# EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning

arXiv: https://arxiv.org/abs/2210.07795 · HTML: https://mlsanity.com/paper/2210.07795/

## Key facts

- Cited by 56 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 65 of its 83 references that are in the map.
- First posted on arXiv 14 Oct 2022.

## Placed in

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

## Builds on (most cited first, 30 of 65)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)

## Built on by (most cited first, 30 of 56)

- [Vision-Language Foundation Models as Effective Robot Imitators](https://mlsanity.com/paper/2311.01378/) (2023)
- [EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models](https://mlsanity.com/paper/2506.10100/) (2025)
- [MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation](https://mlsanity.com/paper/2503.20384/) (2025)
- [V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models](https://mlsanity.com/paper/2408.09251/) (2024)
- [CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers](https://mlsanity.com/paper/2305.17455/) (2023)
- [Efficient Agents: Building Effective Agents While Reducing Cost](https://mlsanity.com/paper/2508.02694/) (2025)
- [MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric](https://mlsanity.com/paper/2403.07839/) (2024)
- [FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance](https://mlsanity.com/paper/2501.02430/) (2025)
- [Vision-Language Models for Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/2502.07855/) (2025)
- [AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention](https://mlsanity.com/paper/2511.18960/) (2025)
- [MIO: A Foundation Model on Multimodal Tokens](https://mlsanity.com/paper/2409.17692/) (2024)
- [Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement](https://mlsanity.com/paper/2412.01282/) (2024)
- [Active Data Curation Effectively Distills Large-Scale Multimodal Models](https://mlsanity.com/paper/2411.18674/) (2024)
- [Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models](https://mlsanity.com/paper/2311.18237/) (2023)
- [MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning](https://mlsanity.com/paper/2404.05621/) (2024)
- [Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models](https://mlsanity.com/paper/2407.11717/) (2024)
- [Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models](https://mlsanity.com/paper/2312.07408/) (2023)
- [UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models](https://mlsanity.com/paper/2505.20154/) (2025)
- [HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models](https://mlsanity.com/paper/2508.00553/) (2025)
- [HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding](https://mlsanity.com/paper/2412.16158/) (2024)
- [Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation](https://mlsanity.com/paper/2504.09480/) (2025)
- [X2-VLM: All-In-One Pre-trained Model For Vision-Language Tasks](https://mlsanity.com/paper/2211.12402/) (2022)
- [MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants](https://mlsanity.com/paper/2507.01887/) (2025)
- [VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models](https://mlsanity.com/paper/2505.17440/) (2025)
- [SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models](https://mlsanity.com/paper/2305.15033/) (2023)
- [VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm](https://mlsanity.com/paper/2512.02700/) (2025)
- [DLIP: Distilling Language-Image Pre-training](https://mlsanity.com/paper/2308.12956/) (2023)
- [Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models](https://mlsanity.com/paper/2309.01479/) (2023)
- [Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data](https://mlsanity.com/paper/2407.10603/) (2024)
- [LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants](https://mlsanity.com/paper/2507.05515/) (2025)

## Abstract (arXiv)

Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and deployment in real-world applications due to space, memory, and latency constraints. In this work, we introduce a distilling then pruning framework to compress large vision-language models into smaller, faster, and more accurate ones. We first shrink the size of a pre-trained large VLM and apply knowledge distillation in the vision-language pre-training stage to obtain a task-agnostic compact VLM. Then we propose a modal-adaptive pruning algorithm to automatically infer the importance of vision and language modalities for different downstream tasks and adaptively remove redundant structures and neurons in different encoders with controllable target sparsity. We apply our framework to train EfficientVLM, a fast and accurate vision-language model consisting of 6 vision layers, 3 text layers, and 3 cross-modal fusion layers, accounting for only 93 million parameters in total, which is 44.3% of the teacher model. EfficientVLM retains 98.4% performance of the teacher model and accelerates its inference speed by 2.2x. EfficientVLM achieves a large absolute improvement over previous SoTA efficient VLMs of similar sizes by a large margin on various vision-language tasks, including VQAv2 (+4.9%), NLVR2 (+5.6%), ITR (R@1 on TR +17.2%, on IR + 15.6% ) and COCO caption generation (CIDEr +6.5), demonstrating a large potential on training lightweight VLMs.