# Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation

arXiv: https://arxiv.org/abs/2403.11808 · HTML: https://mlsanity.com/paper/2403.11808/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 84 of its 101 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 30 of 84)

- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)

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

- [Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models](https://mlsanity.com/paper/2405.14297/) (2024)
- [A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs](https://mlsanity.com/paper/2412.03324/) (2024)
- [Shifting AI Efficiency From Model-Centric to Data-Centric Compression](https://mlsanity.com/paper/2505.19147/) (2025)
- [Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios](https://mlsanity.com/paper/2410.17193/) (2024)
- [Recurrent Diffusion for Large-Scale Parameter Generation](https://mlsanity.com/paper/2501.11587/) (2025)
- [Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference](https://mlsanity.com/paper/2405.14700/) (2024)
- [SparseDiT: Token Sparsification for Efficient Diffusion Transformer](https://mlsanity.com/paper/2412.06028/) (2024)
- [ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis](https://mlsanity.com/paper/2411.06959/) (2024)
- [EA-ViT: Efficient Adaptation for Elastic Vision Transformer](https://mlsanity.com/paper/2507.19360/) (2025)
- [RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer](https://mlsanity.com/paper/2509.22323/) (2025)
- [Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance Learning](https://mlsanity.com/paper/2502.21130/) (2025)
- [Neural-Driven Image Editing](https://mlsanity.com/paper/2507.05397/) (2025)
- [Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials](https://mlsanity.com/paper/2511.00833/) (2025)
- [Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for Vision Transformer](https://mlsanity.com/paper/2409.13999/) (2024)
- [FARTrack: Fast Autoregressive Visual Tracking with High Performance](https://mlsanity.com/paper/2602.03214/) (2026)
- [Dynamic Rank Adaptation for Vision-Language Models](https://mlsanity.com/paper/2507.05668/) (2025)
- [AdaRing: Towards Ultra-Light Vision-Language Adaptation via Cross-Layer Tensor Ring Decomposition](https://mlsanity.com/paper/2508.11870/) (2025)
- [Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning](https://mlsanity.com/paper/2511.03245/) (2025)
- [Mechanisms of Non-Monotonic Scaling in Vision Transformers](https://mlsanity.com/paper/2511.21635/) (2025)
- [Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs](https://mlsanity.com/paper/2604.02689/) (2026)
- [Efficient Multi-View 3D Object Detection by Dynamic Token Selection and Fine-Tuning](https://mlsanity.com/paper/2604.13586/) (2026)
- [Spike-NVPT: Learning Robust Visual Prompts via Bio-Inspired Temporal Filtering and Discretization](https://mlsanity.com/paper/2604.18284/) (2026)
- [Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?](https://mlsanity.com/paper/2606.03837/) (2026)
- [Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers](https://mlsanity.com/paper/2608.10989/) (2026)
- [Position Anchor Tuning: Towards Efficient Adaptation of Pre-Trained Point Cloud Transformers](https://mlsanity.com/paper/2609.18056/) (2026)

## Abstract (arXiv)

Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the exploration of enhancing inference efficiency during adaptation remains underexplored. This limits the broader application of pre-trained ViT models, especially when the model is computationally extensive. In this paper, we propose Dynamic Tuning (DyT), a novel approach to improve both parameter and inference efficiency for ViT adaptation. Specifically, besides using the lightweight adapter modules, we propose a token dispatcher to distinguish informative tokens from less important ones, allowing the latter to dynamically skip the original block, thereby reducing the redundant computation during inference. Additionally, we explore multiple design variants to find the best practice of DyT. Finally, inspired by the mixture-of-experts (MoE) mechanism, we introduce an enhanced adapter to further boost the adaptation performance. We validate DyT across various tasks, including image/video recognition and semantic segmentation. For instance, DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.