Good Papers

Showing papers from Chinese Academy of Sciences Show all papers

57%Worth a look
?Worth a lookVote to see the score
Chinese Academy of SciencesInstitute of Information EngineeU Chinese Academy of SciencesBaiduEfficient attention & state-space models

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping

Sparse Growing Transformer trains-time sparse depth allocation via progressive attention looping to improve efficiency.

Yao Chen, YiLong Chen, Yinqi Yang, Junyuan Shang and 8 more

Published 2026 · 0 citations

– 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 2026WuhanChinese Academy of SciencesDynamic graphs

Neighbor-Aware Snapshot-Based Temporal Graph Learning

Jinxi Yang, He Li, Wei Yu, Xingyu Gao 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 2026Institute of Information EngineeKey Laboratory of Intelligent InChinese Academy of SciencesInstitute of Computing TechnologAlibaba GroupInstruction tuning

ToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning

Sicong Li, Qianqian Xu, Zhiyong Yang, Zitai Wang and 3 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026East China NormalChinese Academy of SciencesEast China Normal UniveristyExploration

OPSRL-SSP: Optimistic Posterior Sampling for Stochastic Shortest Path with Minimax-Optimal Regret

YIMING XU, Xian Wei, Cheng Chen

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 2026Institute of Computing TechnologU the Chinese Academy of ScienceChinese Academy of SciencesTool use & function calling

Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning

Mengdi Liu, Chenghao Jia, Hong Chang, Shiguang Shan

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 2026Institute of Computing Technolognanjing universityChinese Academy of SciencesAgent memory

StateLedger: Path-Addressed External Memory for Persistent Multi-Agent Systems

Geer Yang, Xixuan Liu, Bin Wu, Shaojiang Wang

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 2026SoutheastChinese Academy of SciencesTsinghuaShenzhen Institute of Advanced TU ArizonaSemi- & weakly supervised learning

Seen-Constrained Model-Order Selection for Unknown-$K$ Generalized Category Discovery

Mingfu Yan, Jiancheng Huang, HAIPENG LUO, Yi Huang 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 2026U the Chinese Academy of ScienceChinese Academy of SciencesVisual Information Processing anKey Laboratory of Intelligent InU Chinese Academy of SciencesOptimization

Pairwise AUC Optimization Needs Corrective Power: A Unified View

Jia Chen, Zhiyong Yang, Shilong Bao, Qianqian Xu 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.

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 2026中国科学院大学Renmin University of ChinaU the Chinese Academy of ScienceTsinghuaChinese Academy of SciencesMaterials & chemistry

EP-Flow: Disordered Crystal Structure Prediction without Site-level Annotation

liu qiuliang, Liming Wu, Qi Li, Zhonglong Peng and 4 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 2026TsinghuaChinese Academy of SciencesTsinghua University, TsinghuaSegmentation

BrainEM: A Large-Scale and Diverse Benchmark for EM Neuron Segmentation in Connectomics

Zhenghua Li, Lanyue Zhang, Zekang Yang, Kai Li and 3 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U the Chinese Academy of ScienceChinese Academy of SciencesInstitute of automation, ChineseBandits & online learning

TraceTriage: A Benchmark for Cost-Aware Stop-or-Continue Decisions in Delayed-Outcome Workflows

Sihang Lei, Yihang Qiu, Xueyan Zhao, Yuwei Wang 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.

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 2026WuhanNanyang TechnologicalChinese Academy of SciencesInstruction tuning

Aligned LoRA Updates via Intrinsic Geometry for Federated Low-Rank Adaptation

Yihao Yang, Jian Liang, Wenke Huang, He Li and 2 more

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

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 2026Intelligent Science & TechnoIntelligent Sci. and Tech. AcadeIntelligent Science and TechnoloBeijing Institute of TechnologyTsinghua University, TsinghuaSegmentation

$\textbf{EchMo}$: End-to-End Radar Echo Segmentation

Liwen Zhang, Xinying Fu, Youcheng Zhang, ZijunHu 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026SpotlightTsinghuaTsinghua University, Tsinghua, TsinghuaBeijing Houdu Technology Co., LtPeng Cheng LaboratoryLLM pretraining & scaling laws

Quantile Benchmarking Heterogeneous Web Corpora in Open LLM Pretraining

Kairong Luo, Zhenbo Sun, Xinyu Shi, Shengqi Chen and 8 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
72%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Chinese Academy of SciencesInstitute of Computing TechnologObject detection

Component-Based Out-of-Distribution Detection

Component-Based OOD Detection decomposes inputs into functional components via Component Shift Score and Compositional Consistency Score, improving coarse- and fine-grained out-of-distribution detection without training.

Wenrui Liu, Hong Chang, RuiBing Hou, Shiguang Shan

Sydney Poster Session 3, Wed, Dec 9, 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 4/5
medium 4/10
strict 0/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026, Chinese Academy of SciencesTencent AI LabChinese Academy of SciencesAlibaba GroupInstitute of Computing TechnologUnified 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
91%Must read
?Must readVote to see the score
NeurIPS 2026Shanghai Astronomical ObservatorChinese Academy of SciencesChina/Shanghai/Shanghai AstronomShanghai Jiao TongVision-language models

A systematic evaluation of vision-language models for observational astronomical reasoning tasks

AstroVLBench evaluates VLMs across five astronomical modalities, finding accuracy depends on physical grounding and raw numerical data improves results, yet all models lag behind domain-specialized methods.

Wenke Ren, Hengxiao Guo, Wenwen Zuo, Xiaoman Zhang

Sydney Poster Session 6, Thu, Dec 10, 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.

AI panel: 17 of 20 reviewers recommend it
lenient 5/5
medium 8/10
strict 4/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026XiaohongshuRenmin University of ChinaU Southern CaliforniaBaiduChinese Academy of SciencesLLM agents & planning

OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search

OASES co-trains a search policy and adaptive evaluator to provide outcome-aligned process rewards, outperforming RL baselines on multi-hop QA benchmarks.

Erhan Zhang, Yiqun Chen, Zechun Niu, Wei Yang and 5 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · 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 4/5
medium 6/10
strict 1/5
86%Must read
?Must readVote to see the score
NeurIPS 2026Huazhong University ofscience anLi Auto Inc.Huazhong University of Science aChinese Academy of SciencesVision-language models

ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining

ITO improves image-text pretraining via multi-view cross-modal alignment and discarded training-time fusion, beating CLIP at 100M-1B scale on classification and retrieval.

Hanpeng Liu, Yaqian Li, Zidan Wang, Shuoxi Zhang and 5 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 4/5
medium 8/10
strict 2/5
83%Must read
?Must readVote to see the score
NeurIPS 2026Chinese Academy of SciencesTsinghuaTsinghua University, Tsinghua3D vision & reconstruction

CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy

CORAL introduces a structure-aware benchmark for local and whole-brain neuron reconstruction in light microscopy, revealing current methods need improvement for complete brain-wide tracing.

Zekang Yang, Jiamin Li, Zhenghua Li, Jiaqi Fan and 2 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.

AI panel: 13 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 1/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U the Chinese Academy of ScienceInstitute of Computing TechnologChinese Academy of SciencesInstitute of Computing TechnologMeta, transfer & few-shot learning

Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning

Dynamical Adapter Fusion derives optimal coefficients via PAC-Bayes and Taylor expansion to fuse task-specific adapters into one global adapter, achieving state-of-the-art class-incremental learning results.

RuiQi Liu, Boyu Diao, Zijia An, Runjie Shao and 4 more

Sydney Poster Session 4, Wed, Dec 9, 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 4/5
medium 7/10
strict 0/5
83%Must read
?Must readVote to see the score
NeurIPS 2026Chinese Academy of SciencesXiaohongshu IncXiaohongshuInstitute of Software, Chinese AInstitute of Software, CASVision-language models

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation

Vision-OPD distills a crop-conditioned teacher into a full-image student via on-policy self-distillation to improve fine-grained visual understanding without external teachers or tools. It achieves competitive or superior performance on fine-grained benchmarks against larger open-source, closed-sour

Qianhao Yuan, Jie Lou, XingYu Li, Hongyu Lin and 3 more

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

AI panel: 13 of 20 reviewers recommend it
lenient 4/5
medium 9/10
strict 0/5