Excited to announce our new work on compressing vector database indices!. Highlights: . 🗜️ 7x compression of FAISS indices with no impact on accuracy or search runtime . 🗜️ 30% memory reduction on billion-scale datasets.

RT @k_neklyudov: The supervision signal in AI4Science is so crisp that we can solve very complicated problems almost without any data or RL….

RT @majdi_has: (1/n)🚨You can train a model solving DFT for any geometry almost without training data!🚨. Introducing Self-Refining Training….

@mena_gonzalo.

New work: a scalable way to learn dists over permutations/rankings. The method can trade-off compute and expressivity by varying # NFEs (ie unmasking more than one token at a time), and subsumes well known families of models (eg Mallow' model).

RT @RickyTQChen: We've open sourced Adjoint Sampling!. It's part of a bundled release showcasing FAIR's research and open source commitment….

RT @AIatMeta: Announcing the newest releases from Meta FAIR. We’re releasing new groundbreaking models, benchmarks, and datasets that will….

Hard to describe how incredible Montreal is between May and November. Total vibe.

RT @RickyTQChen: Against conventional wisdom, I will be giving a talk with particular focus on the "how" and the various intricacies of app….

RT @shaulneta: 📣I'll be at the poster session with our follow-up on Discrete Flow Matching. We derive a closed-form solution to the kinetic….

RT @RickyTQChen: Discrete Flow Matching extends the Flow Matching recipe to discrete data. But so far the focus of the community has been o….

RT @RickyTQChen: We are presenting 3 orals and 1 spotlight at #ICLR2025 on two primary topics:. On generalizing the data-driven flow match….

RT @kfountou: .@shenghao_yang's Ph.D Thesis "Perspectives of Graph Diffusion: Computation, Local Partitioning, Statistical Recovery, and Ap….

RT @AmiiThinks: BREAKING: Amii Chief Scientific Advisor, Richard S. Sutton, has been awarded the A.M. Turing Award, the highest honour in c….

RT @thegautamkamath: Congratulations to the latest Turing award winners Barto and Sutton!. At this point, all three Canadian national AI in….

RT @peholderrieth: Our MIT class “6.S184: Introduction to Flow Matching and Diffusion Models” is now available on YouTube!. We teach state-….

RT @roydanroy: Are you a Canadian citizen or PR? 3rd or 4th year in undergrad? Available June 2-13 for a fully funded summer school in stat….

RT @kfountou: Positional Attention: Expressivity and Learnability of Algorithmic Computation (v2). We study the effect of using only fixed….

RT @aidangomez: We will be withdrawing our Waterloo interns from the bay in response to the unjustified unnecessary illegal tariffs.

RT @HannesStaerk: On monday in our reading group we discuss "Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective" http….

I've been reading the PDF copy of this book and it is a nice fresh perspective on info theory (free and legal PDF copy (no really, i'm not being sarcastic)). After you finish Cover and Thomas, take a look: