I'm glad to share that our paper "COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP" (arxiv.org/abs/2305.06754) was accepted at Findings of #ACL2023 ! ❤️🦜 #ACL2023NLP #NLProc #XAI 1/6🧵

We're launching Keras Core, a new library that brings the Keras API to JAX and PyTorch in addition to TensorFlow. It enables you to write cross-framework deep learning components and to benefit from the best that each framework has to offer. Read more: keras.io/keras_core/ann…

I am at #ICML2023 to present my latest work. Is the human performance better than that of diffusion models on the one-shot drawings task ? Attend my oral presentation today to have the answer ! More details below : x.com/VictorBoutin/s…

We are looking for a research engineer to work on domain adaptation and transfer learning École polytechnique near Paris. Come with us to do research, open source Python software and benchmarks. Contact me by email if interested. Please RT (free users need to help each other).

New work on Kernel regression on distributions arxiv.org/abs/2308.14335 where we prove that Rate of convergence is faster ! Applications to forecast distributional variability of 2016 US presidential election. ANITI Toulouse Louis Béthune François Bachoc

👋 Explain big vision model with 𝐂𝐑𝐀𝐅𝐓 🪄🐰 A method that 𝙖𝙪𝙩𝙤𝙢𝙖𝙩𝙞𝙘𝙖𝙡𝙡𝙮 extracts the most important concepts for your favorite pre-trained vision model. e.g., we automatically discover the most important concepts on a ResNet50 for rabbits: eyes, ears, fur. 🧶

If you're interested in a student researcher position at Google DeepMind in 2024, please apply here google.com/about/careers/… before December 15. My team will be looking for a student working on LLM finetuning on site in Paris.

📢 *PhD opening* at Centre Inria de l'Université Grenoble Alpes ! Edouard Pauwels, Samuel Vaiter and myself are looking for a student to work with us on learning theory for bilevel optimization, in particular, the implicit bias in bilevel optimization. If interested, please reach out!

👋👨‍🍳🍵 After a year of cooking up a secret project, I'm thrilled to officially reveal: The 𝐋𝐄𝐍𝐒 𝐏𝐫𝐨𝐣𝐞𝐜𝐭. By combining modern tools of Explainable AI, how much can we explain a ResNet50? 🧶

🍏 Apple ML research in Paris has multiple open internship positions!🍎 We are looking for Ph.D. students interested in generative modeling, optimization, large-scale learning or uncertainty quantification, with applications to challenging scientific problems. Details below 👇

Apple releases AIMv2 Multimodal Autoregressive Pre-training of Large Vision Encoders

This paper maps hardware-cost sweet spots for training efficient small-scale language models. Data shows A100-40GB beats H100 for training cost-effective small language models 🎯 Original Problem: Training small-scale LLMs (under 2B parameters) faces unclear computational

Amitis Shidani Samira Abnar Harshay Shah Alaa El-Nouby Vimal Thilak🦉🐒 and Scaling Laws for Forgetting and Fine-Tuning (E-2708) with Louis Béthune, David Grangier, Eleonora Gualdoni, Marco Cuturi, and Pierre Ablin 🔗 icml.cc/virtual/2025/p…

We propose new scaling laws that predict the optimal data mixture, for pretraining LLMs, native multimodal models and large vision encoders ! Only running small-scale experiments is needed, and we can then extrapolate to large-scale ones. These laws allow 1/n 🧵