Ruozhen He
2 papers · Latest:
Computer Vision
Agentic Discovery with Active Hypothesis Exploration for Visual Recognition
HypoExplore is an agentic framework that discovers neural architectures for visual recognition by actively exploring hypotheses and learning design principles.
2604.12999
Computer VisionBeyond Referring Expressions: Scenario Comprehension Visual Grounding
A new benchmark, RSC, challenges visual grounding models to infer targets from complex scenarios, revealing current model limitations.
2604.02323
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.