🔥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

I’ve just arrived in Vancouver and am excited to join the final stretch of #NeurIPS2024! This morning, we are presenting 3 papers 11am-2pm: - Edge pruning for finding Transformer circuits (#3111, spotlight) Adithya Bhaskar - SimPO (#3410) Yu Meng @ ICLR'25 Mengzhou Xia - CharXiv (#5303)

Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference NeurIPS Conference We have ethical reviews for authors, but missed it for invited speakers? 😡

Announcement #1: our call for papers is up! 🎉 colmweb.org/cfp.html And excited to announce the COLM 2025 program chairs Yoav Artzi Eunsol Choi Ranjay Krishna and Aditi Raghunathan

Introducing MeCo (metadata conditioning then cooldown), a remarkably simple method that accelerates LM pre-training by simply prepending source URLs to training documents. arxiv.org/abs/2501.01956

🤔Now most LLMs have >= 128K context sizes, but are they good at generating long outputs, such as writing 8K token chain-of-thought for a planning problem？ 🔔Introducing LongProc (Long Procedural Generation), a new benchmark with 6 diverse tasks that challenge LLMs to synthesize

If AI isn’t truly open, it will fail us. We can’t close in a black box our greatest invention yet just so that a few can freely monetize. AI needs its Linux moment, and so we started working towards it. This can only succeed if we all work together! #oumi #opensource

🚀 Introducing Goedel-Prover: A 7B LLM achieving SOTA open-source performance in automated theorem proving! 🔥 ✅ Improving +7% over previous open source SOTA on miniF2F 🏆 Ranking 1st on the PutnamBench Leaderboard 🤖 Solving 1.9X total problems compared to prior works on Lean

🚀 Exciting news! Our Goedel-Prover paper is now live on arXiv: arxiv.org/pdf/2502.07640 🎉 We're currently developing the RL version and have a stronger checkpoint than before (currently not included in the report)!🚀🚀🚀 Plus, we’ll be open-sourcing 1.64M formalized

Congratulations to Stanford NLP Group founder Christopher Manning for being elected to The National Academy of Engineering (NAE, National Academies) Class of 2025 for the development and dissemination of natural language processing methods.

🤔 Ever wondered how prevalent some type of web content is during LM pre-training? In our new paper, we propose WebOrganizer which *constructs domains* based on the topic and format of CommonCrawl web pages 🌐 Key takeaway: domains help us curate better pre-training data! 🧵/N

V. happy with this work! We’ve explored domain mixtures and quality filtering (including Alex’s previous work!), but what is even a “domain” in Common Crawl? Can we use these domains to better understand quality filters, and combine them for data curation? Cool visuals too!

Excited to announce our 2025 keynote speakers: Shirley Ho, Nicholas Carlini, Luke Zettlemoyer, and Tom Griffiths!

The success of RLHF depends heavily on the quality of the reward model (RM), but how should we measure this quality? 📰 We study what makes a good RM from an optimization perspective. Among other results, we formalize why more accurate RMs are not necessarily better teachers! 🧵

Nothing like a sunny hike to welcome spring!

Welcome to the official X for the Princeton Laboratory for Artificial Intelligence (“AI Lab” for short). Our mission is to support and expand the scope of AI research Princeton University Follow our page for the latest updates on events, news, research, and more at the AI Lab

Llama 4 Scout claims to support a context window of 10M tokens; the needle-in-a-haystack results are perfect, but can it handle real long-context tasks? We evaluate them on HELMET, our diverse and application-centric long-context benchmark, to be presented at #ICLR2025!

We are proud to highlight the work of the PLI students, post-docs, and faculty which is being showcased at this year's ICLR 2025: pli.princeton.edu/blog/2025/prin…

We're so proud that Princeton researchers have received 1 outstanding paper award and 1 honorable mention at ICLR 2025 2025 Congratulations to Peter Henderson, Xiangyu Qi, Prateek Mittal, Ashwinee Panda @ ICLR 2025, Tianhao Wang ("Jiachen") @ICLR, and Kaifeng Lyu blog.iclr.cc/2025/04/22/ann…

Our warmest congratulations to ⁦Danqi Chen⁩, ⁦Stanford NLP Group⁩ grad and now Associate Professor at ⁦Princeton Computer Science⁩ and Associate Director of ⁦Princeton PLI⁩ on her stunning ⁦⁦ICLR 2025⁩ keynote!

Last day at #ICLR2025. I will be speaking at the DATA-FM workshop this morning!