← Search

Mo Zhu

2 accepted papers

2026

Geometry-Aware Dataset Condensation for Diffusion Model Training

ICML 2026poster

Dataset condensation aims to construct compact datasets from real data via synthesis or selection. However, existing approaches are ill-suited for diffusion model training: synthetic data generation often yields low-fidelity samples unsuitable for authentic modeling, while real subset selection typi…

Cited by 0SourceScholar
2025

Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models

AAAI 2025technical

Knowledge distillation (KD) has become a prevalent technique for compressing large language models (LLMs). Existing KD methods are constrained by the need for identical tokenizers (i.e., vocabularies) between teacher and student models, limiting their versatility in handling LLMs of different archit…