Tao Yu
Tao Yu is an Assistant Professor of Computer Science at the University of Hong Kong and Director of XLANG Lab (Executable Language Grounding Lab). His research focuses on grounding language and perception into executable actions for both digital and physical environments, with particular emphasis on embodied AI agents and Vision-Language-Action policies for robotics. He is best known for contributions including FineVLA, a framework for fine-grained instruction alignment in steerable robot policies, and has received the Google Research Scholar Award (2023) and Amazon Research Award (2022).
“FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies”
Source→“The authors release FineVLA-Tool (the pipeline to unify and annotate datasets), FineVLA-Data (47,159 human-verified trajectories), RoboFine-VLM (a specialized video annotator), and RoboFine-Bench (a benchmark for evaluating execution-level understanding).”
Source→“Yu leads XLANG Lab, which has produced multiple influential works in language-grounded robotics and code/agent systems. His lab's focus on open-source infrastructure for embodied AI makes FineVLA a flagship contribution to the field.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.