Alice Bizeul

✨New Preprint ✨ Ever thought that reconstructing masked pixels for image representation learning seems sub-optimal? In our new preprint, we show how masking principal components—rather than raw pixel patches— improves Masked Image Modelling (MIM). Find out more below 🧵

🚀 We're hiring a Research Scientist, Machine Learning Research (MLR), Barcelona ☀️ 👉 Apply here: jobs.apple.com/en-us/details/… #MachineLearning #MLResearch #AI #Hiring #Apple #Barcelona #ResearchScientist #DeepLearning

What we're looking for: • A track record of publishing at top-tier ML conferences and journals • Hands-on experience across every stage of a research project If this sounds interesting: Know someone who'd be a great fit? Tag them or share this post. 🙏

The Apple MLR team in Barcelona is hiring! I joined 3 months ago and I'm really excited about my job: open science, an experienced team, enough GPUs to keep you busy & research freedom. Feel free to reach out or apply here: jobs.apple.com/en-us/details/…

We're hiring at Apple MLR in Barcelona 🦎 Work on cutting-edge problems in robustness, interpretability, and next-gen archs. Publish at top venues. Contribute to open-source and push the field forward. Apply: jobs.apple.com/en-us/details/… Or meet us at our booth at ICML 2026🇰🇷

🚀 The MLX team is growing! If you love writing blazing-fast GPU kernels or implementing foundational models in Python & Swift, we want you. Drop a DM or apply below! 👇 #MachineLearning #AppleSilicon jobs.apple.com/en-us/details/… github.com/ml-explore

In a multimodal context, even the discrete/continuous divide is a distraction. The real challenge is bridging the semantic gap between inherently high-level language tokens, and the very low-level representations we tend to use for perceptual signals. (I couldn't resist😆)

🎨Activation steering can reliably push a text-to-image generator toward a visual concept, but at a cost: each concept needs its own estimation. ⚡HyperTransport (HT) predicts the intervention directly, matching per-concept SOTA at 3–4 orders of magnitude less cost. [1/6]

Introducing the OpenAI Safety Fellowship, a new program supporting independent research on AI safety and alignment—and the next generation of talent. openai.com/index/introduc…

𝗣𝗮𝗿𝗮𝗥𝗡𝗡: 𝗨𝗻𝗹𝗼𝗰𝗸𝗶𝗻𝗴 𝗣𝗮𝗿𝗮𝗹𝗹𝗲𝗹 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗼𝗳 𝗡𝗼𝗻𝗹𝗶𝗻𝗲𝗮𝗿 𝗥𝗡𝗡𝘀 𝗳𝗼𝗿 𝗟𝗟𝗠𝘀 For years, we’ve given RNNs for doomed, and looked at Transformer as 𝘁𝗵𝗲 LLM—but we just needed better math 📄arxiv.org/abs/2510.21450 💻github.com/apple/ml-parar…

🚀 Excited to share LinEAS, our new activation steering method accepted at NeurIPS 2025! It approximates optimal transport maps e2e to precisely guide 🧭 activations achieving finer control 🎚️ with ✨ less than 32 ✨ prompts! 💻github.com/apple/ml-lineas 📄arxiv.org/abs/2503.10679

@syguoML @GatsbyUCL Thanks for sharing the slides, Siyuan! Any plans to come and present your work at ETH?

Understanding intelligence would be today's most interesting challenge. I think physics of learning -- learning follows the laws of physics -- is a start to derive new algorithms. Very much enjoyed the visit @GatsbyUCL and chat about physics of learning. I can feel the buzz for theory! Slides of the talk are attached. docs.google.com/presentation/d…

We’re excited to share our new paper: Continuously-Augmented Discrete Diffusion (CADD) — a simple yet effective way to bridge discrete and continuous diffusion models on discrete data, such as language modeling. [1/n] Paper: arxiv.org/abs/2510.01329

🚨 Machine Learning Research Internship opportunity in Apple MLR! We are looking for a PhD research intern with a strong interest in world modeling, planning or learning video representations for planning and/or reasoning. If interested, apply by sending an email to me at vthilak@apple.com. Applications will be reviewed until the position is filled.

Super excited to share l3m 🚀, a library for training large multimodal models, which we used to build AIM and AIMv2. Massive thanks to @alaa_nouby @DonkeyShot21 Michal Klein @MustafaShukor1 @jmsusskind and many others.

Had a great time speaking at @NECLabsEU about using activation steering for better instruction-following in LLMs! Check out the talk 🗣️: youtu.be/3ozuaGaEjpo?si… and paper 📜: arxiv.org/abs/2410.12877 This work that I did at @MSFTResearch shows how interpretability-based approaches can improve LLM controllability, connecting model understanding with practical utility.

We hosted an insightful talk by @alesstolfo, PhD student at @ETH and doctoral fellow at the Swiss CYD Campus, on improving instruction-following in language models via activation steering. Watch here: youtu.be/3ozuaGaEjpo?si…. #NECLabs #LLM

Join us tomorrow morning #ACL2025NLP #ACL2025

I am heading to @icmlconf to present our position paper with @randall_balestr @klindt_david @wielandbr on what we believe are the important next steps to advance SSL. It's not either theory or practice, it's both. We as a community need a better discussion.

Is the mystery behind the performance of Mamba🐍  keeping you awake at night? We got you covered! Our ICML2025 paper demystifies input selectivity in Mamba from the lens of approximation power, long-term memory, and associative recall capacity. arxiv.org/abs/2506.11891

@ibalazevic @GoogleDeepMind So cool that you were a part of that ! Congrats !

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team @GoogleDeepMind.