2 citations · 2 across the 6 of their papers we have counts for
7 papers
Physical AI: A Survey of Models, Learning, Systems, and Open Challenges
Bin Gao, Anuj Gautam, Aritra Bagchi +17
Physical AI aims to enable intelligent systems to perceive, reason, act, and learn through interaction with the physical world. Unlike purely digital intelligence, physical agents…
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…
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…
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…
SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs
Zhenyu Bai, Pranav Dangi, Huize Li +1
Efficiently supporting long context length is crucial for Transformer models. The quadratic complexity of the self-attention computation plagues traditional Transformers. Sliding w…
Accelerating Unstructured SpGEMM using Structured In-situ Computing
Huize Li, Tulika Mitra
Sparse matrix-matrix multiplication (SpGEMM) is a critical kernel widely employed in machine learning and graph algorithms. However, real-world matrices' high sparsity makes SpGEMM…
CPSAA: Accelerating Sparse Attention using Crossbar-based Processing-In-Memory Architecture
Huize Li, Hai Jin, Long Zheng +7
The attention mechanism requires huge computational efforts to process unnecessary calculations, significantly limiting the system's performance. Researchers propose sparse attenti…