Systems.ai
Overview
Building high-performance, scalable AI infrastructure: distributed and federated learning, hardware–software co-design, runtime optimization, and system reliability to support next-generation AI workloads.
Location
KR2
Principal Investigators
Recent Publications
-
In defense of parameter sharing for model-compression
Aditya Desai, Anshumali Shrivastava
International Conference on Learning Representations (ICLR) · 2024
-
Speeding up NAS with Adaptive Subset Selection
Vishak Prasad C, Colin White, Paarth Jain, Sibasis Nayak, Ganesh Ramakrishnan
International Conference on Automated Machine Learning — Methods Track (AutoML) · 2024
-
SS1: Accelerating Inference with Fast and Expressive Sketch Structured Transform
Kimia Saedi, Aditya Desai, Apoorv Walia, Jihyeong Lee, Keren Zhou, Anshumali Shrivastava
Conference on Neural Information Processing Systems (NeurIPS) · 2024
-
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava
Conference on Neural Information Processing Systems (NeurIPS) · 2023
-
Random Offset Block Embedding (ROBE) for compressed embedding tables in deep learning recommendation systems
Aditya Desai, L. Chou, A. Shrivastava
Conference on Machine Learning and Systems (MLSys) · 2022