Michael Toker
@michael_toker
PhD student @Technion NLP lab - Developing explainability methods to gain a better understanding of LLMs
ID: 1522869113181413378
https://tokeron.github.io/ 07-05-2022 09:21:40
54 Tweet
107 Followers
433 Following
Our paper Diffusion Lens got accepted to #ACL2024 main conference! 🌴⭐️ Visualize LLMs computation process with our live demo >> huggingface.co/spaces/tokeron… For a quick TL;DR checkout Michael Toker's thread or project website - tokeron.github.io/DiffusionLensW…
Come meet us tomorrow at poster session 3! Hadas Orgad and I will present our work on editing factual knowledge in text-to-image models: technion-cs-nlp.github.io/ReFACT/
Come say hi at poster 46 and talk about editing factual knowledge in text-to-image models! #NAACL24 Hadas Orgad
🚀 At ACL? Don’t miss our poster on Diffusion Lens! 🌟 See how we interpret text-to-image models by generating images from hidden representations. 🖼️ Today at 14:00, Poster Session 2, Convention Center A1. #ACL2024 Hadas Orgad Mor Ventura Dana Arad 🎗️ Yonatan Belinkov
Interested in text-to-image models? Come say hi today at poster session 2 and hear about the diffusion lens - our new method of interpreting text encoders of t2i models ✨📸 #acl2024nlp #ACL2024 w/ Michael Toker Mor Ventura Hadas Orgad Yonatan Belinkov
Had a great time this week at #ISCOL ✨ We presented our work, Diffusion Lens, from #aclnlp2024, this time with the full crew! Michael Toker Mor Ventura Hadas Orgad Check out our paper and demo: tokeron.github.io/DiffusionLensW… and Michael's talk (in Hebrew): youtu.be/8qEeumJL_FM?si…