Presenting two mechanistic interpretability works today at @iclr_conf
Giving a talk from 2-2:15 at the Multimodal Intelligence workshop (204C) on our work “Not All Features are Created Equal: A Mechanistic Study of Vision-Language-Action Models.”
Will also be at the Unifying Concept Representation Learning workshop (209) presenting “Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations.”
Feel free to stop by if you want to talk VLAs, Robotics, or Algebraic Topology!
I'm very excited to finally announce one of the most ambitious projects we've worked on — which makes the front cover of Science Robotics today:
☀️ Learning a Thousand Tasks in a Day ⭐️
Everyday tasks — like those below — can now be learned from a single demonstration each...
333K Followers 3K FollowingHost of Ky Sports Radio and NFL Preview show on ESPN Radio. On Netflix’s “Wrestlers” and Co-owner of OVW. Author of New York Times Bestseller, “Mitch, Please!”
533K Followers 6K FollowingCo-founder & CEO of Discovery Loop. Former Chief Scientist, Google. Helped build many Google products, TPUs, Gemini, TensorFlow, MapReduce, Bigtable, ...
8K Followers 1K FollowingAssistant Professor at @NUScomputing | Robotics & AI PhD @uwcse | Host of @RoboPapers | Ex-@allen_ai robotics lead, @NVIDIA | Magician |
my opinion is my alone.
10K Followers 993 FollowingAssistant Professor @Cambridge_Eng, working on 3D computer vision and computer graphics, previously postdoc @StanfordSVL, PhD @Oxford_VGG
270 Followers 732 Followingmultimodal research @adobe | co-lead of firefly image 5 preview | ex vision research @berkeley_ai | 🇹🇼 | opinions are my own
4K Followers 1K FollowingScaling video world models for robots @RhodaAI |
Built 1st version of ManiSkill https://t.co/NuQOXaNhud |
Prev @UCSanDiego @1x_tech @NVIDIA @MSFTResearch
18K Followers 1K FollowingTraining VLMs at @GoogleDeepMind - ex @Amazon @CarnegieMellon @PoliTOnews @IITalk - I post honest non-AI-generated paper reviews
1K Followers 279 Followingresearch fellow @FlatironCCA working on multi-agent AI safety / AI for science. prev: PhD @physatpenn ‘24, BSE @CIS_Penn '17.