# Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models

arXiv: https://arxiv.org/abs/2312.07408 · HTML: https://mlsanity.com/paper/2312.07408/

## Key facts

- Cited by 11 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 41 of its 48 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## 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 41)

- [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)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT](https://mlsanity.com/paper/1909.05840/) (2019)
- [Prompting Visual-Language Models for Efficient Video Understanding](https://mlsanity.com/paper/2112.04478/) (2021)
- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)
- [CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment](https://mlsanity.com/paper/2203.07190/) (2022)
- [Compressing Visual-linguistic Model via Knowledge Distillation](https://mlsanity.com/paper/2104.02096/) (2021)
- [Improving Image Captioning with Better Use of Captions](https://mlsanity.com/paper/2006.11807/) (2020)
- [EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning](https://mlsanity.com/paper/2210.07795/) (2022)
- [UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers](https://mlsanity.com/paper/2301.13741/) (2023)
- [DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery](https://mlsanity.com/paper/2303.09813/) (2023)
- [Annotation-free Audio-Visual Segmentation](https://mlsanity.com/paper/2305.11019/) (2023)

## Built on by (most cited first, 11 of 11)

- [LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model](https://mlsanity.com/paper/2402.02544/) (2024)
- [FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance](https://mlsanity.com/paper/2501.02430/) (2025)
- [Shifting AI Efficiency From Model-Centric to Data-Centric Compression](https://mlsanity.com/paper/2505.19147/) (2025)
- [Audio-Visual Segmentation via Unlabeled Frame Exploitation](https://mlsanity.com/paper/2403.11074/) (2024)
- [Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training](https://mlsanity.com/paper/2412.00440/) (2024)
- [DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition](https://mlsanity.com/paper/2404.14890/) (2024)
- [Contrast-Unity for Partially-Supervised Temporal Sentence Grounding](https://mlsanity.com/paper/2502.12917/) (2025)
- [DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers](https://mlsanity.com/paper/2602.16968/) (2026)
- [Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization](https://mlsanity.com/paper/2511.01588/) (2025)
- [Squeeze Out Tokens from Sample for Finer-Grained Data Governance](https://mlsanity.com/paper/2503.14559/) (2025)
- [Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation](https://mlsanity.com/paper/2511.01593/) (2025)

## Abstract (arXiv)

Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in real-world scenarios. To achieve acceleration for VLMs, most existing methods focus on the model perspective: pruning, distillation, quantification, but completely overlook the data-perspective redundancy. To fill the overlook, this paper pioneers the severity of data redundancy, and designs one plug-and-play Turbo module guided by information degree to prune inefficient tokens from visual or textual data. In pursuit of efficiency-performance trade-offs, information degree takes two key factors into consideration: mutual redundancy and semantic value. Concretely, the former evaluates the data duplication between sequential tokens; while the latter evaluates each token by its contribution to the overall semantics. As a result, tokens with high information degree carry less redundancy and stronger semantics. For VLMs' calculation, Turbo works as a user-friendly plug-in that sorts data referring to information degree, utilizing only top-level ones to save costs. Its advantages are multifaceted, e.g., being generally compatible to various VLMs across understanding and generation, simple use without retraining and trivial engineering efforts. On multiple public VLMs benchmarks, we conduct extensive experiments to reveal the gratifying acceleration of Turbo, under negligible performance drop.