# Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers

arXiv: https://arxiv.org/abs/2410.14072 · HTML: https://mlsanity.com/paper/2410.14072/

## Key facts

- Cited by 19 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 38 of its 47 references that are in the map.
- First posted on arXiv 17 Oct 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 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [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)
- [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)
- [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)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (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)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [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)
- [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)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [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)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)

## Built on by (most cited first, 19 of 19)

- [VisionZip: Longer is Better but Not Necessary in Vision Language Models](https://mlsanity.com/paper/2412.04467/) (2024)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning](https://mlsanity.com/paper/2507.13348/) (2025)
- [MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention](https://mlsanity.com/paper/2504.16083/) (2025)
- [A Survey of Token Compression for Efficient Multimodal Large Language Models](https://mlsanity.com/paper/2507.20198/) (2025)
- [SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs](https://mlsanity.com/paper/2510.24214/) (2025)
- [AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition](https://mlsanity.com/paper/2512.03794/) (2025)
- [Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping](https://mlsanity.com/paper/2503.21817/) (2025)
- [PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning](https://mlsanity.com/paper/2507.08064/) (2025)
- [The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models](https://mlsanity.com/paper/2412.06646/) (2024)
- [Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs](https://mlsanity.com/paper/2505.19155/) (2025)
- [CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension](https://mlsanity.com/paper/2602.19091/) (2026)
- [HIVTP: A Training-Free Method to Improve VLMs Efficiency via Hierarchical Visual Token Pruning Using Middle-Layer-Based Importance Score](https://mlsanity.com/paper/2509.23663/) (2025)
- [TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens](https://mlsanity.com/paper/2605.16638/) (2026)
- [NanoVLMs: How small can we go and still make coherent Vision Language Models?](https://mlsanity.com/paper/2502.07838/) (2025)
- [Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification](https://mlsanity.com/paper/2601.20742/) (2026)
- [AVA-VLM: Adaptive Visual Attention-Vision Language Model for In-the-Wild Construction Site Monitoring](https://mlsanity.com/paper/2607.05859/) (2026)
- [TDSal: Task-Based Top-Down Saliency Prediction Model](https://mlsanity.com/paper/2607.09827/) (2026)
- [RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection](https://mlsanity.com/paper/2608.04833/) (2026)

## Abstract (arXiv)

Recent advancements in vision-language models (VLMs) have expanded their potential for real-world applications, enabling these models to perform complex reasoning on images. In the widely used fully autoregressive transformer-based models like LLaVA, projected visual tokens are prepended to textual tokens. Oftentimes, visual tokens are significantly more than prompt tokens, resulting in increased computational overhead during both training and inference. In this paper, we propose Visual Compact Token Registers (Victor), a method that reduces the number of visual tokens by summarizing them into a smaller set of register tokens. Victor adds a few learnable register tokens after the visual tokens and summarizes the visual information into these registers using the first few layers in the language tower of VLMs. After these few layers, all visual tokens are discarded, significantly improving computational efficiency for both training and inference. Notably, our method is easy to implement and requires a small number of new trainable parameters with minimal impact on model performance. In our experiment, with merely 8 visual registers--about 1% of the original tokens--Victor shows less than a 4% accuracy drop while reducing the total training time by 43% and boosting the inference throughput by 3.3X.