Overview

Latent action learning studies how to represent meaningful behavior compactly, often by inferring actions from video or trajectories that lack action labels. Common approaches use inverse and forward dynamics, predictive world models, vector-quantized or continuous flow-based representations, and geometric or hierarchical structure. These representations can help vision-language-action policies plan and control robots, especially across long tasks, different embodiments, and limited demonstration data; LIBERO, CALVIN, and RoboTwin are common evaluation settings alongside real robots. A central open tension is that representations good at reconstructing visual changes may capture nuisance or environmental variation rather than controllable actions, so predictive consistency and proxy metrics do not always guarantee better downstream control.

Latest papers

CardsList

123 papers15 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation

    Jan 30, 2026Wu Songwei, Jiang Zhiduo, Sun Wandong +4Flow MatchingLatent Action Learning

  2. Wavelet Policy: Imitation Learning in the Scale Domain with World Prior Memory

    Apr 7, 2025Changchuan Yang, Haoxuan Xu, Yuhang Dong +3Latent Action LearningVisuomotor Policy Learning

  3. Synergistic Action and Style Priors for Learning Legged Locomotion

    Oct 4, 2024Oliver Hausdörfer, Alexander von Rohr, Éric Lefort +1RL for Legged LocomotionRobot Policy Learning