Xin-Yuan Liu

Visually plausible robot videos often disregard explicitly stated physical properties like weight and friction, undermining their utility for real-world applications.

Faulty robot actions can be completely eliminated through a novel enforcement mechanism that validates skill dispatch in real-time, ensuring safe and effective orchestration of robot crews.

Proprietary MLLMs excel in chart annotation, but open-source models are rapidly catching up, especially with clearer instructions.

REDI-Match not only sets a new benchmark in dense feature matching but also accelerates inference speed, achieving 41 FPS on a single GPU.