Yuxiang Lu

FASTER. FASTER: Rethinking Real-Time Flow VLAs

FedHCA2. [CVPR2024] FedHCA^2: Towards Hetero-Client Federated Multi-Task Learning

piper-aio. An imitation learning stack for AgileX Piper arms and Cobot Magic systems—covering the full pipeline from hardware bring-up and teleop data collection to replay, LeRobot conversion, and policy inference.

SAK. [ICLR2025] Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning

MTDP_Lib. A simple code base for multi-task dense prediction methods, supporting both multi-decoder and task-conditional models

CS489_RL_Project. Python