Publications

You can also find my papers on Google Scholar or Semantic Scholar.

2026

• Online Neural Space Time Memory for Dynamic Novel View Synthesis

  Baback Elmieh, Lynn Tsai, Zeman Li, Srinivas Kaza, Tiancheng Sun, Gabor Csapo, Ali Behrouz, Yuan Deng, Stephen Lombardi, Steven M. Seitz, Xuan Luo

  arXiv preprint · 2026 Paper

• ATLAS: Learning to Optimally Memorize the Context at Test Time

  Ali Behrouz, Zeman Li, Praneeth Kacham, Majid Daliri, Yuan Deng, Peilin Zhong, Meisam Razaviyayn, Vahab Mirrokni

  International Conference on Machine Learning · ICML 2026 Paper

• Memory Caching: RNNs with Growing Memory

  Ali Behrouz, Zeman Li, Yuan Deng, Peilin Zhong, Meisam Razaviyayn, Vahab Mirrokni

  International Conference on Machine Learning · ICML 2026 Paper

• Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

  Ali Behrouz, Farnoosh Hashemi, Vahab Mirrokni

  arXiv preprint · 2026 Paper

• Tapered Language Models

  Reza Bayat, Ali Behrouz, Aaron Courville

  arXiv preprint · 2026 Paper

• It’s All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization

  Ali Behrouz, Meisam Razaviyayn, Peilin Zhong, Vahab Mirrokni

  International Conference on Learning Representations · ICLR 2026 Paper Blog

• TNT: Improving Chunkwise Training for Test-Time Memorization

  Zeman Li, Ali Behrouz, Yuan Deng, Peilin Zhong, Praneeth Kacham, Mahdi Karami, Meisam Razaviyayn, Vahab Mirrokni

  International Conference on Learning Representations · ICLR 2026 Paper OpenReview

2025

• Nested Learning: The Illusion of Deep Learning Architectures

  Ali Behrouz, Meisam Razaviyayn, Peilin Zhong, Vahab Mirrokni

  Neural Information Processing Systems · NeurIPS 2025 Featured in various media (e.g., Forbes) Paper Blog NeurIPS Presentation

• Titans: Learning to Memorize at Test Time

  Ali Behrouz, Peilin Zhong, Vahab Mirrokni

  Neural Information Processing Systems · NeurIPS 2025 Featured in various media (e.g., Forbes) Paper Blog

• Trellis: Learning to Compress Key-Value Memory in Attention Models

  Mahdi Karami, Ali Behrouz, Praneeth Kacham, Vahab Mirrokni

  Conference on Language Modeling · COLM 2025 Paper

• MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling

  Mahdi Karami, Ali Behrouz, Peilin Zhong, Razvan Pascanu, Vahab Mirrokni

  Conference on Language Modeling · COLM 2025 Paper

• Best of Both Worlds: Advantages of Hybrid Graph Sequence Models

  Ali Behrouz, Ali Parviz, Mahdi Karami, Clayton Sanford, Bryan Perozzi, Vahab Mirrokni

  International Conference on Machine Learning · ICML 2025 Paper

• Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysis

  Asal Meskin, Alireza Mirrokni, Ali Najar, Ali Behrouz

  arXiv preprint · 2025 Paper

2024

• Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models

  Ali Behrouz, Michele Santacatterina, Ramin Zabih

  Neural Information Processing Systems · NeurIPS 2024 Paper

• BrainMamba: Encoding Brain Activity via Selective State Space Models

  Ali Behrouz, Farnoosh Hashemi

  Conference on Health, Inference, and Learning · CHIL 2024 Best Paper Award Paper Code

• Graph Mamba: Towards Learning on Graphs with State Space Models

  Ali Behrouz, Farnoosh Hashemi

  ACM Knowledge Discovery and Data Mining Conference · KDD 2024 2nd Most Influential Paper of KDD 2024 Paper Code

• A Unified Core Structure in Multiplex Networks: From Finding the Densest Subgraph to Modeling User Engagement

  Farnoosh Hashemi, Ali Behrouz

  ACM Knowledge Discovery and Data Mining Conference · KDD 2024 Paper Code

• Unsupervised Representation Learning of Brain Activity via Bridging Voxel Activity and Functional Connectivity

  Ali Behrouz, Parsa Delavari, Farnoosh Hashemi

  International Conference on Machine Learning · ICML 2024 Paper

  Also presented at the NeurIPS AI4Science Workshop 2023.

• MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection

  Ali Behrouz, Michele Santacatterina, Ramin Zabih

  arXiv preprint · 2024 Paper

2023

• CAT-Walk: Inductive Hypergraph Learning via Set Walks

  Ali Behrouz, Farnoosh Hashemi, Sadaf Sadeghian, Margo Seltzer

  Neural Information Processing Systems · NeurIPS 2023 Paper Code

• Learning Temporal Higher-order Patterns to Detect Anomalous Brain Activity

  Ali Behrouz, Farnoosh Hashemi

  Machine Learning for Health · ML4H 2023 Oral Talk

• Generalized Densest Subgraph in Multiplex Networks

  Ali Behrouz, Farnoosh Hashemi

  Conference on Complex Networks & Their Applications · CNA 2023 Oral Talk Code

• ADMIRE++: Explainable Anomaly Detection in the Human Brain via Inductive Learning on Temporal Multiplex Networks

  Ali Behrouz, Margo Seltzer

  ICML Interpretable ML in Healthcare Workshop · IMLH 2023 Best Paper Award Paper Code

• Anomaly Detection in Human Brain via Inductive Learning on Temporal Multiplex Networks

  Ali Behrouz, Margo Seltzer

  Machine Learning for Healthcare · MLHC 2023 Spotlight Talk Paper Code Video

• CS-TGN: Community Search via Temporal Graph Neural Networks

  Farnoosh Hashemi, Ali Behrouz, Milad Rezaei Hajidehi

  Companion Proceedings of the Web Conference · WWW 2023 Paper Code

• FirmTruss Community Search in Multilayer Networks

  Ali Behrouz, Farnoosh Hashemi, Laks V.S. Lakshmanan

  International Conference on Very Large Databases · VLDB 2023 Paper Code

2022

• Anomaly Detection in Multiplex Dynamic Networks: from Blockchain Security to Brain Disease Prediction

  Ali Behrouz, Margo Seltzer

  NeurIPS Temporal Graph Learning Workshop 2022 Spotlight Talk Paper Code

• Fast Optimization of Weighted Sparse Decision Trees for use in Optimal Treatment Regimes and Optimal Policy Design

  Ali Behrouz, Mathias Lécuyer, Cynthia Rudin, Margo Seltzer

  Advances in Interpretable Machine Learning Workshop · CIKM 2022 Paper

• CS-MLGCN: Multiplex Graph Convolutional Networks for Community Search in Multiplex Networks

  Ali Behrouz, Farnoosh Hashemi

  ACM Conference on Information and Knowledge Management · CIKM 2022 Best Paper Honorable Mention Award Paper

• FirmCore Decomposition of Multilayer Networks

  Farnoosh Hashemi, Ali Behrouz, Laks V.S. Lakshmanan

  ACM Web Conference · WWW 2022 Paper Code

2020

• Green Space and Happiness of Developed Countries

  Farnoosh Hashemi, Ali Behrouz, Jeasurk Yang, Donghee Yvette Wohn, Meeyoung Cha

  IEEE International Conference on Big Data and Smart Computing · 2020 Paper

2018

• Secure Credit Reporting on the Blockchain

  Amir Kafshdar Goharshady, Ali Behrouz, Krishnendu Chatterjee

  IEEE International Conference on Blockchain · 2018 Paper