Good Papers: read the good ones

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

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

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

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

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

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

AI panel: 12 of 20 reviewers recommend it

lenient 4/5

medium 7/10

strict 1/5

83%Must read

?Must readVote to see the score

NeurIPS 2026Nanjing Hithink RoyalFlush Information N nanjing university Ant Group Alibaba Group Graph neural networks

Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering

PyAGC provides a scalable benchmark and modular library for attributed graph clustering across diverse industrial-scale datasets and metrics.

Yunhui Liu, Pengyu Qiu, Yu Xing, Peng Du and 5 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 32

– 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 2026nanjing university Kuaishou- 快手科技 Nanjing university U the Chinese Academy of Science Nanjing Video-language models

ViDiC: Video Difference Captioning

ViDiC introduces a video difference captioning task and ViDiC-1K benchmark that reveals large multimodal models struggle with fine-grained comparative video perception.

Jiangtao Wu, Shihao Li, Zhaozhou Bian, Jialu Chen and 6 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 29 on Hugging Face · Code ★ 15

– 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.

71%Highly rated

?Highly ratedVote to see the score

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

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

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

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

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

– ReadersNo votes yet

7/20 AI panelreviewers recommend it

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

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

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026nanjing university Nanjing Dalian University of Technology City University of Hong Kong RL for LLMs

ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection

ExpLang improves LLM reasoning via on-policy multilingual thinking language selection during RL, outperforming English-only training and extending exploration with diverse language preferences.

Changjiang Gao, Zixian Huang, Kaichen Yang, Jiajun Chen and 2 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

83%Must read

?Must readVote to see the score

NeurIPS 2026Nanjing Yale Human-AI interaction

Path Dependence under Adaptive AI Delegation

Adaptive AI delegation couples error-driven skill decay with performance-driven reliance, producing path-dependent bistability where stronger AI can enlarge the low-skill basin and cause long-run performance below no-AI baselines.

Lingxiao Huang, Nisheeth K. Vishnoi

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.

91%Must read

?Must readVote to see the score

NeurIPS 2026Nanjing nanjing university Backdoors & data poisoning

MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents

MemPoison benchmarks 1227 adversarial cases across memory substrates and finds write-time defenses fail against multi-record and dormant corruption, requiring adaptive defenses.

Jifeng Gao, Kang Xia, Yi Zhang, Xiaobin Hong and 4 more

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

– ReadersNo votes yet

18/20 AI panelreviewers recommend it

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

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

AI panel: 18 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 4/5

80%Must read

?Must readVote to see the score

NeurIPS 2026Nanjing nanjing university LLM reasoning & chain of thought

Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2

ABPR couples LLMs with Prolog meta-interpreters to debug programs via proof-tree analysis, achieving up to 98.33% Pass@2 on ARC-AGI-2 and extending to relational reasoning benchmarks.

Yuning Qiu, Lin-Feng Zou, Jiong-Da Wang, Xue-Rong Yuan and 1 more

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

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

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

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

AI panel: 12 of 20 reviewers recommend it

lenient 4/5

medium 8/10

strict 0/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Nanjing U Illinois at Urbana-Champaign U Technology Sydney Microsoft Research Vision-language-action models

Reinforcing VLAs in Task-Agnostic World Models

RAW-Dream disentangles world models from task data by using task-agnostic pre-trained dynamics and VLM rewards to fine-tune VLAs entirely in zero-shot imagination with verified rollouts.

Yucen Wang, Rui Yu, Fengming Zhang, Junjie Lu and 2 more

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

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

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

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

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

Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE

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

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

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

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

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

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

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026State Key Laboratory of Processo Nanjing U Science and Technology of Chin Institute of Computing Technolog Megvii Technology Inc.Vision-language-action models

Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs

Realtime-VLA FLASH uses a draft model and parallel verification to replace most full diffusion-based VLA inference rounds with faster speculative ones, cutting average latency 3.04x to 19.1 ms.

Jiahui Niu, Kefan Gu, Yucheng Zhao, shengwen Liang and 4 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

10/20 AI panelreviewers recommend it

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

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

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Nanjing Shanghai Jiao Tong U Southern California Nanjing University Optimization

Group Distributionally Robust Optimization with Flexible Sample Queries

A GDRO algorithm via flexible sample queries and a prediction-with-limited-advice game achieves high-probability error O(√(∑ m/r_j)/t) with consistent sample complexity O(m log m/ε²).

Haomin Bai, Dingzhi Yu, Shuai Li, Haipeng Luo and 1 more

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.

AI panel: 6 of 20 reviewers recommend it

lenient 1/5

medium 4/10

strict 1/5

80%Must read

?Must readVote to see the score

NeurIPS 2026Nanjing University of Science an U Washington, Seattle Shanghai Jiaotong Fudan Nanjing Model-based RL

Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving

CoPhy distills vision-language cognition into a BEV encoder and pairs it with an auto-regressive world model for action-conditioned forecasting to enable reinforcement learning with dual physical and cognitive rewards, achieving state-of-the-art autonomous driving results.

Yang Wu, Qiang Meng, Zhaojiang Liu, Youquan Liu and 2 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 6/10

strict 1/5

83%Must read

?Must readVote to see the score

NeurIPS 2026Nanjing nanjing university Electronic Arts Canada Zhejiang Sci-Tech Huawei Technologies Ltd.Agent memory

Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents

Linguistic Trajectory Encoding compresses long-horizon object motion into hybrid language-spatial-visual timelines, outperforming baselines on multi-day spatial memory benchmarks with high compression and sub-second queries.

Xie Tianyidan, Shenyi Wang, Qiang Tang, Mingjie Wang and 6 more

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

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026OralU Cambridge Southern University of Science a Tsinghua University, Tsinghua IMATI-CNR Nanjing 3D vision & reconstruction

SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild

SAM 3D Animal is a promptable framework using the SMAL+ model and Herd3D dataset to reconstruct multiple 3D animals from single images with keypoint and mask prompts, achieving state-of-the-art results.

Xuyi Hu, Jin Lyu, Jiuming Liu, Yebin Liu and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 3 on Hugging Face · Code ★ 13

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

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

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

AI panel: 11 of 20 reviewers recommend it

lenient 4/5

medium 6/10

strict 1/5

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Tongji vivo Nanjing Diffusion models

RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations

RaPD performs diffusion in a continuous neural image field latent space with semantic guidance and coordinate-queried attention rendering, enabling fixed-cost arbitrary-resolution generation with superior quality.

Yanhao Ge, Shanyan Guan, Weihao Wang, Ying Tai and 1 more

Sydney Poster Session 3, Wed, Dec 9, 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 4/5

medium 3/10

strict 0/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Nanjing nanjing university Nanjing University Optimization

Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications

Compressed distributed online convex optimization achieves optimal regret via error feedback and online compression, with applications to distributed non-smooth optimization.

Sifan Yang, Danyue Li, Lijun Zhang

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

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

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

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

AI panel: 10 of 20 reviewers recommend it

lenient 2/5

medium 5/10

strict 3/5

72%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Central South UNSW Sydney U New South Wales Amazon AGI Nanjing 3D vision & reconstruction

Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds

Look-Before-Move separates observation specification from motion execution for narrative-grounded camera planning, improving subject perception, intent consistency, and trajectory quality over baselines.

Jiaming Bian, Bingliang Li, Yuehao Wu, Pichao WANG and 4 more

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

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

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

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

AI panel: 8 of 20 reviewers recommend it

lenient 5/5

medium 3/10

strict 0/5

74%Highly rated

?Highly ratedVote to see the score

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

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

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

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

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

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

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

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

AI panel: 9 of 20 reviewers recommend it

lenient 5/5

medium 4/10

strict 0/5

88%Must read

?Must readVote to see the score

NeurIPS 2026Nanjing Meituan U Rochester Alibaba Group Efficient attention & state-space models

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

RTPurbo converts full-attention LLMs into sparse models within hundreds of steps via retrieval heads and dynamic indexing, achieving near-lossless accuracy with 9.36x prefill and 2.01x decode speedups.

Yanke Zhou, Yiduo Li, Hanlin Tang, Maohua Li and 5 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 90 on Hugging Face

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

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

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

AI panel: 15 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 1/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Shanghai Jiaotong Nanjing university Nanjing AntGroup; Nanjing Shanghai Jiao Tong RL for LLMs

Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models

Hierarchical Token GRPO integrates sketch-then-paint stages and hierarchical credit assignment into diffusion multi-modal LLM reinforcement learning, substantially improving image quality and benchmark scores.

Siqi Luo, Jianghan Shen, Yi Xin, Huayu Zheng and 8 more

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

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

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

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

AI panel: 10 of 20 reviewers recommend it

lenient 4/5

medium 6/10

strict 0/5

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Nanjing Zhongguancun Academy Tencent Hunyuan Tencent Peking Unified multimodal models

Hydra-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

Hydra-X unifies image and video tokenization in one vision transformer via causal temporal attention and hierarchical compression, achieving strong unified understanding and generation performance.

Guozhen Zhang, Xuerui Qiu, Yutao Cui, Tianhui Song and 10 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 31 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 3/5

medium 5/10

strict 1/5

91%Must read

?Must readVote to see the score

NeurIPS 2026University College London nanjing university Nanjing ByteDance Facebook Agent benchmarks & environments

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks

TerminalWorld automatically builds terminal benchmarks from wild recordings, yielding 1,530 tasks where top agents achieve only 62.5% success with weak correlation to expert benchmarks.

Zhaoyang Chu, Jiarui Hu, Xingyu Jiang, Pengyu Zou and 7 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026 · ▲ 8 on Hugging Face · Code ★ 48

– 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

88%Must read

?Must readVote to see the score

NeurIPS 2026nanjing university Nanjing university Fellou AI Nanjing Web & GUI agents

WebNavigator: Global Web Navigation via Interaction Graph Retrieval

WebNavigator overcomes topological blindness via interaction graphs to turn web navigation into deterministic retrieval and pathfinding, doubling multi-site success on WebArena.

Xuanwang Zhang, Yuteng Han, Jinnan Qi, Xinyu Liu and 3 more

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

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

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

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

AI panel: 15 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 2/5