3 papers
cs.AI2026
Who Holds the Pen? Let Specifications, Not Agents, Sign Off
Haiqing Li, Xin Ma, Yinhao Wu +7
Large language model agents increasingly combine generation, decision-making, execution, and self-evaluation within a single agentic loop. Although they operate under external spec…
cs.CV2025
Text-Guided Multi-Instance Learning for Scoliosis Screening via Gait Video Analysis
Haiqing Li, Yuzhi Guo, Feng Jiang +5
Early-stage scoliosis is often difficult to detect, particularly in adolescents, where delayed diagnosis can lead to serious health issues. Traditional X-ray-based methods carry ra…
cs.CV2025
Histopathology Multi-modal Embedding for Pathology Composed Retrieval
Qifeng Zhou, Wenliang Zhong, Thao M. Dang +4
To overcome the black-box nature of predictive AI and the hallucination risks of generative models, retrieval-based models offer an interpretable, evidence-based paradigm for patho…