arXiv (All)
open access
RePair: Turning Retrieval Failures into Counterfactual Hard Pairs
Vision-language retrieval with CLIP-style dual encoders achieves strong cross-modal performance, yet practical accuracy often hinges on localized semantic distinctions where top-ranked near misses differ from the true match by a single critical detail. Hard-sample mining can select confusable candid
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- RePair: Turning Retrieval Failures into Counterfactual Hard Pairs#796831
- Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models#1129887
- Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG#792947
- Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG#788943
- Beyond Patch Removal: Persistent Adversarial Effects in Vision-Language-Action Policies#1014257
Record · ID 798244
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive