🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

The robot hands and Manus glove code are open sourced at bidex-teleop.github.io. Bidex works with many robot arms! #Corl2024 MANUS™ It was led by me and Yulong Li with Jiahui(Jim) Yang Mohan Kumar Srirama Ray Liu, Haoyu Xiong and advisors Russell Mendonca and Deepak Pathak

With joint-to-joint mapping teacher arms + motion capture gloves, Bidex stands out for its intuitive teleoperation experience and high-quality data. Check this thread for further details 👇

Excited to share that I'll be joining University of California at Irvine as a CS faculty in '25!🌟 Faculty apps: Krishna Murthy, Zhuang Liu & I share our tips: unnat.github.io/notes/Hidden_C… PhD apps: I'm looking for students in vision, robot learning, & AI4Science. Details👇

Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics

This is wild🤯

World models that enable zero-shot planning and task-agnostic reasoning at test time! 🚀 Train from offline data and unlock powerful test-time decision-making. Huge thanks to the team for this great collaboration!

🚀 Can we make a humanoid move like Cristiano Ronaldo, LeBron James and Kobe Byrant? YES! 🤖 Introducing ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills Website: agile.human2humanoid.com Code: github.com/LeCAR-Lab/ASAP

We introduce Dexterity Gen (DexGen), a foundation controller that enables unprecedented dexterous manipulation capabilities. For the first time, it allows human teleoperation of tasks such as using a pen, screwdriver, and syringe. Developed by @berkeley_AI and @MetaAI. A Thread.

Super cool setup! Really excited to see how force feedback can boost performance in contact-rich tasks!

FACTR is now open source! You can now build your own low-cost force-feedback teleop system. Hardware: github.com/JasonJZLiu/FAC… Teleop Code: github.com/RaindragonD/fa… Training Code: github.com/RaindragonD/fa…

1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a **discrete diffusion objective**. Our model has all the benefits of diffusion models but now in

"Gr00t" vs "Pi0" vs "Pi0 Fast". I compared top open-source robotic models, and here's a detailed overview based on our own experience:

Over the past few months we've been working with Boston Dynamics on end-to-end dexterous manipulation for the EAtlas:

Meet 𝐀𝐌𝐎 — our universal whole‑body controller that unleashes the 𝐟𝐮𝐥𝐥  kinematic workspace of humanoid robots to the physical world. AMO is a single policy trained with RL + Hybrid Mocap & Trajectory‑Opt. Accepted to #RSS2025. Try our open models & more 👉

our new system trains humanoid robots using data from cell phone videos, enabling skills such as climbing stairs and sitting on chairs in a single policy (w/ Hongsuk Benjamin Choi Junyi Zhang David McAllister)

In the wild data collection enables in the wild generalization! Impressive work, congrats to the team!

Tired of teleoperating your robots? We built a way to scale robot datasets without teleop, dynamic simulation, or even robot hardware. Just one smartphone scan + one human hand demo video → thousands of diverse robot trajectories. Trainable by diffusion policy and VLA models

Excited to share our work: Maximizing Confidence Alone Improves Reasoning Humans rely on confidence to learn when answer keys aren’t available (e.g taking an exam). Surprisingly, LLMs can also learn w/o ground-truth answers, simply by reinforcing high-confidence answers via RL!

One fundamental issue with RL – whether it’s for robots or LLMs – is how hard it is to get rewards. For LLM reasoning, we need ground-truth labels to verify answers. We found that maximizing confidence alone allows LLMs to improve their reasoning with RL!