Yifan Zhou

Gemini now coaches table tennis robots 🤖🏓: In our latest paper, we introduce SAS Prompt – a technique for robot self-improvement with LLMs. Here is how it works 🧵

Very glad that I contributed to this work!

Robot table-tennis from @DeepMind and @ASU 🤖🏓: We present a new method that allows Gemini (LLMs) to teach and coach robots through self-improvement. The method called SAS Prompt will be presented at ICRA 2025. More info here: sites.google.com/asu.edu/sas-ll… #Deepmind #ASU #Robots #LLM

While LLMs cannot verify the correctness of agent plans, they can be good at capturing the "style" of desirable behaviors. Come stop by #COLM2024 poster #34 Wednesday Morning to see how we utilize VLMs as a knowledge source of common human preferences for embodied agents!

@XueFz What's "the mistake" do you mean? -- from a robot learning guy

I sincerely hope that CV researchers don't make the same mistakes that many NLP researchers made a few months ago. The era of Multimodal LLM is coming! Don't be short-sighted in pursuing incremental contributions and use boring stuffs to seize positions. Let us calm down and do something really useful.😊

Looking forward to presenting tomorrow at the #CoRL soft robot learning workshop, where I'll be discussing multimodal learning for soft robots! Website: alpha-mdf.github.io Location: Hub 2 time: 2:30-3:30 pm Acknowledge my co-authors: Yifan @yfzhoucs , and Heni @asurobot

@ericjang11 @1x__tech Hey are you also interested in interns? Junior phd student; published in corl; cited bc-z

@1x__tech we're hiring! check out 1x.tech for our open positions

How it started / How it's going 1xtech.medium.com/1x-raises-23-5…

Code Release: Language-Conditioned Imitation Learning of Robot Policies! Framework includes sims/ML for efficient training policies that execute language commands. @yfzhoucs #ASU #intel [Paper] tinyurl.com/bdz5sswe [Code] github.com/ir-lab/ModAttn [Video] tinyurl.com/2x5ywx53

Announcing Neural Tangents, a new easy-to-use, open-source neural network library that enables researchers to build finite- and infinite-width versions of neural networks simultaneously. Grab the code and try it for yourself at goo.gle/33eErSu