Good Papers: read the good ones

Showing papers from KAIST Show all papers

72%Highly rated

NeurIPS 2026Korea KAIST korea advanced institute of scie U Wisconsin-Madison Ulsan National Institute of Scie In-context learning & prompting

AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

AgentGrad improves multi-agent prompt optimization via sequential intervention and semantic gradient clustering, achieving state-of-the-art performance with 2.5x faster optimization and 21.8% lower cost.

Jaewon Chu, jinwoo seo, Jaewon Cho, Jeehye Na and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 107 on Hugging Face

0% Readers0 of 1 upvoted

15/20 AI panelreviewers recommend it

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

91%Must read

?Must readVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST Kyung Hee Korea Advanced Institute of Scie Multimodal reasoning

CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models

CollabVR pairs vision-language models with video generation models in closed-loop step-level planning and verification, reducing drift and simulation errors for major video reasoning gains.

Joowon Kim, Seungho Shin, Joonhyung Park, Eunho Yang

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 71 on Hugging Face · Code ★ 10

100% Readers1 of 1 upvoted

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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST KAIST, Korea Advanced Institute PYLER LLM reasoning & chain of thought

Continuous Audio Thinking for Large Audio Language Models

Gyojin Han, DongJae Lee, Changho Choi, Jongsuk Kim 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 2026Korea KAIST Parameter-efficient fine-tuning

PRISM: Principal Subspace Alignment for Parameter-Efficient Fine-Tuning

Anh Tong, Kyowoon Lee, Jaesik Choi

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.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST U Michigan - Ann Arbor Korea LLM agents & planning

Refining Compositional Diffusion for Reliable Long-Horizon Planning

Kyowoon Lee, Yunhao Luo, Anh Tong, Jaesik Choi

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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST Feature attribution

TreePII: Efficient Computation of Higher-Order Probabilistic Interaction Indices in Tree Ensembles

Junho Choi, Jaesik Choi

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.

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Samsung Research KAIST Yonsei Korea Advanced Institute of Scie Hallucination & factuality

Beyond Uniform Detection: Adaptive Hallucination Detection for RAG Across Response Regimes

Jungwuk Park, Sejong Ryu, Jy-yong Sohn, Jaekyun Moon

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.

AI panel: 2 of 20 reviewers recommend it

lenient 1/5

medium 1/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Korea Advanced Institute of Scie Domain adaptation

HyperFlow: Gradient-Free Test-Time Adaptation for Cross-Domain Few-Shot Classification

Donggyun Kim, Chanwoo Kim, Seunghoon Hong

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.

AI panel: 1 of 20 reviewers recommend it

lenient 1/5

medium 0/10

strict 0/5

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026barreleye Korea Advanced Institute of Scie Barreleye, inc.KAIST KAIST, Korea Advanced Institute Medical imaging

Anatomy-aware Spatio-Temporal Modeling for Echocardiography Segmentation

Seok-Hwan Oh, Guil Jung, Myeong-Gee Kim, Young-Min Kim and 4 more

Sydney Poster Session 5, Thu, Dec 10, 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.

AI panel: 2 of 20 reviewers recommend it

lenient 2/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026Institute for Basic Science Max Planck Institute for Securit KAIST Knowledge editing

Memoir: Let the Model Direct Its Own Story for Robust Cross-Domain Knowledge Editing

Jea Kwon, Jiwon Kim, Dong Kyum Kim, Meeyoung Cha

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST Vision-language models

InfCLIP: Unified Data Valuation for CLIP Pretraining via Influence-Inspired Scoring

Nohyun Ki, Hye Won Chung

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.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Mechanistic interpretability

Attention Sinks as Spectral Spikes: A Mechanism Analysis of Gated Attention

Seojin Kim, Yehjin Shin, Noseong Park

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 2026KAIST, Korea Advanced Institute KAIST U Wisconsin - Madison KAIST / Meta Pruning & sparsity

SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking

Moonseok Choi, Giung Nam, Jongwon Jeong, Minki Kang and 1 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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Mila - Quebec Artificial Intelli U Edinburgh Université de Montréal & Mil Diffusion models

Aligning Few-Step Generative Model via Amortizing Sample-Based Variational Inference

Jaewoo Lee, Hyeongyu Kang, Dohyun Kim, Kyuil Sim and 8 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.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Korea Advanced Institute of Scie Video generation

PhaseDance: Capturing Rhythm and Expressivity in Dance Modeling

Meongeun Kim, Taehui Lee, Soomin Park, Sung-Hee 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 2026Korea Advanced Institute of Scie KAIST Multi-agent LLM systems

Multi-Agent Coordination via Support-Preserving Distillation

Sangmin Lee, Youngju Na, Chanmi Lee, Sung-eui Yoon

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.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST Mechanistic interpretability

Decision Path Tracing for Causal Analysis in Transformers

Won Jo, Dahee Kwon, Jongeun Baek, Cheongwoong Kang 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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST Kookmin Tokenization

SAVE: Sparsity-Aware Influence Estimation for Vocabulary-Expanded LLMs

Seungyoo Lee, Giung Nam, Seanie Lee, Hyungi Lee 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.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST POSTECH Unified multimodal models

Latent Reasoning in Continuous Space for Unified Multimodal Models

Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee, Minsu Cho 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 2026Korea Advanced Institute of Scie Korea Advanced Institute of Scie KAIST Alignment & preference optimization

AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising

Woo Jae Kim, Seongho Keum, Joonsung Jeon, Suhyeon Ha 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 2026U Electronic Science and Technol Harbin Institute of Technology, College of Information and Contr KAIST Vision-language models

TPRL: Adaptive Visual Token Pruning in LVLMs via Language-Guided Reinforcement Learning

Sihan Cao, Jianwei Zhang, Pengcheng Zheng, Jiaxin Yan and 6 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.

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

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie Korea Advanced Institute of Scie KAIST Diffusion models

SchedDiff: Diffusion-Based Priority Refinement for Job Shop Scheduling

Dong-Yoon Oh, Sang-Hyun Cho, Inguk Choi, Hyun-Jung Kim

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 2026Korea Advanced Institute of Scie KAIST Deep RL

Towards a Unified Model for Flexible Job Shop Scheduling Problems

Inguk Choi, Woo-Jin Shin, Sang-Hyun Cho, Hyun-Jung Kim

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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST Georgia Tech Time series forecasting

TimeOperator: A Function-to-Function Approach to Time Series Modeling

SheoYon Jhin, B. Aditya Prakash, Noseong Park

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.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026VUNO Inc KAIST Sungkyunkwan Active learning

Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition

Juho Jung, Seongjae Kang, Jinyoung Han

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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST Yonsei Korea Advanced Institute of Scie Jailbreaks & red teaming

Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation

NaHyeon Park, Minhyun Lee, Hyunjung Shim

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.

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Weather & climate

PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling

Minseo Yoon, Minseong Bae, Sojin Lee, Hyunwoo J. Kim

Sydney Poster Session 5, Thu, Dec 10, 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.

AI panel: 2 of 20 reviewers recommend it

lenient 2/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST Software engineering agents

Ask KG Agent: A Multi-Agent Framework for Code Localization Using Code and Knowledge Graphs

Chanyoung Chung, Jeemin Kim, Joyce Whang

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.

AI panel: 1 of 20 reviewers recommend it

lenient 1/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST Learning theory

Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and Bandits

Junghyun Lee, Yujun Kim, Chulhee Yun, Se-Young Yun

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 2026Korea Institute for Advanced Stu MIT KAIST Physics-informed ML & PDEs

Variational Monte Carlo for Quantum Excited States via Nested Low-Rank Approximation

Minchan Jeong, Jongha (Jon) Ryu, Se-Young Yun, Gregory Wornell

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 2026Korea Advanced Institute of Scie KAIST Korea Advanced Institute of Scie Korea Korea Advanced Institute of Scie Video understanding

HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies

Youngrae Kim, Yejin Jang, Eunho Kim, Youjin Sung and 3 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 2026KAIST Korea Institute for Advanced Stu Yonsei Korea Institute for Advanced Stu Graph neural networks

Implicit Neural Representations for Variational Problems on Graphons

Taeyoung Kim, Jineon Baek, Joonkyung Lee, Hongseok Yang

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.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST In-context learning & prompting

Transformers Can Learn Multiclass Classification In-Context: Isotropy Governs Generalization

Daehan Yoon, Chulhee Yun

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 2026Korea Advanced Institute of Scie KAIST Domain adaptation

Beyond Average Flatness: Domain-wise Flatness for Domain Generalization

Seungjun Choi, Heeyoung Kim

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 2026Korea Advanced Institute of Scie Korea Advanced Institute of Scie KAIST Microsoft Research Asia MSRA Vision-language models

Logit-Conditioned Diffusion Decoding for Frozen Discrete-Token VLMs

Ji Woo Hong, Hee Suk Yoon, Gwanhyeong Koo, Eunseop Yoon and 4 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 2026Korea Advanced Institute of Scie KAIST Machine unlearning

Example-Based Spatial Guidance for Training-Free Concept Erasure in Diffusion Models

Younghwan Kil, Joonhyeong Park, Giung Nam, Jinwoo Shin and 1 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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026Technion New York Courant Institute of Mathematica KAIST Event sequences

Competing Event Models: Next Event Prediction Under Interventions

Yoav Wald, Xiang Gao, Sumit Chopra, Juho Lee and 1 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.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST Unified multimodal models

Context-Aware Generative Imputation for Robust Multimodal Learning in Missing Modality Scenarios

Jungwon Choi, Juho Lee

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.

AI panel: 1 of 20 reviewers recommend it

lenient 1/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST U Michigan Korea Advanced Institute of Scie Offline RL

Offline Constrained Reinforcement Learning under Partial Data Coverage

Seokmin Ko, Ambuj Tewari, Kihyuk Hong

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 2026Independent Researcher KAIST Instruction tuning

BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning

Juyoung Park, Heejun Lee

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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST KAIST, Korea Advanced Institute LLM reasoning & chain of thought

Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation

Taehoon Kim, Seunggeun Cho, Dongsu Han

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.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST Korea Research Institute of Chem Genentech Korea Advanced Institute of Scie Materials & chemistry

A Structured LLM Framework for Inorganic Material Synthesis Planning

Heewoong Noh, Gyoung S. Na, Namkyeong Lee, Chanyoung Park

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 2026KAIST Genentech HITS Korea Advanced Institute of Scie AI-CRED, KAIST Genomics & single-cell

scTrilemma: Balancing Identity, Invariance, and Reconstruction in Single-Cell Representation Learning

Yunhak Oh, Yoonho Lee, Junseok Lee, Namkyeong Lee and 8 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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026NAVER CLOUD KAIST Korea Advanced Institute of Scie NAVER LLM pretraining & scaling laws

A Simple Unigram Cross-Entropy Lens on the Lexical Imprint of Pre-training Data

Jeonghoon Kim, Woojin Chung, Woomin Song, Cheonbok Park and 2 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.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026Naver Corporation KENTECH KAIST Korea Advanced Institute of Scie Vision-language models

Training-Free Active Test-Time Adaptation for Vision-Language Models

Jihwan Bang, Sumyeong Ahn, Hwanjun Song, Jae-Gil Lee

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 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 2026U Electronic Science and Technol College of Information and Contr Xi'an University of Archite KAIST Adversarial robustness

Dual Feature-Relational Alignment for Transferable Targeted Attacks on MLLMs

Dongshen Han, Xiaorong Tian, Sheng Zheng, Zishan Huang and 5 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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Korea Advanced Institute of Scie Representation & contrastive learning

BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone

Doojin Baek, Junyeob Baek, Mingyu Jo, Hosung Lee and 3 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 2026KAIST Mila - Quebec Artificial Intelli New York LawZero / Mila / U. Montreal Bayesian & probabilistic methods

Probabilistic Recursive Reasoning

Junyeob Baek, Mingyu Jo, Minsu Kim, Mengye Ren 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.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026U Texas at Austin U Alberta Texas A&M University - Colle KAIST Multi-agent RL

Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL

Dongsu Lee, Sooraj Sathish, Joonkyung Kim, Woojun Kim and 1 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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026U Tübingen Technische Universität Darmstadt U Edinburgh KAIST Google Multimodal reasoning

CRISP: Compositional Reasoning over Images via Stackable Programs for VLMs

Arnas Uselis, Yujin Jeong, Yanpeng Zhao, Alexander Rubinstein and 3 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.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST KAIST, Korea Advanced Institute Korea Advanced Institute of Scie Diffusion models

Improving Guidance-Free Visual Generation via Self-Contrastive Alignment for Likelihood Estimation

Jiwan Hur, DongJae Lee, Dongyeun Lee, Gyojin Han 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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST Privacy

Local FDR Membership Inference Attacks: Multiple Testing and the Role of Ridge Regularization

Jinyoung Hong, Bonwoo Lee, Jeongyoun Ahn

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.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026U Wisconsin-Madison KRAFTON KAIST RL for LLMs

Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs?

Shuibai Zhang, Junhyuck Kim, Gyeongman Kim, Jaewoong Cho

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 2026SolverX Korea Advanced Institute of Scie Seoul National Telepix Arizona State Physics-informed ML & PDEs

PDE-PFN: Prior-Data Fitted Neural PDE Solver

Jaehyeon Park, Mingu Kang, Dongseok Lee, Woojin Cho and 4 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.

AI panel: 1 of 20 reviewers recommend it

lenient 1/5

medium 0/10

strict 0/5

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Autoregressive generation

Rethinking Memorization–Generalization Trade-Off in Generative Models

Jiseok Chae, Kyuwon Kim, Donghwan Kim

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 1/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST AI Korea Advanced Institute of Scie KAIST LLM agents & planning

DoG: Sniffing Out Overconfidence in LLM Agents via Post-hoc Trajectory Restructuring

Hyunjun Jeon, Dongha Lim, Kunwoong Kim, Daewon Choi and 1 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.

67%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST KAIST, AITRICS Molecules & drug discovery

Synthon Contrastive Learning for Synthesizable 3D Molecule Generation

Nahyun Kim, Seul Lee, Sung Ju Hwang

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · 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 2/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026DeepAuto.ai KAIST KAIST, AITRICS Time series forecasting

Visual Anchoring for Scenario-Guided Forecasting

Patara Trirat, Jay Heo, Heejun Lee, Sung Ju Hwang

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.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST Efficient inference & serving

Global Importance Estimation for KV Cache Eviction

Seojin Kim, Noseong Park

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 2026Korea Advanced Institute of Scie KAIST Multi-agent RL

Rethinking Credit Assignment in Cooperative MARL via Interventional Reward Response

Chamjin Joo, Myounghoon Ha, Sang Wan Lee

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.

AI panel: 1 of 20 reviewers recommend it

lenient 1/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie Korea Advanced Institute of Scie KAIST UNIST Multi-agent RL

MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals

Jiwon Jeon, Myungsik Cho, Woojun Kim, Seongmin Kim and 3 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.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Korea Advanced Institute of Scie Game playing

AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games

Woohyeon Byeon, Seongmin Kim, Jiwon Jeon, Woojun Kim and 1 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.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

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 2026KAIST AI KAIST Diffusion models

Temporal Alignment Guidance: On-manifold Sampling in Diffusion Models

Youngrok Park, Hojung Jung, Sangmin Bae, Se-Young Yun

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.

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026KAIST KAIST AI Korea Advanced Institute of Scie Diffusion models

DualDrift: Combining Forward and Reverse Drifts for One-Step Generative Modeling

Hojung Jung, Juhyeong Kim, Jaehyun Kwak, Boryeong Cho 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.

AI panel: 1 of 20 reviewers recommend it

lenient 1/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026Korea Institute of Science and T KAIST Yonsei Korea Institute for Advanced Stu Imitation learning

Reconciling Safety and Performance via Dual-Expert Offline Imitation Learning

Seokin Seo, Sung Kuk Shyn, Minji Seo, Yisoo Lee and 3 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.

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie U Washington Exploration

Mitigating Overgeneralization in RND via Spectral Target Design

Minseok Jeong, Yechan Lee, Hyewon Choi, Jeongyong Yang 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.

83%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Flow matching

Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightness

SelFix selects fixed-point solutions by trajectory straightness for rectified flow inversion, improving reconstruction and editing accuracy.

Semin Kim, Jihwan Yoon, Seunghoon Hong

Sydney Poster Session 2, Tue, Dec 8, 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.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie IBM Research - China Fudan RL for LLMs

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR

RLRT reverses teacher signals in self-distillation to reinforce student reasoning tokens on successful rollouts, substantially outperforming exploration baselines across Qwen3 models.

Jeonghye Kim, Jiwon Jeon, Dongsheng Li, Yuqing Yang

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 15 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 3/5

medium 7/10

strict 1/5

83%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Ghent Korea Advanced Institute of Scie Samsung Medical Center Clinical NLP & EHR

Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records

EHR-ReasonCon introduces a reasoning-intensive benchmark for clinical note-table consistency verification, and EHR-Inspector achieves state-of-the-art results via LLM-based verification with table exploration.

Yeonsu Kwon, Jiho Kim, Junseong Choi, Paloma Rabaey and 9 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.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Seoul National Learning theory

Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions

SupSplitLog achieves near-optimal logistic bandit regret without context diversity assumptions via sample splitting and Newton-type corrections.

Seoungbin Bae, Dabeen Lee

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.

86%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Korea Advanced Institute of Scie Materials & chemistry

AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction

AtomMOF uses all-atom flow matching to predict MOF and adsorbate structures directly from 2D graphs, improving match rates and sampling efficiency.

Nayoung Kim, Honghui Kim, Sihyun Yu, Minkyu Kim and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · Code ★ 19

– 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 2026Korea Advanced Institute of Scie KAIST KAIST, AITRICS Privacy

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

SELFCI uses complementary self-distillation to decouple information suppression from task resolution, improving contextual integrity without degrading utility.

Sangwoo Park, Woongyeong Yeo, Yumin Choi, Hyomin Lee and 5 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 29 on Hugging Face · Code ★ 6

– 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.

83%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Diffusion models

LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling

LENS modulates low-frequency noise subspaces via a lightweight network to boost distilled diffusion quality, cutting compute and parameters by orders of magnitude versus prior methods.

Haewon Jeon, Si-Hyeon Lee

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.

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST Offline RL

Trust Region Q Adjoint Matching

TRQAM introduces trust-region Q-adjoint matching with adaptive path-space KL control via projected dual descent, enabling stable off-policy flow-policy fine-tuning and achieving 68% success on OGBench.

Yonghoon Dong, Kyungmin Lee, Changyeon Kim, Jaehyuk Kim and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 24 on Hugging Face · Code ★ 20

– 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.

91%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie AutoML & architecture search

Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization

Kernel Discovery uses an LLM-driven evolutionary framework to search broad kernel spaces for high-dimensional Bayesian optimization, achieving average rank 1.2 out of 17.

Taeyoung Yun, Woocheol Shin, Inhyuck Song, Jaewoo Lee and 1 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.

86%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Google RL for LLMs

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

Echo-GRPO rewrites off-policy reasoning traces into a student VideoLLM's idiolect to avoid gradient clipping, improving reasoning distillation across backbones and benchmarks.

Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 24 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.

86%Must read

?Must readVote to see the score

NeurIPS 2026KAIST KAIST AI Imperial College London KTH LLM evaluation & benchmarks

Instance-Optimal Estimation with Multiple LLM Judges on a Budget

EST-IVWE adaptively allocates a budget across judges and instances via biased variance estimates to achieve instance-optimal score estimation, with matching local minimax lower bounds.

Junghyun Lee, Sanghwa Kim, Yassir Jedra, Alexandre Proutiere 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.

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Korea Advanced Institute of Scie Molecules & drug discovery

Screening Lipid Nanoparticles through Structure-Ratio Alignment

STRATA predicts lipid nanoparticle transfection by aligning molecular structure and composition ratio representations to model component interactions. It improves accuracy and generalizes to unseen molecules and ratios.

Yoonho Lee, Yunhak Oh, Hoyoung Choi, Chanyoung Park

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 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.

91%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Carnegie Mellon School of Computer Science, Carn Korea Advanced Institute of Scie CMU, Carnegie Mellon LLM pretraining & scaling laws

Flow Map Language Models: One-step Language Modeling via Continuous Denoising

Continuous flow language models outperform discrete diffusion in quality and speed, and distilling their unique flow map enables one-step generation surpassing eight-step discrete diffusion.

Chanhyuk Lee, Jaehoon Yoo, Manan Agarwal, Sheel Shah and 5 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 4 on Hugging Face · Code ★ 172

– 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.

70%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Korea Telecom Research Korea Advanced Institute of Scie 3D vision & reconstruction

DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions

DySurface bridges explicit dynamic Gaussians and implicit SDFs via voxel guidance to reconstruct temporally consistent, watertight 4D surfaces.

Minje Kim, Younghyun Noh, Jaesoon Kim, Tae-Kyun Kim

Sydney Poster Session 6, Thu, Dec 10, 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.

88%Must read

?Must readVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST Korea Advanced Institute of Scie Vision-language models

Multi-view Relational Distillation for Spatial Reasoning with Vision-Language Models

Multi-view relational distillation improves vision-language model spatial reasoning by distilling cross-view patch similarities rather than features, preserving language alignment with minimal overhead.

Kiet Nguyen, Hanbo Shim, Jinwoo Kim, Seunghoon Hong

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.

83%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Georgia Institute of Technology Diffusion models

Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning

CoFi separates global structure formation from local refinement via coarse scaffolds, improving long-horizon compositional diffusion coherence with 2-8x fewer denoiser evaluations.

Byoungwoo Park, Utkarsh Mishra, Jaemoo Choi, Juho Lee and 1 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.

83%Must read

?Must readVote to see the score

NeurIPS 2026Department of Computer Science, KAIST Google, TUM ETH Zurich ETHZ - ETH Zurich Flow matching

GenRec: Knowing Where to Reconstruct and Where to Generate

GenRec separates reconstruction and generation via observation masks to preserve fidelity in visible regions while synthesizing plausible unobserved content.

Ata Çelen, Jaewoo Jung, Federico Tombari, Marc Pollefeys and 3 more

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.

70%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026U Texas at Austin KAIST Korea Advanced Institute of Scie AutoML & architecture search

Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization

Reformulating constrained black-box optimization as latent-space posterior inference with flow-based surrogates and amortized diffusion sampling improves high-dimensional optimization performance.

Kiyoung Om, Kyuil Sim, Taeyoung Yun, Hyeongyu Kang and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 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.

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.

80%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Spatio-temporal forecasting

Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions

MASF redesigns score-based filtering with a measurement-aware forward process that transforms states toward measurements, yielding accurate likelihood scores, stronger assimilation under sparse nonlinear observations, and up to 28.2x faster inference.

EUNBEE YOUN, Donghan Kim, Dae W 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.

86%Must read

?Must readVote to see the score

NeurIPS 2026OralKAIST Korea Advanced Institute of Scie Korea Advanced Institute of Scie Amazon Multi-agent LLM systems

ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling

ExComm detects cross-agent factual conflicts during exploration to correct errors via soft belief updates and trajectory diversification, improving test-time scaling by up to 5.7%.

Woomin Song, Beomjun Kim, Daewon Choi, Sai Muralidhar Jayanthi and 3 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.

AI panel: 14 of 20 reviewers recommend it

lenient 4/5

medium 10/10

strict 0/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie NVIDIA Diffusion models

Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion

CDM amortizes twisted SMC for discrete diffusion by learning a twist function via contrastive samples, adding under 5% overhead while outperforming baselines on text, DNA, protein, and LLM tasks.

Jaihoon Kim, Taehoon Yoon, Prin Phunyaphibarn, Seungjun Kim and 2 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.

AI panel: 11 of 20 reviewers recommend it

lenient 3/5

medium 7/10

strict 1/5

83%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Multimodal reasoning

On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs

Attention sinks in Omni-LLMs serve as global representation biases rather than redundant heads, and the proposed OutRo decoding method improves video reasoning with minimal overhead.

Suho Yoo, Youngjoon Jang, Joon Son Chung

Sydney Poster Session 6, Thu, Dec 10, 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.

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Embodied agents

CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter

CrafterDojo introduces CrafterVPT, CrafterCLIP, and CrafterSteve-1 alongside toolkits to unlock Crafter as a lightweight testbed for open-ended embodied agents.

Junyeong Park, Hyeonseo Cho, Sungjin Ahn

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.

80%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Efficient inference & serving

PatchKV: Weight Space Compensation of KV Cache

PatchKV improves KV cache compression by computing a context-specific weight patch via ridge regression to align compressed and full-cache activations, preserving long-context accuracy without increasing per-query cost.

Chanryeol Lee, Chanhyuk Lee, Yeonwoo Choi, Donggyun Kim 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 5/5

medium 7/10

strict 0/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Korea KAIST Korea Advanced Institute of Scie Video generation

Retrieve What’s Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation

COVRAG uses depth-based coverage maps and residual-gain frame selection to improve long-horizon geometric consistency in autoregressive video generation with low latency.

Minseok Joo, Dogyun Park, Taehoon Lee, Kyujin Lee and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 25 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

ECCV 2026WorkshopKAIST Korea Advanced Institute of Scie KAIST AI Video generation

CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation

CRePE encodes tokens as depth-aware distributions along curved unified-camera rays to unify camera control, lens geometry, and external geometry guidance in video generation.

Seonghyun Jin, youngmin Kim, Sunwoo Park, Jong Chul Ye

Sydney Poster Session 3, Wed, Dec 9, 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.

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST Korea Advanced Institute of Scie Korea Advanced Institute of Scie Proteins

Atom-level Protein Representation Learning Improves Protein Structure Prediction

TriProRep pretrains structure-aware protein representations via joint amino-acid, backbone, and full-atom token recovery, improving homodimer co-folding, interaction prediction, and monomer structure prediction over sequence-only models.

Taewon Kim, Hyosoon Jang, Hyunjin Seo, Seonghwan Seo and 5 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.

80%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Segmentation

Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement

A preference-guided framework adapts open-vocabulary segmentation using prompt disagreement as binary supervision, yielding consistent benchmark gains without pixel-level masks.

Hyun-Kurl Jang, Jihun Kim, Kuk-Jin Yoon

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

– 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

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026MPI-SWS Max Planck Institute for Softwar KAIST RL for LLMs

GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards

GeoX acquires geospatial reasoning via self-play with executable programs and verifiable rewards, improving base VLMs up to 5.5 points without large-scale human-curated data.

Kyeongjin Ahn, Seungeon Lee, Krishna Gummadi, Meeyoung Cha

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 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.

86%Must read

?Must readVote to see the score

NeurIPS 2026KAIST NVIDIA Korea Advanced Institute of Scie Tool use & function calling

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

SpatialClaw uses a stateful Python kernel with step-wise code execution to enable flexible spatial reasoning, achieving 59.9% average accuracy across 20 benchmarks.

Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su and 7 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.

70%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026U Oxford Technische Universität Wien KAIST Department of Computer Science, TU Wien, AITHYRA, University of LLM agents & planning

RelAgent: LLM Agents as Data Scientists for Relational Learning

RelAgent is an LLM agent that builds SQL feature queries and selects predictive models for relational learning, yielding fast, interpretable predictions deployable via standard databases.

Xingyue Huang, Louis Tichelman, Jinwoo Kim, Krzysztof Olejniczak and 1 more

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.

80%Must read

?Must readVote to see the score

NeurIPS 2026KAIST LG AI Research KAIST AI Seoul National Graph generation

MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

MolHIT uses hierarchical discrete diffusion and decoupled atom encoding to generate molecular graphs with near-perfect validity, surpassing 1D baselines on MOSES.

Hojung Jung, Rodrigo Hormazabal, Jaehyeong Jo, Youngrok Park and 4 more

Sydney Poster Session 6, Thu, Dec 10, 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.

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST U California, Los Angeles Seoul National Model-based RL

Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret

Strong duality holds for weakly communicating average-reward CMDPs, yielding a primal-dual algorithm with O(T^{2/3}) regret and constraint violations.

Kihyun Yu, Beomhan Baek, Dabeen Lee

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.

AI panel: 10 of 20 reviewers recommend it

lenient 2/5

medium 5/10

strict 3/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Seoul National Learning theory

Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret

CQB-η-2 improves contextual queueing bandit queue length regret to O~(T^-1/2) via phased exploration, matching a minimax lower bound.

Seoungbin Bae, Dabeen Lee

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 1/5

medium 6/10

strict 3/5

88%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Video-language models

Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs

VideoLLMs lose temporal representations across layers, so Temporal Activation Injection reinforces fading divergence at inference to improve video reasoning without training.

Youngwoo Shin, Yusung Ro, Minseo Kim, Junmo Kim

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

– 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 4/5

medium 9/10

strict 2/5

72%Highly rated

?Highly ratedVote to see the score

ICML 2026WorkshopKorea Advanced Institute of Scie KAIST KAIST AI Diffusion models

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models

Reward Score Matching unifies reward-based diffusion and flow fine-tuning via value-guided score matching, clarifying tradeoffs and yielding simpler, more efficient designs.

Jeongjae Lee, Jinho Chang, Jeongsol Kim, Jong Chul Ye

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.

AI panel: 8 of 20 reviewers recommend it

lenient 4/5

medium 4/10

strict 0/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST KAIST, AITRICS Unified multimodal models

ES-Merging: Biological MLLM Merging via Embedding Space Signals

ES-Merging estimates merging coefficients from embedding space signals to combine biological multimodal models, improving cross-modal reasoning and single-modal knowledge preservation.

Wonbin Lee, Dongki Kim, Sung Ju Hwang

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

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie The University of Tokyo Rakuten Group Pruning & sparsity

POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models

POP enables context-conditioned online structural pruning of foundation models via coarse-to-fine partitioned masking without offline calibration or retraining, improving accuracy with lower latency.

Yi Chen, Wonjin Shin, Shuhong Liu, Tho Mai 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.

AI panel: 11 of 20 reviewers recommend it

lenient 5/5

medium 6/10

strict 0/5

83%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Multimodal reasoning

VocalCoachBench: Benchmarking Audio-Language Models on Expert Feedback for Singing

VocalCoachBench benchmarks audio-language models on expert singing feedback, revealing they identify broad vocal issues but fall below baselines on fine-grained diagnosis and strict alignment.

Hayeon Bang, Hounsu Kim, Wonil Kim, Juhan Nam

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.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 5/10

strict 3/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST POSTECH Bandits & online learning

Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences

Online RLHF with generalized bilinear preferences achieves polylogarithmic regret via generic strong convexity and skew-symmetry, proving fast rates are not KL-specific.

Junghyun Lee, Minju Hong, Kwang-Sung Jun, Chulhee Yun and 1 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.

AI panel: 10 of 20 reviewers recommend it

lenient 3/5

medium 5/10

strict 2/5

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Yonsei KAIST Machine unlearning

Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning

SAEParate clusters diffusion latent features by concept via contrastive learning to improve precise concept unlearning with reduced cross-concept interference.

Hyeonjin Kim, Hangyeol Jung, Heechan Yun, Sungjun Yun 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.

AI panel: 8 of 20 reviewers recommend it

lenient 5/5

medium 3/10

strict 0/5

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.

AI panel: 14 of 20 reviewers recommend it

lenient 4/5

medium 8/10

strict 2/5

88%Must read

?Must readVote to see the score

NeurIPS 2026ELLIS Tübingen U Tübingen KAIST Vision-language models

Half-Truths Break Similarity-Based Retrieval

CLIP-style dual encoders often prefer half-true image descriptions with incorrect added details over correct shorter ones due to weak part-level supervision; CS-CLIP improves half-truth accuracy to 69.3% through component-level contrastive fine-tuning.

Bora Kargi, Arnas Uselis, Seong Joon Oh

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026 · ▲ 6 on Hugging Face · Code ★ 15

– 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 4/5

medium 9/10

strict 2/5

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie VGG, University of Oxford Google DeepMind KAIST ENPC / IP Paris Unified multimodal models

Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment

A unified sign-language model with privacy-preserving keypoint inputs and sliding perceiver aggregation achieves state-of-the-art translation and alignment on BSL and generalizes to ASL.

Youngjoon Jang, Liliane Momeni, Zifan Jiang, Joon Son Chung and 2 more

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

medium 2/10

strict 0/5

91%Must read

?Must readVote to see the score

NeurIPS 2026New York NYU KAIST Feature attribution

Explanation Multiplicity in SHAP: Characterization and Assessment

SHAP produces multiple valid yet different explanations for identical predictions due to intrinsic stochasticity, and magnitude-based stability metrics mask substantial rank instability across datasets and models.

Hyunseung Hwang, Seungeun Lee, Lucas Rosenblatt, Steven Whang and 1 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.

AI panel: 17 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 4/5

80%Must read

?Must readVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie Ajou Korea Advanced Institute of Scie KAIST Vision-language-action models

Pose6DAug: Physically Plausible Multi-View Object Swapping for Robot Data Augmentation

Pose6DAug augments robot training by swapping objects in successful episodes via 3D mesh pose trajectories, improving VLA success on novel objects by 16.5%.

Jonghoon Lee, Seong Hyeon Park, Minha Lee, Byungwoo Jeon 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 5/5

medium 7/10

strict 0/5

86%Must read

?Must readVote to see the score

NeurIPS 2026U Bristol Korea Advanced Institute of Scie KAIST Diffusion models

Probability-Conserving Flow Guidance

Guidance decomposes into divergence and score-parallel terms via the continuity equation; AdaMaG bounds both to improve flow-based generation realism and reduce hallucinations without added cost.

Parsa Esmati, Junha Hyung, Amirhossein Dadashzadeh, Jaegul Choo and 1 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.

AI panel: 14 of 20 reviewers recommend it

lenient 3/5

medium 8/10

strict 3/5

91%Must read

?Must readVote to see the score

NeurIPS 2026Amazon / University of Minnesota KAIST Seoul National U Minnesota LLM agents & planning

Meta$^n$: Recursive Self-Improvement through Emergent Depth

Meta^n fixes its meta-operation and recurses on growing inputs to build unbounded self-improving agent depth, outperforming prior agents across eight benchmark families including ARC-AGI-2.

Zae Myung Kim, Young-Jun Lee, Seungyeon Jwa, Dongyeop Kang

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 17 on Hugging Face

– 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.

AI panel: 17 of 20 reviewers recommend it

lenient 4/5

medium 10/10

strict 3/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Kaist AI Korea KAIST AI Image restoration

Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models

AVIS uses autoregressive diffusion for streaming video inverse problems, cutting latency from 114s to 4s and boosting throughput to 1.18 FPS with better quality, while AVIS Flash reaches 5.91 FPS.

Taesung Kwon, Jonghyun Park, Hyungjin Chung, Jong Chul Ye

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.

AI panel: 10 of 20 reviewers recommend it

lenient 5/5

medium 5/10

strict 0/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026KAIST Optimization

Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles

Schedule-Free gradient and stochastic gradient descent achieve optimal nonconvex convergence rates and escape strict saddles with small perturbations via Lyapunov analysis.

Jiseok Chae, Donghwan Kim

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.

86%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Ajou Korea Advanced Institute of Scie Yonsei Multimodal reasoning

ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation

A new benchmark reveals current multimodal AI fails at multi-step ECG reasoning, achieving near-zero completion in linking clinical criteria to visual signal evidence.

Jungwoo Oh, Hyunseung Chung, Junhee Lee, Min-Gyu Kim and 5 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 6 on Hugging Face · Code ★ 18

– 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 2026Korea Advanced Institute of Scie KAIST Kakao Brain Kakao Corp kakaocorp Instruction tuning

Mixture-Trained Merging for Unified Multi-Objective Models

Mixture-Trained Merging trains multi-objective branches on biased data mixtures to enable compatible weight-space merging, outperforming naive merging while preserving distinct capabilities.

SeongHyeon Kim, Chaeyun Jang, Seungyoo Lee, Jiyeon Ham and 3 more

Sydney Poster Session 1, Tue, Dec 8, 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

89%Must read

?Must readVote to see the score

NeurIPS 2026Korea Korea Advanced Institute of Scie UW-Madison KAIST Diffusion models

Learning to Solve Generative ODEs Beyond the Linear Span

SpanLift augments scalar ODE solvers with a spatial residual operator to overcome span limitations, achieving state-of-the-art few-step generative sampling without extra model evaluations.

Sihyeon Kim, Seunghun Lee, Vikas Singh, Hyunwoo J. Kim

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.

AI panel: 16 of 20 reviewers recommend it

lenient 4/5

medium 10/10

strict 2/5

83%Must read

?Must readVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST 42dot 3D vision & reconstruction

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

TrackCraft3R repurposes video diffusion transformers for feed-forward dense 3D tracking via dual latents and temporal alignment, achieving state-of-the-art results with lower memory and faster speed.

Jisu Nam, Jahyeok Koo, Soowon Son, Jaewoo Jung and 3 more

Sydney Poster Session 2, Tue, Dec 8, 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.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 1/5

80%Must read

?Must readVote to see the score

NeurIPS 2026KAIST AI Korea Advanced Institute of Scie KAIST Efficient inference & serving

BASTION: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting

BASTION uses budget-aware tree-structured block diffusion drafting and adaptive expansion to achieve up to 6.61x speedup over autoregressive decoding, outperforming baselines by 39%.

Soowon Oh, Nam Cao, Yujin Kim, Hojung Jung and 3 more

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 2/5

medium 9/10

strict 1/5

83%Must read

?Must readVote to see the score

NeurIPS 2026KAIST Korea Advanced Institute of Scie Korea Advanced Institute of Scie Korea Advanced Institute of Scie Molecules & drug discovery

A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning

Boltz2's protein-ligand co-folding representations match or outperform standalone models on ADMET, generative modeling, and ligand optimization tasks while complementing conventional molecular supervision.

Hyosoon Jang, Hyunjin Seo, Honghui Kim, Taewon Kim and 3 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.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 1/5