5 papers
Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning
Yuxuan Huang, Xingyu Zeng, Tianhang Zheng +1
Released aligned large language models remain vulnerable to malicious downstream finetuning. Existing defenses are largely designed for the fine-tuning-as-a-service (FTaaS) paradig…
A fast reduced order method for linear parabolic inverse source problems
Yuxuan Huang, Yangwen Zhang
In this paper, we propose a novel, computationally efficient reduced order method to solve linear parabolic inverse source problems. Our approach provides accurate numerical soluti…
CMIS-Net: A Cascaded Multi-Scale Individual Standardization Network for Backchannel Agreement Estimation
Yuxuan Huang, Kangzhong Wang, Eugene Yujun Fu +2
Backchannels are subtle listener responses, such as nods, smiles, or short verbal cues like "yes" or "uh-huh," which convey understanding and agreement in conversations. These sign…
Synthesis by Design: Controlled Data Generation via Structural Guidance
Lei Xu, Sirui Chen, Yuxuan Huang +1
Mathematical reasoning remains challenging for LLMs due to complex logic and the need for precise computation. Existing methods enhance LLM reasoning by synthesizing datasets throu…
Orca: Enhancing Role-Playing Abilities of Large Language Models by Integrating Personality Traits
Yuxuan Huang
Large language models has catalyzed the development of personalized dialogue systems, numerous role-playing conversational agents have emerged. While previous research predominantl…