RT @jaseweston: 🤖Introducing OptimalThinkingBench 🤖.📝: - Thinking LLMs use a lot of tokens & overthink; non-thinkin….

RT @pratyushmaini: 1/Pretraining is hitting a data wall; scaling raw web data alone leads to diminishing returns. Today @datologyai shares….

RT @lyang36: 🚨 Olympiad math + AI:. We ran Google’s Gemini 2.5 Pro on the fresh IMO 2025 problems. With careful prompting and pipeline desi….

RT @lmthang: Very excited to share that an advanced version of Gemini Deep Think is the first to have achieved gold-medal level in the Inte….

RT @tungnd_13: 🚀 Introducing PhysiX: One of the first large-scale foundation models for physics simulations!. PhysiX is a 4.5B parameter mo….

RT @nouhadziri: 📢 Can LLMs really reason outside the box in math? Or are they just remixing familiar strategies? . Remember DeepSeek R1, o1….

RT @RyanHuynh1108: CVPR-bound! ✈️. I'll be presenting CoLLM on Friday, 6/13 (Morning, #364) and looking for my next challenge as a full-tim….

RT @xue_yihao65785: 🎉 Our paper “Representations Shape Weak-to-Strong Generalization” is accepted at #ICML2025!.We study weak-to-strong gen….

RT @xuandongzhao: 🚀 Excited to share the most inspiring work I’ve been part of this year:. "Learning to Reason without External Rewards"….

RT @sjoshi804: #ICLR2025.Can you pre-train deep models with small, synthetic datasets? 🤯. We introduce the first effective dataset distilla….

🎉 Achievement unlocked: having papers with all of my labmates and somehow all ended up at ICLR!. I’ll be presenting our work “Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures” at #ICLR2025 🇸🇬. Come by and chat! 👋 on Fri, Apr 25 | 10 AM GMT+8.

RT @Yihe__Deng: 🚀Excited to share our latest work: OpenVLThinker, an exploration into enhancing vision-language models with R1 reasoning ca….

RT @Yihe__Deng: 🤖 I just updated my repository of RL(HF) summary notes to include a growing exploration of new topics, specifically adding….

RT @duynguyen772: LLMs must be helpful, unbiased, etc. but optimizing for one attribute can hurt others. 🚀 We introduce MAT-Steer for st….

RT @lmthang: Excited to share details of AlphaGeometry2 (AG2), part of the system that achieved silver-medal standard at IMO 2024 last July….

RT @Yihe__Deng: New paper & model release!. Excited to introduce DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails….

RT @TheGradient: (1/2) Ever wondered why Sharpness-Aware Minimization (SAM) yields greater generalization gains in vision than in NLP? I'll….

RT @natolambert: Since everyone wants to learn RL for language models now post DeepSeek, reminder that I've been working on this book quiet….

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 @behrouz_ali: Attention has been the key component for most advances in LLMs, but it can’t scale to long context. Does this mean we need….