What if I told you that you can simultaneously enhance an LLM's task performance and reduce its size with no additional training?. We find selective low-rank reduction of matrices in a transformer can improve its performance on language understanding tasks, at times by 30% pts!🧵

RT @TEDAISF: 🐋 Can AI help us understand whales — and ourselves? 📷 New TED Talk recorded at @TEDAISF is live!. @MIT researcher @pratyusha_P….

RT @nlp_mit: Hello everyone! We are quite a bit late to the twitter party, but welcome to the MIT NLP Group account! follow along for the l….

RT @ShikharMurty: Super excited to share NNetnav : A new method for generating complex demonstrations to train web agents—driven entirely v….

RT @TEDAI2024: Presenting now at #TEDAI 2024 stage: Pratyusha Sharma @pratyusha_PS, Researcher at @MIT. How do we understand the communica….

RT @gupta_abhinav_: Excited to announce @SkildAI. In a thrilling year with.@pathak2206 and SKILD AI team, we have scaled and built a founda….

RT @xiaolonw: Cannot believe this finally happened! Over the last 1.5 years, we have been developing a new LLM architecture, with linear co….

RT @MIT_CSAIL: A picture is worth a thousand words, but can a LLM get the picture if it has never seen images before? 🧵. MIT CSAIL research….

RT @alexrives: We have trained ESM3 and we're excited to introduce EvolutionaryScale. ESM3 is a generative language model for programming….

RT @belindazli: As the world changes, documents go out of date. How can we adapt RAG systems to a stream of changing world data?. We introd….

RT @davidbau: The National Deep Inference Fabric #NDIF, an @NSF-funded AI research infrastructure project, is awarding 2024 **Summer Engine….

RT @seungwookh: 🚀 Stronger, simpler, and better! 🚀. Introducing Value Augmented Sampling (VAS) - our new algorithm for LLM alignment and pe….

RT @bjkingape: Exciting: Scientists including @pratyusha_PS @sgero say sperm whales "use a much richer set of sounds than previously know….

RT @jacobandreas: And for something completely different: our paper on the combinatorial structure of sperm whale vocalizations (led by @pr….

RT @MIT_CSAIL: If sperm whales could talk, what would they say?. New research on their communication reveals a complex combinatorial system….

RT @phillip_isola: Our computer vision textbook is released!. Foundations of Computer Vision.with Antonio Torralba and Bill Freeman.https:/….

RT @ShikharMurty: Want scalable LLM agents for websites and APIs, without human labeled data? . We propose BAGEL, a method where agents sy….

RT @haotiannnnnnnnn: Excited to present LAST: A new framework for discovering skills from demonstrations! By combining LLM initial segmenta….

RT @jacobandreas: When Pratyusha showed me the results from her summer internship my head 🤯. Incredibly surprising results about knowledge….

RT @AchyutaBot: This indicates that we aren’t training right… (or that there’s some cool sparse regularization that makes models faster + b….

RT @HanGuo97: Check out this super cool paper from @pratyusha_PS!.