Embodied Robotics Research

Tag: zero-shot

7 items with this tag.

  • Aug 27, 2026

    CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators

    • world-model
    • cross-embodiment
    • video-generation
    • zero-shot
    • action-conditioning
    • internet-video
  • Aug 26, 2026

    Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization

    • world-action-model
    • in-context-learning
    • human-video
    • synthetic-data-pipeline
    • zero-shot
    • vla-posttraining
  • Jun 30, 2026

    Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors

    • world-models
    • sim-to-real
    • synthetic-data
    • cosmos-policy
    • zero-shot
    • vla-posttraining
  • Apr 06, 2026

    Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?

    • world-model
    • video-generation
    • veo-3
    • inverse-dynamics
    • hierarchical-policy
    • zero-shot
    • tsinghua
  • Apr 03, 2026

    Hierarchical Planning with Latent World Models

    • hierarchical-planning
    • latent-world-model
    • zero-shot
    • long-horizon
    • Meta-FAIR
    • VJEPA2
    • pick-and-place
  • Mar 28, 2026

    SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

    • reward-model
    • video-language
    • chain-of-thought
    • online-RL
    • zero-shot
    • dense-reward
    • manipulation
  • Feb 17, 2026

    World Action Models are Zero-shot Policies (DreamZero)

    • world-model
    • zero-shot
    • cross-embodiment
    • video-diffusion
    • WAM
    • generalization

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).