Generative Vector Search To Improve Pathology Foundation Models Across Multimodal Vision-language Tasks

Abstract

Retrieval-augmented generation improves large language models by grounding outputs in external knowledge sources, reducing hallucinations and addressing knowledge cutoffs. However, standard embedding-based retrieval fails to capture the complexity of multi-concept queries, particularly in domains like biomedicine, where biological data are inherently high-dimensional. For example,omics datasets, and clinical reports simultaneously exhibit numerous molecular, cellular, and physiological features. We present Stochastic Latent Matching (STHLM), a generative vector search method that samples query-conditioned embeddings from text or image inputs to enhance retrieval performance. Analogous to how Chain-of-Thought reasoning enables language models to "think longer" on complex problems, STHLM allows retrieval systems to "search wider" through iterative sampling. STHLM demonstrates critical improvements over classical vector retrieval across diverse benchmarks, including scientific literature,

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyekvall2025generative

Related papers

• HOMIE: Histopathology Omni-modal Embedding For Pathology Composed Retrieval (2025)0.00
• Look, Imagine And Match: Improving Textual-visual Cross-modal Retrieval With Generative Models (2017)18.52
• Re-ranking The Context For Multimodal Retrieval Augmented Generation (2025)0.00
• A Little More Like This: Text-to-image Retrieval With Vision-language Models Using Relevance Feedback (2025)0.00
• Lvlm-aware Multimodal Retrieval For Rag-based Medical Diagnosis With General-purpose Models (2025)0.00
• Genir: Generative Visual Feedback For Mental Image Retrieval (2025)0.00
• Graph-based Retriever Captures The Long Tail Of Biomedical Knowledge (2024)0.00
• Accurate And Scalable Multimodal Pathology Retrieval Via Attentive Vision-language Alignment (2025)2.26