NEW: Better In-Context Learning ICL, Improved RAG (Harvard)
18:42
NEW Knowledge Graph based RAG: SimGRAG (no training)
29:27
Dirichlet Energy Minimization Explains In-Context Learning (Harvard)
16:28
AMAZING DeepSeek R1-Distill-Qwen-32B Reasoning SLM explained
22:09
NEW: Multi-Agent Fine-Tuning (MIT, Harvard, Stanford, DeepMind)
12:42
QUBIC - AGI Scientific Whitepaper Summary AI AIGarth
24:09
The Dark Matter of AI [Mechanistic Interpretability]
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
33:29