5 papers
Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
Changming Li, Kaixing Zhang, Haoyun Xu +4
Large language models (LLMs) demonstrate strong reasoning abilities in solving complex real-world problems. Yet, the internal mechanisms driving these complex reasoning behaviors r…
The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
Zichen Wen, Jiashu Qu, Zhaorun Chen +13
Diffusion-based large language models (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs, offering faster inference and greater interactivity via parall…
MedCT: A Clinical Terminology Graph for Generative AI Applications in Healthcare
Ye Chen, Dongdong Huang, Haoyun Xu +5
We introduce the world's first clinical terminology for the Chinese healthcare community, namely MedCT, accompanied by a clinical foundation model MedBERT and an entity linking mod…
An Improved Reversible Data Hiding Algorithm Based on Reconstructed Mapping for PVO-k
Yusen Zhang, Haoyun Xu, Jingwen Li
Reversible Data Hiding (RDH) is a practical and efficient technique for information encryption. Among its methods, the Pixel-Value Ordering (PVO) algorithm and its variants primari…
Let's Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model
Haoyun Xu, Runzhe Zhan, Derek F. Wong +1
Large Language Models (LLMs) are composed of neurons that exhibit various behaviors and roles, which become increasingly diversified as models scale. Recent studies have revealed t…