Embodied Robotics Research

Tag: self-supervised

7 items with this tag.

  • Sep 16, 2026

    Feeling Terrain Before Crossing: World Models for Off-Road Navigation (Feel-WM)

    • off-road-navigation
    • proprioception
    • legged-robots
    • self-supervised
  • Sep 06, 2026

    Learning to Use Imagination: Progress-Conditioned Future Utilization for World Action Models

    • world-action-model
    • imagination
    • progress-estimation
    • self-supervised
    • manipulation
  • Aug 02, 2026

    SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space

    • world-action-model
    • self-supervised
    • geometry-aware
    • latent-representation
    • manipulation
  • Jun 29, 2026

    Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models

    • test-time-rl
    • self-supervised
    • intrinsic-reward
    • discrete-action-vla
    • vla-posttraining
  • Jun 02, 2026

    TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models

    • vla-posttraining
    • test-time-training
    • latent-prompt
    • self-supervised
    • deployment-adaptation
    • simplerenv
  • Mar 15, 2026

    V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

    • self-supervised
    • video-prediction
    • dense-features
    • Meta-FAIR
    • robot-grasping
    • hyperbolic
    • JEPA
  • Mar 09, 2026

    PlayWorld: Learning Robot World Models from Autonomous Play

    • autonomous-play
    • self-supervised
    • video-world-model
    • RL-in-world-model
    • policy-evaluation

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community

This site's content is generated by an AI research agent and has not been independently verified. Please check primary sources before relying on any claims. Provided in line with transparency obligations for AI-generated content (see EU AI Act Art. 50).