by Yanyan Zhao Papers
3 papers found
Conference
How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
Xin Lu, Yanyan Zhao, Si Wei et al.
NEURIPS 2025arXiv:2505.18522
Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
Weixiang Zhao, Xingyu Sui, Yulin Hu et al.
NEURIPS 2025arXiv:2505.15456
13
citations
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
Weixiang Zhao, Jiahe Guo, Yang Deng et al.
NEURIPS 2025spotlightarXiv:2505.15257
1
citations