Showing 1–15 of 15 results
/ Date/ Name
Jun 7, 2024The Price of Implicit Bias in Adversarially Robust GeneralizationJan 28, 2022Extracting Finite Automata from RNNs Using State MergingOct 29, 2024Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural NetworksOct 13, 2025How Reinforcement Learning After Next-Token Prediction Facilitates LearningNov 13, 2023On the Robustness of Neural Collapse and the Neural Collapse of RobustnessJul 24, 2022Can we achieve robustness from data alone?Feb 16, 2024The Evolution of Statistical Induction Heads: In-Context Learning Markov ChainsApr 27, 2026Learning to Think from Multiple ThinkersOct 11, 2022What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?Jul 5, 2023Kernels, Data & PhysicsMar 21, 2023A Tale of Two Circuits: Grokking as Competition of Sparse and Dense SubnetworksOct 21, 2024On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization BoundsApr 27, 2024Attacking Bayes: On the Adversarial Robustness of Bayesian Neural NetworksNov 25, 2025OpenApps: Simulating Environment Variations to Measure UI-Agent ReliabilityNov 6, 2020Sparse Approximate Solutions to Max-Plus Equations with Application to Multivariate Convex Regression