Papers

Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.

Filtered by domain: offline-reinforcement-learningClear

TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models

18 Oct 2026

Large-scale action pretraining equips Embodied Foundation Models (EFMs) with strong manipulation capabilities, with particular strengths in generalization and closed-loop robustness, but reproducing such pretraining requires substantial robot data and computation.

Offline Reinforcement Learning Reinforcement Learning Robotics

Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,663 papers.