Good Papers

Showing papers from The Hong Kong Polytechnic University Show all papers

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026The Hong Kong PolytechnicHong Kong PolytechnicVision-language models

Revitalizing Medical Time Series with Vision-Informed Retrieval: A Vision-Language Perspective

Guoqi Yu, Juncheng Wang, Shujun Wang

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
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026The Hong Kong PolytechnicHong Kong University of Science Southern University of Science aNanyang TechnologicalRutgersRL for LLMs

Train at the Moving Edge: Rollout-Efficient RL for Large Reasoning Models

Jiahao Wu, Ning Lu, Shengcai Liu, Kun Wang and 5 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
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026The Hong Kong PolytechnicHong Kong PolytechnicThe Hong Kong Polytechnic UnivDiffusion models

Phase-wise Velocity Distillation: Towards Effective Image Generation with A Single NFE

Zhen Guo, Rongyuan Wu, Qiaosi Yi, Chenxi Xie and 2 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
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The Hong Kong PolytechnicMcGill University & Mila - QHong Kong PolytechnicTongji universityTongjiDeep RL

Preference-Guided Adversarial Policy Optimization for Long-Tail Robust Driving

Tong Nie, Yihong Tang, Junlin He, Yuewen Mei and 4 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
2/20 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: 2 of 20 reviewers recommend it
lenient 2/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026The Hong Kong PolytechnicHong Kong PolytechnicRegressor, Inc.3D vision & reconstruction

FoundSurface: Feedforward Ray-Based 3D Scene Surface Reconstruction from Unposed Images

Shenxing Wei, Jinxi Li, Zihui Zhang, Ajay Kumar and 2 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
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026The Hong Kong PolytechnicSUN YAT-SEN UNIVERSITYVIPL,ICT,Chinese academic of sciControllable generation

$SE(2)$-Aware Conditional Distribution Transport for Vehicle Trajectory Generation

Di Wen, Zhaocheng He, Shuhui Wang

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 2026Huazhong University of Science aThe Hong Kong PolytechnicHong Kong University of Science LLM agents & planning

SeaPilot: Mobile Agent with Self-refining Environment Alignment

Zhigang Zuo, Senyao Li, Yufeng Jiang, Haozhao 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
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 2026Hong Kong PolytechnicThe Hong Kong PolytechnicThe University of TokyoUNSW SydneyDeep RL

Discovering Programmatic Policies from Reinforcement Learning-Based Traffic Signal Controllers

Lindong Xie, Yang Zhang, Beiyu Song, XING Zeren and 2 more

Sydney Poster Session 2, Tue, Dec 8, 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
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Huazhong University of Science aThe Hong Kong PolytechnicHong Kong University of Science Graphs & LLMs

FedProG: Federated Graph Learning via Server-Side LLM Semantic Bridging and Uncertainty-Aware Distillation

Haitao Wang, Haozhao Wang, Wenchao Xu, Yichen Li and 4 more

Paris Poster Session 3, Thu, Dec 10, 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Huazhong University of Science aThe Hong Kong PolytechnicNanjing University of Posts and MBZUAIMulti-agent LLM systems

Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM Training

Qiyu Qin, Yichen Li, Haozhao Wang, Tianzhe Xiao and 3 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
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Huazhong University of Science aBeijing University of Posts and The Hong Kong PolytechnicU CambridgePrivacy

Personalized Safety in Federated Fine-Tuning of Large Language Models

Tianzhe Xiao, Gaozhuo Liu, Yichen Li, Haozhao Wang and 3 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 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 2026Huazhong University of Science aThe Hong Kong PolytechnicZhengzhouWatermarking & AI-text detection

FedTrace: Generated-Content-Based Watermark Verification for Traitor Tracing in Federated Learning

Tianzhe Xiao, Haozhao Wang, Yichen Li, Qiyu Qin and 2 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026The Hong Kong PolytechnicSingapore ManagementNanyang TechnologicalJilinHong Kong PolytechnicLLM pretraining & scaling laws

Language Models Demand New Computer Science

Chang Yang, Xinrun Wang, Shuxin Li, Qinggang Zhang and 4 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026The HongKong PolytechnicThe Hong Kong PolytechnicSichuanRecommender systems

SituRecBench: A Benchmark for Situated Recommendation in 3D Interactive Environments

Jingtong Yang, Dongding LIN, Jian Wang, Wenjie Li

Sydney Poster Session 6, Thu, Dec 10, 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
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Huazhong University of Science aThe Hong Kong PolytechnicHong Kong University of Science TsinghuaMBZUAIWatermarking & AI-text detection

VERITAS: Veracity-Enhanced Robust Identification of LLM-generated Text Against Style-shifts

Xiaoquan Yi, Haozhao Wang, Yichen Li, Wenchao Xu and 5 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 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: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Hong Kong PolytechnicGuangdong OPPO Mobile TelecommunThe Hong Kong PolytechnicOPPO Research InstituteThe Hong Kong Polytechnic UnivLLM agents & planning

AURA: An Autonomous Retouching Agent with Photographic Visual Thinking

Shuaizheng Liu, Fangzhou Han, Jiarong Liao, Yujing Sun and 7 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
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The Hong Kong PolytechnicPrivacy

Exposing Private Corpus Leakage in Multimodal RAG

Yihao LIU, XINQI LYU, Dong Wang, Bin Xiao

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

– ReadersNo votes yet
2/20 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: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The Hong Kong PolytechnicBackdoors & data poisoning

Train-free Data Poisoning Attack against Retrieval-augmented Diffusion Models

XINQI LYU, Yihao LIU, Yiming Cao, Bin Xiao

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

– ReadersNo votes yet
2/20 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: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
88%Must read
?Must readVote to see the score
NeurIPS 2026XPeng MotorsSouthern University of Science aFudanThe Hong Kong PolytechnicAlibaba GroupAgent benchmarks & environments

Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents

VIGIL decouples world-state completion from terminal commitment in embodied agents, revealing that comparable execution yields up to 19.7 pp differences in correct episode termination.

Ying Chen, Lihuang Fang, Rui Jiang, Mingxu Wang and 3 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 4/5
medium 8/10
strict 3/5
91%Must read
?Must readVote to see the score
NeurIPS 2026FudanInstitute of automation, ChineseShanghai Artificial IntelligenceThe Hong Kong PolytechnicUNSW, SydneyJailbreaks & red teaming

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

SciHazard benchmarks LLM scientific safety risks via decomposed harm scoring across 3,000 real-world grounded queries, finding deep research agents 32.3% more harmful than standard models.

Chunxiao Li, Yuan Xiong, Lijun Li, Tianyi Du and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 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
89%Must read
?Must readVote to see the score
NeurIPS 2026The Hong Kong PolytechnicWestlakeAlibaba GroupThe Hong Kong University of ScieMonashText-to-image

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution

RankE co-evolves discrete text-to-image policy and decoder via alternating optimization to eliminate latent covariate shift, improving both FID and CLIP scores.

Siyonng Jian, Siyuan Li, Luyuan Zhang, Zedong WANG and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 18 on Hugging Face · Code ★ 21

– 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 4/5
medium 10/10
strict 2/5
88%Must read
?Must readVote to see the score
NeurIPS 2026SpotlightThe Hong Kong PolytechnicThe Hong Kong University of ScieU California, BerkeleyHong Kong PolytechnicByteDance Inc.LLM agents & planning

VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries

VisInteract introduces interactive text-to-visualization with imperfect queries via VisInteract-Bench and Vis-MCTS, boosting success by over 13% versus interactive baselines.

Wenxin XU, Jinwei Lu, Hwanhee Kim, Chen J Zhang and 3 more

Sydney Poster Session 2, Tue, Dec 8, 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 7/10
strict 3/5
80%Must read
?Must readVote to see the score
NeurIPS 2026National University of SingaporeThe Hong Kong PolytechnicQuantization

Q-ARVD: Quantizing Autoregressive Video Diffusion Models

Q-ARVD quantizes autoregressive video diffusion via frame-weighted objectives and adaptive outlier isolation, cutting inference costs while preserving generation quality.

Siao Tang, Xinyin Ma, Gongfan Fang, Xingyi Yang and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 18 on Hugging Face · Code ★ 23

– 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 2026SpotlightHong Kong PolytechnicDepartment of Computer Science aZhejiangU Technology SydneyThe Hong Kong PolytechnicModel merging

FeatCal: Feature Calibration for Post-Merging Models

FeatCal reduces post-merging feature drift via layer-wise closed-form weight calibration without gradients, outperforming Surgery and ProbSurgery on CLIP and GLUE benchmarks.

Yanggan Gu, Shuo CAI, Zihao Wang, Wenjun Wang and 6 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
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U CambridgeHarbin Institute of TechnologyHong Kong PolytechnicThe Hong Kong PolytechnicCambridgePhysics-informed ML & PDEs

Adaptive Coordinate Transforms for Neural Operators

ACT introduces a plug-and-play block that learns adaptive coordinate transforms for neural operators, reducing spatial misalignment and significantly improving predictive accuracy across PDE benchmarks.

Chaoyu Liu, Zhonghao Li, Gaohang Chen, Zakhar Shumaylov and 4 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · 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
92%Must read
?Must readVote to see the score
NeurIPS 2026Hong Kong University of Science Northwest Polytechnical UniversiNorthwestern PolytechnicalNanyang TechnologicalSoutheast3D 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
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The Hong Kong PolytechnicTongji universityHong Kong PolytechnicMcGill University & Mila - QTongjiAdversarial robustness

World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning

Adversarial World Modeling casts robust planner learning as a constrained min-max game solved via decoupled self-play, yielding competitive closed-loop performance in nominal and adversarial traffic scenarios.

Tong Nie, Yuewen Mei, Junlin He, Yihong Tang and 2 more

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