Quanquan Peng

"Cross-embodiment" is a sign of generalization. We’ve seen huge progress in manipulation and navigation — but what about humanoid whole-body control? Can ONE policy control multiple different humanoids? Meet our #ICRA2026 work 🦅EAGLE: Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control. Instead of brute-force URDF / morphology domain randomization, we iteratively distill specialists into one generalist. We also find that embodiment-aware representations matter for policy learning. 🔗 website: eagle-wbc.github.io 📜 arXiv: arxiv.org/abs/2602.02960

@DJiafei Congrats Jiafei!

4 years have been simply amazing! I’m happy to share that I have successfully defended my PhD! Thank you to everyone who came to support me, and most importantly, to my thesis committee, advisors, collaborators, friends, and family for being part of this journey.

Excited to share that ARI (Assured Robot Intelligence) is joining @Meta! When we co-founded ARI a year ago, the mission was clear: build humanoid intelligence for the real world. Joining Meta Superintelligence Labs (MSL), we'll continue advancing frontier robotics models toward physical superintelligence in the physical world. Huge thanks to my co-founders, the incredible ARI team, and our investors led by @aixventureshq for backing this from day one. This is just the beginning.

@xiaolonw @Meta Huge Congrats!

Excited to share that Assured Robot Intelligence (ARI) has joined @Meta to help build the future of humanoid intelligence! When we started ARI one year ago, our mission was clear: achieve physical AGI. Through deep customer engagements and real-world deployments, it became clear to us that serving the massive opportunity ahead requires training a truly general-purpose physical agent. We believe this agent will be humanoid — and that scaling will come from learning directly from human experience, not teleoperation alone. Meta’s ecosystem brings together the key components needed to make this vision possible. We will be joining Meta Superintelligence Labs (MSL) to help bring personal superintelligence into the physical world. We are incredibly grateful to the brilliant minds, robotics researchers, engineers, partners, and supporters who have worked with us on this journey. Thank you to our investors and angels, led by @aixventureshq , for believing in our mission. This is just the beginning.

ARI is joining @Meta! Over the past year, we have been building ARI (Assured Robot Intelligence) with the mission to build industry-grade physical AI for humanoids. The ARI stack is built on human experience, condensed into actionable tokens that can be rapidly adapted to real-world hardware. But the most rewarding part of ARI has been the people. I feel truly blessed to have worked alongside some of the world's best roboticists, a top-notch investor pool led by @aixventureshq, and the many supporters pushing for us behind the scenes. Starting next week, ARI will join the Meta Superintelligence Labs (MSL) to continue advancing frontier robotics models that advance personal superintelligence in the physical world. We have the potential to transform AI that can think and talk to AI that can do, assisting humans safely and reliably in the physical world. To the many people behind the scenes who supported us: Thank you! This is just the beginning. More in the Bloomberg article:

VLA/VAs are doing well on short skills like pick-and-place. But real tasks rarely stop after one action, they require 1) many interdependent steps, 2) progress tracking, and 3) recovery from mistakes. In our paper LoHo-Manip, we address long-horizon manipulation with trace-conditioned VLA planning: a task manager tracks what’s done, plans what remains, and guides execution with visual traces.

@jianglong_ye @xiaolonw @Apple Huge congrats! Well deserved!🙌

Excited to share that I've been selected as a 2026 Apple Scholar in AIML🎉 Huge thanks to my advisor @xiaolonw , and to all my mentors and collaborators for their support. Grateful to @Apple for recognizing and supporting my research🍎 machinelearning.apple.com/updates/apple-…

Reasoning VLAs can think. They just can't think fast. Until now. Introducing FlashDrive⚡ 🚀 716 ms → 159 ms on RTX PRO 6000 (up to 5.7×) ✅ Zero accuracy loss FlashDrive = streaming inference + DFlash speculative reasoning + ParoQuant W4A8 Real-time reasoning for autonomous driving is here! z-lab.ai/projects/flash…

Introducing GEN-1. Our latest milestone in scaling robot learning. We believe it to be the first general-purpose AI model to master simple physical tasks. 99% success rates, 3x faster speeds, adapts in real time to unexpected scenarios, w/ only 1 hour of robot data. More🧵👇

We’re building UWLab, a shared ecosystem for training robot policies in simulation and transferring them to the real world, built on Isaac Lab. This includes the full OmniReset codebase, along with tasks, algorithms, and deployment in one clean, modular stack: github.com/UW-Lab/UWLab

You don’t need tedious reward shaping for RL. Omnireset provides rich prior knowledge for rl exploration!

Introducing EgoVerse: an ecosystem for robot learning from egocentric human data. Built and tested by 4 research labs + 3 industry partners, EgoVerse enables both science and scaling 1300+ hrs, 240 scenes, 2000+ tasks, and growing Dataset design, findings, and ecosystem 🧵

Cross hand embodiment representation matters. If you are interested, please checkout Guangqi’s new work on VLA!

Learning from vast video data allows point-flow-based planners to create generalizable task plans, guiding robots via future keypoint trajectories. But how can we ensure low-level execution doesn't become the system's bottleneck? Introducing our #ICLR2026 paper, HinFlow: Translating Flow to Policy via Hindsight Online Imitation

@lmsysorg @radixark I will vote for Qwen-series, means a lot for robotics people. 😜

🎁 SGLang GTC Giveaway — 20 FREE Passes! SGLang is an open-source LLM serving engine that helps models like DeepSeek, Qwen, Kimi, Minimax, GLM, and Llama run efficiently at production scale. Thanks to our sponsor @radixark, we're giving away 20 NVIDIA GTC 4-day exhibit passes (worth $930 each)! 🎟️ To enter the lottery: 1️⃣ Follow us → @lmsysorg 2️⃣ ⭐ Star SGLang on GitHub → github.com/sgl-project/sg… 3️⃣ Reply with: your favorite open-source model and what you use it for 4️⃣ Repost this for extra visibility How we pick winners: 🏆 Top 5 most engaging comments win directly 🎲 Remaining 15 drawn randomly via xpickr We'll verify your GitHub star before sending tickets, so make sure you've starred the repo! Let's go 👇

To what extent can the humanoid cross-embodiment do? Please check out the latest work! 💪 If you've done humanoid, then you must know how hard it is to get those different robots work at the same time!

@yswhynot That’s the price you pay when you do real world experiments. lol 🤣

Why is one robot headless 😨

@carlosdponx @chris_j_paxton That's a fair point. I am sure the team will release a new work that addresses your concern. Stay tuned tomorrow!

hmm, I guess the question I have, which doesn't seem demonstrated in the paper, is if it's possible to train an expert and distill into the main policy, and have the main policy drive behavior on the new embodiment that was *not* trained into that embodiment's expert. Otherwise, I'm not understanding what the benefit of this approach is over just training for the specific embodiment, right?

You dont need brute force randomization for cross embodiment whole body control