Embodied Robotics Research

Tag: benchmark

5 items with this tag.

  • May 05, 2026

    RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models

    • reward-alignment
    • video-world-model
    • GRPO
    • RL-post-training
    • long-horizon
    • benchmark
  • Apr 05, 2026

    VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models

    • machine-unlearning
    • safety
    • OpenVLA
    • embodied-AI
    • benchmark
  • Mar 24, 2026

    Grounding Sim-to-Real Generalization in Dexterous Manipulation: An Empirical Study with Vision-Language-Action Models

    • sim-to-real
    • domain-randomization
    • photorealistic-rendering
    • RL
    • benchmark
    • dexterous-manipulation
  • Mar 24, 2026

    ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment

    • world-model
    • physics-alignment
    • diffusion-transformer
    • DPO
    • manipulation
    • benchmark
  • Mar 23, 2026

    Do World Action Models Generalize Better than VLAs? A Robustness Study

    • robustness
    • benchmark
    • generalization
    • VLA-comparison
    • LIBERO
    • RoboTwin
    • perturbation

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community