🚨 New @GoogleDeepMind paper 🚨 We trained Foundational Large Autorater Models (FLAMe) on extensive human evaluations, achieving the best RewardBench perf. among generative models trained solely on permissive data, surpassing both GPT-4 & 4o. 📰: 🧵:👇

RT @lmarena_ai: News: @GoogleDeepMind Gemini-2.0 family (Pro, Flash, and Flash-lite) is now live in Arena! - Gemini-2.0-Pro takes #1 spot…

RT @sundarpichai: 1/ New Gemini 2.0 updates, here we go! Gemini 2.0 Flash is now GA, so devs can now build production applications. Find…

RT @jacobaustin132: Making LLMs run efficiently can feel scary, but scaling isn’t magic, it’s math! We wanted to demystify the “systems vie…

RT @Muennighoff: DeepSeek r1 is exciting but misses OpenAI’s test-time scaling plot and needs lots of data. We introduce s1 reproducing o1…

RT @srush_nlp: What to know about DeepSeek In which we aim to understand MoE, o1, scaling, tech reporting, moder…

RT @WenhuChen: Everyone is talking about RL these days. But are we done with SFT? The answer is NO. If we revive SFT in another form, it ca…

RT @karpathy: We have to take the LLMs to school. When you open any textbook, you'll see three major types of information: 1. Background…

RT @allen_ai: Here is Tülu 3 405B 🐫 our open-source post-training model that surpasses the performance of DeepSeek-V3! The last member of t…

RT @Azaliamirh: We are releasing CodeMonkeys, a system for solving SWE-bench problems with a focus on careful parallel and serial scaling o…

RT @wzihanw: 🚀 Introducing RAGEN—the world’s first reproduction of DeepSeek-R1(-Zero) methods for training agentic AI models! We’re bettin…

RT @arankomatsuzaki: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training Shows that: - RL generalizes in…

RT @JayAlammar: The Illustrated DeepSeek-R1 Spent the weekend reading the paper and sorting through the intuitions. Here's a visual guide…

RT @mar_kar_: Microsoft Translator group is looking for a Ph.D. student #intern this summer to work with us in Redmond on machine translati…

RT @jennajrussell: People often claim they know when ChatGPT wrote something, but are they as accurate as they think? Turns out that while…

RT @junxian_he: We replicated the DeepSeek-R1-Zero and DeepSeek-R1 training on 7B model with only 8K examples, the results are surprisingly…

RT @ClementDelangue: Our science team has started working on fully reproducing and open-sourcing R1 including training data, training scrip…

RT @lmarena_ai: Breaking News: DeepSeek-R1 surges to the top-3 in Arena🐳! Now ranked #3 Overall, matching the top reasoning model, o1, whi…

RT @DanHendrycks: We’re releasing Humanity’s Last Exam, a dataset with 3,000 questions developed with hundreds of subject matter experts to…

@profnaren Congratulations, Naren!! 🎉

RT @lmarena_ai: Breaking news from Text-to-Image Arena! 🖼️✨ @GoogleDeepMind’s Imagen 3 debuts at #1, surpassing Recraft-v3 with a remarkab…