Article

Tiny Recursive Policy: Recursive Latent Refinement for Visuomotor Control

The authors propose Tiny Recursive Policy (TRP), a parameter-efficient behavior cloning policy that repeatedly updates high-level and low-level latent states using a shared computation module at each control step before decoding an action sequence, and propagates the state to subsequent predictions.

Part of the event: TRP: Behavior Cloning Policy with Recursive Latent State Refinement

This page provides a summary and source link only.