Going In Deep On Data | YC Paper Club
Episode details
Episode description
This week's YC Paper Club is focused on data. Three domain experts give talks to break down the challenges and frontiers of training data, benchmarks, and multilingual pre-training. Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs Chapters: 00:00 - Francois Chaubard: Why a whole night about data? 9:51 - Vincent Sunn Chen: The Art & Science of Benchmarking Agents 28:44 - Volo Kuleshov: Inception: Diffusion Language Models for Production 40:26 - Shayne Longpre: ATLAS: Practical Scaling Laws for Multilingual Models
AI summary
YC Paper Club examines challenges in training data, benchmarking, and multilingual pre-training through talks by three domain experts. Vincent Sunn Chen discusses benchmarking agents, while Volo Kuleshov presents diffusion language models for production. Shayne Longpre covers practical scaling laws for multilingual models through ATLAS.
Watch also from the same channel
More episodes from this channel
You might be interested in
