Dear MAGA friends, I have been worrying about STEM in the US a lot, because right now the Senate is writing new laws that cut 75% of the STEM budget in the US. Sorry for the long post, but the issue is really important, and I want to share what I know about it. The entire

If the US wants to be less dependent on foreign-born scientists and engineers, then you’d think we’d be wanting to increase the production of US-born scientists and engineers. But, apparently not. 🤔

Data curation is crucial for LLM reasoning, but how do we know if our dataset is not overfit to one benchmark and generalizes to unseen distributions? 🤔 𝐃𝐚𝐭𝐚 𝐝𝐢𝐯𝐞𝐫𝐬𝐢𝐭𝐲 is key, when measured correct—it strongly predicts model generalization in reasoning tasks! 🧵

What happens when you ✨scale up RL✨? In our new work, Prolonged RL, we significantly scale RL training to >2k steps and >130k problems—and observe exciting, non-saturating gains as we spend more compute 🚀.

OpenThinker3-7B is the SOTA open-data 7B reasoning models, powered by our new OpenThoughts3-1.2M dataset! We beat DeepSeek-R1-Distill-7B on our benchmarks by 33% on average 🚀🚀. Our new paper 📝 offers unique insights into data curation. Filtering questions works, but

🔆 I'm hiring! 🔆 There are two open positions: 1. Summer research position (best for master's or graduate student); focus on computational social cognition. 2. Postdoc (currently interviewing!); focus on computational social cognition and AI safety. sites.google.com/corp/site/sydn…

Currently, reinforcement learning from human feedback (RLHF) is the predominant method for ensuring LLMs are safe and aligned. And yet it provides no guarantees that they won’t say something harmful, copyrighted, or inappropriate. In our latest paper, we use online adversarial

🔥We are excited to present our work Synthetic Visual Genome (SVG) at #CVPR25 tomorrow! 🕸️ Dense scene graph with diverse relationship types. 🎯 Generate scene graphs with SAM segmentation masks! 🔗Project link: bit.ly/4e1uMDm 📍 Poster: #32689, Fri 2-4 PM 👇🧵

Knowledge propagation in LLM is notoriously challenging. Check out our paper that improves it substantially by training a hypernetwork to target knowledge propagation!

Wanna 🔎 inside Internet-scale LLM training data w/o spending 💰💰💰? Introducing infini-gram mini, an exact-match search engine with 14x less storage req than the OG infini-gram 😎 We make 45.6 TB of text searchable. Read on to find our Web Interface, API, and more. (1/n) ⬇️

Today, I’m launching a deeply personal project. I’m betting $100M that we can help computer scientists create more upside impact for humanity. Built for and by researchers, including Jeff Dean & Joelle Pineau on the board, Laude Institute catalyzes research with real-world impact.

My next professional move is to go to the Source of the Compute. Soon™ I'll be hanging out with the incredible researchers NVIDIA as a RS working on open source/science post training esp reasoning VLA models for embodied agents! There is no ASGI without embodiment!

PolyGuard will appear at COLM 2025!!

(1/4)🚨 Introducing Goedel-Prover V2 🚨 🔥🔥🔥 The strongest open-source theorem prover to date. 🥇 #1 on PutnamBench: Solves 64 problems—with far less compute. 🧠 New SOTA on MiniF2F: * 32B model hits 90.4% at Pass@32, beating DeepSeek-Prover-V2-671B’s 82.4%. * 8B > 671B: Our 8B

life update: I'll be starting my PhD in CS at Stanford this September! I'm very excited to continue my research on reasoning of language models and to make new friends in the Bay Area! I'm deeply grateful to everyone who supported me and made this milestone possible

Quick Update: I’ve officially started my PhD at Stanford (go trees i think?!?)! After an amazing year at UW (go huskies!), I’m super happy to continue my CS PhD with my amazing advisors Ludwig Schmidt and Yejin Choi! If you see me on campus, please say hi and listen to me rant

Life update: I’m excited to share that I’ll be starting as faculty at the Max Planck Institute for Software Systems(Max Planck Institute for Software Systems) this Fall!🎉 I’ll be recruiting PhD students in the upcoming cycle, as well as research interns throughout the year: lasharavichander.github.io/contact.html

Super thrilled that HALoGEN, our study of LLM hallucinations and their potential origins in training data, received an Outstanding Paper Award at ACL! Joint work w/i Shrusti Ghela*, and David Wadden Yejin Choi 💫

HALoGEN: Fantastic LLM Hallucinations and Where to Find Them won Outstanding Paper Award at #ACL2025! ✨🥹 The initial hallucination was thinking this would be a quick project XD. Loved every minute of it working with Abhilasha Ravichander* and David Wadden, Yejin Choi ☀️

🚀 How far can RL scaling take LLMs? Drop ProRLv2! 🔥With ProRLv2, we keep expanding LLM’s reasoning boundaries through 3,000+ RL steps over 5 domains and set a new state-of-the-art 🌟 among 1.5B reasoning models. 🔗 Full blog: research.nvidia.com/labs/lpr/prorl… 🤗Open model: