PPL
Masaaki Imaizumi
Papers (5)
Anti Mode-Collapse in Mean-Field Transformer via Auxiliary VariablesExtended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax OptimalityTraining-Induced Escape from Token Clustering in a Mean-Field Formulation of TransformersSpectrum-Adaptive Generalization Bounds for Trained Deep TransformersCITE: Anytime-Valid Statistical Inference in LLM Self-Consistency