3 papers
cs.AI2025
WeMusic-Agent: Efficient Conversational Music Recommendation via Knowledge Internalization and Agentic Boundary Learning
Wendong Bi, Yirong Mao, Xianglong Liu +4
Personalized music recommendation in conversational scenarios usually requires a deep understanding of user preferences and nuanced musical context, yet existing methods often stru…
cs.CL2025
MuCPT: Music-related Natural Language Model Continued Pretraining
Kai Tian, Yirong Mao, Wendong Bi +2
Large language models perform strongly on general tasks but remain constrained in specialized settings such as music, particularly in the music-entertainment domain, where corpus s…
cs.CL2025
Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities
Hanbin Wang, Xiaoxuan Zhou, Zhipeng Xu +7
This paper introduces Code-Vision, a benchmark designed to evaluate the logical understanding and code generation capabilities of Multimodal Large Language Models (MLLMs). It chall…