Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Haoyang Wang

Haoyang Wang

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2ML×2Vision×2NLP×1Robotics×1

Frequent co-authors

Zhaoyang Wang1×
Qianhui Wu1×
Haorui Wang1×
Simon Yu1×
Baolin Peng1×
Canwen Xu1×

Research Timeline

2026
MeshLoom: Feed-Forward Non-Rigid Registration of Mesh Sequences

MeshLoom is a feed-forward registration network that directly reconstructs vertex deformations across mesh sequences.

Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving

This paper proposes Rollout-Retrieval Lifelong Policy Learning (R$^2$LPL), a framework for continual policy improvement in autonomous driving by retrieving corrective targets from recoverable mistakes and retaining the resulting knowledge.

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

The paper proposes a scalable pipeline for synthesizing controllable environments and tasks for training general computer-use agents.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CLcs.LGEmpiricalRecentOct 19, 2026

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

Zhaoyang Wang, Qianhui Wu, Haorui Wang, Simon Yu +8 more

The paper proposes a scalable pipeline for synthesizing controllable environments and tasks for training general computer-use agents.

View →
cs.ROcs.AIcs.CVEmpirical
Recent
Jun 29, 2026

Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving

Cheng Gong, Haoyang Wang, Chao Lu, Zirui Li +1 more

This paper proposes Rollout-Retrieval Lifelong Policy Learning (R$^2$LPL), a framework for continual policy improvement in autonomous driving by retrieving corrective targets from recoverable mistakes…

View →
cs.CVEmpiricalRecentJun 15, 2026

MeshLoom: Feed-Forward Non-Rigid Registration of Mesh Sequences

Jianqi Chen, Jiraphon Yenphraphai, Xiangjun Tang, Sergey Tulyakov +3 more

MeshLoom is a feed-forward registration network that directly reconstructs vertex deformations across mesh sequences.

View →