Yali Wang

VideoChat-r1.5: visual test-time scaling to reinforce multimodal reasoning by iterative perception

VRBench: a benchmark for multi-step reasoning in long narrative videos

Task preference optimization: improving multimodal large language models with vision task alignment

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding