# CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models

arXiv: https://arxiv.org/abs/2412.16869 · HTML: https://mlsanity.com/paper/2412.16869/

## Key facts

- Cited by 3 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 34 of its 41 references that are in the map.
- First posted on arXiv 22 Dec 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 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [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)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [Multi-Modal Hallucination Control by Visual Information Grounding](https://mlsanity.com/paper/2403.14003/) (2024)
- [Making LLaMA SEE and Draw with SEED Tokenizer](https://mlsanity.com/paper/2310.01218/) (2023)
- [ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://mlsanity.com/paper/2312.00784/) (2023)
- [Osprey: Pixel Understanding with Visual Instruction Tuning](https://mlsanity.com/paper/2312.10032/) (2023)
- [AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model](https://mlsanity.com/paper/2309.16058/) (2023)
- [Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models](https://mlsanity.com/paper/2312.06109/) (2023)
- [Fine-Grained Visual Prompting](https://mlsanity.com/paper/2306.04356/) (2023)
- [RegionGPT: Towards Region Understanding Vision Language Model](https://mlsanity.com/paper/2403.02330/) (2024)
- [Kaleido-BERT: Vision-Language Pre-training on Fashion Domain](https://mlsanity.com/paper/2103.16110/) (2021)
- [Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models](https://mlsanity.com/paper/2308.13437/) (2023)
- [FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval](https://mlsanity.com/paper/2005.09801/) (2020)
- [Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs](https://mlsanity.com/paper/2310.00582/) (2023)
- [VCoder: Versatile Vision Encoders for Multimodal Large Language Models](https://mlsanity.com/paper/2312.14233/) (2023)

## Built on by (most cited first, 3 of 3)

- [Adaptive Global and Fine-Grained Perceptual Fusion for MLLM Embeddings Compatible with Hard Negative Amplification](https://mlsanity.com/paper/2602.05729/) (2026)
- [Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models](https://mlsanity.com/paper/2503.18556/) (2025)
- [DGSeg: Dynamic Gating of Semantic-Spatial Guided Predictions for Reasoning Segmentation](https://mlsanity.com/paper/2607.04779/) (2026)

## Abstract (arXiv)

The impressive performance of Large Language Model (LLM) has prompted researchers to develop Multi-modal LLM (MLLM), which has shown great potential for various multi-modal tasks. However, current MLLM often struggles to effectively address fine-grained multi-modal challenges. We argue that this limitation is closely linked to the models' visual grounding capabilities. The restricted spatial awareness and perceptual acuity of visual encoders frequently lead to interference from irrelevant background information in images, causing the models to overlook subtle but crucial details. As a result, achieving fine-grained regional visual comprehension becomes difficult. In this paper, we break down multi-modal understanding into two stages, from Coarse to Fine (CoF). In the first stage, we prompt the MLLM to locate the approximate area of the answer. In the second stage, we further enhance the model's focus on relevant areas within the image through visual prompt engineering, adjusting attention weights of pertinent regions. This, in turn, improves both visual grounding and overall performance in downstream tasks. Our experiments show that this approach significantly boosts the performance of baseline models, demonstrating notable generalization and effectiveness. Our CoF approach is available online at https://github.com/Gavin001201/CoF.