Embodied AI 101

Shaoqing Tan
  • 5.0（1則評分）
  • 科技
  • 每日更新

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

  1. 13 小時前

    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 分鐘

  2. 22 小時前

    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 分鐘

  3. 1 天前

    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 分鐘

  4. 1 天前

    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 分鐘

  5. 5 天前

    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 分鐘

  6. 5 天前

    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 分鐘

  7. 5 天前

    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 分鐘

  8. 6 天前

    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 分鐘
顯示全部 (167)

簡介

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

資訊

  • 創作者
    Shaoqing Tan
  • 活躍年代
    2025年 - 2026年
  • 集數
    167
  • 年齡分級
    兒少適宜
  • 版權
    © 2026 Shaoqing Tan

你可能也會喜歡