DPO to TPO: Test-Time Preference Optimization (RL)
26:19
Goodbye RAG - Smarter CAG w/ KV Cache Optimization
38:41
FUSION: Knowledge GRAPHS are more than TOOLS for LLM
1:19:37
Paper: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
27:22
AI Is Making You An Illiterate Programmer
48:46
Direct Preference Optimization (DPO) explained: Bradley-Terry model, log probabilities, math
19:11
ULTIMATE Fact Checking AI (Johns Hopkins, Stanford)
28:44
SMARTER: AI Reasoning w Knowledge Graphs + Agents
34:05