Tathagata Srimani

Research focus

Architecture Design (Transformers, SSMs, MoE) (2)Training Efficiency & Optimization (2)Inference & Quantization (1)Distributed Systems & Hardware (1)

Frequent co-authors

Kerem Y. Camsari (2)Kyle Lee (1)Corentin Delacour (1)Kevin Callahan-Coray (1)

Papers (2)

May 3, 2026

Uni- versity of California2w ago·also CMU ML, UMich

Stochastic Sparse Attention for Memory-Bound Inference

Attention bottlenecks in long-context decoding? SANTA slashes memory bandwidth demands by stochastically sampling value vectors, achieving 1.5x speedups without sacrificing accuracy.

Kyle Lee, Corentin Delacour, Kevin Callahan-Coray +5

Architecture Design (Transformers, SSMs, MoE)Inference & Quantization Training Efficiency & Optimization

Feb 15, 2026

CMU MLFeb 15, 2026·also NYU, Purdue, UCSB, Uni- versity of California

Probabilistic approximate optimization using single-photon avalanche diode arrays

Variational learning can tame the inherent chaos of nanoscale devices, paving the way for practical, larger-scale probabilistic computers.

Ziyad Alsawidan, Abdelrahman S. Abdelrahman, Md Sakibur Sajal +9

Architecture Design (Transformers, SSMs, MoE)Distributed Systems & Hardware Training Efficiency & Optimization

Search

Tathagata Srimani

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)