🔥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

LLMs excel at fitting finetuning data, but are they learning to reason or just parroting🦜? We found a way to probe a model's learning process to reveal *how* each example is learned. This lets us predict model generalization using only training data, amongst other insights: 🧵

I'm really fascinated by this dataset from the AI poetry survey paper. Here's another visualization I just made. Survey respondents were shown one of these 10 poems, and either told that they were authored by AI, human, or not told anything.

LLMs surpass human experts in predicting neuroscience results Scientific discovery is the next big goal for AI. We are seeing a huge number of research studies tackling AI-powered scientific discovery from different angles and for different problems. This new paper published in

I’ll be at NeurIPS this week presenting our work on interpretable embeddings — drop me a message if you want to chat!

Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics

Absolutely. In any hypothesis test between A and B about the working of a complex system, the right answer is invariably none of the above. Systems identification is a much better paradigm for neuroscience discovery; it allows us to efficiently explore huge hypothesis spaces.

🧠💡 Our LLMs just had a ‘memory augmentation’—now they can deliberate like seasoned thinkers! arxiv.org/abs/2412.17747

Cool new paper interpreting neurons in macaque V4 biorxiv.org/content/10.110…

New results for a new year! “Linking neural population formatting to function” describes our modern take on an old question: how can we understand the contribution of a brain area to behavior? biorxiv.org/content/10.110… 🧵1/

The data science revolution is getting closer. TabPFN v2 is published in Nature: nature.com/articles/s4158… On tabular classification with up to 10k data points & 500 features, in 2.8s TabPFN on average outperforms all other methods, even when tuning them for up to 4 hours🧵1/19

New preprint! 🧠🤖 Brain encoding in 21 languages! biorxiv.org/content/10.110… w/ Saima Malik-Moraleda, Greta Tuckute, and Ev (like in 'evidence', not Eve) Fedorenko 🇺🇦 (1/)

arxiv.org/abs/2502.10385 This is our latest work SimDINO that, again based on coding rate principle, significantly simplifies the popular (but unnecessarily sophisticated) visual self-supervised learning methods DINO and DINOv2. The power of understanding and principles is

Thanks for featuring our work! Aran Komatsuzaki. 🔥Today we are thrilled to announce our MSR flagship project Magma! This is a fully open-sourced project. We will roll out all the stuff: code, model and training data through the following days. Check out our full work here:

Humans just saw a *new* color—literally outside the known visual spectrum. BAIR faculty and visual computing expert Ren Ng and collaborators made it possible with the Oz Vision System. 🌈👁️ Newly published in Science Advances: science.org/doi/10.1126/sc… popsci.com/health/new-col…

🤯Your LLM just threw away 99.9 % of what it knows. Standard decoding samples one token at a time and discards the rest of the probability mass. Mixture of Inputs (MoI) rescues that lost information, feeding it back for more nuanced expressions. It is a brand new

🚨 New Paper! 🚨 Guard models slow, language-specific, and modality-limited? Meet OmniGuard that detects harmful prompts across multiple languages & modalities all using one approach with SOTA performance in all 3 modalities!! while being 120X faster 🚀 arxiv.org/abs/2505.23856

We automated systematic reviews using gpt-4.1 and o3-mini ! Our platform (otto-SR) beat humans at all tasks and conducted 12 years of systematic review research in just two days. We also show how otto-SR can be used in the real world to rapidly update clinical guidelines 🧵

Even the smartest LLMs can fail at basic multiturn communication Ask for grocery help → without asking where you live 🤦‍♀️ Ask to write articles → assumes your preferences 🤷🏻‍♀️ ⭐️CollabLLM (top 1%; oral ICML Conference) transforms LLMs from passive responders into active collaborators.

Reinforcement Learning Teachers of Test Time Scaling In this new paper, we introduce a new way to teach LLMs how to reason by learning to teach, not solve! The core idea: A teacher model is trained via RL to generate explanations from question-answer pairs, optimized to improve