@PokeBot_Global. Final year PhD Tsinghua University, IIIS.
Joined July 2021
- Tweets291
- Following672
- Followers737
- Likes868
Pinned Tweet
🌶️🤖𝐖𝐞 𝐜𝐨𝐨𝐤𝐞𝐝 𝐭𝐡𝐞 𝐫𝐨𝐛𝐨𝐭𝐢𝐜𝐬 𝐰𝐨𝐫𝐥𝐝’𝐬 𝐟𝐢𝐫𝐬𝐭 𝐩𝐥𝐚𝐭𝐞 𝐨𝐟 𝐌𝐚𝐩𝐨 𝐓𝐨𝐟𝐮.🤖🌶️
This was not just a cooking demo. It was a 30-minute, long-horizon robotics challenge packed with delicate, continuous, high-dexterity actions.
With only a small number of demonstrations, our model learned to perform complex manipulation over an extended sequence. At the same time, we pushed hard on motion control and system-level optimization, making the robot move smoothly while keeping the high success rate.
For us, this plate of Mapo Tofu is more than a dish. It is a small but meaningful step toward home robots that can handle real everyday tasks with the dexterity, consistency, and reliability people expect.
Zhecheng Yuan retweeted
Really enjoy playing with Poke’s RoboAPI in our lab. The whole system is plug-and-play. I’ll definitely stay tuned and look forward to their future updates.
teapawt.org/PokeBot_Global/status/…
cool!
This is truly impressive work!
I used RoboAPI to reproduce a zero-shot task, and it worked on the very first try. Even more impressively, the robot knows when something goes wrong and can retry on its own.
Huge thanks to @HarryXu12 and his team @PokeBot_Global for their incredible work!
Zhecheng Yuan retweeted
Finally releasing the results of the arch ablations I was running with bux over the weekend
Zhecheng Yuan retweeted
We had a lot of fun testing out RoboAPI, the set up is very easy if you want to try it out yourself! :)
Don't trust demos. Try it yourself.
Introducing RoboAPI, powered by Poke-Aurora, our world-action model.
Give compatible robots natural-language instructions through a simple API. No task-specific training.
More information: pokebot.com/ai
Zhecheng Yuan retweeted
Witnessed the birth of RoboAPI. Can't wait to see everyone try it out! 🚀
Don't trust demos. Try it yourself.
Introducing RoboAPI, powered by Poke-Aurora, our world-action model.
Give compatible robots natural-language instructions through a simple API. No task-specific training.
More information: pokebot.com/ai
Today we’re launching 𝗥𝗼𝗯𝗼𝗔𝗣𝗜, our first product, powered by 𝑷𝒐𝒌𝒆-𝑨𝒖𝒓𝒐𝒓𝒂, our latest world-action model.
Ready to use out of the box. No extra training data. No fine-tuning.
Can’t wait to see what you build with it.
Don't trust demos. Try it yourself.
Introducing RoboAPI, powered by Poke-Aurora, our world-action model.
Give compatible robots natural-language instructions through a simple API. No task-specific training.
More information: pokebot.com/ai
Zhecheng Yuan retweeted
Collecting data for dexterous hands is hard. Teleop needs a full setup. Bringing UMI-like devices to 20-dof hands is challenging.
Introducing DexPort 🖐️: a hand-held interface w/ a real robot hand. No embodiment gap, recorded joint state AND actions, easy to use.
Zhecheng Yuan retweeted
Common belief: Robot policies need continuous action heads; discrete actions are 𝐥𝐞𝐬𝐬 𝐧𝐚𝐭𝐢𝐯𝐞 𝐚𝐧𝐝 𝐥𝐞𝐬𝐬 𝐩𝐫𝐞𝐜𝐢𝐬𝐞.
❗We find policies w/ the simplest discrete representations 𝐦𝐚𝐭𝐜𝐡 𝐨𝐫 𝐛𝐞𝐚𝐭 continuous ones—in sim & real, in single-step & diffusion/flow settings.
Here's why 🧵
Zhecheng Yuan retweeted
We recently published the eight-week process behind scaling our UMI dataset to 1M+ tasks and 45k+ new tasks a day.
Now, we’re open-sourcing DiverseUMI-100, a collection of 12,000+ tasks from a 100-hour sample of our dataset, complete with dense annotations by Argus, our advanced robotics annotation pipeline.
How do you build the most diverse UMI dataset in robotics?
In the last 8 weeks, we scaled an international UMI data collection operation from 5 to 90 operators, built out a dataset of over 1M+ unique tasks, and continue to capture over 45k+ new tasks each day.
Robotic World Models require much higher diversity of tasks than imitation learning. Here's the why and how behind our operations. 🧵
Zhecheng Yuan retweeted
What’s missing from robot foundation models? An explicit understanding of WHY motions work: why move in this direction, why place the object in this way, how hard to grasp the object. This motion-level reasoning bridges instructions to actions—and provides knowledge that can generalize across embodiments and scenes.
Pure behavior cloning supervises WHAT actions to take, but leaves models to infer WHY those actions work. This becomes especially limiting when learning from large-scale heterogeneous data, including egocentric human data, where humans and robots can take very different actions to achieve the same physical effect. We need models to extract the intent behind those motions, rather than simply recite them. Why leave that knowledge buried in trajectories when we can teach it explicitly?
Introducing EgoLAP: a shared language for human and robot motion. Language actions teach HOW to move; motion-level reasoning teaches WHY the motion works. Together, they unlock, to our knowledge, unprecedented gains in zero-shot performance for robot foundation models without additional robot demonstrations.
arxiv.org/abs/2610.08726
ego-lap.github.io/
Zhecheng Yuan retweeted
DINOv2 has never seen a caption, and Qwen3 has never seen an image. We still aligned their embedding spaces without a single image-caption pair.
It even works when the images and the captions come from different datasets.
Project page: dominik-schnaus.github.io/un…
⬇️
Zhecheng Yuan retweeted
In PRH, we argued that representational geometry is converging, but it's still an open question exactly in what sense.
I want to share some new evidence that might clarify the picture.
The evidence comes from our work here, led by @dominik_schnaus: dominik-schnaus.github.io/un…
1/n
Zhecheng Yuan retweeted
(1/5) Everyone says dexterous manipulation needs real-world data. These policies were trained with none. Our robots mesh gears, thread nuts, and insert pegs zero-shot from RGB, and the same recipe works for locomotion across terrains much harder than before.
The missing piece wasn't a better RL algorithm, but a small tweak to what the robot practices.
Today we're releasing Success-Guided Sampling (SGS), a simple change to the task sampler that unlocks new levels of dexterity and agility with large-scale, end-to-end sim2real RL.
No demonstrations, no per-task reward tuning. Just PPO at scale.
Check out the policies yourself at sgs-rl.github.io! All videos at 1x speed! 🧵 🔈
Zhecheng Yuan retweeted
Can a humanoid learn robust whole-body loco-manipulation directly from a human? No robot, no teleop, no retargeting.
Meet Workhorse 🐴: our G1 topples and climbs a suitcase, catches a thrown box, and sorts boxes with hands and a kick. Fully autonomous.
More videos at hybridrobotics.github.io/wor…
Zhecheng Yuan retweeted
🤖 Reusing skills is one possible way for embodied agents to generalize. Manipulation varies but shares a few skills: wiping a table or a window is one skill. Many works give agents skills to plan with. But where do these skills, and their data, come from?
📼 Today, VLMs mostly label videos one at a time, and nothing carries over. People don't learn that way. As experience streams in, we spot skills we know, add new ones, and reuse them later. This streaming setting matters, but it has received little attention.
🧠 VLMs may become the brains of embodied agents. So we ask: from streaming experience, can they find reusable skills and keep one consistent skill library?
🧵 Video2Skill: From Streaming Experience to Reusable Embodied Skills
Why it matters:
📈 It can label much more data for training agents.
🔁 It is planning in reverse. If a model can't find skills in what it has seen, how can it plan with them for something new?
📄 Paper: arxiv.org/abs/2609.36691
🌐 Project: andyzworks.github.io/video2s…
🤗 Data: huggingface.co/datasets/Ster…
Zhecheng Yuan retweeted
由于最近读论文的需求激增，加上本人已经受够了沉浸式翻译和DeepL这些翻译软件的垃圾排版和垃圾翻译，受够了Zotero这些old软件的垃圾文献管理，所以忙里偷闲搓了个玩具
EasyRead就是为了让你更舒服地读论文，不用在claude和gpt这些应用里面很难受地读（老艺术家喜欢原汁原味地读全文而不是让大模型直接总结），支持文献管理、自定义模型、原文对照、文献搜索与pdf导入（搜索我只试了arxiv，原谅我，有人用了再说）、能在阅读页直接对话（这不爆杀alphaxiv？），唯一的缺点是烧自己的额度，不过也没多少
项目链接：github.com/Edwardxlai/easyre…，点个star支持一下呀
Zhecheng Yuan retweeted
Argus: an open-source robotics data annotation and quality pipeline.
With new frontier VLMs like GPT-6 Astra, we can generate rich, high-quality annotations for robotics data for both training and dataset analysis. Argus delivers detailed, timestamp-level annotations while catching issues like mislabeled instructions, sped-up recordings, swapped camera streams, and unflagged operator mistakes.
To support better data quality for the robotics community, we’re open-sourcing Argus for anyone to use 🧵
Zhecheng Yuan retweeted
What will be the “RLHF” moment for robotics? What will it take to get robotics to where LLMs are today and beyond?
New blog post with @chelseabfinn sharing some thoughts on the state of RL for frontier robotics models and what's missing 👇
Blog: pd-perry.github.io/posts/pos…
