Good Papers

Showing papers from JD Explore Academy Show all papers

80%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Institute of Information EngineeInstitute of Information EnginerJD.comInstitute of Information EngineeJoy Future Academy at JD.ComRL for LLMs

Co-Evolving Policy Distillation

Co-Evolving Policy Distillation co-trains experts via bidirectional online policy distillation during RLVR to avoid divergence and absorption gaps, integrating multi-modal reasoning to surpass domain-specific experts.

Naibin Gu, Chenxu Yang, Qingyi Si, Chuanyu Qin and 6 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 67 on Hugging Face

100% Readers1 of 1 upvoted
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 7/10
strict 1/5
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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Shanghai Jiao TongFudanU Michigan - Ann ArborMMLab@CUHKShanghai JiaotongRL for LLMs

Self-Calibrated GUI Reward Model via Inverse Dynamic Modeling

Zeyi Sun, Shengyuan Ding, Xingpeng Xia, Jinsong Li and 3 more

Sydney Poster Session 1, Tue, Dec 8, 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 2026Nanyang TechnologicalNational University of SingaporeJD Explore AcademyA*STARU SydneyMulti-agent LLM systems

FlowLeak: Coverage-Guided Extraction of Dynamic Workflows in LLM-Based Multi-Agent Systems

Zhiyao Ren, Siyuan Liang, Yibing Zhan, Jun L Tan 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026South China University of TechnoJD.COMSun Yat-SenJD Explore AcademyQuantization

Improving Quantized Zeroth-Order Optimization through Reconstructed Low-Rank Structures

Fei Wang, Shuai Xie, Li Shen, Chao Xue and 2 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
72%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Shanghai Jiao TongAMAP, Alibaba GroupNanyang TechnologicalJD Explore AcademyTTI ChicagoVideo generation

PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory

PermaVid disentangles video memory into RGB appearance and depth structure with edit-aware updates to maintain long-term consistency across modifications.

Shuai Yang, Bingjie Gao, Ziwei Liu, Jiaqi Wang and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 6 on Hugging Face · Code ★ 44

– 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
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026ZhejiangFudanJD Explore AcademyDiffusion models

DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders

DecQ uses lightweight detail-condensing queries to extract fine-grained VFM features, improving representation autoencoder reconstruction and generative fidelity without disrupting semantic space.

Tianhang Wang, Yitong Chen, Wei Song, Zuxuan Wu and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 3 on Hugging Face · Code ★ 8

– 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 4/10
strict 1/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U Science and Technology of ChinWuhanJD Explore AcademyRL for LLMs

Not Only Where, But When: Temporal Scheduling for RLVR

Scheduling credit allocation criteria over RLVR training improves stability and efficiency by prioritizing targeted tokens before gradually attenuating to general optimization.

Jinghao Zhang, Ruilin Li, Feng Zhao, Jiaqi Wang

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

– 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 3/5
medium 7/10
strict 0/5
76%Highly rated
NeurIPS 2026SpotlightInstitute of Information EnginerInstitute of Information EngineeJD.comU the Chinese Academy of ScienceInstitute of Information EngineeRL for LLMs

Self-Distilled RLVR

RLSD combines RLVR and self-distillation, using token-level policy differences for update magnitudes and environmental feedback for directions, improving convergence and stability.

Chenxu Yang, Chuanyu Qin, Qingyi Si, Minghui Chen and 6 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 145 on Hugging Face

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

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

AI panel: 10 of 20 reviewers recommend it
lenient 3/5
medium 6/10
strict 1/5
80%Must read
?Must readVote to see the score
NeurIPS 2026East China NormalJD.comU the Chinese Academy of ScienceInstitute of Information EnginerInstitute of Information EngineeVideo-language models

Harnessing Streaming Video in the Wild

Streaming-Train-248K and Streaming Harness adapt VLMs to real-time video streams with proactive interaction, 12-hour memory, and sub-second latency.

Dingyu Yao, Shuhuan Gu, Qingyi Si, Junhao Zhou and 7 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 5/5
medium 5/10
strict 2/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026ZhejiangFudanUCAS/EPFLJD Explore AcademyAlibaba GroupAutoregressive generation

Channel-wise Vector Quantization

Channel-wise Vector Quantization replaces patch tokens with channel tokens to achieve full codebook usage and improves reconstruction and text-to-image generation via sequential channel prediction.

Wei Song, Tianhang Wang, Yitong Chen, Zuxuan Wu and 4 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 14 on Hugging Face · Code ★ 11

– 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 4/10
strict 1/5
80%Must read
?Must readVote to see the score
NeurIPS 2026The Hong Kong University of ScieThe Hong Kong University of ScieHong Kong University of Science Beijing University of TechnologyShenzhen MSU-BITVision-language-action models

HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning

HumanoidArena benchmarks egocentric hierarchical whole-body learning via seven leg-critical tasks, finding policies solve diverse interactions but cross-tracker transfer remains fragile.

Taowen Wang, Zikang Xie, Bin Yang, Yunheng Wang and 12 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 18 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 5/5
medium 6/10
strict 1/5
86%Must read
?Must readVote to see the score
NeurIPS 2026PekingQihoo 360FudanThe Chinese University of HongKoShanghai Artificial IntelligenceRL for LLMs

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning

RLVR discards group error diversity, but shaping penalties by intra-group error diversity improves training; EDAS boosts DAPO by 6.29 points on math benchmarks.

Wenpu Liu, Yuqi Xu, Weichu Xie, Yongfu Zhu and 7 more

Sydney Poster Session 2, Tue, Dec 8, 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
88%Must read
?Must readVote to see the score
NeurIPS 2026WuhanFudanZhejiangShanghai JiaotongJD Explore AcademyRL for LLMs

Visual-ERM: Reward Modeling for Visual Equivalence

Visual-ERM is a multimodal generative reward model that evaluates vision-to-code outputs in rendered visual space, improving Qwen3-VL-8B-Instruct by up to 8.4 points and outperforming larger models on fine-grained visual discrepancy benchmarks.

Ziyu Liu, Shengyuan Ding, Xinyu Fang, Xuanlang Dai and 5 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 21 on Hugging Face · Code ★ 69

– 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