Baiye Cheng

[Baiye Cheng @Shutter_Chen]

Great work! Congrats, Suning!

[Suning Huang @suning_huang]

🤖Low-data post-training can teach a VLA policy a new robot skill. But it also makes it too attached to the training demos.

We call this lock-in🔒: the policy can execute the post-training task, yet fails to respond to seemingly obvious prompt changes.

DeLock preserves steerability using only the policy’s own pretrained knowledge. No extra supervision needed!🚀🚀🚀

#Robotics #AI #EmbodiedAI #VLA

[Baiye Cheng @Shutter_Chen]

@GChongkai Thank you, chongkai

[Baiye Cheng @Shutter_Chen]

ICRA 2026 Accepted! See you in Vienna🇦🇹! #ICRA #robotics 🤖

Can we make Diffusion Policies robust and interpretable🤔?

Introducing MoE-DP: An MoE-Enhanced architecture that decomposes complex skills to recover from failures.

👇 https://t.co/zHSdsXAOhA (1/n)

[Baiye Cheng @Shutter_Chen]

Big thanks to the incredible team for making this possible: @Shutter_Chen, TIanhai Liang, @suning_huang, Maanping Shao, Feihong Zhang, Botian Xu, @ZhengrongX, @HarryXu12
Paper link: https://t.co/70Hp9cTDrX (7/n)

[Baiye Cheng @Shutter_Chen]

How to rearrange tasks? We propose a hierarchical VLM-based planning framework:

1️⃣ Summarization: Maps experts to semantic skills (e.g., Expert 5→Close Drawer). 2️⃣ Execution: Translates high-level goals into expert sequences to steer the policy. (6/n)