DisRFM embeds graph representations on constant-curvature manifolds with polar flow matching to prevent structural degeneration and optimization instability, outperforming state-of-the-art graph domain adaptation methods.

Yingxu Wang, Xinwang Liu, Siyang Gao, Mengzhu 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

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.

89%Must read

?Must readVote to see the score

NeurIPS 2026SUN YAT-SEN UNIVERSITY Chinese University of Hong Kong The Chinese University of Hong K Nanjing University of Aeronautic Southwest Jiaotong Multimodal reasoning

AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoning

AgroOmni introduces 288K multi-view agricultural VQA pairs across scales, and AgroNVILA achieves state-of-the-art 62.32% on AgroMind while demonstrating strong cross-scale generalization.

Jiarui Zhang, Junqi Hu, Zurong Mai, Yang Liu and 9 more

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.

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Monash VAST The Chinese University of Hong K Multimodal reasoning

OpenView: Empowering MLLMs with Out-of-view VQA

OpenView introduces out-of-view VQA via panoramic synthesis, boosting MLLM accuracy from 48.6% to 64.1%.

Qixiang Chen, Cheng Zhang, Chi-Wing Fu, Jingwen Ye and 1 more

Sydney Poster Session 1, Tue, Dec 8, 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.

AI panel: 9 of 20 reviewers recommend it

lenient 4/5

medium 5/10

strict 0/5

86%Must read

?Must readVote to see the score

NeurIPS 2026The Chinese University of Hong K Shanghai Jiaotong SenseTime Reseach Spoken language models

MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation

MultiTalk introduces 57.6k hours of synthetic multi-party bilingual dialogue data and MultiTalkBench for long-form full-duplex evaluation, training a model that sustains coherent extended multi-party English-Chinese conversation and outperforms open-source baselines.

Ke Wang, Houxing Ren, Zimu Lu, Yunqiao Yang and 3 more

Sydney Poster Session 5, Thu, Dec 10, 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 7/10

strict 2/5

80%Must read

?Must readVote to see the score

NeurIPS 2026U Toronto Tsinghua The Chinese University of Hong K Tsinghua University, Tsinghua GigaAI Embodied agents

DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning

DriveDreamer-Policy unifies depth generation, video prediction, and motion planning via geometry-aware world representations, achieving 89.2 PDMS on Navsim v1 and 88.7 EPDMS on v2.

Yang Zhou, Xiaofeng Wang, Hao Shao, Letian Wang and 7 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face · Code ★ 60

– 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 2026The University of Hong Kong The Chinese University of Hong K Wuhan Huazhong University of Science a Diffusion models

EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting

EO-WM is a diffusion transformer that forecasts satellite imagery via physically structured weather conditioning and improves vegetation-decline prediction accuracy by up to 7.8% on new diagnostic benchmarks.

Junwei Luo, Shuai Yuan, Zhenya YANG, Yansheng Li and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 3 on Hugging Face · Code ★ 33

– 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.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Department of Computer Science a City University of Hong Kong Huawei Technologies Ltd.The Chinese University of Hong K TokenRhythm Technologies Long-context modeling

MemDLM: Memory-Enhanced DLM Training

MemDLM augments diffusion language model training via bi-level optimization with parametric memory, improving convergence, long-context representations, and needle retrieval.

Zehua Pei, Hui-Ling Zhen, Weizhe Lin, Sinno Pan and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 3 on Hugging Face · Code ★ 11

– 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.

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026The Chinese University of Hong K Tsinghua Shenzhen International University College London, Unive University College London Nanjing Unified multimodal models

Meow-Omni 1: A Multimodal Large Language Model for Feline Ethology

Meow-Omni 1 integrates video, audio, physiological time-series, and text to reach 71.16% feline intent recognition, outperforming baseline multimodal models.

Jucheng Hu, Zhangquan Chen, Yulin Chen, Chengjie Hong and 8 more

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

89%Must read

?Must readVote to see the score

NeurIPS 2026U Illinois Urbana-Champaign Microsoft U Illinois at Urbana-Champaign Amazon Microsoft Research Web & GUI agents

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

OpenWebRL enables open online RL for visual web agents, with a 4B model reaching 67% Online-Mind2Web and 64% DeepShop success using minimal initialization data.

Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai and 6 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 19 on Hugging Face · Code ★ 52

– 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.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026The Hong Kong University of Scie U Science and Technology of Chin Hong Kong University of Science The Chinese University of Hong K Vision-language models

Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation

Direct product flow matching decouples radial and angular dynamics via constant-speed geodesic transport and hidden-state conditioning for state-of-the-art few-shot vision-language adaptation.

Hongxu Chen, Yanghao Wang, Bowei Zhu, Hongxiang Li and 5 more

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.

86%Must read

?Must readVote to see the score

NeurIPS 2026The Chinese University of Hong K Shanghai Jiaotong national university of singaore,Advanced Machine Intelligence ByteDance Inc.Autoregressive generation

BitDance: Scaling Autoregressive Generative Models with Binary Tokens

BitDance is an autoregressive image generator that predicts binary visual tokens via a diffusion head and next-patch decoding, achieving state-of-the-art FID with far fewer parameters and much faster inference.

Yuang Ai, Jiaming Han, Shaobin Zhuang, Weijia Mao and 7 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 46 on Hugging Face · Code ★ 485

– 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 8/10

strict 2/5

86%Must read

?Must readVote to see the score

NeurIPS 2026Shanghai Jiao Tong Xiaohongshu, Inc.Ant Group Shanghai Jiaotong U Science and Technology of Chin LLM pretraining & scaling laws

xHC: Expanded Hyper-Connections

xHC expands Transformer hyper-connections beyond four streams via sparse updates and temporal augmentation, improving scaling efficiency. It boosts 18B MoE downstream scores by 4.0 points over mHC with lower compute and reduced memory traffic via xHC-Flash.

Xiangdong Zhang, Xiaohan Qin, Tuo Dai, Xiaoming Shi and 7 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 54 on Hugging Face · Code ★ 68

– 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 3/5

medium 8/10

strict 3/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Southwest The Hong Kong University of Scie Tsinghua ByteDance Inc.Guangdong OPPO Mobile Telecommun Web & GUI agents

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization

SMTL replaces sequential reasoning with parallel evidence acquisition for efficient long-horizon agentic search, achieving state-of-the-art results on multiple benchmarks with far fewer reasoning steps.

Chengjun Yu, Shu XU, Jiaqi Wu, Qianben Chen and 20 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 23 on Hugging Face · Code ★ 3

– 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.

89%Must read

?Must readVote to see the score

NeurIPS 2026U California, Santa Barbara Johns Hopkins The Chinese University of Hong K NUS, CMU U Southern California Agent memory

WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction

WorldMemArena evaluates multimodal agent memory through an action-world loop, showing writing and storage improvements do not guarantee performance and harness-based memory remains costly and unreliable.

Chengzhi Liu, Yuzhe YANG, Sophia Xiao Pu, Yepeng Liu and 15 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 13 on Hugging Face · Code ★ 29

– 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.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026City University of Hong Kong The Chinese University of Hong K The Chinese University of Hong K Shanghai University of Finance a Agent benchmarks & environments

LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs

LiveOption evaluates LLM option-trading agents via structured sequential decision-making with nonlinear payoffs, showing current agents rarely achieve competitive returns.

Haochen Luo, YIFAN LI, An B Minh, Xiaolong Luo and 3 more

Sydney Poster Session 2, Tue, Dec 8, 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 4/10

strict 1/5

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026The Chinese University of Hong K Northeastern Southeast The Chinese University of Hong K The Chinese University of Hong K Deep RL

ReFPO: Reflow Regularization for Flow Matching Policy Gradients

ReFPO adds explicit reflow regularization to flow matching policy gradients, stabilizing training and enabling high-fidelity one-step inference that matches multi-step performance across control tasks.

Ge Wang, Yibo Peng, Fan Feng, Shenhao Yan and 9 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 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.

91%Must read

?Must readVote to see the score

NeurIPS 2026The Hong Kong University of Scie Alibaba Group Renmin University of China The Chinese University of Hong K Peking LLM agents & planning

Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents

A visual-native harness with an image bank and on-policy data evolution improves multimodal deep search agents, raising Qwen3-VL-8B to 39.0% average and surpassing Gemini-2.5 Pro.

Shijue Huang, Hangyu Guo, Guanting Dong, Chenxin Li and 7 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 21 on Hugging Face · Code ★ 30

– 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.

80%Must read

?Must readVote to see the score

NeurIPS 2026Tongji The Chinese University of Hong K Institute of automation, Chinese Tianjin Inner Mongolia RL for LLMs

AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition

AffectGPT-RL applies reinforcement learning to open-vocabulary emotion recognition, improving performance by optimizing non-differentiable metrics and enabling reasoning.

Zheng Lian, Fan Zhang, Lan Chen, Yazhou Zhang and 7 more

Sydney Poster Session 2, Tue, Dec 8, 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.

86%Must read

?Must readVote to see the score

NeurIPS 2026The Chinese University of Hong K CUHK, Google DeepMind Video generation

OpenCoF: Learning to Reason Through Video Generation

OpenCoF introduces a 17K video reasoning dataset and Wan-CoF model that improves chain-of-frame reasoning via diverse temporal supervision and reasoning tokens.

Xinyan Chen, Renrui Zhang, Ziyu Guo, Dongzhi JIANG and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 26 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.

88%Must read

?Must readVote to see the score

NeurIPS 2026U Hong Kong The University of Hong Kong The Chinese University of Hong K The Chinese University of Hong K Agent benchmarks & environments

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks

UniClawBench introduces a capability-driven benchmark evaluating proactive agents via 400 real-world tasks with live Docker evaluation and multi-turn feedback.

Zhekai Chen, CHENGQI DUAN, Kaiyue Sun, Bohao Li and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 34 on Hugging Face · Code ★ 39

– 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.

70%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Tsinghua The Chinese University of Hong K The Hong Kong University of Scie Applied Research Center, Tencent Wuhan Controllable generation

AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization

AnchorWorld improves egocentric world simulation via full-body interaction supervision and anchor-view customization with consistent spatio-temporal dynamics.

Yu Li, Menghan Xia, Gongye Liu, Xintao Wang and 7 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 30 on Hugging Face

– 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.

88%Must read

?Must readVote to see the score

NeurIPS 2026UCLA | Tencent Hunyuan The Chinese University of Hong K Tencent AI Lab East China Normal The Hong Kong University of Scie Web & GUI agents

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents

OpenSearch-VL introduces an open-source recipe training multimodal deep search agents via curated data, diverse tools, and multi-turn fatal-aware GRPO, achieving over 10-point benchmark gains comparable to proprietary models.

Shuang Chen, Kaituo Feng, Hangting Chen, Wenxuan Huang and 6 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 57 on Hugging Face · Code ★ 289

– 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.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026U Chinese Academy of Sciences Shenyang Institute of Automation The Chinese University of Hong K Tencent weixin Object detection

Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm

FDEP integrates frozen visual foundation model representations into infrared small target detection via semantic alignment fusion and implicit self-distillation, achieving state-of-the-art accuracy with no inference overhead.

Chuang Yu, Jinmiao Zhao, Yunpeng Liu, Yaokun Li and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 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.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026The Chinese University of Hong K Max-Planck-Institute for Intelli Westlake Max Planck Institute for Intelli CUHK LLM pretraining & scaling laws

Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation

Pion updates weight matrices via orthogonal equivalence transformations that preserve singular values during LLM training, offering a stable, competitive optimizer alternative.

Kexuan Shi, Hanxuan Li, Zeju Qiu, Yandong Wen and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 5 on Hugging Face · Code ★ 39

– 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.

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Sun Yat-sen The Chinese University of Hong K Nanyang Technological SUN YAT-SEN UNIVERSITY The University of Hong Kong Image editing

ProEdit: Inversion-based Editing From Prompts Done Right

ProEdit improves inversion-based image and video editing via KV-mix and Latents-Shift to achieve state-of-the-art results.

Zhi Ouyang, Dian Zheng, Xiao-Ming Wu, Jian-Jian Jiang and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 19 on Hugging Face · Code ★ 116

– 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.

88%Must read

?Must readVote to see the score

NeurIPS 2026Beijing Academy of Artificial In Shanghai Jiaotong U Electronic Science and Technol Hainan The Hong Kong University of Scie 3D vision & reconstruction

Focusable Monocular Depth Estimation

FocusDepth uses spatially-aligned multi-scale prompt fusion to boost target-region depth accuracy and sharp boundaries while preserving global geometry, outperforming global baselines on FDE-Bench.

Yuxin Du, Tao Lin, Zile Zhong, Runting Li and 6 more

Sydney Poster Session 3, Wed, Dec 9, 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.

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026National University of Singapore Baidu Tsinghua University, China pjlab.org.cn Baidu Inc.Video generation

ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration

ONE-SHOT factorizes compositional video generation via spatial-decoupled motion injection and hybrid context integration, achieving fine-grained human-environment control and minute-level consistency without 3D alignment.

Fengyuan Yang, Luying Huang, Jiazhi Guan, Quanwei Yang and 7 more

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

– 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.

80%Must read

?Must readVote to see the score

NeurIPS 2026Department of Computer Science a Huawei Technologies Ltd.Huawei AI Lab, Hong Kong Researc The Chinese University of Hong K Chinese University of Hong Kong Unified multimodal models

Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM

TextPro-SLM minimizes speech-text modality gap by feeding prosody-aware text inputs to LLMs, cutting the gap at 3B and 7B scales with only ~1,000 hours of audio.

Wenqian Cui, Xiao-Hui Li, Daxin Tan, Qiyong Zheng and 1 more

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.

AI panel: 12 of 20 reviewers recommend it

lenient 4/5

medium 7/10

strict 1/5

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Southern University of Science a Mohamed bin Zayed University of The Chinese University of Hong K Uncertainty & calibration

Occupancy-based Quantile Risk Control

OQRC partitions calibration losses into ordered bins to tightly upper-bound quantile risk with finite-sample guarantees converging at rate O_p(n^{-1/2}).

Zihao Shi, Huajun Xi, Bingyi Jing, Hongxin Wei

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 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.

86%Must read

?Must readVote to see the score

NeurIPS 2026The University of Hong Kong Shanghai Jiaotong Fudan Beijing University of Aeronautic The Chinese University of Hong K Embodied agents

Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators

Astra enhances vision-language model spatial reasoning by letting agents generate imagined simulator views via RL, improving MMSI-Bench scores over direct answering.

Chenming Zhu, Jingli Lin, Yilin Long, Peizhou Cao and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 16 on Hugging Face · Code ★ 32

– 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 2026Mohamed bin Zayed University of Xi'an Jiaotong-Liverpool U Liverpool Huazhong University of Science a The Chinese University of Hong K Medical LLMs

DoAtlas-1: A Causal Compilation Paradigm for Clinical AI

DoAtlas-1 introduces causal compilation to convert medical evidence into executable causal estimands, achieving 98.5% canonicalization accuracy and 80.5% query executability across 1,445 effect kernels.

Yulong Li, Jianxu Chen, Xiwei Liu, Chuanyue Suo and 7 more

Sydney Poster Session 1, Tue, Dec 8, 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.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026The Hong Kong University of Scie The Hong Kong University of Scie The Hong Kong Univeristy of Scie Huawei Technologies Ltd.The Chinese University of Hong K 3D generation

Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation

Seg3DParts uses segmentation-grounded generation with structured cross-part interaction to produce controllable, coherent part-level 3D meshes from single images while introducing the PartObjectNet dataset.

Jiantao Lin, Meixi Chen, Yingjie Xu, Chenbo FU and 4 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 2026The Hong Kong University of Scie knowin.ai The Hong Kong Univeristy of Scie The Chinese University of Hong K Diffusion models

DirectUV: Image-Conditioned UV Texture Generation with Surface-Aware Positional Encoding

DirectUV generates UV textures via diffusion with surface-aware positional encoding that attains 3D coherence across seams and improves occluded regions.

Jiantao Lin, Yingjie Xu, Mingzhi Sheng, Yangkai Wei and 2 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 2026The Chinese University of Hong K U Georgia Fudan university U Oxford Shanghai AI Lab RL for LLMs

StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction

StraTA introduces trajectory-level strategies into agentic reinforcement learning via hierarchical rollout training, improving long-horizon decision-making and reaching 93.1% on ALFWorld.

Xiangyuan Xue, Yifan Zhou, ZiDong Wang, Shengji Tang and 4 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 27 on Hugging Face · Code ★ 47

– 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.

89%Must read

?Must readVote to see the score

NeurIPS 2026The Chinese University of Hong K U Montreal Department of Computer Science a AI oversight & deception

Safe Evolution with Circuit Anchors

Self-evolving LLMs can misevolve into dangerous entities, and anchoring a small safety circuit during evolution preserves safety with minimal capability loss.

Yan Liu, Jie Fu, Tsung-Yi Ho

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 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.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026The Chinese University of Hong K Aalto Taobao (China) Software Co., Ltd Technical University of Denmark Feature attribution

From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows

Fixed-path attribution uniquely requires Aumann-Shapley line integrals, while transport-geodesic paths via minimized kinetic action yield more stable, structured explanations.

Cenwei Zhang, Lin Zhu, Manxi Lin, Lei You

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 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 2/5

medium 6/10

strict 2/5

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026The Chinese University of Hong K CUHK Tencent Quantum Lab Chinese University of Hong Kong Optimization

Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise

Quantum estimators for heavy-tailed noise enable QNSGD and QPSGD to find ε-stationary or optimal solutions with poly(√d, ε) oracle queries, beating classical lower bounds in low dimensions.

Bin Luo, Chengchang Liu, Jonathan Allcock, Shengyu Zhang and 1 more

Sydney Poster Session 2, Tue, Dec 8, 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.

AI panel: 6 of 20 reviewers recommend it

lenient 2/5

medium 3/10

strict 1/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026The University of Hong Kong Shanghai Jiao Tong Northwestern Polytechnical U Science and Technology of Chin Fudan 3D vision & reconstruction

PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction

PLANING decouples geometry and appearance via explicit primitives and neural Gaussians for fast, high-quality streaming monocular 3D reconstruction with reduced redundancy.

Changjian Jiang, Kerui Ren, Xudong Li, Kaiwen Song and 8 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 21 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.

AI panel: 11 of 20 reviewers recommend it

lenient 5/5

medium 6/10

strict 0/5

86%Must read

?Must readVote to see the score

NeurIPS 2026Zhejiang Beijing University of Aeronautic The Chinese University of Hong K Shandong nanjing university Agent benchmarks & environments

EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies

EcoGym benchmarks long-horizon LLM economic planning across open-source environments, revealing no single model dominates and exposing strategic and execution suboptimalities.

Xueyu Hu, Jinxiang Xia, Shengze Xu, Kangqi Song and 12 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 11 on Hugging Face · Code ★ 99

– 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

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026SUN YAT-SEN UNIVERSITY The Hong Kong University of Scie Huawei Technologies Ltd.The Chinese University of Hong K Huawei Noah’s Ark Lab Embodied agents

Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving

IRR-Drive uses adaptive multimodal text and BEV reflection to self-correct driving intentions before trajectory generation, achieving state-of-the-art NAVSIM results.

Zisheng Chen, Yuping Qiu, Jianhua Han, Tao Tang and 5 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.

AI panel: 11 of 20 reviewers recommend it

lenient 5/5

medium 6/10

strict 0/5

89%Must read

?Must readVote to see the score

NeurIPS 2026The University of Hong Kong Huazhong University of Science a The Chinese University of Hong K zhejiang university Vision-language-action models

FASTER: Rethinking Real-Time Flow VLAs

FASTER accelerates real-time flow vision-language-action models via horizon-aware sampling that compresses immediate-action denoising into one step, slashing reaction latency on dynamic robot tasks.

Yuxiang Lu, Zhe Liu, Xianzhe Fan, Zhenya YANG and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 61 on Hugging Face · Code ★ 157

– 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

83%Must read

?Must readVote to see the score

NeurIPS 2026Department of Computer Science a Beijing University of Posts and Peking Simplexity Robotics The Chinese University of Hong K Robot manipulation

LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning

LaST-R1 uses reinforcement learning with adaptive latent reasoning to optimize robotic action policies, achieving 99.9% success on LIBERO and up to 22.5% real-world gains.

Hao Chen, Zhonghao Yan, Jiaming Liu, Nuowei Han and 6 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 3 on Hugging Face · Code ★ 122

– 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.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 1/5

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Shanghai Jiaotong Fudan Nanjing Shanghai Jiao Tong Xiamen Vision-language models

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution

ViCO minimizes vision tokens via consistency training across compression ratios, cutting tokens up to 50% while preserving capabilities through semantic-based routing.

Long Cui, Weiyun Wang, Jie Shao, Zichen Wen and 4 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 5 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 5/5

medium 4/10

strict 0/5

80%Must read

?Must readVote to see the score

NeurIPS 2026Department of Computer Science a The Chinese University of Hong K Knowin AI Wuhan Video-language models

CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive Querying

CAM uses continuous knowledge graph extraction and adaptive multi-method querying to answer entity-centric video questions, improving accuracy by up to 23 points over baselines.

Yizhou Tian, Zizhe Chen, Shiyuan Deng, Garry YANG and 6 more

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.

AI panel: 12 of 20 reviewers recommend it

lenient 4/5

medium 7/10

strict 1/5

80%Must read

?Must readVote to see the score

NeurIPS 2026Tsinghua The Chinese University of Hong K Ant Group Tsinghua University, Tsinghua Renmin University of China LLM pretraining & scaling laws

CausalMix: Data Mixture as Causal Inference for Language Model Training

CausalMix frames data mixture optimization as causal inference to dynamically estimate optimal mixtures via conditional average treatment effects, improving LLM performance without retraining proxy models.

Zinan Tang, YUKUN ZHANG, Shaomian Zheng, Zhuoshi Pan and 5 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 19 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

Show 20 more papers