Titans: Learning to Memorize at Test Time
1:19:37
Paper: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
1:09:58
MIT Introduction to Deep Learning | 6.S191
1:10:55
LLaMA explained: KV-Cache, Rotary Positional Embedding, RMS Norm, Grouped Query Attention, SwiGLU
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
54:52
BERT explained: Training, Inference, BERT vs GPT/LLamA, Fine tuning, [CLS] token
52:35
Die Rückkehr der Moore | Paradiese aus Menschenhand | ARTE Family
48:46
Direct Preference Optimization (DPO) explained: Bradley-Terry model, log probabilities, math
2:15:13