Podcast Episodes
Back to Search
Thompson Sampling Regret Bounds for Logistic Bandits
Dive into the mathematics of decision-making under uncertainty, exploring how Thompson Sampling helps balance exploration and exploitation in online …
1Â year, 6Â months ago
Bi-Level Optimization for Redundant Manipulator Trajectory Optimization
Exploring efficient solutions for robotic arm movement planning using dual-layer optimization - where mathematics meets practical robotics applicatio…
1Â year, 6Â months ago
An end-to-end attention-based approach for learning on graphs
Deep dive into graph neural networks and attention mechanisms, exploring a breakthrough approach that enhances how AI systems understand and learn fr…
1Â year, 6Â months ago
DMRA_ Diffusion Model with Representation Alignment for Protein Inverse Folding
Discover how AI revolutionizes protein engineering through diffusion models and deep learning. Exploring a novel approach to predicting protein sequ…
1Â year, 6Â months ago
Training Jacobians of Neural Networks
Journey into deep learning fundamentals: Exploring how neural networks learn through their Jacobian matrices, and what this reveals about the traini…
1Â year, 6Â months ago
xAI's Colossus_ A Million-GPU Supercomputer
xAI's Colossus_ A Million-GPU Supercomputer
1Â year, 6Â months ago
Situational Awareness_ The Coming Age of Superintelligence
Situational Awareness_ The Coming Age of Superintelligence
1Â year, 7Â months ago
The Return of Pseudoscience in AI
The Return of Pseudoscience in AI
1Â year, 7Â months ago
Surpassing OpenAI's O1_ Distillation and the Bitter Lesson
Surpassing OpenAI's O1_ Distillation and the Bitter Lesson
1Â year, 7Â months ago
Rebooting the Arsenal of Democracy
Rebooting the Arsenal of Democracy
1Â year, 7Â months ago