Zhecheng Yuan

@PokeRobotics. Final year PhD @Tsinghua University, IIIS.

[Zhecheng Yuan @fancy_yzc]

🌶️🤖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.

[mimic @mimicrobotics]

From day one, mimic has been focused on a single goal: general-purpose dexterous manipulation. Today we're proud to announce the mimic hand M1 and the mimic wearable U1.

We believe the only way to solve dexterous manipulation at scale is by going full-stack at the frontier of physical AI, building every layer ourselves around one fixed point, the human hand.

The M1 is a highly backdrivable, tendon-driven hand that covers the full range of human capability, from heavy payloads to fine manipulation.

[Dian Wang @Dian_Wang_]

Long horizon bimanual mobile manipulation requires reasoning in many coordinate frames: base, L/R hands, etc. In which frame would policy work best?
It really depends, so don’t pick. Mixture of Frames Policy: denoise in multiple frame in parallel.
🌐https://t.co/GnKSeNqzHA (1/9)

[lingxiao guo @Lingxiao234]

Reality of mobile manipulation: 1,000 demos buy you 1 task, in 1 scene.

Introducing 𝐖𝐀𝐍𝐃𝐀: a synthetic data engine that turns ONE demo into thousands of trajectories across unseen scenes — and the policy works in the open world.

One demo in. An open world out.

🧵

[Shuangyu Xie @Shuangyu0_0Xie]

🤖How well do today's VLMs actually understand real-world robotics? 👀

Excited to share RoboVista at #RSS2026 — a systematic evaluation and benchmark for VLMs across diverse, real-world robot applications. Website, dataset and paper: https://t.co/saNSk3iVsg

Developed by researchers at @UCBerkeley, @GoogleDeepMind, and @Princeton. 🧵👇

[Zhenyang Chen @DanielZhenyang]

Today's frontier VLAs can do many tasks—but they're far less steerable than advertised. Switch the instruction mid-execution and frontier models often plow ahead with the original task anyway.

🤖In our #RSS2026 paper, we measure steerability, explain why it breaks, and fix it. Introducing **ReSteer** (1/7)

[Utkarsh Mishra @utkarshm0410]

WAMs are popular because of their promise of better generalization. Is that true? We started playing with Video-Action-Model (VAMs) and realized a gap: video model backbones can compositionally generalize but VAMs often do not.

We coin this the Video-Action-Generalization (VAG) gap and present a study on how to explain and improve it. More details: https://t.co/kwoxy2SCVu

🧵 below

[Marcel Torné @marceltornev]

We should stop optimizing robot policies against a single overall reward. Trajectories differ along many axes, such as speed, precision, and subtask completion, and one can be better on some while worse on others. If we collapse all of that into a single overall axis we lose this structure making the reward ambiguous and harder to optimize.

Blog: https://t.co/WXWue03RVq
Paper: https://t.co/AvJ904Xt9S

[Sarvesh Patil @servo97]

Interaction with the real world is the major bottleneck in robot learning. So what would robot RL look like if we didn’t need to limit compute per interaction? Our latest work, Off-Policy Generative Policy Optimization (OGPO, accepted to ICML26) embarks on answering this question (spoiler alert: when done correctly, it helps massively!).
🧵(1/N)

[Zhecheng Yuan @fancy_yzc]

@TX_Leo_Wang very insightful！

[Zhecheng Yuan @fancy_yzc]

@xyz2maureen @LuccaChiang thx, Prof. Zou hh

[Huanyu Li @imhuanyuli]

Impressive long-horizon robustness!

[Zhecheng Yuan @fancy_yzc]

@micoolcho Thx, Michael! We may release a relevant technical report in the future.

[Zhecheng Yuan @fancy_yzc]

🌶️🤖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.

[Michael Cho - Rbt/Acc @micoolcho]

This is incredible! This isn't a 24-hr stream doing essentially the same tasks over and over. This is a 30-min continuous sequence of various subtasks; any of them failing along the way we won't be getting no Mapo Tofu!

Great stuff from @fancy_yzc & the PokeBot team.

[Guangqi Jiang @LuccaChiang]

When will I be invited to see such a long-horizon demo? It’s awesome.👏

[Lawrence 🤖 @RAYBEAZY]

Doesn’t seem that crazy anymore to have a robot chef. Impressive long horizon work!

[Zhecheng Yuan @fancy_yzc]

@gazorp5 Each robot has its own e2e policy with subtask prediction.

[Zhecheng Yuan @fancy_yzc]

@ysongtwitt Awesome! You’re very welcome to come try it!

[atharva ☆ @k7agar]

more long horizon task and more robust manipulation systems!!'

[satyam @satiyum]

Long horizon specialist models on the edge is what a lot of robots applications need