# PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation

arXiv: https://arxiv.org/abs/2403.09192 · HTML: https://mlsanity.com/paper/2403.09192/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 79 of its 106 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Builds on (most cited first, 30 of 79)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)

## Built on by (most cited first, 17 of 17)

- [PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction](https://mlsanity.com/paper/2410.17247/) (2024)
- [NVILA: Efficient Frontier Visual Language Models](https://mlsanity.com/paper/2412.04468/) (2024)
- [TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval](https://mlsanity.com/paper/2409.01156/) (2024)
- [DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding](https://mlsanity.com/paper/2407.08801/) (2024)
- [Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference](https://mlsanity.com/paper/2405.14700/) (2024)
- [YOLO-UniOW: Efficient Universal Open-World Object Detection](https://mlsanity.com/paper/2412.20645/) (2024)
- [Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations](https://mlsanity.com/paper/2507.09500/) (2025)
- [VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models](https://mlsanity.com/paper/2505.17440/) (2025)
- [Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning](https://mlsanity.com/paper/2411.17217/) (2024)
- [Distribution-Aligned Decoding for Efficient LLM Task Adaptation](https://mlsanity.com/paper/2509.15888/) (2025)
- [Quantized Prompt for Efficient Generalization of Vision-Language Models](https://mlsanity.com/paper/2407.10704/) (2024)
- [UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs](https://mlsanity.com/paper/2502.00439/) (2025)
- [Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models](https://mlsanity.com/paper/2503.08019/) (2025)
- [Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation](https://mlsanity.com/paper/2508.03388/) (2025)
- [Dynamic Pyramid Network for Efficient Multimodal Large Language Model](https://mlsanity.com/paper/2503.20322/) (2025)
- [Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models](https://mlsanity.com/paper/2504.08915/) (2025)
- [Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2608.25653/) (2026)

## Abstract (arXiv)

Recently, the scale of transformers has grown rapidly, which introduces considerable challenges in terms of training overhead and inference efficiency in the scope of task adaptation. Existing works, namely Parameter-Efficient Fine-Tuning (PEFT) and model compression, have separately investigated the challenges. However, PEFT cannot guarantee the inference efficiency of the original backbone, especially for large-scale models. Model compression requires significant training costs for structure searching and re-training. Consequently, a simple combination of them cannot guarantee accomplishing both training efficiency and inference efficiency with minimal costs. In this paper, we propose a novel Parallel Yielding Re-Activation (PYRA) method for such a challenge of training-inference efficient task adaptation. PYRA first utilizes parallel yielding adaptive weights to comprehensively perceive the data distribution in downstream tasks. A re-activation strategy for token modulation is then applied for tokens to be merged, leading to calibrated token features. Extensive experiments demonstrate that PYRA outperforms all competing methods under both low compression rate and high compression rate, demonstrating its effectiveness and superiority in maintaining both training efficiency and inference efficiency for large-scale foundation models. Our code is available at https://github.com/THU-MIG/PYRA.