Talks and presentations
See a map of all the places I've given a talk!
TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
Rio de Janeiro, Brazil
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
Philadelphia, PA, USA
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
Providence, RI, USA
Simple Analysis of Priority Sampling
Alexandria, VA, USA
Accelerating Transformers via Kernel Density Estimation
Honolulu, Hawaii, US
Weighted MinHash for Inner Product Estimation
Seattle, WA, USA
Efficient Approximations for Cache-conscious Data Placement
San Diego, CA, USA (online presentation)
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
New York, NY, USA
View slides