🔥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

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? 😡

Huge congrats to Prasann Singhal for being one of the 8 CRA Outstanding Undergraduate Researcher Award winners! It has been an absolute privilege to work with Prasann during his time at UT. (And he's applying for PhD programs this year...hint hint...) Prasann's work... 🧵

R1 is awesome and I love how R1, being a super introvert, is trying hard to pretend to be an extrovert.

🚀 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

Constitutional AI works great for aligning LLMs, but the principles can be too generic to apply. Can we guide responses with context-situated principles instead? Introducing SPRI, a system that produces principles tailored to each query, with minimal to no human effort. [1/5]

🤔 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

🌟Job ad🌟 We (Greg Durrett, Matt Lease and I) are hiring a postdoc fellow within the CosmicAI Institute, to do galactic work with LLMs and generative AI! If you would like to push the frontiers of foundation models to help solve myths of the universe, please apply!

Meet the recipients of the 2024 ACM A.M. Turing Award, Andrew G. Barto and Richard S. Sutton! They are recognized for developing the conceptual and algorithmic foundations of reinforcement learning. Please join us in congratulating the two recipients! bit.ly/4hpdsbD

Can we generate long text from compressed KV cache? We find existing KV cache compression methods (e.g., SnapKV) degrade rapidly in this setting. We present 𝐑𝐞𝐟𝐫𝐞𝐬𝐡𝐊𝐕, an inference method which ♻️ refreshes the smaller KV cache, which better preserves performance.

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!

Evaluating language model responses on open-ended tasks is hard! 🤔 We introduce EvalAgent, a framework that identifies nuanced and diverse criteria 📋✍️. EvalAgent identifies 👩‍🏫🎓 expert advice on the web that implicitly address the user’s prompt 🧵👇

In a new blog post, Howard Yen and Xi Ye introduce HELMET and LongProc, two benchmarks from a recent effort to build a holistic test suite for evaluating long-context LMs. Read now: pli.princeton.edu/blog/2025/long…

Some personal news: I'll join UMass Amherst CS as an assistant professor in fall 2026. Until then, I'll postdoc at Meta nyc. Reasoning will continue to be my main interest, with a focus on data-centric approaches🤩 If you're also interested, apply to me (phds & a postdoc)!

Introducing ChartMuseum🖼️, testing visual reasoning with diverse real-world charts! ✍🏻Entirely human-written questions by 13 CS researchers 👀Emphasis on visual reasoning – hard to be verbalized via text CoTs 📉Humans reach 93% but 63% from Gemini-2.5-Pro & 38% from Qwen2.5-72B