Benlin Liu

I am a PhD student in Computer Science at the University of Washington and a Doctoral Researcher at Google DeepMind. My research focuses on multimodal intelligence, with an emphasis on bridging perception and reasoning in vision-language models and visual agents.My work spans multimodal reasoning, long-video understanding, visual representation learning, and agentic AI. I am particularly interested in building unified systems that can perceive, reason, remember, and act in complex visual environments.Previously, I conducted research at Google DeepMind and Meta Reality Labs. I received my M.S. in Computer Science from UCLA and my B.Eng. from Tsinghua University.