Check out our new work on conditioning pre-trained generative models via activation steering. LineAS has been accepted at NeurIPS 2025. Code and paper are online:
💻 github.com/apple/ml-lin...
📄 arxiv.org/abs/2503.10679
23.10.2025 09:16 — 👍 0 🔁 0 💬 0 📌 0
New blog post that explains our work on Controlling Diffusion and LLMs using steering and optimal transport:
machinelearning.apple.com/research/tra...
This work will be presented at ICLR2025 in Singapore. See you there!
17.04.2025 15:49 — 👍 1 🔁 0 💬 0 📌 0
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 🧵
10.12.2024 13:09 — 👍 47 🔁 15 💬 3 📌 5
Paper🧵 (cross-posted at X): When does composition of diffusion models "work"? Intuitively, the reason dog+hat works and dog+horse doesn’t has something to do with independence between the concepts being composed. The tricky part is to formalize exactly what this means. 1/
11.02.2025 05:59 — 👍 39 🔁 15 💬 2 📌 2
🚨 One question that has always intrigued me is the role of different ways to increase a model's capacity: parameters, parallelizable compute, or sequential compute?
We explored this through the lens of MoEs:
28.01.2025 06:25 — 👍 18 🔁 8 💬 1 📌 3
The Apple Machine Learning Research (MLR) team in Paris has openings for both FTE roles and a short-term post-doc position to contribute to our team's research agenda. Researchers at Apple's MLR (led by Samy Bengio) target impactful publications in top-tier ML venues and OSS.
18.12.2024 17:05 — 👍 13 🔁 3 💬 1 📌 2
ML Research @ Apple.
Understanding deep learning (generalization, calibration, diffusion, etc).
preetum.nakkiran.org
PhD student with Alex Ecker & Fabian Sinz.
DL engineer, toddler neuroscientist, topology enthusiast. Searching for cell types.
machine learning researcher @ Apple machine learning research
Professor, Santa Fe Institute. Research on AI, cognitive science, and complex systems.
Website: https://melaniemitchell.me
Substack: https://aiguide.substack.com/
Research fellow @OxfordStats @OxCSML, spent time at FAIR and MSR
Former quant 📈 (@GoldmanSachs), former former gymnast 🤸♀️
My opinions are my own
🇧🇬-🇬🇧 sh/ssh
PhD student in NLP at GMU w/ Antonios Anastasopoulos. Focus: L2 acquisition, low-resource NLP, psycholinguistics. Passionate about empowering heritage speakers. Berkeley '19
Visiting PhD at Stanford🌲, CS PhD student at NUS 🇸🇬, PhD Fellow @ Google, NLP researcher📒
https://yocodeyo.github.io
Working on Social Intelligence and Evaluation
PhD Candidate at Duke
https://defnecirci.github.io/
PhD student @ CMU LTI. efficiency/data in NLP/ML
LTI PhD at CMU on evaluation and trustworthy ML/NLP, prev AI&CS Edinburgh University, Google, YouTube, Apple, Netflix. Views are personal 👩🏻💻🇮🇩
athiyadeviyani.github.io
PhD student @ CMU LTI. working on text generation + long context
https://www.cs.cmu.edu/~abertsch/
Postdoc at UW NLP 🏔️. #NLProc, computational social science, cultural analytics, responsible AI. she/her. Previously at Berkeley, Ai2, MSR, Stanford. Incoming assistant prof at Wisconsin CS. lucy3.github.io/prospective-students.html
PhD student at Johns Hopkins University
Alumni from McGill University & MILA
Working on NLP Evaluation, Responsible AI, Human-AI interaction
she/her 🇨🇦
Assistant prof in the Amsterdam Machine Learning Lab at the University of Amsterdam | ELLIS scholar | #causality #causalML anything #causal | 🇮🇹🇸🇮 in 🇳🇱 | #UAI2025 program chair and #UAI2026 general chair
https://saramagliacane.github.io/
Sr. Principal Research Manager at Microsoft Research, NYC // Machine Learning, Responsible AI, Transparency, Intelligibility, Human-AI Interaction // WiML Co-founder // Former NeurIPS & current FAccT Program Co-chair // Brooklyn, NY // http://jennwv.com
Associate Professor at MIT EECS.
RL & Meta-Learning @ DeepMind.
