darioamodei.com/post/we-must...

Dario Amodei — We Must Pace the Frontier

darioamodei.com

Coming up at ICML: 🤯Distribution shifts are still a huge challenge in ML. There's already a ton of algorithms to address specific conditions. So what if the challenge was just selecting the right algorithm for the right conditions?🤔🧵

ChatBotArena is far from the first eval to be overfit to. It's becoming underrated. Likely the single most impactful evaluation project since ChatGPT. The labs are the ones releasing these slightly off models.

Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)

NeurIPS participation in Europe

We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...

docs.google.com

Hiring two student researchers for Gemma post-training team at @GoogleDeepMind Paris! First topic is about diversity in RL for LLMs (merging, generalization, exploration & creativity), second is about distillation. Ideal if you're finishing PhD. DMs open!

🥁Introducing Gemini 2.5, our most intelligent model with impressive capabilities in advanced reasoning and coding. Now integrating thinking capabilities, 2.5 Pro Experimental is our most performant Gemini model yet. It’s #1 on the LM Arena leaderboard. 🥇

This is a very tidy little RL paper for reasoning. Their GRPO changes: 1 Two different clip hyperparams, so positive clipping can uplift more unexpected tokens 2 Dynamic sampling -- remove samples w flat reward in batch 3 Per token loss 4 Managing too long generations in loss dapo-sia.github.io

Welcome Gemma 3, Google’s new open-weight LLM. All sizes (1B, 4B, 12B and 27B) excel on benchmarks, but the key result may be the 27B reaching 1338 on LMSYS. For this, we scaled post-training, with our novel distillation, RL and merging strategies. Report: storage.googleapis.com/deepmind-med...

My new paper "Deep Learning is Not So Mysterious or Different": arxiv.org/abs/2503.02113. Generalization behaviours in deep learning can be intuitively understood through a notion of soft inductive biases, and formally characterized with countable hypothesis bounds! 1/12

Modern post-training is essentially distillation then RL. While reward hacking is well-known and feared, could there be such a thing as teacher hacking? Our latest paper confirms it. Fortunately, we also show how to mitigate it! The secret: diversity and onlineness! arxiv.org/abs/2502.02671

On Teacher Hacking in Language Model Distillation

Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii) reinforcement learn...

arxiv.org

Daniil Tiapkin@dtiapkin.bsky.social · 2y ago

1/ If you’re familiar with RLHF, you likely heard of reward hacking—where over-optimizing the imperfect reward model leads to unintended behaviors. But what about teacher hacking in knowledge distillation: can the teacher be hacked, like rewards in RLHF?

We just released the Helium-1 model , a 2B multi-lingual LLM which @exgrv.bsky.social and @lmazare.bsky.social have been crafting for us! Best model so far under 2.17B params on multi-lingual benchmarks 🇬🇧🇮🇹🇪🇸🇵🇹🇫🇷🇩🇪 On HF, under CC-BY licence: huggingface.co/kyutai/heliu...

Kyutai@kyutai-labs.bsky.social · 2y ago

Meet Helium-1 preview, our 2B multi-lingual LLM, targeting edge and mobile devices, released under a CC-BY license. Start building with it today! huggingface.co/kyutai/heliu...

ILYA: "PRETRAINING IS DONE. WE ARE NOW IN THE POST TRAINING ERA."

Of all of OpenAI's days, the RL API is still the most revealing of the state of AI research trends. Lots of open doors for those looking at RL. OpenAI's Reinforcement Finetuning and RL for the masses The cherry on Yann LeCun’s cake has finally been realized.

OpenAI's Reinforcement Finetuning and RL for the masses

The cherry on Yann LeCun’s cake has finally been realized.

buff.ly

🚨So, you want to predict your model's performance at test time?🚨 💡Our NeurIPS 2024 paper proposes 𝐌𝐚𝐍𝐨, a training-free and SOTA approach! 📑 arxiv.org/pdf/2405.18979 🖥️https://github.com/Renchunzi-Xie/MaNo 1/🧵(A surprise at the end!)

The right place for your phd: With Colin Raffel, UofT works on decentralizing, democratizing, and derisking large-scale AI. Wanna work on model m(o)erging, collaborative/decentralized learning, identifying & mitigating risks, etc. Apply (deadline is Monday!) web.cs.toronto.edu/graduate/how... 🤖📈

How to Apply — Department of Computer Science, University of Toronto

web.cs.toronto.edu

🥐 Building a Computer Vision FR Starter Pack! 👉 Who else should be included? Comment below or DM me to be added go.bsky.app/dfvcLZ

distributed learning for LLM? recently, @primeintellect.bsky.social have announced finishing their 10B distributed learning, trained across the world. what is it exactly? 🧵

Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling by Bairu Hou et al. #ICML2024 tl;dr: generate multiple clarifications of input txt w/ external LLM then forward: >disagreement btw outputs -> data uncertainty >avg uncertainty in each output -> model uncertainty

This year, there are 16 positions at CNRS in computer science (8 in "applied" domains → ask me - 8 on "fundamental" domains → ask the other David). @mathurinmassias.bsky.social has a good list of advice mathurinm.github.io/cnrs_inria_a... Official 🔗 www.ins2i.cnrs.fr/en/cnrsinfo/... Don't wait!

David Monniaux@monniauxd.bsky.social · 2y ago

Recently graduated ? Or a postdoc ? How about a PERMANENT FULL TIME RESEARCH POSITION? Apply to CNRS or INRIA. (You can ask me questions.)

Feeling that Paris is "The Place To Be" for computer vision and AI in general.

Min-p Sampling: arxiv.org/abs/2407.01082 1. Get max prob 2. Find min prob based on a threshold \in [0, 1] \times that max prob 3. Gather only tokens probs above that min prob 4. Sample in that pool, according to renormalized probs More robust to change in temperature!

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs

Large Language Models (LLMs) generate text by sampling the next token from a probability distribution over the vocabulary at each decoding step. However, popular sampling methods like top-p (nucleus…

arxiv.org

My growing list of #computervision researchers on Bsky. Missed you? Let me know. go.bsky.app/M7HGC3Y

Bluesky now has over 20M people!! 🎉 We've been adding over a million users per day for the last few days. To celebrate, here are 20 fun facts about Bluesky:

New people in AI have joined recently, I can't cite all, but here are some: @fguney.bsky.social @natalianeverova.bsky.social @damienteney.bsky.social @jdigne.bsky.social @nbonneel.bsky.social @steevenj7.bsky.social @douillard.bsky.social @ramealexandre.bsky.social @stonet2000.bsky.social 1/