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.

LeJEPA

AI overview

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

Headlines · 2

  1. Qianjue Technology unveils Polibrain predictive world model for robot brains

    At the first 2026 Physical AI and World Models Conference in Nanjing on October 20, Qianjue Technology founder Gao Haichuan released Polibrain, a predictive world model positioned as an embodied-intelligence brain for the real physical world. Rather than generating future frames or reconstructing visual detail, Polibrain predicts task-relevant state changes in a latent representation space, built on the company's polynomial representation architecture and a counterfactual-inference causal memory mechanism, with a loosely coupled design that separates reusable environment understanding from body-specific execution. Qianjue says Polibrain has been adapted to nearly 50 robot configurations, including industrial arms, wheeled bases, dexterous hands and bipedal humanoids, and is being validated in service, logistics, retail and home scenarios; QbitAI reports adaptation work across humanoid, wheeled, single-arm and dual-arm forms and notes that closed-loop reliability in complex scenes still needs fuller real-world test data.

    量子位(原生 RSS) · 🔥 0
  2. LeCun's AMI open-sources H-JEPA, a hierarchical world model for visual planning

    AMI (Advanced Machine Intelligence), the world-model startup chaired by Yann LeCun, released a paper with NYU, INRIA Paris and Brown University describing H-JEPA: multiple JEPA modules stacked so each layer predicts states at its own timescale, with a high level setting a coarse plan and lower levels refining predicted intermediate states into executable actions. The paper reports 73% success for a three-layer model versus 18% for a single-layer model on the Visual AntMaze simulated maze task, with better results at lower planning compute on several tasks; code and pretrained weights were released. The report also says AMI previously raised $1.03B at a $3.5B pre-money valuation, while its website still shows mainly research direction and hiring rather than a public product.

    36氪 人工智能 · 🔥 0

Experience and discussion from the community

Share my LeJEPA experienceAsk about LeJEPA

Nobody has shared their experience with LeJEPA yet.