# CATCH: A Modular Cross-domain Adaptive Template with Hook

arXiv: https://arxiv.org/abs/2510.26582 · HTML: https://mlsanity.com/paper/2510.26582/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 53 of its 93 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 53)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.15647/) (2023)
- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [Machine Learning for Synthetic Data Generation: A Review](https://mlsanity.com/paper/2302.04062/) (2023)
- [A survey on domain adaptation theory: learning bounds and theoretical guarantees](https://mlsanity.com/paper/2004.11829/) (2020)
- [JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation](https://mlsanity.com/paper/2509.22548/) (2025)
- [GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph](https://mlsanity.com/paper/2309.13625/) (2023)
- [MedCoT: Medical Chain of Thought via Hierarchical Expert](https://mlsanity.com/paper/2412.13736/) (2024)
- [DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration](https://mlsanity.com/paper/2411.15692/) (2024)
- [FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval](https://mlsanity.com/paper/2503.21309/) (2025)
- [VisRL: Intention-Driven Visual Perception via Reinforced Reasoning](https://mlsanity.com/paper/2503.07523/) (2025)
- [BALF: Simple and Efficient Blur Aware Local Feature Detector](https://mlsanity.com/paper/2211.14731/) (2022)
- [Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.02899/) (2024)
- [WonderTurbo: Generating Interactive 3D World in 0.72 Seconds](https://mlsanity.com/paper/2504.02261/) (2025)
- [OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation](https://mlsanity.com/paper/2411.18499/) (2024)
- [ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction](https://mlsanity.com/paper/2508.08170/) (2025)
- [FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging](https://mlsanity.com/paper/2507.20016/) (2025)
- [SIFThinker: Spatially-Aware Image Focus for Visual Reasoning](https://mlsanity.com/paper/2508.06259/) (2025)
- [TWIN-GPT: Digital Twins for Clinical Trials via Large Language Model](https://mlsanity.com/paper/2404.01273/) (2024)
- [FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation](https://mlsanity.com/paper/2310.00339/) (2023)
- [SETransformer: A Hybrid Attention-Based Architecture for Robust Human Activity Recognition](https://mlsanity.com/paper/2505.19369/) (2025)
- [ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models](https://mlsanity.com/paper/2507.09876/) (2025)

## Built on by (most cited first, 6 of 6)

- [Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG](https://mlsanity.com/paper/2605.28044/) (2026)
- [Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization](https://mlsanity.com/paper/2607.08057/) (2026)
- [SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation](https://mlsanity.com/paper/2605.18920/) (2026)
- [Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite](https://mlsanity.com/paper/2606.11257/) (2026)
- [Support Thresholds, Not Algorithms, Limit Rare-Association Recovery in Co-Purchase Networks](https://mlsanity.com/paper/2609.20171/) (2026)
- [UniMark: Unified Adaptive Multi-bit Watermarking for Autoregressive Image Generators](https://mlsanity.com/paper/2604.11843/) (2026)

## Abstract (arXiv)

Recent advances in Visual Question Answering (VQA) have demonstrated impressive performance in natural image domains, with models like LLaVA leveraging large language models (LLMs) for open-ended reasoning. However, their generalization degrades significantly when transferred to out-of-domain scenarios such as remote sensing, medical imaging, or math diagrams, due to large distributional shifts and the lack of effective domain adaptation mechanisms. Existing approaches typically rely on per-domain fine-tuning or bespoke pipelines, which are costly, inflexible, and not scalable across diverse tasks. In this paper, we propose CATCH, a plug-and-play framework for cross-domain adaptation that improves the generalization of VQA models while requiring minimal changes to their core architecture. Our key idea is to decouple visual and linguistic adaptation by introducing two lightweight modules: a domain classifier to identify the input image type, and a dual adapter mechanism comprising a Prompt Adapter for language modulation and a Visual Adapter for vision feature adjustment. Both modules are dynamically injected via a unified hook interface, requiring no retraining of the backbone model. Experimental results across four domain-specific VQA benchmarks demonstrate that our framework achieves consistent performance gains without retraining the backbone model, including +2.3 BLEU on MathVQA, +2.6 VQA on MedVQA-RAD, and +3.1 ROUGE on ChartQA. These results highlight that CATCH provides a scalable and extensible approach to multi-domain VQA, enabling practical deployment across diverse application domains.