Speaker
Priya Anand
Lattice Systems
Speaks at
-
Speculative Decoding Beyond Draft Models
September 15, 2026 10:00 · Room 210
Getting speculative-decoding speedups without training and hosting a separate draft model.
-
Data-Efficient Distillation from Mixture-of-Experts Teachers
September 16, 2026 09:00 · Aurora Hall
Compressing a sparse expert model into a dense student without losing calibration.
Priya Anand is a research engineer at Lattice Systems focused on low-latency inference. She has shipped speculative-decoding stacks into production serving billions of tokens a day, and cares deeply about the gap between benchmark speedups and real deployments.