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

arXiv: https://arxiv.org/abs/2610.00973 · HTML: https://mlsanity.com/paper/2610.00973/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://mlsanity.com/paper/1909.07606/) (2019)
- [Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language](https://mlsanity.com/paper/1912.03590/) (2019)
- [Matryoshka Representation Learning](https://mlsanity.com/paper/2205.13147/) (2022)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [Span-based Localizing Network for Natural Language Video Localization](https://mlsanity.com/paper/2004.13931/) (2020)
- [Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking](https://mlsanity.com/paper/2601.04720/) (2026)
- [Query-Dependent Video Representation for Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2303.13874/) (2023)
- [MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs](https://mlsanity.com/paper/2411.02571/) (2024)
- [Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese](https://mlsanity.com/paper/2211.01335/) (2022)
- [Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2305.15023/) (2023)
- [Gemini Embedding: Generalizable Embeddings from Gemini](https://mlsanity.com/paper/2503.07891/) (2025)
- [VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding](https://mlsanity.com/paper/2405.13382/) (2024)
- [K-LITE: Learning Transferable Visual Models with External Knowledge](https://mlsanity.com/paper/2204.09222/) (2022)
- [TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2401.02309/) (2024)
- [TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval](https://mlsanity.com/paper/2409.01156/) (2024)
- [BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos](https://mlsanity.com/paper/2312.00083/) (2023)
- [ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos](https://mlsanity.com/paper/2411.14901/) (2024)
- [Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models](https://mlsanity.com/paper/2509.24365/) (2025)
- [SmartCLIP: Modular Vision-language Alignment with Identification Guarantees](https://mlsanity.com/paper/2507.22264/) (2025)
- [Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding](https://mlsanity.com/paper/2411.16932/) (2024)
- [What Makes a Maze Look Like a Maze?](https://mlsanity.com/paper/2409.08202/) (2024)
- [VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding](https://mlsanity.com/paper/2410.08593/) (2024)
- [Test-time Adaptation for Cross-modal Retrieval with Query Shift](https://mlsanity.com/paper/2410.15624/) (2024)
- [Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective](https://mlsanity.com/paper/2410.12816/) (2024)
- [Unveiling the Mystery of Visual Attributes of Concrete and Abstract Concepts: Variability, Nearest Neighbors, and Challenging Categories](https://mlsanity.com/paper/2410.11657/) (2024)

## Abstract (arXiv)

Science teachers frequently search for documentary excerpts not by describing what appears on screen, but by querying the abstract concepts they intend to teach. This use case exposes a limitation of existing language-based video moment retrieval methods, which typically assume that queries describe observable events, whereas instructional search requires retrieving concrete visual phenomena that instantiate an underlying scientific principle. We study this setting as concept-to-example video retrieval, an abstract-needle-in-a-haystack problem where compact curriculum concepts must be grounded in temporally sparse documentary evidence. To bridge this abstraction gap, we propose Concept-Driven Domain Adaptation (CDDA), a three-stage framework for adapting two-tower vision-language models to concept-level retrieval. CDDA treats concepts as intermediate semantic anchors: it first structures the textual embedding space with textbook and teacher-handbook example-concept pairs, then transfers this concept-aware geometry to documentary visuals under a frozen visual encoder, and finally jointly adapts both encoders with sparse visual concept supervision. From a geometric perspective, this staged alignment reduces text-concept and vision-concept angular gaps, thereby encouraging concept-level adaptation while preserving the pretrained model's concrete image description alignment. On a curated middle-school physics retrieval benchmark, CDDA achieves stronger pedagogically oriented concept retrieval than several competitive multimodal baselines, including Qwen3-VL-Embedding-2B, while maintaining concrete image-text matching after adaptation.