3 papers
cs.AR2026
Accelerating Multi-Scale Deformable Attention Using Near-Memory-Processing Architecture
Huize Li, Qinggang Wang, Bing Gao +3
Multi Scale Deformable Attention (MSDAttn) has become a fundamental component in various vision tasks due to its effective multi scale grid sampling (MSGS). However, its reliance o…
cs.AR2025
SCREME: A Scalable Framework for Resilient Memory Design
Fan Li, Mimi Xie, Yanan Guo +2
The continuing advancement of memory technology has not only fueled a surge in performance, but also substantially exacerbate reliability challenges. Traditional solutions have pri…
cs.AR2025
Hybrid Photonic-digital Accelerator for Attention Mechanism
Huize Li, Dan Chen, Tulika Mitra
The wide adoption and substantial computational resource requirements of attention-based Transformers have spurred the demand for efficient hardware accelerators. Unlike digital-ba…