@animaanandkumar - AI Dynamics

How can we mix active and transfer learning in few-shot learning setting with pre-trained LLMs? We show that you need to label only few samples in-domain and leverage on transfer learning from out-domain along with ingrained knowledge in pretrained models

→ View original post on X — @animaanandkumar

5 February 2023

Minedojo Featured in Foundation Models for Decision Making Article

By

@animaanandkumar

–

01 February 2023 18h31

Thank you @laxmevy for featuring Minedojo in an in-depth article on using pre-trained foundation models for decision making

→ View original post on X — @animaanandkumar

1 February 2023

AI4Science Workshop Registration Deadline at Caltech February 3rd

By

@animaanandkumar

–

01 February 2023 16h39

Deadline to register for AI4Science workshop at @caltech on Feb. 3rd

→ View original post on X — @animaanandkumar

1 February 2023

Discussion on MineDojo Award-Winning Paper with TWML AI

By

@animaanandkumar

–

31 January 2023 20h43

It was great to talk to @samcharrington after a long time for @twimlai and talk about Minedojo, our award winning paper with @DrJimFan @yukez @guanzhi_wang @YunfanJiang @yyupsong @AjayMandlekar @HaoyiZhu @deanh_tw @nvidia https://t.co/6Sopy0XK63
— Prof. Anima Anandkumar (@AnimaAnandkumar) 31 janvier 2023

It was great to talk to @samcharrington after a long time for @twimlai and talk about Minedojo, our award winning paper with @DrJimFan @yukez @guanzhi_wang @YunfanJiang @yyupsong @AjayMandlekar @HaoyiZhu @deanh_tw @nvidia

→ View original post on X — @animaanandkumar

31 January 2023

Argonne Impact Award for ACM Gordon Bell Prize Genome Scale Language Model

By

@animaanandkumar

–

31 January 2023 19h10

Proud to be awarded @argonne_lcf Impact Award for winning team of @TheOfficialACM 2022 Gordon Bell Special Prize for building #genome scale #LM to help predict new variants of concern #SARSCoV2 with @arvindr_ @yuntiandeng @wn8_nie @ChaoweiX @ArashVahdat @sacdallago @nvidia

→ View original post on X — @animaanandkumar

31 January 2023

FNO Predicts Flows in Milliseconds for Predictive Control

By

@animaanandkumar

–

24 January 2023 2h05

FNO predicts flows in milliseconds, enabling faster-than-real-time modeling for predictive flow control in physical systems. First results on experimental data: fully data-driven and no need for simulations. @SahinLale @Caltech

→ View original post on X — @animaanandkumar

24 January 2023