[GRPO Explained] DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
25:36
DeepSeek R1 Theory Overview | GRPO + RL + SFT
33:26
ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
37:06
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
24:22
Group Relative Policy Optimization (GRPO) - Formula and Code
18:09
La genialidad del aumento de eficiencia de 57X de DeepSeek [MLA]
37:17
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
29:33