Small Language Models (SLMs) don’t have the capacity to remember everything in their training data. Which tokens should they learn to predict, and when should they ask for help? We tackle this question in our new preprint. You can check it out on arxiv: arxiv.org/abs/2602.12005 🧵1/7

With other folks at 🍏, @brunokm.bsky.social has worked on a complete(d) parameterisation for NNs that can *transfer* locally tuned hyperparameters: tune optimizers' parameters (e.g. LR) *per module/depth* using an evolutionary search on small models → they transfer perf. gains to much larger models

Bruno Mlodozeniec@brunokm.bsky.social · 7mo ago

In our new work — Complete(d)P — we try to answer 3 questions about hyperparameter (HP) scaling: ● How to transfer across model size, tokens&batch-size?→ Complete(d)P ● Do per-module HPs matter? ✔️2x speed-ups possible ● Do they transfer to larger scale? ✔️ With the right parameterisation

I am at #NeurIPS2025. We can chat about data mixing, efficient training, ML@Apple and more.

my 2 cents on the ICLR drama: It's been years that the system has been under attack. But it's also been years that we hear, year after year, that there is no way to enforce protection mechanisms (e.g. deny lists for dishonest authors or reviewers etc..) for legal reasons.

📢 We’re looking for a researcher in in cogsci, neuroscience, linguistics, or related disciplines to work with us at Apple Machine Learning Research! We're hiring for a one-year interdisciplinary AIML Resident to work on understanding reasoning and decision making in LLMs. 🧵

We have been working with Michal Klein on pushing a module to train *flow matching* models using JAX. This is shipped as part of our new release of the OTT-JAX toolbox (github.com/ott-jax/ott) The tutorial to do so is here: ott-jax.readthedocs.io/tutorials/ne...

Afternoon talks by: @marcocuturi.bsky.social Elena Agliari Jan Gerken Thanks all for the great talks, conversations, and engagement! Fingers crossed we get to host this event a 4th time next year and see many of you back in Gothenburg 🤞🇸🇪

🚀 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://github.com/apple/ml-lineas 📄https://arxiv.org/abs/2503.10679

It's that time of the year! 🎁 The Apple Machine Learning Research (MLR) team in Paris is hiring a few interns, to do cool research for ±6 months 🚀🚀 & work towards publications/OSS. Check requirements and apply: ➡️ jobs.apple.com/en-us/detail... More❓→ ✉️ mlr_paris_internships@group.apple.com

While working on semidiscrete flow matching this summer (➡️ arxiv.org/abs/2509.25519), I kept looking for a video illustrating that the velocity field solving the Benamou-Brenier OT problem is NOT constant w.r.t. time ⏳... so I did it myself, take a look! ott-jax.readthedocs.io/tutorials/th...

LLMs are currently this one big parameter block that stores all sort of facts. In our new preprint, we add context-specific memory parameters to the model, and pretrain the model along with a big bank of memories. 📑 arxiv.org/abs/2510.02375 [1/10]🧵

Wow! Finally OT done on the entire training set to train a diffusion model!

Marco Cuturi@marcocuturi.bsky.social · 10mo ago

Our two phenomenal interns, Alireza Mousavi-Hosseini and Stephen Zhang @syz.bsky.social have been cooking some really cool work with Michal Klein and me over the summer. Relying on optimal transport couplings (to pick noise and data pairs) should, in principle, be helpful to guide flow matching 🧵

Our two phenomenal interns, Alireza Mousavi-Hosseini and Stephen Zhang @syz.bsky.social have been cooking some really cool work with Michal Klein and me over the summer. Relying on optimal transport couplings (to pick noise and data pairs) should, in principle, be helpful to guide flow matching 🧵

New Apple #ML Research Highlight: The "Super Weight:" How Even a Single Parameter can Determine an #LLM's Behavior machinelearning.apple.com/research/the...

The

A recent paper from Apple researchers,

machinelearning.apple.com

scaling up the computation of optimal transport couplings to hundreds of thousands of 3k dimensional vectors made easy using sharding and OTT-JAX! check this notebook, it only takes a few lines of code thanks to JAX's native sharding abilities ott-jax.readthedocs.io/en/latest/tu...

New Apple #ML Research Highlight: "FastVLM: Efficient Vision Encoding for Vision Language Models" machinelearning.apple.com/research/fas...

FastVLM: Efficient Vision Encoding for Vision Language Models

Vision Language Models (VLMs) enable visual understanding alongside textual inputs. They are typically built by passing visual tokens from a…

machinelearning.apple.com

So pleased and proud to share with you what our team has been up to, on an ambitious journey to build a video foundation model for scientific domains ! ✨ 🚀 🎞️ 🧪 #ICCV2025 #AI4Science

@hassony2.bsky.social · last yr.

Thrilled to share our latest work on SciVid, to appear at #ICCV2025! 🎉 SciVid offers cross-domain evaluation of video models in scientific applications, including medical CV, animal behavior, & weather forecasting 🧪🌍📽️🪰🐭🫀🌦️ 📝 Check out our paper: arxiv.org/abs/2507.03578 [1/4]🧵

The NeurIPS paper checklist corroborates the bureaucratic theory of statistics.

Standard error of what now?

The NeurIPS checklist corroborates the bureaucratic theory of statistics.

argmin.net

Can LLMs access and describe their own internal distributions? With my colleagues at Apple, I invite you to take a leap forward and make LLM uncertainty quantification what it can be. 📄 arxiv.org/abs/2505.20295 💻 github.com/apple/ml-sel... 🧵1/9

www.kyotoprize.org/en/laureates...

Shun-ichi Amari | Kyoto Prize

Shun-ichi Amari

kyotoprize.org

Shunichi Amari has been awarded the 40th (2025) Kyoto Prize in recognition of his pioneering research in the fields of artificial neural networks, machine learning, and information geometry www.riken.jp/pr/news/2025...

甘利 俊一 栄誉研究員が「京都賞」を受賞

甘利 俊一栄誉研究員（本務：帝京大学 先端総合研究機構 特任教授）は、人工ニューラルネットワーク、機械学習、情報幾何学分野での先駆的な研究が評価され、第40回（2025）京都賞（先端技術部門　受賞対象分野：情報科学）を受賞しました。

riken.jp

NEW PAPER ALERT: Recent studies have shown that LLMs often lack robustness to distribution shifts in their reasoning. Our paper proposes a new method, AbstRaL, to augment LLMs’ reasoning robustness, by promoting their abstract thinking with granular reinforcement learning.

Now that @interspeech.bsky.social registration is open, time for some shameless promo! Sign-up and join our Interspeech tutorial: Speech Technology Meets Early Language Acquisition: How Interdisciplinary Efforts Benefit Both Fields. 🗣️👶 www.interspeech2025.org/tutorials ⬇️ (1/2)

Today we have released the code and a demo iOS application for FastVLM - our extremely efficient and fast vision language model which runs on your device using MLX! You can check out the code and the app here: github.com/apple/ml-fas...

#ICLR #TrainBetterLM I am at ICLR, come to our posters for improved language model training! Recycle gradients for faster neural net training with AdEMAmix iclr.cc/virtual/2025... (Fri Apr 25, 10 am). 1/3

New post: "Apple Machine Learning Research at #ICLR 2025" - highlighting a selection of the many Apple #ML research papers to be presented at @iclr-conf.bsky.social this week: machinelearning.apple.com/research/icl...

Apple Machine Learning Research at ICLR 2025

Apple researchers are advancing machine learning (ML) and AI through fundamental research that improves the world’s understanding of this…

machinelearning.apple.com

Thrilled to share the latest work from our team at @Apple where we achieve interpretable and fine-grained control of LLMs and Diffusion models via Activation Transport 🔥 📄 arxiv.org/abs/2410.23054 🛠️ github.com/apple/ml-act 0/9 🧵

The trader made millions. Why was this unusual? For a few reasons: - Firstly new opening volume on chain, minutes after market open - IVR of +80 on $QQQ, with iv percentile of medium. - happened at once, at ask -otm - market was bearish, across the board Unusual. Come learn: unusualwhales.com

I'm calling for an investigation into whether President Trump manipulated the market to benefit his Wall Street donors—all while working people and small businesses paid the price. Did Trump help insiders cash in on his tariff flip-flopping? It sure looks like corruption.

Did Trump help insiders cash in on his tariff flip-flopping?

YouTube video by Senator Elizabeth Warren

youtu.be

Accepted as a Spotlight at @iclr-conf.bsky.social the work shares a new method for fine-grained control over #genAI output - without the computational overhead, complexity, and volume of data needed by #RLHF or fine-tuning, and with more reliable results than prompt engineering.