distillation
12 talks
Traditional vs LLM Recommender Systems: Are They Worth It?
PodcastTricks to Fine Tuning
PodcastFrom Rules to Reasoning Engines
Reading groupDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
PodcastLLM Distillation and Compression
Reading groupRAG: The Future of AI Search (and Prompt Engineering)
Reading groupSmall Models, Big Ideas: The Next Frontier in AI
Making LLM Inference Affordable
Foundation Models in the Modern Data Stack
Cost Optimization and Performance
Solving the Last Mile Problem of Foundation Models with Data-Centric AI
PodcastFoundational Models are the Future but...