Pinned Tweet
Most VLAs are memoryless: when a robot's hardware drifts, the policy repeats the same failure every trial.
What if it could learn from its own failed rollouts and fix itself, without tedious recalibration?
Introducing a post-training recipe to remedy this: Self-Adaptive VLA 🧵
Hongxin Zhang retweeted
Genesis is entering its next phase.
Today we've raised a $500M Series A at $3.5B.
We can imagine far more than we can build physically today. Almost everything we are creating is still paid for in human time, by human hands. We want to remove the physical limits on human ambition.
We are building general-purpose robots with human level intelligence and capability. Ones that work reliably across entire workflows for years.
There are countless versions of possible futures where billions of robots are deployed everywhere, and we aspire to bring the brightest one that carries our hopes into reality.
Hongxin Zhang retweeted
Two years ago, we released Genesis, a universal physics engine for robotics.
Today, I’m excited to announce 🍎 Eden — a robot learning framework built from the ground up for agents, unleashing full potential of Genesis.
One task definition. From simulation to real robots. Sim-to-sim and sim-to-real just got easier.
Coding agents build tasks 1.6–4× faster than in Isaac Lab.
🧵 1/11
Check out RoboWits, a robotic creative problem solving benchmark for agentic robotics! I’ll be at CoRL and happy to talk about anything about how to leverage agents/context to advance robotics!
🎉Excited to share that RoboWits has been accepted to #NeurIPS2026!
Robots in the real world keep running into the unexpected. A task solution may not match the task instruction; can robot policies nowadays reason, adapt, and use tools creatively when that happens? 🧵
6
190
Self-Adaptive VLA helps with cross-workstation deployment. When moved to a new station, the base policy fails 5/5 episodes. With 2 failed trials as context, Self-Adaptive VLA succeeds on 5/5.
Check out our paper!
Paper: arxiv.org/abs/2609.30092
Project page: icefoxzhx.github.io/self-ada…
Joint work with amazing @ChunruLin01, @johnsonwang0810, @Zhenjia_Xu, and @gan_chuang.
Can't wait to build powerful agents with the powerful engine!
We are back again :) After three weeks of quiet building.
Introducing Genesis World 1.0, our latest simulation platform, the second release in our full-stack suite. Open-sourced.
Robotics is still bottlenecked by the 1× speed of the physical world. Every model, checkpoint, and data recipe eventually needs to be tested on physical hardware, slowly, expensively, and with limited coverage.
One hour in reality can become 100 days in simulation. That is how robotics model iteration moves from a wall-clock bottleneck to a compute problem.
To make this work, simulation has to be both fast and trustworthy.
Over the past year, we rebuilt the entire stack: a GPU-accelerated cross-platform compiler, penetration-free multi-physics contact solvers, unified rigid and deformable physics, and a photo-realistic renderer purpose-built for physical AI applications.
We built Nyx, a high-performance path-traced rendering engine for robotics application.
Genesis World 1.0 achieves near realtime performance with our latest development for penetration-free IPC solver, supporting various types of deformables beyond rigid bodies. It supports contact-rich, dexterous manipulation simulation across different embodiments: unitree, sharpa, wuji, genesis hand and various types of grippers.
Under the hood is Quadrants, our effort in pushing forward cross-platform GPU-accelerated computation. Quadrants started as a fork of Taichi, and we rebuilt most of the critical parts for optimizing simulation workloads, giving 10x faster launch time and up to 4.6x runtime performance compared to the initial Genesis release.
Together, they bring us to an unprecedentedly low sim-to-real gap, enabling zero-shot real-to-sim model evaluation and much faster iteration of GENE.
All available today.
Genesis World 1.0: github.com/Genesis-Embodied-…
Quadrants: github.com/Genesis-Embodied-…
Nyx: github.com/Genesis-Embodied-…
2
137
Hongxin Zhang retweeted
We are back. After one year of quiet building.
Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability.
For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans.
Solving it means rethinking the whole stack from the ground up:
- A robotics-native foundation model.
- A 1:1 human-like robotic hand.
- A noninvasive data collection glove for motion, force, and touch.
- A simulator that turns weeks of experiments into minutes.
GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm.
Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on)
We are approaching the endgame for robotics.
And this is just a beginning.
thanks @_akhaliq for highlighting our work! Build your own community today based on real-world 3D scenes and physically plausible simulations, and see how current AI Agents can achieve!
4
331
Check out Virtual Community! A unified platform for Embodied AI Research on Robots, Agents, and Societies, based on real-world 3D Scenes and physically plausible simulations! Build your own community today and see what current AI Agents could achieve!
virtual-community-ai.github.…
World Simulator, reimagined — now alive with humans, robots, and their vibrant society unfolding in 3D real-world geospatial scenes across the globe!
🚀 One day soon, humans and robots will co-exist in the same world. To prepare, we must address:
1️⃣ How can robots cooperate or compete intelligently?
2️⃣ How do humans build social bonds and communities?
3️⃣ How can both co-exist in an open, dynamic world?
Announcing Virtual Community Project — a social-physical world simulator, where human characters and robotic agents can interact, grow, and co-evolve within open-world societies, stretching from London to New York, and beyond!
Key features include:
✅ Unified multi-agent physics simulations for rich social + physical interactions of humans and robots
✅ Massive auto-generated 3D scenes grounded with the rea-world geospatial data
✅ Agent communities populated by robots and LLM-driven human characters with rich appearances, personalities, and social ties.
🌍 Enter our Virtual Community, an open world to study embodied AI at scale— one social-physical world model at a time!
🔗 Project: virtual-community-ai.github.…
💻 Code: github.com/UMass-Embodied-AG…
Paper: virtual-community-ai.github.…
1/n
2
274
Hongxin Zhang retweeted
Thanks @_akhaliq for sharing our work TesserAct: Learning 4D Embodied World Models!
Step into the TesserAct and explore — or push the boundaries of TesserAct!
Tomorrow (4.24), 15:00-17:30 at ICLR Hall 3 + Hall 2B #34,
I'll present COMBO: Compositional World Models for Embodied Multi-Agent Cooperation.
Come to talk!
Hongxin Zhang retweeted
Excited to introduce 3D-Mem!
Spatial Intelligence simply isn’t possible without robust 3D Scene Memory. That’s why we developed 3D-Mem, an effective framework for lifelong exploration and reasoning.
Thrilled to share that it’s been accepted to #CVPR2025 !












