Ali Behrouz

Intern@Google·美国·OpenReview

研究方向

Optimization · ML for Time Series · Sequence Modeling · Deep Learning Architectures · Transformers · Recurrent Neural Networks · Associative Memory · Hypergraphs · Machine Learning on Graphs · Social Network Analysis · Brain Networks · Fairness in Graph Learning · Explainability in Graph Learning · ML in Healthcare · Time Series

Ali Behrouz

TNT: Improving Chunkwise Training for Test-Time Memorization

ATLAS: Learning to Optimally Memorize the Context at Test Time

Memory Caching: RNNs with Growing Memory

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

Leto: Modeling Multivariate Time Series with Memorizing at Test Time

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

Titans: Learning to Memorize at Test Time

TRELLIS: Learning to Compress Key-Value Memory in Attention Models

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

Nested Learning: The Illusion of Deep Learning Architectures

Best of Both Worlds: Advantages of Hybrid Graph Sequence Models

Towards an Understanding of Graph Sequence Models