About Me

Hi, I’m currently a Senior Applied Scientist at Amazon working on multimodal LLMs, VLMs, and agentic AI systems for video understanding. I focus on post-training foundation models for video action prediction, captioning, and multimodal safety, with an emphasis on building practical, scalable AI agents that reason, plan, and act over video content.

Previously, I worked at Sony (2021–2022) as a Senior Research Scientist, where I developed 3D character motion for real-time game engines. From 2018 to 2021, I was a Senior Researcher at Tencent America, focusing on human pose estimation and motion analysis. Earlier in my career, I held a postdoctoral role at Bosch (2017–2018), working on sensor-based 3D hand gesture recognition.

My research bridges multimodal learning, computer vision, and agentic AI. I aim to design scalable, agent-driven multimodal AI systems that connect foundation models with real-world perception and action.

Photo: Standing before Mount Rainier — a quiet moment that mirrors my work in AI: navigating complexity, appreciating scale, and always aiming higher.