3 papers
cs.LG2026
R2V Agent: Teaching SLMs When to Ask for Help
Raghu Vamshi Hemadri, Humaira Firdowse Mohammed, Rishabh Maheshwary +5
Efficient agentic systems should incur expensive frontier-model costs only on decisions where a cheaper local model is likely to fail. Existing LLM cascades usually route whole que…
cs.CL2025
ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval
Ahmed Masry, Megh Thakkar, Patrice Bechard +9
Retrieval-augmented generation has proven practical when models require specialized knowledge or access to the latest data. However, existing methods for multimodal document retrie…
cs.IR2025
Optimizing What Matters: AUC-Driven Learning for Robust Neural Retrieval
Nima Sheikholeslami, Erfan Hosseini, Patrice Bechard +2
Dual-encoder retrievers depend on the principle that relevant documents should score higher than irrelevant ones for a given query. Yet the dominant Noise Contrastive Estimation (N…