Embodied AI 101

Shaoqing Tan

Stay in the loop on research in AI and physical intelligence.

  1. APR 8

    Claw-Eval: Toward Trustworthy and Transparent Evaluation of Autonomous Agents

    Benchmark with 2,159 rubric items across 300 tasks using trajectory-aware grading and 3-trial Pass^3 scoring to mitigate luck. Evaluates agent reliability in real-world robotics settings.

    29 min

  2. APR 8

    LIBERO-Para: Paraphrase Robustness in Robotic Manipulation

    Reveals paraphrase fragility in VLAs causing 22-52% success drops due to task misidentification. Introduces PRIDE metric weighting success by paraphrase difficulty on LIBERO benchmark manipulation tasks.

    32 min

  3. APR 7

    YOR: Your Own Mobile Manipulator for Generalizable Robotics

    Low-cost mobile manipulator design and training strategies for broad generalization in real-world tasks.

    27 min

  4. APR 7

    EgoSim: Egocentric World Simulator for Embodied Interaction Generation

    Closed-loop egocentric video simulator maintaining persistent 3D scene state for consistent interactions, enabling cross-embodiment transfer from human videos to robotic manipulation.

    51 min

  5. APR 7

    Accelerating Video World Models: From Generative Videos to Real-Time Simulators

    Comprehensive survey taxonomizing efficient architectures/algorithms for video world models as simulators, targeting compute bottlenecks in embodied AI, autonomous driving, and games with techniques like short-window attention for real-time long-horizon prediction.

    39 min

  6. APR 7

    From Tokens to Thoughts: Continuous Latent Reasoning in Large Models and Robot Control

    Curated collection of 100+ works surveying shift to continuous latent spaces in LLMs/VLMs/VLAs for improved reasoning over discrete tokens, with relevance to robotics action modeling.

    27 min

  7. APR 6

    CaP-X: Coding Agents for Physical eXecution

    CaP-X is an open-source agentic robotics framework where LLMs/VLMs generate code to call perception and control APIs for execution across diverse simulated and real robots in CaP-Gym's 187 manipulation tasks. The framework includes CaP-Bench for evaluating frontier models and CaP-RL, which boosts a 7B model's success from 20% to 72% with minimal sim-to-real gap.

    14 min

  8. APR 6

    DoRA: Weight-Decomposed Low-Rank Adaptation

    An upgrade over LoRA for parameter-efficient fine-tuning, enabling better performance in LLMs by decomposing weights into magnitude and direction components.

    39 min
See All (44)

About

Stay in the loop on research in AI and physical intelligence.

Information

  • Creator
    Shaoqing Tan
  • Years Active
    2025 - 2026
  • Episodes
    44
  • Rating
    Clean
  • Copyright
    © 2026 Shaoqing Tan

You Might Also Like