# ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

arXiv: https://arxiv.org/abs/2405.15738 · HTML: https://mlsanity.com/paper/2405.15738/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 49 of its 54 references that are in the map.
- First posted on arXiv 24 May 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (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)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (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)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (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)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)

## Built on by (most cited first, 26 of 26)

- [MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?](https://mlsanity.com/paper/2408.13257/) (2024)
- [Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models](https://mlsanity.com/paper/2408.15556/) (2024)
- [Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance](https://mlsanity.com/paper/2410.16261/) (2024)
- [MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning](https://mlsanity.com/paper/2409.20566/) (2024)
- [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025)
- [OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text](https://mlsanity.com/paper/2406.08418/) (2024)
- [MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models](https://mlsanity.com/paper/2410.09733/) (2024)
- [MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding](https://mlsanity.com/paper/2410.11829/) (2024)
- [Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG](https://mlsanity.com/paper/2503.01222/) (2025)
- [Law of Vision Representation in MLLMs](https://mlsanity.com/paper/2408.16357/) (2024)
- [Phantom of Latent for Large Language and Vision Models](https://mlsanity.com/paper/2409.14713/) (2024)
- [VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models](https://mlsanity.com/paper/2412.01822/) (2024)
- [Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception](https://mlsanity.com/paper/2509.16944/) (2025)
- [Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning](https://mlsanity.com/paper/2510.01681/) (2025)
- [Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion](https://mlsanity.com/paper/2412.01289/) (2024)
- [Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks](https://mlsanity.com/paper/2505.02413/) (2025)
- [INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model](https://mlsanity.com/paper/2407.16198/) (2024)
- [Attention Guided Alignment in Efficient Vision-Language Models](https://mlsanity.com/paper/2511.17793/) (2025)
- [CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation](https://mlsanity.com/paper/2604.10410/) (2026)
- [Scope: Selective Cross-modal Orchestration of Visual Perception Experts](https://mlsanity.com/paper/2510.12974/) (2025)
- [Recursive Think-Answer Process for LLMs and VLMs](https://mlsanity.com/paper/2603.02099/) (2026)
- [Input-Adaptive Visual Preprocessing for Efficient Fast Vision-Language Model Inference](https://mlsanity.com/paper/2512.20839/) (2025)
- [CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception](https://mlsanity.com/paper/2605.23655/) (2026)
- [ActiveScope: Actively Seeking and Correcting Perception for MLLMs](https://mlsanity.com/paper/2606.24292/) (2026)
- [Towards High-Resolution Visual Perception via Hierarchical Entity Exploration](https://mlsanity.com/paper/2607.00816/) (2026)
- [ConvCue: Complementary Visual Inductive Biases for Vision-Language Models](https://mlsanity.com/paper/2609.34196/) (2026)

## Abstract (arXiv)

High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating excessive visual tokens. However, the redundancy in visual tokens is the key problem as it leads to more substantial compute. To mitigate this issue, we propose ConvLLaVA, which employs ConvNeXt, a hierarchical backbone, as the visual encoder of LMM to replace Vision Transformer (ViT). ConvLLaVA compresses high-resolution images into information-rich visual features, effectively preventing the generation of excessive visual tokens. To enhance the capabilities of ConvLLaVA, we propose two critical optimizations. Since the low-resolution pretrained ConvNeXt underperforms when directly applied on high resolution, we update it to bridge the gap. Moreover, since ConvNeXt's original compression ratio is inadequate for much higher resolution inputs, we train a successive stage to further compress the visual tokens, thereby reducing redundancy. These optimizations enable ConvLLaVA to support inputs of 1536x1536 resolution generating only 576 visual tokens, capable of handling images of arbitrary aspect ratios. Experimental results demonstrate that our method achieves competitive performance with state-of-the-art models on mainstream benchmarks. The ConvLLaVA model series are publicly available at https://github.com/alibaba/conv-llava.