🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We’re excited to share the completed preprint of Delphy — our new tool for scalable, near-real-time #Bayesianphylogenetics for outbreaks! 🚀 Check it out here: biorxiv.org/content/10.110… Explore Delphy: delphy.fathom.info Led by #PatrickVarilly sabeti_lab Fathom 🧵1/16

I’m thrilled to share our latest preprint! We analyzed >130,000 SARS-CoV-2 genomes from MA to investigate complex transmission dynamics—from statewide patterns, within specific facilities, and at the individual level 🦠🧬 Check out the preprint here ⬇️ medrxiv.org/content/10.110…

The all mighty Albert pop off 😈

introducing chipmunk—a training-free algorithm making ai video generation 3.7x & image gen 1.6x faster! ⚡️ our kernels for column-sparse attention are 9.3x faster than FlashAttention-3 and column-sparse GEMM is 2.5x faster vs. cuBLAS a thread on the GPU kernel optimizations 🧵

I'm at #ICLR2025 this week to present our work on🔬high-precision algorithm learning🔬with Transformers! Stop by our poster session Thursday afternoon! 🔗arxiv.org/abs/2503.12295 With Jess Grogan, Owen Dugan , Ashish Rao, Simran Arora , Atri Rudra, and hazyresearch!

We studied (and will now talk about) how these ideas let us: - Take existing Transformer LLMs, and turn them into SoTA subquadratic LLMs - Get SoTA quality, despite only training 0.2% of past methods' model parameters, with 0.4% of their training tokens (i.e., a 2500x boost in

Incredible work and genuinely amazing product by Raunak Chowdhuri and Adit. Excited for the future of document understanding at scale :)

Excited to release SWiRL: A synthetic data generation and multi-step RL approach for reasoning and tool use! With SWiRL, the model’s capability generalizes to new tasks and tools. For example, a model trained to use a retrieval tool to solve multi-hop knowledge-intensive

Honestly this album changed my life, FFYL has consistently been one of my favorite songs!

Phillipe Rigollet also teaches non asymptotic statistics, this spring which has been such an enjoyable class!

10k likes and we'll do it

Anthropic intelligence*

"Pre-training was hard, inference easy; now everything is hard."-Jensen Huang. Inference drives AI progress b/c of test-time compute. Introducing inference aware attn: parallel-friendly, high arithmetic intensity – Grouped-Tied Attn & Grouped Latent Attn

You did it, MIT students! We’re so proud of you. Image: Jenny Baek '25

In the test time scaling era, we all would love a higher throughput serving engine! Introducing Tokasaurus, a LLM inference engine for high-throughput workloads with large and small models! Led by Jordan Juravsky, in collaboration with hazyresearch and an amazing team!

exciting to see that hybrid models maintain reasoning performance with few attention layers. benefits of linear architectures are prominent for long reasoning traces, when efficiency is bottlenecked by decoding - seems like a free win if reasoning ability is preserved as well!

Excited to share our new work on Self-Adapting Language Models! This is my first first-author paper and I’m grateful to be able to work with such an amazing team of collaborators: Jyo Pari Han Guo Ekin Akyürek Yoon Kim Pulkit Agrawal

1/ Excited to share our recent work in #ICML2025, “A multi-region brain model to elucidate the role of hippocampus in spatially embedded decision-making”. 🎉 🔗 minzsiure.github.io/multiregion-br… Joint w/ FieteGroup Jaedong Hwang, Brody Lab, Princeton Neuroscience Institute ⬇️ 🧵 for key takeaways