Adaptive Model Compression (AMC): Saliency-Driven Resource Allocation for Ultra-Low-Power Transformer Inference

• URL: http://arxiv.org/abs/2607.10109v1
• Date: Sat, 11 Jul 2026 04:05:26 GMT
• Title: Adaptive Model Compression (AMC): Saliency-Driven Resource Allocation for Ultra-Low-Power Transformer Inference
• Abstract summary: We propose a saliency-driven framework that dynamically allocates hardware resources based on token importance.<n>AMC achieves a 59.2% reduction in system energy and a 2.24x increase in throughput on 45nm CMOS hardware.<n>This approach effectively extends the battery life of mobile devices by utilizing high-definition compute only where necessary, maintaining robust performance with a marginal 3.6% accuracy trade-off.
• Score: 5.702671649886992
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deploying large-scale transformer models on resource-constrained edge devices remains a challenge due to the high energy and memory overhead inherent in static inference, which processes simple and complex tokens with uniform intensity. To address this, we propose Adaptive Model Compression (AMC), a saliency-driven framework that dynamically allocates hardware resources based on token importance. By implementing a multi-tier architecture, our system identifies critical high-saliency information for full-precision processing while aggressively reducing the rank and bit-width of less significant data. Experimental results demonstrate that AMC achieves a 59.2% reduction in system energy and a 2.24x increase in throughput on 45nm CMOS hardware. This approach effectively extends the battery life of mobile devices by utilizing high-definition compute only where necessary, maintaining robust performance with a marginal 3.6% accuracy trade-off.

Related papers

• Towards Compact Unified Multimodal Tracking: Synergizing Knowledge Distillation with Structural Pruning [80.73561460934809]
  multimodal object tracking has achieved remarkable robustness by leveraging complementary sensor data.<n>We identify the prediction head as a critical but often overlooked efficiency bottleneck.<n>By strategically streamlining the decoder architecture, we unlock the potential for real-time inference.
  arXiv  Detail & Related papers  (2026-08-02T20:41:33Z)
• Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution [69.17533212524447]
  We propose a Difficulty-aware Dynamic Routing ( DDR) strategy that overcomes the rigid, one-size-fits-all processing paradigm.<n>Specifically, we design a difficulty estimator to predict the restoration cost of each input image, enabling automatic assignment to a network of appropriate capacity.<n>Extensive experiments have demonstrated the superior efficiency and effectiveness of the proposed model compared to recent state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-17T07:49:05Z)
• QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks [63.04549067734431]
  Low-bit quantization is widely used to compress super-resolution (SR) models.<n>However, when SR models are pushed to ultra-low precision (2-4 bits), performance can drop sharply.<n>We propose QuantSR+, a unified framework that improves quantization operators, network design, and training optimization.
  arXiv  Detail & Related papers  (2026-05-21T11:38:52Z)
• A Fast and Energy-Efficient Latch-Based Memristive Analog Content-Addressable Memory [0.03262230127283451]
  We introduce a strong-arm latched memristor (SALM) aCAM cell that replaces static voltage division with a dynamic current-race comparator.<n>Compared to 6T2M, SALM reduces read energy by 33% at identical latency while eliminating the gain and crosstalk limitations that prevent 6T2M from scaling to large arrays.
  arXiv  Detail & Related papers  (2026-05-12T09:30:24Z)
• EdgeFlex-Transformer: Transformer Inference for Edge Devices [2.1130318406254074]
  We propose a lightweight yet effective multi-stage optimization pipeline designed to compress and accelerate Vision Transformers (ViTs)<n>Our methodology combines activation profiling, memory-aware pruning, selective mixed-precision execution, and activation-aware quantization (AWQ) to reduce the model's memory footprint without requiring costly retraining or task-specific fine-tuning.<n>Experiments on CIFAR-10 demonstrate that the fully optimized model achieves a 76% reduction in peak memory usage and over 6x lower latency, while retaining or even improving accuracy compared to the original FP32 baseline.
  arXiv  Detail & Related papers  (2025-12-17T21:45:12Z)
• Low Power Vision Transformer Accelerator with Hardware-Aware Pruning and Optimized Dataflow [0.0]
  This paper presents a low power Vision Transformer accelerator, optimized through algorithm-hardware co-design.<n>The model complexity is reduced using hardware-friendly dynamic token pruning without introducing complex mechanisms.<n>We achieve a peak throughput of 1024 GOPS at 1GHz, with an energy efficiency of 2.31 TOPS/W and an area efficiency of 858.61 GOPS/mm2.
  arXiv  Detail & Related papers  (2025-10-16T07:44:42Z)
• EfficientLLM: Efficiency in Large Language Models [64.3537131208038]
  Large Language Models (LLMs) have driven significant progress, yet their growing counts and context windows incur prohibitive compute, energy, and monetary costs.<n>We introduce EfficientLLM, a novel benchmark and the first comprehensive empirical study evaluating efficiency techniques for LLMs at scale.
  arXiv  Detail & Related papers  (2025-05-20T02:27:08Z)
• VAE-based Feature Disentanglement for Data Augmentation and Compression in Generalized GNSS Interference Classification [42.14439854721613]
  We propose variational autoencoders (VAEs) for disentanglement to extract essential latent features that enable accurate classification of interferences.<n>Our proposed VAE achieves a data compression rate ranging from 512 to 8,192 and achieves an accuracy up to 99.92%.
  arXiv  Detail & Related papers  (2025-04-14T13:38:00Z)
• Secure Resource Allocation via Constrained Deep Reinforcement Learning [49.15061461220109]
  We present SARMTO, a framework that balances resource allocation, task offloading, security, and performance.<n>SARMTO consistently outperforms five baseline approaches, achieving up to a 40% reduction in system costs.<n>These enhancements highlight SARMTO's potential to revolutionize resource management in intricate distributed computing environments.
  arXiv  Detail & Related papers  (2025-01-20T15:52:43Z)
• LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization [17.190984773586745]
  Current AR-based visual generation models require substantial computational resources, limiting their applicability on resource-constrained devices. We propose efficient attention mechanism and low-bit quantization method to enhance the efficiency of VAR models while maintaining performance.
  arXiv  Detail & Related papers  (2024-11-26T07:32:36Z)
• Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach [58.57026686186709]
  We introduce the Convolutional Transformer layer (ConvFormer) and propose a ConvFormer-based Super-Resolution network (CFSR) CFSR inherits the advantages of both convolution-based and transformer-based approaches. Experiments demonstrate that CFSR strikes an optimal balance between computational cost and performance.
  arXiv  Detail & Related papers  (2024-01-11T03:08:00Z)
• Improved Transformer for High-Resolution GANs [69.42469272015481]
  We introduce two key ingredients to Transformer to address this challenge. We show in the experiments that the proposed HiT achieves state-of-the-art FID scores of 31.87 and 2.95 on unconditional ImageNet $128 times 128$ and FFHQ $256 times 256$, respectively.
  arXiv  Detail & Related papers  (2021-06-14T17:39:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.