Embodied Robotics Research

Tag: vla

8 items with this tag.

  • Jun 25, 2026

    LA4VLA: Learning to Act without Seeing via Language-Action Pretraining

    • vla
    • language-action-pretraining
    • language-grounding
    • data-efficient
    • pretraining
  • Jun 15, 2026

    Geometric Action Model for Robot Policy Learning

    • vla
    • 3d-geometry
    • geometric-foundation-model
    • world-model
    • robot-policy
    • kaist
    • eth-zurich
  • Jun 04, 2026

    Robots Need More than VLA and World Models

    • vla
    • world-models
    • position-paper
    • data-interfaces
    • embodiment-gap
    • reward-modeling
    • survey
  • Jun 04, 2026

    TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies

    • vla
    • speed-control
    • trajectory-augmentation
    • manipulation
    • execution-speed
  • Jun 03, 2026

    FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization

    • vla
    • reinforcement-fine-tuning
    • flow-matching
    • preference-optimization
    • reward-free
    • tencent-robotics
  • May 29, 2026

    Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

    • vla
    • unified-model
    • cross-embodiment
    • navigation
    • manipulation
    • alibaba
    • qwen
  • May 12, 2026

    RAW-Dream: Reinforcing VLAs in Task-Agnostic World Models

    • world-model
    • rl
    • vla
    • task-agnostic
    • reward-free
    • vlm-reward
    • microsoft-research
  • Mar 18, 2026

    AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models

    • rl-infrastructure
    • distributed-rl
    • async-rl
    • world-model
    • vla
    • training-framework
    • open-source

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community