Akhilan Boopathy

Towards Permutation Invariant Learning with High-Dimensional Particle Filters

Generalization Aware Minimization

Large Pretraining Datasets Don't Guarantee Robustness after Fine-Tuning

Fast Few-Shot Graph Flow Prediction

Scale-time Equivalence in Neural Network Training

Breaking Neural Network Scaling Laws with Modularity

Permutation Invariant Learning with High-Dimensional Particle Filters

Generalization Aware Minimization

ImageNet-RIB Benchmark: Large Pre-Training Datasets Don't Guarantee Robustness after Fine-Tuning

Fast Few-Shot Graph Flow Prediction

Unified Neural Network Scaling Laws and Scale-time Equivalence