Upcoming
Past Sessions
28
Feb
Benchmark Design: What Makes a Good LLM Evaluation?
Exploring pitfalls of data contamination, overfitting, and metric selection in modern benchmarks
B
Lecture · 75 min · Recording Available
15
Feb
Scaling Laws & Emergent Behaviors in Large Language Models
Why bigger isn't always better — and when emergence actually happens in neural networks
S
Lecture · 80 min · Recording Available
01
Feb
Mixture of Experts: Architecture, Trade-offs & Real-world Use
A close look at sparse MoE models — how routing works, and why it matters for efficiency
M
Lecture · 70 min · Recording Available
18
Jan
Chain-of-Thought Prompting: Why & When It Works
Dissecting the mechanics of CoT and its relationship with model scale and task structure
C
Lecture · 65 min · Recording Available