# From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

arXiv: https://arxiv.org/abs/2310.08825 · HTML: https://mlsanity.com/paper/2310.08825/

## Key facts

- Cited by 98 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 42 of its 52 references that are in the map.
- First posted on arXiv 13 Oct 2023.

## 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 42)

- [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)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [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)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)

## Built on by (most cited first, 30 of 98)

- [TokenPacker: Efficient Visual Projector for Multimodal LLM](https://mlsanity.com/paper/2407.02392/) (2024)
- [Exploring scalable medical image encoders beyond text supervision](https://mlsanity.com/paper/2401.10815/) (2024)
- [Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models](https://mlsanity.com/paper/2404.13013/) (2024)
- [Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models](https://mlsanity.com/paper/2404.07973/) (2024)
- [VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding](https://mlsanity.com/paper/2412.03735/) (2024)
- [Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model](https://mlsanity.com/paper/2312.12423/) (2023)
- [Visual Agents as Fast and Slow Thinkers](https://mlsanity.com/paper/2408.08862/) (2024)
- [Dense Connector for MLLMs](https://mlsanity.com/paper/2405.13800/) (2024)
- [MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models](https://mlsanity.com/paper/2407.12709/) (2024)
- [Diffusion Feedback Helps CLIP See Better](https://mlsanity.com/paper/2407.20171/) (2024)
- [Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models](https://mlsanity.com/paper/2503.17349/) (2025)
- [SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion](https://mlsanity.com/paper/2409.17531/) (2024)
- [Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach](https://mlsanity.com/paper/2412.18108/) (2024)
- [CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology](https://mlsanity.com/paper/2412.12077/) (2024)
- [Libra: Leveraging Temporal Images for Biomedical Radiology Analysis](https://mlsanity.com/paper/2411.19378/) (2024)
- [Interpretable and Testable Vision Features via Sparse Autoencoders](https://mlsanity.com/paper/2502.06755/) (2025)
- [MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding](https://mlsanity.com/paper/2410.11829/) (2024)
- [Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices](https://mlsanity.com/paper/2503.06063/) (2025)
- [Toward Generalizable Forgery Detection and Reasoning](https://mlsanity.com/paper/2503.21210/) (2025)
- [Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models](https://mlsanity.com/paper/2506.02557/) (2025)
- [SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning](https://mlsanity.com/paper/2603.27437/) (2026)
- [USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation](https://mlsanity.com/paper/2406.05271/) (2024)
- [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation](https://mlsanity.com/paper/2604.00892/) (2026)
- [Learning Invariant Visual Representations for Planning with Joint-Embedding Predictive World Models](https://mlsanity.com/paper/2602.18639/) (2026)
- [Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models](https://mlsanity.com/paper/2411.09691/) (2024)
- [RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations](https://mlsanity.com/paper/2412.01826/) (2024)
- [Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models](https://mlsanity.com/paper/2501.01720/) (2025)
- [HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies](https://mlsanity.com/paper/2512.05693/) (2025)
- [Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision](https://mlsanity.com/paper/2410.08209/) (2024)
- [Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks](https://mlsanity.com/paper/2510.02286/) (2025)

## Abstract (arXiv)

Multi-modal Large Language Models (MLLMs) have made significant strides in expanding the capabilities of Large Language Models (LLMs) through the incorporation of visual perception interfaces. Despite the emergence of exciting applications and the availability of diverse instruction tuning data, existing approaches often rely on CLIP or its variants as the visual branch, and merely extract features from the deep layers. However, these methods lack a comprehensive analysis of the visual encoders in MLLMs. In this paper, we conduct an extensive investigation into the effectiveness of different vision encoders within MLLMs. Our findings reveal that the shallow layer features of CLIP offer particular advantages for fine-grained tasks such as grounding and region understanding. Surprisingly, the vision-only model DINO, which is not pretrained with text-image alignment, demonstrates promising performance as a visual branch within MLLMs. By simply equipping it with an MLP layer for alignment, DINO surpasses CLIP in fine-grained related perception tasks. Building upon these observations, we propose a simple yet effective feature merging strategy, named COMM, that integrates CLIP and DINO with Multi-level features Merging, to enhance the visual capabilities of MLLMs. We evaluate COMM through comprehensive experiments on a wide range of benchmarks, including image captioning, visual question answering, visual grounding, and object hallucination. Experimental results demonstrate the superior performance of COMM compared to existing methods, showcasing its enhanced visual capabilities within MLLMs.