Jun Wang retweeted
Hey hey! I'll be at #UIST2024 to present 𝗖𝗼𝗼𝗸𝗔𝗥 ☺️
CookAR is an AI-powered wearable AR prototype that augments kitchen tool affordances in near real-time for low vision users, enabling safer and more efficient tool interactions. (1/6)
Jun Wang retweeted
Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models?
Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation.
Project page: robofail-vlm.github.io/
🧵Thread👇 Aha!
🧵7/8: More Info
We hope EVE will expedite the incorporation of robots into daily lives.
For more information, check out:
📜Paper: arxiv.org/abs/2404.06089
🔗Website: junwang0510.github.io/EVE/
Also, I will be presenting this work at UIST 2024. Come say hi if you are in Pittsburgh!
🧵8/8: Acknowledgements
Finally, I would like to thank my collaborators and advisors Chun-Cheng Chang, @DJiafei , Dieter Fox, and @RanjayKrishna !
This is my first first-authored paper, and I am looking forward to more collaboration in the future.
Jun Wang retweeted
Prof. Gil Strang's last lecture is ... Monday! Watch it via live stream: grinfeld.org/strang/








