iiinova — where your digital self keeps evolving

lucazapp.bsky.social @lucazapp.bsky.social · 23/10/2025

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

github.com

GitHub - apple/ml-lineas

Contribute to apple/ml-lineas development by creating an account on GitHub.

000

lucazapp.bsky.social @lucazapp.bsky.social · 17/04/2025

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!

machinelearning.apple.com

Controlling Language and Diffusion Models by Transporting Activations

Large generative models are becoming increasingly capable and more widely deployed to power production applications, but getting these…

010

Reposted by @lucazapp.bsky.social

Pau Rodriguez @paurodriguez.bsky.social · 10/12/2024

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 🧵

34715

Reposted by @lucazapp.bsky.social

Preetum Nakkiran @preetumnakkiran.bsky.social · 11/02/2025

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/

Left Image: A shaggy dog-horse hybrid standing in a rural landscape.
Right Image: A golden dog wearing a red beret against a blurred outdoor background.

23915

Reposted by @lucazapp.bsky.social

Samira @samiraabnar.bsky.social · 28/01/2025

🚨 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:

1188

Reposted by @lucazapp.bsky.social

Marco Cuturi @marcocuturi.bsky.social · 18/12/2024

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.

1133