Intern @Google, Ph.D. Student @Cornell_CS. Interested in machine learning, LLM, brain, and healthcare. abehrouz.github.iohttps://bsky.app/profile/alibehrouz.bsky.socialhttps://bsky.app/profile/alibehrouz.bsky.social/post/3lcljuajsnk2bI'll be at #NeurIPS2024 next week, and would be happy to chat about deep learning architectures, sequence modeling, reasoning, neuroscience, world models, graphs, and almost anything :) I also will be presenting Chimera (a 2D SSM) on Wednesday (4:30 PM).05 Dec 2024 20:43 +0000at://did:plc:ukaal4e34zh36gtkhy7yebab/app.bsky.feed.post/3lcljuajsnk2bhttps://bsky.app/profile/alibehrouz.bsky.social/post/3lcgn23hruc2g🌟 Best of Both Worlds! ❓Have you ever wondered why hybrid models (RNN + Transformers) are powerful? We answer this through the lens of circuit complexity and graphs! Excited to share our work on understanding Graph Sequence Models (GSM), which allows the use of any sequence model for graphs.03 Dec 2024 21:57 +0000at://did:plc:ukaal4e34zh36gtkhy7yebab/app.bsky.feed.post/3lcgn23hruc2ghttps://bsky.app/profile/alibehrouz.bsky.social/post/3lbdt5ietbs2hAre univariate SSMs effective when there are 2D dependencies? ✨In our #NeurIPS paper we show how to effectively model multivariate time series by input-dependent (selective) 2-dimensional state space models with fast training using a 2D parallel scan. (1/8)20 Nov 2024 01:43 +0000at://did:plc:ukaal4e34zh36gtkhy7yebab/app.bsky.feed.post/3lbdt5ietbs2h