Matryoshka Quantization
21:43
DeepCrossAttention: Supercharging Transformer Residual Connections
18:15
When One LLM Drools, Multi-LLM Collaboration Rules
23:58
Self-Regulation and Requesting Interventions
35:13
Demystifying Long Chain-of-Thought Reasoning in LLMs
31:40
Scaling up Test-Time Compute with Latent Reasoning:A Recurrent Depth Approach
11:02
Stop being your own worst (financial) enemy
1:53:12
The Elegant Math Behind Machine Learning
30:00