[2606.05011] CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimation
Abstract page for arXiv paper 2606.05011: CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimation
America Forever Bytes
Other
Abstract page for arXiv paper 2606.05011: CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimation
Abstract page for arXiv paper 2606.02581: Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs
Abstract page for arXiv paper 2606.02737: Attention Calibration for Position-Fair Dense Information Retrieval
Abstract page for arXiv paper 2606.02814: Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors
Abstract page for arXiv paper 2606.02245: When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation
Abstract page for arXiv paper 2605.31229: Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval
Abstract page for arXiv paper 2605.29224: Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
Abstract page for arXiv paper 2605.28522: Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability
Abstract page for arXiv paper 2605.28641: Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA
Abstract page for arXiv paper 2605.27951: Beyond Similarity: Task-Aligned Retrieval for Language Models