Concept Driven Domain Adaptation: Finding an Abstract Needle in a Haystack

The paper introduces Concept-Driven Domain Adaptation (CDDA), a three-stage framework that adapts vision‑language models for concept‑to‑example video retrieval in educational settings. CDDA first structures textual embeddings using textbook and teacher‑handbook concept pairs, then transfers this geometry to documentary visuals with a frozen visual encoder, and finally jointly fine‑tunes both encoders with sparse visual concept supervision. On a middle‑school physics benchmark, CDDA outperforms several multimodal baselines in retrieving concept‑driven moments while preserving concrete image‑text alignment.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• llms
• rag
• fine-tuning
• multimodal
• benchmarks
• safety