← Search

Jianhua Xu

2 accepted papers

2025

Understanding the Repeat Curse in Large Language Models from a Feature Perspective

ACL 2025finding

Large language models (LLMs) have made remarkable progress in various domains, yet they often suffer from repetitive text generation, a phenomenon we refer to as the ”Repeat Curse”. While previous studies have proposed decoding strategies to mitigate repetition, the underlying mechanism behind this…

2024

DMKD: Improving Feature-Based Knowledge Distillation for Object Detection Via Dual Masking Augmentation

ICASSP 2024accepted

Recent mainstream masked distillation methods function by reconstructing selectively masked areas of a student network from the feature map of its teacher counterpart. In these methods, the masked regions need to be properly selected, such that reconstructed features encode sufficient discrimination…

Cited by 0SourceScholar