4 papers
Skill-R1: Agent Skill Evolution via Reinforcement Learning
Yash Vishe, Rohan Surana, Xunyi Jiang +8
Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved throu…
CSyMR: Benchmarking Compositional Music Information Retrieval in Symbolic Music Reasoning
Boyang Wang, Yash Vishe, Xin Xu +4
Natural language information needs over symbolic music scores rarely reduce to a single step lookup. Many queries require compositional Music Information Retrieval (MIR) that extra…
WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning
Gagan Mundada, Yash Vishe, Amit Namburi +4
Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, their reasoning abilities in th…
Evaluating Music Context Preservation: A Multi-facet Framework for Music Editing Systems
Yash Vishe, Eric Xue, Xunyi Jiang +4
Music editing plays a vital role in modern music production, with applications in film, broadcasting, and game development. Recent advances in music editing systems have enabled di…