Good Papers: read the good ones

UniT unifies human and humanoid actions via visual anchoring into shared latent tokens for scalable policy learning and world modeling. It achieves state-of-the-art data efficiency, zero-shot transfer, and cross-embodiment dynamics alignment.

Boyu Chen, Yi Chen, Lu QIU, Jerry Bai and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 32 on Hugging Face · Code ★ 103

– 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

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026, Chinese Academy of Sciences Tencent AI Lab Chinese Academy of Sciences Alibaba Group Institute of Computing Technolog Unified multimodal models

AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

AnyMo introduces OmniHuMo dataset with 5,000 hours of multimodal motion data and proposes a masked modeling framework for scalable any-modality conditional motion synthesis with flexible spatial and stylistic control.

Yiheng Li, Zhuo Li, RuiBing Hou, Yingjie Chen and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 2 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 3/10

strict 1/5

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Northeastern U California, Los Angeles Cornell Shanghai Artificial Intelligence Tencent LLM agents & planning

PhotoFlow: Agentic 3D Virtual Photography Missions

PhotoFlow uses a Director-Reviewer-Reflector agent for closed-loop camera search to generate language-conditioned virtual photographs in arbitrary 3D scenes, outperforming baselines on quality, alignment, and success rate.

Jiarui Guo, Haojia Wei, Yiming Zhang, Yifei Liu and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 24 on Hugging Face · Code ★ 43

– 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

83%Must read

?Must readVote to see the score

NeurIPS 2026SUN YAT-SEN UNIVERSITY Wechat Search, Tencent Inc.U Michigan - Ann Arbor Shenzhen Loop Area Institute Tencent RL for LLMs

Stabilizing Policy Optimization via Logits Convexity

Logits convexity explains supervised fine-tuning stability versus RL instability, and the proposed LCO framework improves policy optimization stability and benchmark performance.

Hongzhan Chen, Tao Yang, Yuhua Zhu, Shiping Gao and 2 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · 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 4/5

medium 9/10

strict 0/5

88%Must read

?Must readVote to see the score

NeurIPS 2026Shanghai Jiaotong Tencent Huawei Technologies Ltd.The Hong Kong University of Scie U Edinburgh, University of Edinb Hallucination & factuality

BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation

BALTO applies balanced token-level credit assignment to mitigate LLM hallucinations by redistributing probability from unsupported to faithful content, outperforming response-level methods on faithfulness benchmarks.

Ning Li, Zixuan Guo, Yan Xu, Wenbo Fei and 6 more

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

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

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

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

AI panel: 15 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 1/5

80%Must read

?Must readVote to see the score

NeurIPS 2026U Science and Technology of Chin Tencent Zhejiang School of data science, Fudan un Nankai Tokenization

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation

SimCT recovers lost cross-tokenizer supervision by comparing multi-token continuations in on-policy distillation, improving reasoning and code generation over exact token matching.

Jie Sun, Mao Zheng, Mingyang Song, Qiyong Zhong and 5 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 4/5

medium 8/10

strict 0/5

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Tsinghua Department of Automation, Tsingh Tsinghua University, Tsinghua U Maryland, College Park Independent Researcher RL for LLMs

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex

Listwise Policy Optimization explicitly projects policies onto target distributions over response simplices via divergence minimization, improving reasoning performance and stability over group-based policy gradients.

Yun Qu, Qi Wang, Yixiu Mao, Heming Zou and 10 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 67 on Hugging Face

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

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

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

AI panel: 8 of 20 reviewers recommend it

lenient 2/5

medium 6/10

strict 0/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Nanyang Technological The Hong Kong University of Scie Tencent Representation & contrastive learning

Delve into the Applicability of Advanced Optimizers for Multi-Task Learning

Advanced optimizers weaken multi-task learning because instant gradients barely affect updates, so the APT framework with adaptive momentum and Muon direction preservation improves results across four datasets.

Zhipeng Zhou, Linxiao Cao, Yiming Cao, Pengcheng Wu and 2 more

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 2/5

medium 8/10

strict 1/5

86%Must read

?Must readVote to see the score

NeurIPS 2026Hong Kong University of Science Tencent Sea AI Lab Penn State Hallucination & factuality

Scalable Token-Level Hallucination Detection in Large Language Models

TokenHD trains token-level hallucination detectors via scalable synthetic data and importance weighting, with small models outperforming larger reasoning models and scaling consistently.

Rui Min, Tianyu Pang, Chao Du, Minhao Cheng and 1 more

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

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

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

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

AI panel: 14 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 1/5

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Nanyang Technological Tencent AI Lab Tencent Beijing University of Posts and Alibaba Group Video generation

FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation

FaithfulFaces improves identity-preserving video generation via pose-shared identity alignment and achieves state-of-the-art consistency across pose changes and occlusions.

Yuanzhi Wang, Xuhua Ren, Jiaxiang Cheng, bing ma and 6 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

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

89%Must read

?Must readVote to see the score

NeurIPS 2026Tencent Harbin Institute of Technology Hong Kong Polytechnic Westlake Jiangnan Alignment & preference optimization

Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning

Balanced Fine-Tuning uses dual-scale token and sequence reweighting targeting dense epistemic uncertainty to align LLMs with biomedical knowledge, improving reasoning and sparse-reward RL over standard fine-tuning.

Zhenchao Tang, Fang Wang, Haohuai He, Jiale Zhou and 12 more

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

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

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

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

AI panel: 16 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 2/5

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Harvard Tencent Shandong Harvard University/Google Resear Alignment & preference optimization

LLM Active Alignment: A Nash Equilibrium Perspective

A game-theoretic framework predicts and steers LLM populations via Nash equilibrium analysis, deriving closed-form alignments that prevent political exclusion and guide socially desirable outcomes.

Tonghan Wang, Yuqi Pan, Xinyi Yang, Xinrui Song and 3 more

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

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

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

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

AI panel: 9 of 20 reviewers recommend it

lenient 4/5

medium 5/10

strict 0/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Baidu Tencent Xiamen Wuhan Baidu Inc.Unified multimodal models

Native Audio-Visual Alignment for Generation

NAVA proposes native audio-visual alignment with an Align-then-Fuse MMDiT architecture for joint audio-video generation, achieving superior synchronization, video quality, and timbre control with 6.3B parameters.

Longbin Ji, Guan Wang, xuan wei, Chenye Yang and 4 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 31 on Hugging Face · Code ★ 226

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

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

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

AI panel: 11 of 20 reviewers recommend it

lenient 4/5

medium 7/10

strict 0/5

88%Must read

?Must readVote to see the score

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

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

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

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

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

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

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

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

AI panel: 15 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 2/5

72%Highly rated

?Highly ratedVote to see the score

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

Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm

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

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

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

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

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

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

AI panel: 8 of 20 reviewers recommend it

lenient 4/5

medium 4/10

strict 0/5

83%Must read

?Must readVote to see the score

NeurIPS 2026Fudan Alibaba Group Tencent Shanghai AI Laboratory U Michigan Web & GUI agents

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents

ToolCUA learns optimal GUI-tool switching via scaled synthetic interleaved trajectories, tool-bootstrapped reinforcement learning, and online agentic rewards, achieving 46.85% accuracy on OSWorld-MCP.

XuHao Hu, Xi Zhang, Haiyang Xu, Kyle Qiao and 5 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 26 on Hugging Face · Code ★ 62

– 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 8/10

strict 0/5

Show 20 more papers