Reference, context, and preference-based metrics, self-consistency, and catching hallucinations.
The fundamentals of text-to-image generation, relevant papers, and experimenting with DDPM.
Simple baselines, ideas, tech stacks, and packages to try.
Emphasis on bias, more sequential models & bandits, robust offline evaluation, and recsys in the wild.
Examining the broad strokes of NLP progress and comparing between models
Part II of the previous write-up, this time on applications and frameworks of Spark in production
Sharing my notes & practical knowledge from the conference for people who don't have the time.
What I learned about measuring diversity, novelty, surprise, and serendipity from 10+ papers.
Join 5,700+ readers getting updates on machine learning, RecSys, LLMs, and engineering.