3 papers
cs.LG2026
Echo-LoRA: Parameter-Efficient Fine-Tuning via Cross-Layer Representation Injection
Yihang Peng, Peng Jin, Jie Gong +4
Parameter-efficient fine-tuning (PEFT) has become a practical route for adapting large language models to downstream tasks, with LoRA-style methods being particularly attractive be…
cs.CL2026
HistLens: Mapping Idea Change across Concepts and Corpora
Yi Jing, Weiyun Qiu, Yihang Peng +1
Language change both reflects and shapes social processes, and the semantic evolution of foundational concepts provides a measurable trace of historical and social transformation.…
cs.LG2026
Efficient Personalization of Generative User Interfaces
Yi-Hao Peng, Samarth Das, Jeffrey P. Bigham +1
Generative user interfaces (UIs) create new opportunities to adapt interfaces to individual users on demand, but personalization remains difficult because desirable UI properties a…