Pau Rodriguez
@paurodriguez.bsky.social
Research Scientist at Apple Machine Learning Research. Previously ServiceNow and Element AI in Montréal.
Existing methods estimate layer-wise 🥞 interventions. While powerful, layer-wise methods have some approximation error since the optimization is done locally, without considering multiple layers at once 🤔. We circumvent this problem in LinEAS with an end-to-end optimization ⚙️!
October 21, 2025 at 10:00 AM
Existing methods estimate layer-wise 🥞 interventions. While powerful, layer-wise methods have some approximation error since the optimization is done locally, without considering multiple layers at once 🤔. We circumvent this problem in LinEAS with an end-to-end optimization ⚙️!
🚀 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
💻https://github.com/apple/ml-lineas
📄https://arxiv.org/abs/2503.10679
October 21, 2025 at 10:00 AM
🚀 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
💻https://github.com/apple/ml-lineas
📄https://arxiv.org/abs/2503.10679