# InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression

arXiv: https://arxiv.org/abs/2503.21307 · HTML: https://mlsanity.com/paper/2503.21307/

## Key facts

- Cited by 21 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 48 of its 54 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)
- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

## Builds on (most cited first, 30 of 48)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [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)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [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)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [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)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [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)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)

## Built on by (most cited first, 21 of 21)

- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO](https://mlsanity.com/paper/2505.16673/) (2025)
- [LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models](https://mlsanity.com/paper/2507.02279/) (2025)
- [Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts](https://mlsanity.com/paper/2505.21079/) (2025)
- [Thinking with Images as Continuous Actions: Numerical Visual Chain-of-Thought](https://mlsanity.com/paper/2602.23959/) (2026)
- [EventFlash: Towards Efficient MLLMs for Event-Based Vision](https://mlsanity.com/paper/2602.03230/) (2026)
- [Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?](https://mlsanity.com/paper/2506.10912/) (2025)
- [Drive-P2D: A Progressive Perception-to-Decision Benchmark for VLMs in Autonomous Driving](https://mlsanity.com/paper/2601.14702/) (2026)
- [V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval](https://mlsanity.com/paper/2602.06034/) (2026)
- [PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval](https://mlsanity.com/paper/2603.01493/) (2026)
- [LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?](https://mlsanity.com/paper/2605.08985/) (2026)
- [Re-purposing SAM into Efficient Visual Projectors for MLLM-Based Referring Image Segmentation](https://mlsanity.com/paper/2509.13676/) (2025)
- [An Efficient Token Compression Framework for Visual Object Tracking](https://mlsanity.com/paper/2605.08329/) (2026)
- [HAP: Head-Adaptive Visual Token Pruning via Cross-Modal Alignment](https://mlsanity.com/paper/2608.23921/) (2026)
- [Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving](https://mlsanity.com/paper/2601.21288/) (2026)
- [ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models](https://mlsanity.com/paper/2602.00946/) (2026)
- [R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?](https://mlsanity.com/paper/2602.03300/) (2026)
- [CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models](https://mlsanity.com/paper/2605.28115/) (2026)
- [CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models](https://mlsanity.com/paper/2608.01644/) (2026)
- [SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding](https://mlsanity.com/paper/2608.05137/) (2026)
- [ENCORE: Entropy-Guided Cropping and Attention Regularization for Robust Vision--Language Understanding](https://mlsanity.com/paper/2608.22996/) (2026)

## Abstract (arXiv)

Most multimodal large language models (MLLMs) treat visual tokens as "a sequence of text", integrating them with text tokens into a large language model (LLM). However, a great quantity of visual tokens significantly increases the demand for computational resources and time. In this paper, we propose InternVL-X, which outperforms the InternVL model in both performance and efficiency by incorporating three visual token compression methods. First, we propose a novel vision-language projector, PVTC. This component integrates adjacent visual embeddings to form a local query and utilizes the transformed CLS token as a global query, then performs point-to-region cross-attention through these local and global queries to more effectively convert visual features. Second, we present a layer-wise visual token compression module, LVTC, which compresses tokens in the LLM shallow layers and then expands them through upsampling and residual connections in the deeper layers. This significantly enhances the model computational efficiency. Futhermore, we propose an efficient high resolution slicing method, RVTC, which dynamically adjusts the number of visual tokens based on image area or length filtering. RVTC greatly enhances training efficiency with only a slight reduction in performance. By utilizing 20% or fewer visual tokens, InternVL-X achieves state-of-the-art performance on 7 public MLLM benchmarks, and improves the average metric by 2.34% across 12 tasks.