Search papers, labs, and topics across Lattice.
School of Artificial Intelligence, University of Chinese Academy of Sciences
3
0
5
Forget robot-specific fine-tuning: a unified diffusion model can now learn policies across diverse robot embodiments, boosting performance by 15% and opening doors to truly generalizable robotic agents.
Forget slow, multi-step action generation: CF-VLA's coarse-to-fine approach slashes latency by 75% while boosting real-robot success rates to a new high of 83%.
Current VLM-driven embodied agents struggle with fundamental skills like navigation and object manipulation when evaluated in realistic, low-level action spaces, severely hindering their performance on complex tasks.
