William Xie @wxie.bsky.social · 10/09/2026this student was awarded the GRF btw. my takeaway (and from their panel reviews) is that so long as your contributions can be framed within broad scientific accessibility (geographic, somewhat socioeconomic), you will be well received. probably well known, but one more data point for the pile 111
William Xie @wxie.bsky.social · 11/06/2026I turn 26 the night of game 5. 26 years of godforsaken Knicks fandom… 000
William Xie @wxie.bsky.social · 24/04/2026Matt Mason visited our lab yesterday and one of our undergrads, in the midst of a VLA demo, asked if he knew what a neural net was 010
William Xie @wxie.bsky.social · 17/03/2026we had an alarming failure while deploying a policy on our humanoid. claude did a pretty good job of analyzing our diagnostic data, finding the root cause, and writing it up: www.williamxie.nyc/blog/re3_fai... (vetted, verified, and edited by me, of course) (no, i will not share the video)williamxie.nycRoot Cause Analysis: RE3 Deployment Disaster 000
William Xie @wxie.bsky.social · 26/02/2026Anybody know how to connect & drive this type of ATI F/T sensor cable? We are trying to buy secondhand and I am unable to find info about it, no clue how to connect to our Net F/T box. 000
William Xie @wxie.bsky.social · 15/10/2025yesterday i advised self-censorship to a undergrad student im helping apply for grfp re: their research & personal motivations. i think they've got as good a shot as any other. i think im making the right call, but it feels deeply wrong and capitulatory. any thoughts (esp from reviewers)? 001
Reposted by William XieGavin Schmidt @climateofgavin.bsky.social · 31/05/2025Last day at the GISS building (Wed. May 28th). 🥲 50716146
Reposted by William XieYonatan Grad @yhgrad.bsky.social · 22/05/2025NSF GRFPs terminated for those in graduate school and already attending Harvard, too. 59159
William Xie @wxie.bsky.social · 20/04/2025for my area exam last month i reviewed 25 touch-based IL works from 2024/5, taxonomized across tasks, sensor type, model architecture, and more (up now at arxiv.org/abs/2504.11827). here's a perhaps intuitive plot of policy action space--the in-figure citations are clickable in the pdf/html! 140
Reposted by William XieEnora @covetedfish.bsky.social · 16/04/2025I'm giving a lecture on language model debiasing to my undergrad NLP course on Friday but I'm not super up to date on the research. Does anyone have any suggestions for papers/topics to cover? 012
William Xie @wxie.bsky.social · 28/02/2025pleasantly surprised at how easy it was to setup rerun data viz for both my RLDS dataset and its raw data 110
William Xie @wxie.bsky.social · 14/01/2025reading a pratchett speech from 1985 on the wizard/witch dichotomy in fantasy: ansible.uk/misc/tpspeec... "The classical witch, on the other hand, with her often malevolent interest in the small beer of human affairs, is everything we fear only too well that we would in fact become."ansible.ukWhy Gandalf Never Married 120
William Xie @wxie.bsky.social · 21/12/2024i read five papers on tactile robot policies and wrote about them: medium.com/correll-lab/... the first step of me writing my prelim and i hope to have some more interesting synthesis soon. this is in no way a comprehensive review and i welcome recommendations of papers to read!medium.comA review on tactile end-to-end robot policiesCan learning unify the tactile experience across different sensing modalities? 242
William Xie @wxie.bsky.social · 28/11/2024hyperlocal politics warning/enormously hot take—the chinatown superjail is not tenable, for so many reasons. i would rather the city continue failing to run rikers than nuke the neighborhood. this will be a bigger deal than the proposed shsat reform, because it is actually happening 000
William Xie @wxie.bsky.social · 24/11/2024is anyone exploring (or know of work on) motion event typology for language robot models? seems like this is the kind of underlying structure we can/should leverage across embodiments/contexts. stuck on this passing thought and don't know the right search terms, so sorry if this is uninformed 100
Reposted by William XieCorrell Lab @correlllab.bsky.social · 18/11/2024Hi, I'm a Professor of robotics at CU, writing about robotics on my Medium blog medium.com/@nikolaus.co... and our lab's work on medium.com/correll-lab, and looking forward to amplify robotic news on BlueSky.medium.comNikolaus Correll – MediumRead writing from Nikolaus Correll on Medium. Nikolaus is a Professor of Computer Science and Robotics at the University of Colorado Boulder, robotics entrepreneur, and consultant. 051
William Xie @wxie.bsky.social · 15/11/2024my corl postmortem for the void, very loosely 1/? quoting Jitendra Malik, it took us ~500 million years to develop human-level sensorimotor capabilities and ~100,000 years to develop language. to riff off that, is the robot data scaling problem "simply" 5000x the semantics problem? 262
