Biao Wu

Automotive-ENV: Benchmarking Multimodal Agents in Vehicle Interface Systems

Remote Sensing-Oriented World Model

Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing

UniVid: The Open-Source Unified Video Model

Motion Generalist: Multimodal Motion Generation

Can Large Vision-Language Models Refuse Synthetic Images in Geo-localization?

BagelScore: Visual-Language Evaluation Made Easy

Thin-Thick Adapter: Segmenting Thin Scans Using Thick Annotations