# A 28nm 0.22{\\mu}J/token memory-compute-intensity-aware CNN-Transformer accelerator with hybrid-attention-based layer-fusion and cascaded pruning for semantic-segmentation

Source: [A 28nm 0.22{\\mu}J/token memory-compute-intensity-aware CNN-Transformer accelerator with hybrid-attention-based layer-fusion and cascaded pruning for semantic-segmentation](<https://www.sota2.com/research/paper/6948d069423ea42265729e5e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-06T05:00:04.579Z

Authors: Pingcheng Dong, Yonghao Tan, Xuejiao Liu, Peng Luo, Yu Liu, Luhong Liang, Yitong Zhou, Di Pang, Man-To Yung, Dong Zhang, Xijie Huang, Shih-Yang Liu, Yongkun Wu, Fengshi Tian, Chi-Ying Tsui, Fengbin Tu, Kwang-Ting Cheng

Published: 2025-12-19T13:24:06.000Z

## Abstract

This work presents a 28nm 13.93mm2 CNN-Transformer accelerator for semantic segmentation, achieving 3.86-to-10.91x energy reduction over previous designs. It features a hybrid attention unit, layer-fusion scheduler, and cascaded feature-map pruner, with peak energy efficiency of 52.90TOPS/W (INT8).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.17555>)

[PDF](<https://arxiv.org/pdf/2512.17555.pdf>)