Wassim (Wes) Bouaziz
3.4K posts
@_Vassim
AI Scientist - Safety & Security @MistralAI | PhD from @MetaAI and @Polytechnique I confront equations and inequalities💡 my tweets reflect my own views only.
arxiv.org/abs/2605.28751 Now many studies try to do extrapolation through model merging. arxiv.org/abs/2605.26484
Our paper on Subliminal Learning was just published in Nature! Last July we released our preprint. It showed that LLMs can transmit traits (e.g. liking owls) through data that is unrelated to that trait (numbers that appear meaningless). What’s new?🧵
1/ today we're releasing muse spark, the first model from MSL. nine months ago we rebuilt our ai stack from scratch. new infrastructure, new architecture, new data pipelines. muse spark is the result of that work, and now it powers meta ai. 🧵
I hate tmux It's so incredibly user unfriendly The shortcuts make no sense I wish someone would make a better tmux Even just logging into tmux attaching the screen is an illogical hell to type Again I hate tmux, it's so shit
Introducing DINOv3: a state-of-the-art computer vision model trained with self-supervised learning (SSL) that produces powerful, high-resolution image features. For the first time, a single frozen vision backbone outperforms specialized solutions on multiple long-standing dense prediction tasks. Learn more about DINOv3 here: ai.meta.com/blog/dinov3-se…
Of course, what do you expect from a conference that receives over 20,000 submissions?
Very happy that our paper MEXMA has been featured on the bundle release by @AIatMeta 🎉 paper: arxiv.org/abs/2409.12737 code: github.com/facebookresear… Model: huggingface.co/facebook/MEXMA Checkout the full bundle here: ai.meta.com/blog/fair-news…
An LLM generates an article verbatim—did it “train on” the article? It’s complicated: under n-gram definitions of train-set inclusion, LLMs can complete “unseen” texts—both after data deletion and adding “gibberish” data. Our results impact unlearning, MIAs & data transparency🧵
