Pegah Khayatan

PhD student at ISIR 🤖 Exploring how to understand & manipulate MLLMs🪄 Previously at École Polytechnique, EPFL, and Télécom Paris.

[Pegah Khayatan @PKhayatan]

Big congrats to @TrueBeerus, @MustafaShukor1, Arnaud, Alasdair & @quobbe!
- Arxiv: https://t.co/FEnTVoDnKm
- Blog/Project page: https://t.co/7gsVOwBjSp
- Code: https://t.co/8o0Cex6EaU
Come by and share your thoughts 🙌

[Pegah Khayatan @PKhayatan]

ELLIS Unconference at #EurIPS 🚀 Attended the Theory of Explainable ML Workshop—packed with ideas: B-Cosification, minimal+sufficient explanations, and concept-based insights. Great poster chats too!
Tomorrow we present our work on input-dependent MLLM steering — Poster #108

[Jayneel Parekh @TrueBeerus]

🎉Happy to share our #NeurIPS2025 paper Learn-to-Steer (L2S). Offers flexible and better steering control for MLLMs than standard mean-steering approaches! Congrats @PKhayatan, @MustafaShukor1, Arnaud, Alasdair, and @quobbe!

- Arxiv: https://t.co/O3jMSwZXVO

[Pegah Khayatan @PKhayatan]

@lucacarlone1 Thank you, interested.