# From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information

arXiv: https://arxiv.org/abs/2401.17981 · HTML: https://mlsanity.com/paper/2401.17981/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 50 of its 84 references that are in the map.
- First posted on arXiv 31 Jan 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 50)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [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)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)

## Built on by (most cited first, 16 of 16)

- [Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models](https://mlsanity.com/paper/2405.15574/) (2024)
- [Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)](https://mlsanity.com/paper/2504.03151/) (2025)
- [ChartThinker: A Contextual Chain-of-Thought Approach to Optimized Chart Summarization](https://mlsanity.com/paper/2403.11236/) (2024)
- [Phantom of Latent for Large Language and Vision Models](https://mlsanity.com/paper/2409.14713/) (2024)
- [Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge](https://mlsanity.com/paper/2407.04681/) (2024)
- [HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks](https://mlsanity.com/paper/2412.17574/) (2024)
- [Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions](https://mlsanity.com/paper/2408.01091/) (2024)
- [DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?](https://mlsanity.com/paper/2505.16915/) (2025)
- [Visual Language Models show widespread visual deficits on neuropsychological tests](https://mlsanity.com/paper/2504.10786/) (2025)
- [ZALM3: Zero-Shot Enhancement of Vision-Language Alignment via In-Context Information in Multi-Turn Multimodal Medical Dialogue](https://mlsanity.com/paper/2409.17610/) (2024)
- [Attention Basin: Why Contextual Position Matters in Large Language Models](https://mlsanity.com/paper/2508.05128/) (2025)
- [Towards Reliable and Interpretable Document Question Answering via VLMs](https://mlsanity.com/paper/2509.10129/) (2025)
- [Intriguing Properties of Large Language and Vision Models](https://mlsanity.com/paper/2410.04751/) (2024)
- [Human-in-the-loop Reasoning For Traffic Sign Detection: Collaborative Approach Yolo With Video-llava](https://mlsanity.com/paper/2410.05096/) (2024)
- [Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts](https://mlsanity.com/paper/2411.13909/) (2024)
- [Ground-Truth Depth in Vision Language Models: Spatial Context Understanding in Conversational AI for XR-Robotic Support in Emergency First Response](https://mlsanity.com/paper/2602.15237/) (2026)

## Abstract (arXiv)

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. Vision detection models excel at recognizing fine-grained image details, prompting researchers to use them to enhance MLLMs. One effective strategy is to infuse detection information in text format, which has proven simple and effective. However, most studies utilize this method without training, leaving the potential of adaptive training largely unexplored. Adaptive training could significantly enhance MLLMs' comprehension of unique inputs while filtering out irrelevant information. This paper addresses the crucial question: How does training impact MLLMs' understanding of infused textual detection information? We systematically experiment with various representative models to evaluate the effects of training-free, retraining, and fine-tuning strategies. We also examine the influence of training on MLLMs' original abilities and the interchangeability of detection models. Our findings indicate that fine-tuning a pre-trained MLLM to incorporate textual detection information delivers superior results compared to training-free and retraining methods, improving performance by 6.71% across 10 widely recognized benchmarks. Furthermore, fine-tuning enables MLLMs to retain performance enhancements even when detection models are swapped, indicating improved understanding of formatted textual data. We release our codes to support further exploration of fusion strategies for vision detection models and the enhancement of MLLMs' fine-grained multimodal capabilities.