AI VIDEOS
Menu

Representation Learning Videos

Videos about how AI systems learn internal features and abstractions from data rather than relying on hand-built rules.

Search the index

Find videos

Showing 1–13 of 13 videos

Clear filters
  1. Yves Raimond in blue and Jacqueline Wood in off-white beside the blue-and-white SPOTIFY'S LLM RECS headline on black.
    Teaching LLMs to Speak Spotify - Yves Raimond & Jacqueline Wood, Spotify
    AI Engineer19m 40s
  2. Devansh Tandon in a blue shirt beside the headline “LLM RECOMMENDERS” on a black background.
    Why LLM Recommenders Will Be AI's Biggest Consumer App - Devansh Tandon, Meta
    AI Engineer18m
  3. Raghav Saboo in a blue shirt beside the headline “DISTILL THE LLM” on a black background.
    Distill the LLM, Don't Serve It: Search & Personalization at DoorDash - Raghav Saboo, DoorDash
    AI Engineer22m 10s
  4. Tim Scarfe and Tom McGrath beside the words Design AI from the Inside
    How Interpretability Can Shape AI from Within
    Machine Learning Street Talk1h 40m
  5. Pierce Freeman, Richard Diehl Martinez, Sophia Kivelson against black with the blue and white headline "CAN AI READ DNA?".
    We Tried Evo Designer: Stanford's Wild New Genomics AI Model
    The Pretrained Pod18m 37s
  6. Sangwu Lee presenting the data and training pipeline behind the Krea 2 image model
    Training Krea 2: What matters in generative model training - Sangwu Lee, Krea.ai
    AI Engineer21m 46s
  7. Bilawal Sidhu beside the headline Video Becomes a World
    Why AI Video Is Becoming a World Simulator
    Bilawal Sidhu8m 14s
  8. Portraits of Tim Scarfe and Matthieu Wyart beside the words Predict Latents
    AI Is Learning at the Wrong Level of Abstraction - Matthieu Wyart
    Machine Learning Street Talk1h 18m
  9. Pierce Freeman, Richard Diehl Martinez, Andrej Karpathy and Yann LeCun above the blue and white headline "FROM AI EXPERIMENTS TO WORLD MODELS" on black.
    Autoresearch, OpenClaw and the Next AI Research Bets
    The Pretrained Pod51m 37s
  10. Pierce Freeman in an off-white shirt gestures beside a smiling Richard Diehl Martinez in blue against black, beneath the white and blue headline 'SEE HOW YOUR MODEL LEARNS'.
    Pico: Building Language Models You Can Analyze During Training
    The Pretrained Pod16m 55s
  11. Pierce Freeman and Richard Diehl Martinez in blue and white tops against black, one touching his chin, alongside the blue and white headline "DEEPSEEK'S NEW BLUEPRINT".
    DeepSeek's New Architectures: mHC, Engram and Conditional Memory
    The Pretrained Pod1h
  12. Pierce Freeman and Richard Diehl Martinez in blue and white tops against black, alongside the blue and white headline "WHY AGENTS CHEAT".
    Why Agents Cheat: Reward Hacking, Fine-Tuning and Model Internals
    The Pretrained Pod1h
  13. Pierce Freeman and Richard Diehl Martinez in blue and white tops against black, alongside the blue and white headline "SMALL MODELS, BIG QUESTIONS".
    Richard Diehl Martinez on Small Models, Learning Dynamics and an AI PhD
    The Pretrained Pod56m 22s