3 papers
cs.AI2025
ToolForge: A Data Synthesis Pipeline for Multi-Hop Search without Real-World APIs
Hao Chen, Zhexin Hu, Jiajun Chai +7
Training LLMs to invoke tools and leverage retrieved information necessitates high-quality, diverse data. However, existing pipelines for synthetic data generation often rely on te…
cs.AI2025
MedBookVQA: A Systematic and Comprehensive Medical Benchmark Derived from Open-Access Book
Sau Lai Yip, Sunan He, Yuxiang Nie +4
The accelerating development of general medical artificial intelligence (GMAI), powered by multimodal large language models (MLLMs), offers transformative potential for addressing…
cs.CV2024
GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration
Sunan He, Yuxiang Nie, Hongmei Wang +21
Generalist foundation models (GFMs) are renowned for their exceptional capability and flexibility in effectively generalizing across diverse tasks and modalities. In the field of m…