9 papers
HSF-S: Speed-Optimized Compilation and Acceleration for Hybrid Schrodinger-Feynman Quantum Circuit Emulation
Sechan Park, Kyeongwon Lee, Mundo Jeong +2
Hybrid Schrodinger-Feynman (HSF) simulation offers an attractive memory-path tradeoff for exact quantum-circuit emulation, but its practical runtime is often dominated by exponenti…
CMAX-CAMEL: A Coarse-to-Fine Adaptive, Memory-Efficient, and Low-Power Edge Processor for Contrast Maximization
Kyeongpil Min, Jongin Choi, Kyeongwon Lee +1
Contrast maximization (CMAX) is a direct geometric framework for event-based motion estimation, but its iterative warp-and-accumulate pipeline incurs input-dependent computation an…
SA-Kura: An Energy-Efficient Systolic Array Accelerator for Locally-Coupled Kuramoto Drift in Diffusion Sampling
Jeongmin Jin, Kyeongwon Lee, Mundo Jeong +2
Diffusion inference remains costly for edge deployment, yet existing accelerators focus almost exclusively on score networks because standard drift is merely a trivial linear scali…
TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AI
Kyeongpil Min, Sangmin Jeon, Jae-Jin Lee +1
Cloud-edge AI must jointly satisfy model compression and security under tight device budgets. While Tensor-Train Decomposition (TTD) shrinks on-device models, prior selective-encry…
TT-Edge: A Hardware-Software Co-Design for Energy-Efficient Tensor-Train Decomposition on Edge AI
Hyunseok Kwak, Kyeongwon Lee, Kyeongpil Min +2
The growing demands of distributed learning on resource constrained edge devices underscore the importance of efficient on device model compression. Tensor Train Decomposition (TTD…
LoRA-Edge: Tensor-Train-Assisted LoRA for Practical CNN Fine-Tuning on Edge Devices
Hyunseok Kwak, Kyeongwon Lee, Jae-Jin Lee +1
On-device fine-tuning of CNNs is essential to withstand domain shift in edge applications such as Human Activity Recognition (HAR), yet full fine-tuning is infeasible under strict…