Good Papers

Showing papers from The University of Hong Kong Show all papers

78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The University of Hong KongU WaterlooUCSCMetaMassachusetts Institute of TechnUnified multimodal models

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Tuna-2 replaces vision encoders with patch embeddings for end-to-end pixel-space multimodal understanding and generation, achieving state-of-the-art results that outperform encoder-based designs at scale.

Zhiheng Liu, Weiming Ren, Xiaoke Huang, Shoufa Chen and 11 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 70 on Hugging Face · Code ★ 756

– ReadersNo votes yet. 1 from authors or colleagues not counted
11/20 AI panelreviewers recommend it

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

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

AI panel: 11 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 1/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Zhejiang University, WestlakeU Science and Technology of ChinTencentCity University of Hong KongThe University of Hong Kong3D generation

MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation

Zhiqi Li, Wenhuan Li, Tengfei Wang, Zhenwei Wang and 7 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.

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 2026The University of Hong KongU BirminghamU SydneyOptimization

Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems

Shuang Zeng, Yunwen Lei, Yiming Ying

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 2026U Hong KongMMLab@CUHKJD Explore AcademyThe University of Hong KongVisual grounding

Diffusion Fine-Tuning: Iterative Refinement for Advanced Grounding with Diffusion Large Language Models

Zhangyang Qi, Jinsong Li, Jiaqi Wang, Hengshuang Zhao

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 2026The University of Hong KongThe Univeristy of HongkongDeep learning theory

Looped Transformers with Layer Normalization Provably Learn the Power Method

Lyumin Wu, Chenyang Zhang, Yuan Cao

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 0/5
medium 0/10
strict 1/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Huazhong University of Science aThe University of Hong KongThe Chinese University of Hong KU Hong KongShanghai Artificial IntelligenceVideo-language models

StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models

Zhe Liu, Jinghua Hou, Yuxiang Lu, Zhenya YANG and 6 more

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

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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

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

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 2026PekingHunYuanTencentTEGThe University of Hong KongVideo generation

ReGen: Agentic Video World Modeling with Synergized Reasoning and Generation

Chenguo Lin, Yu Tang, Weiqiao Zheng, Enhua Jiang and 10 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.

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 2026Shanghai JiaotongTencent YoutuTencent Youtu LabTongjiThe International Digital EconomVisual grounding

HiLoc: A Hierarchical Representation Method for Spatial Localization in Multimodal Large Language Models

Evelyn Zhang, Fufu Yu, Hanjun Li, Aoqi Wu and 7 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.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
69%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The Chinese University of Hong KBeihangThe Chinese University of Hong KByteDance Inc.TencentJailbreaks & red teaming

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents

Zhengyang Tang, Yi Zhang, Chenxin Li, Xin Lai and 17 more

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

– ReadersNo votes yet
3/20 AI panelreviewers recommend it

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

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

AI panel: 3 of 20 reviewers recommend it
lenient 2/5
medium 1/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026ByteDance, Inc.Institute of automation, ChineseByteDance / TikTokBytedanceInstitute of Automation, ChineseVideo-language models

CineMME: Benchmarking Fine-Grained Perception and Plot Reasoning in Multimodal Large Language Models

Jin Liu, Dawei Du, Yexiang Liu, Sijie Zhu and 6 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.

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 2026U California, San DiegoThe University of Hong KongUCSDAgent benchmarks & environments

ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making

Liu Dai, Haina Wang, Weikang Wan, Hao Su

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 2026The University of Hong KongU HoustonMeta, transfer & few-shot learning

From Generic to Dedicated: A Novel Optimizer for Online Continual Learning

Yongyi Wu, Zheng Wang, Sen Lin

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.

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 2026The Hong Kong University of ScieNanjingTencent AI LabU Science and Technology of ChinTongjiDeep RL

Canopy: Tree-Aware Rollout Scheduling for Agent Reinforcement Learning

Feiyuan Zhang, LI Pengbo, Ziniu Li, Yuhao Jiang and 8 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.

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 2026The University of Hong KongHong Kong PolytechnicU Hong KongProbing & representation analysis

From Pixels to Concepts: Do Segmentation Models Understand What They Segment?

Shuang Liang, Zeqing Wang, Yuxian LI, Xihui Liu and 1 more

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

– 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026SpotlightBeihangZhejiangThe University of Hong KongTsinghuaXiamenFlow matching

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

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

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

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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

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

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 2026City University of Hong KongXidianColumbiaThe University of Hong KongVideo-language models

Diagnosing and Correcting Bias in MLLM for Long Video Understanding

Xusheng Liang, Jianqiao Sun, Hao Zhang, Yulei Niu and 2 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 1/5
medium 1/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The University of Hong KongIn-context learning & prompting

One-Layer Transformers Provably Learn In-Context K-Nearest Neighbor Prediction with Chain-of-Thought

Lyumin Wu, Yuan Cao

Sydney Poster Session 4, Wed, Dec 9, 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 2026CUHKHKUTsinghua universityThe University of Hong KongDepartment of Computer Science aRL for LLMs

Fast-RL: Accelerating Reinforcement Learning for LongCoT Reasoning Models

Sitong Wu, Haoru Tan, bin xia, Bei Yu and 2 more

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

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

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

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

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 2026CUHKHKUThe University of Hong KongDepartment of Computer Science aRL for LLMs

Historical Relative Policy Optimization for Bootstrapping LLM Reasoning

Sitong Wu, Haoru Tan, Bei Yu, Xiaojuan Qi 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.

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 2026SpotlightThe University of Hong KongThe University of TokyoU Hong KongU British ColumbiaLLM agents & planning

RAOP: Step-Level Resource Orchestration for LLM Agents across Edge and Cloud

Jinze Li, Xin Yang, Shuo Yang, Jinfeng Xu and 1 more

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

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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

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

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 2026ZhejiangBytedanceThe University of Hong Kong3D vision & reconstruction

Beyond Spatial and Temporal Priors: A Generalizable Approach for Dense Correspondence Matching

Luping Liu, Bingyi Kang, Yifan Wang, Dong Xu

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.

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 2026Origin AIOrigin WirelessOrigin ResearchOrigin Research Origin Wireless AITime series foundation models

AmbientFM: A Foundation Model for Ambient Sensing

Guozhen Zhu, Yuqian Hu, Sakila S Jayaweera, Wei-Hsiang Wang and 5 more

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

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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

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

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 2026Nanyang TechnologicalThe University of Hong KongMeituanU Science and Technology BeijingSoutheastUnified multimodal models

LEAF: Language-EEG Aligned Foundation Model for Brain-Computer Interfaces

Muyun Jiang, Shuailei Zhang, Zhenjie Yang, Wu Mengjun and 9 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.

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 2026The University of Hong KongU Hong KongTencent3D generation

Seeing Both the Forest and the Trees: Reusing Holistic 3D Priors for Part-Decomposed Generation

Yiqun Zhao, Binbin Huang, Haobin Duan, Zibo Zhao 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.

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 2026U Hong KongThe University of Hong KongTencentUC Berkeley3D generation

Generative Structure from Motion with Native 3D Diffusion

Haobin Duan, Binbin Huang, Mochu Xiang, Yiqun Zhao and 3 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026The University of Hong KongU Hong KongDeep RL

Multi-Stage Planning from Single-Stage Data: Reinforcement Learning Helps Composition but Requires Anchoring

Boyuan Zheng, Zidong Liu, Yingyu Liang

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

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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

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

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 2026Chinese University of Hong Kongthe University of Hong Kong, UniThe University of Hong KongDepartment of Computer Science aAlignment & preference optimization

Bias-Variance Optimized Preference Optimization for Large Reasoning Models

Mingkang Zhu, Xi Chen, Bei Yu, Hengshuang Zhao 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.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Universidad Rey Juan CarlosRobloxThe University of Hong KongSnap Inc.Universidad Rey Juan Carlos. VATVideo generation

Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes

C2R generates realistic, temporally consistent urban crowd videos from coarse 3D simulations via a neural renderer guided by text and a synthetic-real domain-hedging strategy.

Gonzalo Gomez-Nogales, Yicong Hong, Chongjian GE, Peiye Zhuang and 3 more

Sydney Poster Session 6, Thu, Dec 10, 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.

AI panel: 9 of 20 reviewers recommend it
lenient 5/5
medium 4/10
strict 0/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Tsinghua Shenzhen International Tsinghua University, TsinghuaTsinghuaHarbin Institute of TechnologyThe University of Hong KongPruning & sparsity

EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning

Event Cascade Pruning uses event-camera motion cues to prune video tokens in first-person spatial reasoning, improving accuracy by 1.31 points with 80% fewer tokens and 1.89x speedup.

Pengtao Ma, Ziliang Zhou, Ciyu Ruan, Haoyang Wang and 6 more

Sydney Poster Session 6, Thu, Dec 10, 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.

AI panel: 9 of 20 reviewers recommend it
lenient 5/5
medium 4/10
strict 0/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Johns HopkinsCalifornia Institute of TechnoloNortheasternThe University of Hong KongJHULLM agents & planning

How to Interpret Agent Behavior

ACT*ONOMY introduces a three-level taxonomy of 10 actions and 46 subactions for describing autonomous agent behavior at runtime, plus an open repository and automated analysis pipeline that compares behavioral profiles and surfaces failure patterns.

Sophia Gao, Kaiser Sun, Jen-Tse Huang, Katherine Van Koevering and 7 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
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
91%Must read
?Must readVote to see the score
NeurIPS 2026The University of Hong KongImmunocan BiotechPekingInternational Digital Economy AcInternational Digital Economy AcMolecules & drug discovery

Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization

SGRPO directly rewards set-level diversity via leave-one-out contributions in a flexible GRPO framework, expanding the utility-diversity Pareto frontier across biomolecular design tasks.

Xinwu Ye, He CAO, Li Hao, Bin Feng and 4 more

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

– 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 9/10
strict 3/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U Hong KongSouthern University of Science aHuazhong University of Science aU Michigan - Ann ArborShenzhen Institutes of Advanced Navigation & SLAM

SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control

SRL-MPC integrates reinforcement-learned parameter updates with shape-aware model predictive control via geometric separation features to navigate dense heterogeneous robot crowds safely and adaptively.

Ruihua Han, Rui Gao, Zhe Liu, Xinyi WANG and 5 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 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 5/5
medium 4/10
strict 0/5
80%Must read
?Must readVote to see the score
NeurIPS 2026The University of Hong KongFudanShanghai Jiao TongShanghai JiaotongTsinghuaRobot manipulation

HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing

HandEdit provides a 200M-instance benchmark and dataset for transforming egocentric human hands into diverse dexterous robot embodiments via image editing. It evaluates 11 baselines across hand-only and hand-arm tracks with embodiment-aware metrics.

Zhenjie Yang, Xingyu Jiao, Guopeng Zhong, Shuzhe Yang and 17 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.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 6/10
strict 1/5
80%Must read
?Must readVote to see the score
NeurIPS 2026The University of Hong KongThe Chinese University of Hong KWuhanHuazhong University of Science aDiffusion 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.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 6/10
strict 1/5
80%Must read
?Must readVote to see the score
NeurIPS 2026The University of Hong KongU Hong KongRL for LLMs

Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning

RaPO reduces visual continual learning forgetting via trajectory-level reward shaping that penalizes policy drift from prior tasks.

Meng Lou, Hanzhong Guo, Linwei Chen, Yizhou Yu

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 6 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 4/5
medium 8/10
strict 0/5
80%Must read
?Must readVote to see the score
NeurIPS 2026The University of Hong KongLLM agents & planning

HACO: Hedged Agent Computing for Reliable LLM Systems

HACO treats role requests as reliability-constrained selection over agent instances, adaptively hedging candidates via optimistic ranking plus conservative reliability accumulation to improve robustness at lower cost.

Enhan Li, Hongyang Du

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.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5
70%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026PrincetonThe University of Hong KongNorthwesternFlow matching

A Theory on Flow Matching with Neural Networks

Flow matching with over-parameterized 2-layer ReLU networks achieves convergence, generalization, and sample-generation Wasserstein guarantees via multi-task representation bounds.

Yihan He, Qishuo Yin, Yuan Cao, Jianqing Fan and 1 more

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

AI panel: 5 of 20 reviewers recommend it
lenient 2/5
medium 2/10
strict 1/5
88%Must read
?Must readVote to see the score
NeurIPS 2026U Hong KongThe University of Hong KongThe Chinese University of Hong KThe Chinese University of Hong KAgent 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.

AI panel: 15 of 20 reviewers recommend it
lenient 5/5
medium 8/10
strict 2/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The University of Hong KongU Hong KongRobot manipulation

Reverse to Advance: Teleoperation-Cost Effective Hard Policy Learning from Reversed Easy Tasks

It proposes reversing easy-task trajectories to train hard-task policies via automated collection, hierarchical refinement, and iterative learning, achieving higher success with less teleoperation.

Qiyuan Qiao, Ge Yuan, Can Wang, Dong Xu

Sydney Poster Session 3, Wed, Dec 9, 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
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Sun Yat-senThe Chinese University of Hong KNanyang TechnologicalSUN YAT-SEN UNIVERSITYThe University of Hong KongImage 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.

AI panel: 9 of 20 reviewers recommend it
lenient 3/5
medium 6/10
strict 0/5
83%Must read
?Must readVote to see the score
NeurIPS 2026StanfordThe University of Hong KongU California, BerkeleyComputer Science Department, StaStanfordMental health

TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots

TherapyGym introduces CTRS-based fidelity and multi-label safety evaluation for therapy chatbots, with RL training raising expert-rated CBT adherence from 0.10 to 0.60.

Fangrui Huang, Souhad Chbeir, Arpandeep Khatua, Sheng Wang and 7 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · 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 6/10
strict 2/5
86%Must read
?Must readVote to see the score
NeurIPS 2026The University of Hong KongShanghai JiaotongFudanBeijing University of AeronauticThe Chinese University of Hong KEmbodied 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 ★ 31

– ReadersNo votes yet
14/20 AI panelreviewers recommend it

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

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

AI panel: 14 of 20 reviewers recommend it
lenient 4/5
medium 9/10
strict 1/5
92%Must read
?Must readVote to see the score
NeurIPS 2026The Chinese University of Hong KU WaterlooThe Chinese University of HongkoThe University of Hong KongChinese University of Hong KongTabular data

TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders

TRL-Bench standardizes cross-paradigm evaluation of tabular encoders via shared representation-level probes, finding encoder quality is task-specific and best pipelines combine capability-matched specialists.

Wei Pang, Xiangru Jian, Hehan Li, Zhixuan Yu and 9 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 54 on Hugging Face · Code ★ 10

– ReadersNo votes yet
19/20 AI panelreviewers recommend it

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

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

AI panel: 19 of 20 reviewers recommend it
lenient 5/5
medium 10/10
strict 4/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The University of Hong KongShanghai Jiao TongNorthwestern PolytechnicalU Science and Technology of ChinFudan3D 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
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The University of Hong KongAgent memory

GLOVE: Global Verifier for LLM Memory-Environment Realignment

GLOVE verifies LLM memory consistency via active probing against fresh observations, improving agent success rates without ground-truth supervision.

XINGKUN YIN, Hongyang Du

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
91%Must read
?Must readVote to see the score
NeurIPS 2026U Hong KongThe Univeristy of Hong KongCMU, Carnegie MellonAlibaba GroupThe University of Hong KongVision-language-action models

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies

FineVLA introduces fine-grained action-aligned supervision for steerable vision-language-action policies, yielding up to 86.8% simulation and 62.7 real-world success and boosting steerable control over coarse instructions.

Xintong Hu, Xuhong Huang, JINYU ZHANG, Yutong Yao and 8 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 9 on Hugging Face

– ReadersNo votes yet
18/20 AI panelreviewers recommend it

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

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

AI panel: 18 of 20 reviewers recommend it
lenient 5/5
medium 10/10
strict 3/5
89%Must read
?Must readVote to see the score
NeurIPS 2026The University of Hong KongHuazhong University of Science aThe Chinese University of Hong Kzhejiang universityVision-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
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026SpotlightBytedance Seed; The University oThe Australian NationalPekingRenmin University of ChinaChinese University of Hong KongLLM pretraining & scaling laws

Continuous Latent Diffusion Language Model

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

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

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

– ReadersNo votes yet
11/20 AI panelreviewers recommend it

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

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

AI panel: 11 of 20 reviewers recommend it
lenient 3/5
medium 7/10
strict 1/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U Hong KongTencentTencent AI LabThe University of Hong KongVision-language models

From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model

ReDiff reframes vision-language diffusion as active refining via error-correction training and online self-correction loops, breaking error cascades to improve coherence, factual accuracy, and parallel generation.

Yatai Ji, Teng Wang, Yuying Ge, Zhiheng Liu and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 30 on Hugging Face · Code ★ 45

– 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