# PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models

arXiv: https://arxiv.org/abs/2412.09613 · HTML: https://mlsanity.com/paper/2412.09613/

## Key facts

- Cited by 25 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 121 of its 150 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## 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 121)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [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)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [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)
- [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)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [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)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)

## Built on by (most cited first, 25 of 25)

- [LaViDa: A Large Diffusion Language Model for Multimodal Understanding](https://mlsanity.com/paper/2505.16839/) (2025)
- [Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark](https://mlsanity.com/paper/2504.14693/) (2025)
- [VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding](https://mlsanity.com/paper/2512.12360/) (2025)
- [LensWalk: Agentic Video Understanding by Planning How You See in Videos](https://mlsanity.com/paper/2603.24558/) (2026)
- [VideoNSA: Native Sparse Attention Scales Video Understanding](https://mlsanity.com/paper/2510.02295/) (2025)
- [EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs](https://mlsanity.com/paper/2512.10324/) (2025)
- [EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding](https://mlsanity.com/paper/2606.24422/) (2026)
- [ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling](https://mlsanity.com/paper/2603.22911/) (2026)
- [EarlyTom: Early Token Compression Completes Fast Video Understanding](https://mlsanity.com/paper/2605.30010/) (2026)
- [Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning](https://mlsanity.com/paper/2505.11945/) (2025)
- [Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs](https://mlsanity.com/paper/2605.11605/) (2026)
- [Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction](https://mlsanity.com/paper/2606.24156/) (2026)
- [HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes](https://mlsanity.com/paper/2508.13692/) (2025)
- [MESH -- Understanding Videos Like Human: Measuring Hallucinations in Large Video Models](https://mlsanity.com/paper/2509.08538/) (2025)
- [ZAYA1-VL-8B Technical Report](https://mlsanity.com/paper/2605.08560/) (2026)
- [Multimodal Long Video Modeling Based on Temporal Dynamic Context](https://mlsanity.com/paper/2504.10443/) (2025)
- [Parallel In-context Learning for Large Vision Language Models](https://mlsanity.com/paper/2603.16092/) (2026)
- [Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication](https://mlsanity.com/paper/2608.16192/) (2026)
- [Seeing Beyond Redundancy: Task Complexity's Role in Vision Token Specialization in VLLMs](https://mlsanity.com/paper/2602.06914/) (2026)
- [Prompt-Guided Prefiltering for VLM Image Compression](https://mlsanity.com/paper/2604.00314/) (2026)
- [Zamba2-VL Technical Report](https://mlsanity.com/paper/2606.00390/) (2026)
- [ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs](https://mlsanity.com/paper/2606.00543/) (2026)
- [GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory](https://mlsanity.com/paper/2606.06532/) (2026)
- [Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs](https://mlsanity.com/paper/2609.10355/) (2026)
- [VideoResearcher: Self-Improving Tool Design for Long-Video Understanding](https://mlsanity.com/paper/2609.19664/) (2026)

## Abstract (arXiv)

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing high-performance models usually process images and videos separately with different token compression strategies, limiting the capabilities of combining images and videos. To this end, we extend each image into a "static" video and introduce a unified token compression strategy called Progressive Visual Token Compression (PVC), where the tokens of each frame are progressively encoded and adaptively compressed to supplement the information not extracted from previous frames. Video tokens are efficiently compressed with exploiting the inherent temporal redundancy. Images are repeated as static videos, and the spatial details can be gradually supplemented in multiple frames. PVC unifies the token compressing of images and videos. With a limited number of tokens per frame (64 tokens by default), spatial details and temporal changes can still be preserved. Experiments show that our model achieves state-of-the-art performance across various video understanding benchmarks, including long video tasks and fine-grained short video tasks. Meanwhile, our unified token compression strategy incurs no performance loss on image benchmarks, particularly in detail-sensitive tasks.