How to visualize training dynamics in neural networks
May 1, 2025
Distributional Scaling Laws for Emergent Capabilities
Mar 1, 2025
Sometimes I am a Tree: Data drives fragile hierarchical generalization
Feb 1, 2025
Transcendence: Generative Models Can Outperform The Experts That Train Them
Jan 1, 2024
Causation Does Not Imply Correlation: A Study of Circuit Mechanisms and Model Behaviors
Jan 1, 2024
Attribute Diversity Determines the Systematicity Gap in VQA
Jan 1, 2024
Linear Connectivity Reveals Generalization Strategies
Jan 1, 2023
Delays, Detours, and Forks in the Road: Latent State Models of Training Dynamics
Jan 1, 2023
The MultiBERTs: BERT Reproductions for Robustness Analysis
Jan 1, 2022
Learning Transductions to Test Systematic Compositionality
Jan 1, 2022