Keivan Rezaei
@RezaeiKeivan
Research Intern @Adobe || CS Ph.D. Student @UofMaryland || Prv. Student Researcher @GoogleAI || Prv. intern @allen_ai Ai2 || Alum @SharifSocial
🥳Excited to share our paper RESTOR: Knowledge Recovery in Machine Unlearning is accepted to #TMLR! We introduce a benchmark where unlearning means not just forgetting target data, but recovering the behavior of an ideal model that never saw them. Paper: openreview.net/pdf?id=BbwlJpN…
🖋️ Curious how writing differs across (research) cultures? 🚩 Tired of “cultural” evals that don't consult people? We engaged with researchers to identify & measure ✨cultural norms✨in scientific writing, and show that❗LLMs flatten them❗ 📜 arxiv.org/abs/2506.00784 1/11
🚀 Check out our draft on localizing knowledge in DiTs! Using attention contribution, we find that styles, objects, and facts can be localized to a small set of layers—though more diffusely than in UNets.
🚀New Paper: Localizing Knowledge in Diffusion Transformers 🌐Project page: armanzarei.github.io/Localizing-Kno… 📄Paper: arxiv.org/abs/2505.18832 Joint work with: @BasuSamyadeep, @RezaeiKeivan, Zihao Lin, @nagsayan112358, @FeiziSoheil
🥳🎉Happy to share that starting next week, I’ll be a research intern at @Adobe in San Jose, joining the Document Intelligence Lab!
Can mechanistic insights lead to tangible applications for multimodal models? Check out our recent survey on this topic! We highlight the practical aspects of interpretability methods and lay down various open-problems in the area.
✨ Introducing MutaGReP (Mutation-guided Grounded Repository Plan Search) - an approach that uses LLM-guided tree search to find realizable plans that are grounded in a target codebase without executing any code! Ever wanted to provide an entire repo containing 100s of 1000s of…
🎉Happy to share that I’m starting a new role this week as a Student Researcher at @Google, where I’ll be focusing on data-centric GenAI!
Join us on Wednesday at 11 to check out our poster on “Ad Auctions for LLMs via Retrieval Augmented Generation”! Unfortunately, I can’t attend due to visa issues, but my collaborators @SuhoShin327 and Sebastien Lahaie will be there to share our work! #NeurIPS2024
Let’s monetize LLMs! 💰💵 We are happy to share that our paper "Ad Auctions for LLMs via Retrieval Augmented Generation" has been accepted to #NeurIPS2024 🎇🎉 Check out the paper arxiv.org/abs/2406.09459