Baiye Cheng

@Shutter_Chen

Katılım Haziran 2021

186 Takip Edilen14 Takipçiler

Baiye Cheng@Shutter_Chen·2d

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

English

422

Baiye Cheng@Shutter_Chen·5 Şub

@GChongkai Thank you, chongkai

English

Heeger@GChongkai·5 Şub

@Shutter_Chen Great work! Congrats to Baiye and Suning!

English

Baiye Cheng@Shutter_Chen·4 Şub

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. 👇 moe-dp-website.github.io/MoE-DP-Website/ (1/n)

English

4.2K

Baiye Cheng@Shutter_Chen·4 Şub

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: arxiv.org/abs/2511.05007 (7/n)

English

Baiye Cheng@Shutter_Chen·4 Şub

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)

English

146

Keşfet

@GChongkai @suning_huang @ZhengrongX @HarryXu12 @elonmusk @BarackObama @taylorswift13 @cristiano