3 papers
cs.LG2026
Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training
Jingwei Zuo, Cong Zeng, Ilyas Chahed +6
The training paradigm of large language models has shifted from traditional one-pass training to multi-epoch training, as reasonable reuse of limited high-quality data can improve…
cs.LG2025
MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics
Bowei Guo, Shengkun Tang, Cong Zeng +1
Diffusion models are renowned for their generative capabilities, yet their pretraining processes exhibit distinct phases of learning speed that have been entirely overlooked in pri…
cs.CL2025
Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
Cong Zeng, Shengkun Tang, Yuanzhou Chen +6
The rapid advancement of large language models (LLMs) such as ChatGPT, DeepSeek, and Claude has significantly increased the presence of AI-generated text in digital communication.…