Embodied AI 101

Shaoqing Tan

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

  1. há 9 h

    Contact-Grounded Policy: Dexterous Visuotactile Policy with Generative Contact Grounding

    Learns dexterous manipulation policies that explicitly ground actions in generative contact predictions from visuotactile observations, improving robustness on contact-rich tasks.

    27 min

  2. há 18 h

    Freeform Preference Learning (FPL) for Robotic Manipulation

    Introduces multi-axis preference supervision to learn dense, language-conditioned rewards across speed/precision/subtask axes without segmentation; enables compositional generalization and better long-horizon credit assignment than single-reward baselines.

    49 min

  3. há 1 dia

    Orca: The World is in Your Mind

    Proposes a general world foundation model leveraging Next-State-Prediction to jointly generate text, images, and embodied actions within a unified framework.

    29 min

  4. há 1 dia

    Qwen-RobotNav: A Scalable Unified Navigation Model for Agentic Robotics

    A unified 2B–8B parameter model for robot navigation tasks (VLN, ObjectNav, tracking, autonomous driving) via a configurable observation protocol, with demonstrated zero-shot deployment on real quadruped robots using agentic planners.

    37 min

  5. há 5 dias

    Scaling Robot Skills from Cheap Human Videos

    Replaces noisy 6-DoF hand poses with relative wrist translation as a shared action space between humans and bimanual robots, enabling scalable skill acquisition from inexpensive video data. This approach outperforms full-pose baselines for robot skill learning.

    15 min

  6. há 5 dias

    ABC: An Open Behavior Cloning Stack for Bimanual Manipulation

    Large-scale open-source framework for real-world robotic manipulation using behavior cloning, including the ABC-130K dataset with 3,500 hours and 130K+ episodes across 195 tasks. Provides hardware setups, simulators, and training recipes for Diffusion Transformers and Vision-Language-Action models.

    33 min

  7. há 5 dias

    Qwen-RobotManip: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

    Presents alignment techniques to scale robotic manipulation foundation models, building on the Qwen model family for dexterous robot control.

    20 min

  8. há 6 dias

    ASPIRE: Automated Skill Discovery for Robotics

    Introduces the first automated system that continuously discovers, evolves, and accumulates reusable sensorimotor skills via evolutionary search over control programs, enabling compounding multi-task, sim-to-real, and cross-embodiment transfer without retraining end-to-end policies.

    31 min
Ver tudo (167)

Sobre

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

Informações

  • Criado por
    Shaoqing Tan
  • Anos de atividade
    2025 - 2026
  • Episódios
    167
  • Classificação
    Livre
  • Copyright
    © 2026 Shaoqing Tan

Você também pode gostar de