Pseudo-Labeling for Covariate Shift Adaptation
42:10
Transfer learning for weak-to-strong generalization
1:11:23
How Do Transformers Learn Variable Binding?
30:06
Are Polar Codes Practical?
48:08
Masterclass avec Cédric Villani sur l'Intelligence Artificielle
1:05:42
Matthias Carosi: False vacuum decay beyond the quadratic approximation
1:11:10
How DeepSeek changes the LLM story
1:01:46
More accurate behavioral predictions with hybrid Bayesian-Transformer models
48:01