Nice to meet you! I am a Computer Science and Engineering PhD student in UC San Diego co-advised by the wonderful Assistant Professor Dan Fu and Associate Professor Yu-Xiang Wang!
Previously, I worked under Dr. Anshumali Shrivastava at Rice University and researched topics including Approximate Nearest Neighbor Search, Large Scale Machine Learning, and Quantization.
I was also a co-founder and AI engineer of xMAD.ai. We aimed to break the neural scaling curve tradeoff between compute and accuracy and create high performance models at a fraction of the compute. We recently have been acquired by Workato.
NeurIPS 2024
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
Tianyi Zhang · Jonah Yi · Bowen Yao · Zhaozhuo Xu · Anshumali Shrivastava
NeurIPS 2024
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
Tianyi Zhang · Jonah Yi · Zhaozhuo Xu · Anshumali Shrivastava
CAPS: A Practical Partition Index for Filtered Similarity Search
Gaurav Gupta · Jonah Yi · Benjamin Coleman · Chen Luo · Vihan Lakshman · Anshumali Shrivastava
Class 12 of OwlSpark
As part of xMAD.ai, I took part in OwlSpark Startup and Small Business Accelerator this summer! I connected with industry leaders, investors and mentors, and did a final presentation at the Eleventh Annual Bayou Startup Showcase!
Here is xMAD.ai's introductory video!