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

Wei Ma

3 indexed papers

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

Publications per year

3
26

Top categories

AI×2NLP×1Comp. Eng.×1

Frequent co-authors

Junqi Liu1×
Salena Song1×
Yuhan Wang1×
Jiawei Mao1×
Hardy Chen1×
Xiaoke Huang1×

Research Timeline

2026
CamGeo: Sparse Camera-Conditioned Image-to-Video Generation with 3D Geometry Priors

CamGeo is a novel framework that improves sparse camera-conditioned image-to-video generation by distilling rich 3D geometric priors into the diffusion backbone, resulting in geometrically consistent motion.

AutoMedBench: Towards Medical AutoResearch with Agentic AI Models

The paper introduces AutoMedBench, a novel workflow-aware benchmark that evaluates autonomous medical-AI agents across a five-stage research process, revealing that agents struggle most with validation and submission.

MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation

MobEvolve introduces an agentic self-evolving heuristic system that significantly improves human mobility generation by iteratively refining its internal logic using an LLM agent, outperforming deep generative and LLM-based methods.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentJun 1, 2026

AutoMedBench: Towards Medical AutoResearch with Agentic AI Models

Junqi Liu, Salena Song, Yuhan Wang, Jiawei Mao +11 more

The paper introduces AutoMedBench, a novel workflow-aware benchmark that evaluates autonomous medical-AI agents across a five-stage research process, revealing that agents struggle most with validatio…

View →
cs.AIcs.CLRecentJun 1, 2026

MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation

Junlin He, Yihong Tang, Tong Nie, Ao Qu +5 more

MobEvolve introduces an agentic self-evolving heuristic system that significantly improves human mobility generation by iteratively refining its internal logic using an LLM agent, outperforming deep g…

View →
cs.CERecentMay 29, 2026

CamGeo: Sparse Camera-Conditioned Image-to-Video Generation with 3D Geometry Priors

Xuanyi Liu, Deyi Ji, Liqun Liu, Lanyun Zhu +7 more

CamGeo is a novel framework that improves sparse camera-conditioned image-to-video generation by distilling rich 3D geometric priors into the diffusion backbone, resulting in geometrically consistent…

View →