YI LI
@yili_ai
Followers
181
Following
47
Media
16
Statuses
38
🎓UW PhD | Ex-Nvidia, Microsoft Research Asia, Tsinghua
Joined June 2023
🚀 Meet 🐹HAMSTER, our new hierarchical Vision-Language-Action (VLA) framework for robot manipulation!. 🔹 High-level VLM for perception & reasoning.🔹 Low-level 3D policy for precise control.🔹 Bridged by 2D paths for trajectory planning.HAMSTER learns from cost-effective
7
26
105
RT @ryan_hoque: Imitation learning has a data scarcity problem. Introducing EgoDex from Apple, the largest and most diverse dataset of de….
0
95
0
RT @jang_yoel: Introducing 𝐃𝐫𝐞𝐚𝐦𝐆𝐞𝐧!. We got humanoid robots to perform totally new 𝑣𝑒𝑟𝑏𝑠 in new environments through video world models.….
0
74
0
RT @JunyaoShi: On my way to Atlanta to present ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos at @ieee_ras_icra! Stay tu….
0
4
0
RT @NVIDIARobotics: 🎊 That's a wrap on #ICLR2025. Shout out to all the amazing research in #robotics, machine vision, and more. Missed it….
0
20
0
RT @RemiCadene: Meet SO-101, next-gen robot arm for all, by @huggingface 🤗. Enables smooth takeover to boost AI capabilities, faster assemb….
0
139
0
RT @QinYuzhe: Meet our first general-purpose robot at @DexmateAI . Adjustable height from 0.66m to 2.2m: compact en….
0
33
0
It is exciting to see another Hierarchical VLA models in the same month! 🎉.Hi Robot from @physical_int uses language, Helix from @Figure uses latent embedding, our HAMSTER from @NVIDIA uses 2d paths. We’re all inspired by Thinking, Fast and Slow—combining fast, intuitive (System
Vision-language models can control robots, but what if the prompt is too complex for the robot to follow directly?. We developed a way to get robots to “think through” complex instructions, feedback, and interjections. We call it the Hierarchical Interactive Robot (Hi Robot).
0
7
28
RT @chris_j_paxton: Its extremely clear to me that this sort of approach is the future, especially in relatively structured warehouse and l….
0
11
0
RT @RemiCadene: ⛔ STOP WHAT YOU'RE DOING ⛔. THERE IS A NEW ROBOT IN TOWN ~ LeKiwi 🥝 ~. build it yourself to automate daily choirs with….
0
62
0
RT @abhishekunique7: Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources….
0
17
0
RT @deepseek_ai: 🚀 Day 0: Warming up for #OpenSourceWeek! . We're a tiny team @deepseek_ai exploring AGI. Starting next week, we'll be open….
0
3K
0
Check out our results in the screenshots from Figure AI's video! 📸. The prompt is displayed in the top-left corner, and the trajectory transitions from blue to red—with blue circles indicating gripper closure and red circles for opening. For more details, check out my other
0
0
1