research ReGRPO — Reflection-Augmented RL for Tool-Using Agents Group-relative policy optimization with structured self-reflection for long-horizon tool use. RCFC — Lifelong Robot Imitation Learning Prototype replay and coarse-to-fine compatibility for lifelong imitation learning. Ego-centric Predictive Model Two-stage egocentric video prediction conditioned on hand trajectories. Task-Agnostic Compatible Adapter (TaCA) Upgrade visual foundation models without retraining downstream tasks.
