Alice Bizeul

Research Scientist @ Apple MLR | Previously @ETH Zurich @EPFL @MIT, Research Intern @Amazon

[Alice Bizeul @AliceBizeul]

✨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 🧵

[Sander Dieleman @sedielem]

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😆)

[Valentino Maiorca @ValeMaiorca]

🎨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]

[OpenAI @OpenAI]

Introducing the OpenAI Safety Fellowship, a new program supporting independent research on AI safety and alignment—and the next generation of talent.

https://t.co/vAQKvf8KyO

[Federico Danieli @FedericoDa40495]

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
📄https://t.co/lFQrUEfEvZ
💻https://t.co/Lg7gbcwgFU

[Pau Rodríguez @prlz77]

🚀 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!

💻https://t.co/IdZOpwtFXC
📄https://t.co/sfPHk5sT2B

[Alice Bizeul @AliceBizeul]

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

[Huangjie Zheng @UnderGroundJeg]

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: https://t.co/fQ8qxx4Pge

[Vimal Thilak🦉🐒 @AggieInCA]

🚨 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 [email protected]. Applications will be reviewed until the position is filled.

[Victor Turrisi @victorturrisi]

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.

[Alessandro Stolfo @alesstolfo]

Had a great time speaking at @NECLabsEU about using activation steering for better instruction-following in LLMs!

Check out the talk 🗣️: https://t.co/nFcy1wBbuM
and paper 📜: https://t.co/ujMWHdzmXG

This work that I did at @MSFTResearch shows how interpretability-based approaches can improve LLM controllability, connecting model understanding with practical utility.

[NEC Laboratories Europe @NECLabsEU]

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: https://t.co/zn9g6Ex70y. #NECLabs #LLM

[Jakub Macina @dmacjam]

Join us tomorrow morning #ACL2025NLP #ACL2025

[Patrik Reizinger @rpatrik96]

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.

[Teresa Huang @TeresaNHuang]

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.
https://t.co/dWDYyIWLzt

[Alice Bizeul @AliceBizeul]

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

[Afra Amini @afra_amini]

Current KL estimation practices in RLHF can generate high variance and even negative values! We propose a provably better estimator that only takes a few lines of code to implement.🧵👇
w/ @xtimv and Ryan Cotterell
code: https://t.co/3r7JycAVxz
paper: https://t.co/yxC8ZXrmYe

[Alizée Pace @AlizeePace]

Paper: https://t.co/YIeRqpBgj1

[Javier Abad Martinez @JavierAbadM]

Presenting our work at #ICLR this week! Come by the poster or oral session to chat about copyright protection and AI/LLM safety

📌 𝐏𝐨𝐬𝐭𝐞𝐫: Friday, 10 a.m. – 12.30 p.m. | Booth 537
📌 𝐎𝐫𝐚𝐥: Friday, 3.30 – 5 p.m. | Room Peridot

@FraPintoML @DonhauserKonst @FannyYangETH

[Attila Juhos @JuhosAttila]

Interested in understanding feature extraction of an amazing self-supervised method, DIET (https://t.co/hZqGlTKWi1)? Come to our talk on Sat 11am at Garnet 216-218 and poster #310 at 3pm.

My fabulous co-authors: @rpatrik96 @AliceBizeul @randall_balestr @klindt_david @wielandbr.

[Attila Juhos @JuhosAttila]

I am at #ICLR25 😎 and looking for collaborations on self-supervised learning/ understanding representation learning and logical reasoning. Let's chat. 💭

Otherwise, come by on Sat 3pm to our poster #308 on cross-entropy based SSL.