Institution profile

University of Applied Sciences Western Switzerland

Academic institutioneurope · ch
Official website
Research library71linked papers
Opportunities0open roles
Selected work

Representative Papers

MatrixFlow: System-Accelerator co-design for high-performance transformer applications

Mar 07, 2025

Transformer models face severe acceleration bottlenecks due to their high computational demands and memory bandwidth requirements. Method: This paper proposes MatrixFlow, a hardware–software co-designed architecture featuring a novel loosely coupled systolic array and a dataflow-driven matrix multiplication mechanism, enabling system-level joint optimization of computation, data movement, and memory access. It further introduces a flexible hardware–software mapping algorithm supporting diverse models—including BERT and ViT—and validates the design via full-system gem5 simulation. Contribution/Results: Experiments show that MatrixFlow achieves up to 22× speedup over many-core CPUs, and outperforms state-of-the-art loosely coupled and tightly coupled accelerators by 5× and 8×, respectively. It significantly reduces memory overhead and improves energy efficiency.

1 citationsRead paper

Spatially Adaptive Noise Injection

Sep 16, 2026

该研究针对图像生成中噪声注入均匀性问题,提出空间自适应噪声注入(SANI)方法,动态调整每个像素的噪声应用,提升生成图像质量。

0 citationsRead paper

Climate Physics Dynamic Matching

Aug 27, 2026

为解决天气预报中物理模型不完整和数据驱动模型黑盒问题,提出ClimPhyDM框架,结合物理先验与数据驱动,在ERA5基准上表现优异。

0 citationsRead paper
Recent publications

Latest Papers

Spatially Adaptive Noise Injection

Sep 16, 2026

该研究针对图像生成中噪声注入均匀性问题,提出空间自适应噪声注入(SANI)方法,动态调整每个像素的噪声应用,提升生成图像质量。

0 citationsRead paper

Climate Physics Dynamic Matching

Aug 27, 2026

为解决天气预报中物理模型不完整和数据驱动模型黑盒问题,提出ClimPhyDM框架,结合物理先验与数据驱动,在ERA5基准上表现优异。

0 citationsRead paper

Symmetry-Breaking De Novo Crystal Generation via Markovian Jump Diffusion

Aug 13, 2026

Existing crystal generation models struggle to capture global symmetry and structural dependencies, often restricting themselves to site symmetry and relying on empirical sampling of space groups. Inspired by spontaneous symmetry breaking, this work proposes a Markov jump diffusion–based generative framework that starts from a minimal symmetry prior and explicitly models dynamic transitions among space groups, enabling a physics-driven evolution of symmetry-breaking processes to generate complete crystal structures end-to-end. By introducing space group transition mechanisms into crystal generation for the first time, the method significantly outperforms symmetry-preserving baselines on the MP20 and MPTS-52 datasets, demonstrating its effectiveness and state-of-the-art performance.

0 citationsRead paper