Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

π₀.₅

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 3

  1. Claude Fable 5.2 Tops RoboColiseum’s Expanded Embodied AI Leaderboard

    According to 新智元, Claude Fable 5.2 ranked first in RoboColiseum’s new season with an overall score of 18.30, leading the fine-manipulation and cross-embodiment tracks. The updated benchmark adds 50 tasks across dexterous-hand operation, whole-body coordination, fine manipulation and embodiment transfer, while agents scored particularly poorly on dexterous-hand tasks. The report also says the platform added hidden and dynamic test sets, human review, separate agent and policy rankings, and execution-efficiency scoring.

    新智元 · 🔥 0
  2. GR-BC reuses useful actions from imperfect robot demonstrations

    Zhejiang University, TeleAI, and Gamma Intelligence proposed Graph-Reweighted Behavior Cloning (GR-BC), which links multiple robot attempts in a graph and uses reverse Dijkstra search to estimate progress toward successful outcomes. Action chunks receive positive training weights when they show sufficient net progress and limited retreat, allowing useful local behavior to be retained even in unsuccessful trajectories. With X-VLA as the backbone, the team reported final success rates of 98%, 93%, 89%, and 83% across four real-robot manipulation tasks, averaging about 91%.

    机器之心 · 🔥 0
  3. uni-robot-agent opens a unified harness for robot control

    Researchers from Tsinghua and UC Berkeley introduced and open-sourced uni-robot-agent, a modular harness that connects general-purpose language models to robots through standardized tools and supports further training. Hugging Face · Papers reports that Qwen3.8-Flash-Next scored 31.39 on RoboDojo without privileged inputs, above the previously published 28.97 result for GPT-6 Astra with Astra-RoboProbe. The 36氪 人工智能 report also covers 19 physical manipulation tasks, but notes that some real-world comparisons used different sensor inputs, limiting attribution to the models alone.

    Hugging Face · Papers · 🔥 0

Experience and discussion from the community

Share my π₀.₅ experienceAsk about π₀.₅

Nobody has shared their experience with π₀.₅ yet.