Good Papers: read the good ones

DocScope benchmarks verifiable long-document reasoning via structured trajectory evaluation, finding correct answers rarely include complete evidence chains and region grounding remains weakest.

Xiang Feng, Jiawei Zhou, Zhangfeng Huang, Kewei Wang and 5 more

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

– 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 9/10

strict 5/5

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Southeast nuaa Huawei Technologies Ltd.Nanyang Technological Institute of automation, Chinese LLM agents & planning

PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning

PhGPO learns reusable tool-transition patterns from past trajectories via pheromone guidance to improve long-horizon tool planning.

Yu Li, Guangfeng Cai, shengtian yang, Han Luo and 4 more

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

– ReadersNo votes yet

6/20 AI panelreviewers recommend it

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

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

AI panel: 6 of 20 reviewers recommend it

lenient 4/5

medium 2/10

strict 0/5

89%Must read

?Must readVote to see the score

NeurIPS 2026Australian Institute for Machine Southeast Hunan U Adelaide Singapore University of Technolo Agent benchmarks & environments

LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation

LangMap introduces human-verified hierarchical open-vocabulary navigation benchmarks across scene, room, region, and instance levels with 18K tasks, and PlaNaVid achieves top RGB-only success via planning and memory.

Bo Miao, Weijia Liu, Jun Luo, Lachlan Shinnick and 7 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 53

– 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

72%Highly rated

?Highly ratedVote to see the score

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

ReFPO: Reflow Regularization for Flow Matching Policy Gradients

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

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

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

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

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

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

AI panel: 8 of 20 reviewers recommend it

lenient 3/5

medium 5/10

strict 0/5

83%Must read

?Must readVote to see the score

NeurIPS 2026Tsinghua Tsinghua University, Tsinghua StableAI Southeast Siemens Corporate Research Diffusion models

Breaking the Quality–Privacy Tradeoff in Tabular Data Generation via In-Context Learning

DiffICL frames tabular synthesis as in-context learning using pretrained structural priors to avoid memorization, improving both quality and privacy in small-data settings.

Xinyan Han, yan Lu, Xiaoyu Lin, Yuanyuan Jiang and 4 more

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.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 0/5

80%Must read

?Must readVote to see the score

NeurIPS 2026Comenius University in Bratislav Czech Technical Univeresity in P Southeast CIIRC, Czech Technical Universit Czech Technical University in Pr 3D vision & reconstruction

Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth

Depth2Pose evaluates monocular depth estimators via downstream pose estimation accuracy using only camera poses, introducing a challenging out-of-distribution benchmark where standard metrics fail to predict generalization.

Viktor Kocur, Sithu Aung, Gabrielle Flood, Yaqing Ding and 3 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · 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

83%Must read

?Must readVote to see the score

NeurIPS 2026U Hong Kong U Electronic Science and Technol Shenzhen Alibaba Group Shanghai Jiao Tong Multi-agent LLM systems

Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback

Agent2World uses adaptive multi-agent feedback to generate symbolic world models, achieving state-of-the-art inference and 30.95% fine-tuning gains.

Mengkang Hu, Bowei Xia, Yuran Wu, Ailing Yu and 8 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face · Code ★ 26

– 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

83%Must read

?Must readVote to see the score

NeurIPS 2026SpotlightSoutheast Nanjing University of Informatio Ant Group Efficient inference & serving

TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding

TreeGraft combines small and large drafters with a scheduler to build shared draft trees, boosting speculative decoding by 15.1% over single-drafter methods.

Jiaming Fan, Daming Cao, Canchen Huang, Jiale Fu and 5 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 4/5

medium 7/10

strict 2/5

83%Must read

?Must readVote to see the score

NeurIPS 2026Southeast City University of Hong Kong Alibaba Group AntGroup Backdoors & data poisoning

The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training

Platonic Representation Defense detects and purifies backdoored self-supervised encoder representations via cross-model energy functions without labels or training data. It substantially improves robustness across multiple encoders and over ten attacks in fully black-box settings.

Tuo Chen, Minjing Dong, Benlei Cui, Jian liu and 1 more

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.

AI panel: 13 of 20 reviewers recommend it

lenient 4/5

medium 8/10

strict 1/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Southeast City University of Hong Kong Caritas Institute of Higher Educ City University of Hong Kong, Ho Vision-language models

Language-Assisted Image Clustering Guided by Discriminative Relational Signals and Adaptive Semantic Centers

A language-assisted clustering framework uses cross-modal relational signals and adaptive semantic centers to improve clustering accuracy by 2.6% over state-of-the-art methods.

Jun Ma, Xu Zhang, Zhengxing Jiao, Yaxin Hou and 3 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 4/5

medium 5/10

strict 1/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Southeast HohaiUniversity Robot manipulation

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation

GTP-FA decouples grasping from planning with failure attribution to diagnose failures and optimize both modules, substantially improving robotic manipulation success across diverse policy learners.

Jiahao Xu, Peiyuan Wang, Hanzhuo Zhang, Zihao Yu and 7 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

71%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Guangzhou Zhejiang Southeast Deep RL

Generative Actor-Critic with Soft Bridge Policies

SoftGAC proposes a soft generative actor-critic with stochastic bridge policies that expose a tractable MaxEnt objective via single-pass sampling, outperforming diffusion and flow baselines on continuous control with lower latency.

Ke He, Le He, Shunpu Tang, Yafei Wang and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 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 2/5

medium 5/10

strict 0/5

86%Must read

?Must readVote to see the score

NeurIPS 2026Southeast ai2 U Texas at Austin In-context learning & prompting

PULSE: Identifying Demonstration-Utility Features with Sparse Autoencoders

PULSE uses sparse autoencoders to identify internal features linked to demonstration utility and improves selection across classification, generation, and reasoning tasks.

Chenduo Hao, Chuanbao Gao, Pinjun Zeng, Jingze Zhu and 3 more

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

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

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

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

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 2026Hong Kong University of Science Northwest Polytechnical Universi Northwestern Polytechnical Nanyang Technological Southeast 3D vision & reconstruction

SpatialBench: Is Your Spatial Foundation Model an All-Round Player

SpatialBench evaluates 41 spatial foundation models across 19 datasets and finds none are all-round players, with full-context attention maximizing accuracy and domain alignment exceeding scaling for embodied tasks, plus it introduces DA-Next-5M and DA-Next.

Haosong Peng, Hao Li, jiaqi chen, Yuhao Pan and 9 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 69 on Hugging Face · Code ★ 138

– 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

86%Must read

?Must readVote to see the score

NeurIPS 2026City University of Hong Kong U Sydney Southeast Huawei Noah's Ark Lab City University of Hong Kong Multimodal hallucination

Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking

Causal-Invariant Masking decomposes MLLM uncertainty via semantic divergence to capture epistemic limitations, and Expected Embedding Drift accelerates quantification by nearly 50%.

Haoyang Luo, Linwei Tao, Jie Gui, Xinghao Chen and 3 more

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

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

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

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

AI panel: 14 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 0/5

83%Must read

?Must readVote to see the score

NeurIPS 2026Alibaba Group Southeast U Michigan Instruction tuning

From Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMs

NSFT decomposes MoE experts into channel groups to enable sub-expert-level parameter-efficient fine-tuning that outperforms expert-level methods with fewer trainable parameters.

Zhentao Tan, Chang Liu, Yao Liu, Yue Wu and 1 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 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 5/5

medium 8/10

strict 0/5