Conference
|
2024 |
LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs
Taeho Kim
International Joint Conference on Artificial Intelligence (IJCAI) 2024, pp.6324-6332 |
|
|
Journal
|
2024 |
Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems
Jemin Lee
IEEE Internet of Things Journal, v.권호미정, pp.1-14 |
0 |
|
Conference
|
2024 |
Visual Preference Inference: An Image Sequence-Based Preference Reasoning in Tabletop Object Manipulation
Joonhyung Lee
International Conference on Robotics and Automation (ICRA) 2024 : Workshop, pp.1-5 |
|
|
Journal
|
2024 |
Performance Analysis of Deep Learning Accelerator for Edge Inference
박시형
전자공학회논문지, v.61, no.1, pp.23-26 |
|
|
Conference
|
2023 |
ACLTuner: A Profiling-Driven Fast Tuning to Optimized Deep Learning Inference
Yongin Kwon
Conference on Neural Information Processing Systems (NeurIPS) 2023 : Workshop, pp.1-12 |
|
|
Journal
|
2023 |
Design and Verification of a Common Interface for Proprietary NPU Code Generation in General-Purpose AI Compilers
이제민
전자공학회논문지, v.60, no.10, pp.29-32 |
|
|
Journal
|
2023 |
Profile-based Optimization for Deep Learning on Heterogeneous Multi-core CPUs
차주형
전자공학회논문지, v.60, no.7, pp.40-49 |
|
|
Journal
|
2023 |
Tensor slicing and optimization for multicore NPUs
Rafael Sousa
Journal of Parallel and Distributed Computing, v.175, pp.66-79 |
2 |
|
Journal
|
2023 |
PartitionTuner: An operator scheduler for deep-learning compilers supporting multiple heterogeneous processing units
Misun Yu
ETRI Journal, v.45, no.2, pp.318-328 |
0 |
|
Conference
|
2023 |
A Study on Scheduler for High Throughput in Heterogeneous Computing and Multiple Deep Learning Models
차주형
한국통신학회 종합 학술 발표회 (동계) 2023, pp.1071-1072 |
|
|
Conference
|
2023 |
A Study on the Performance Improvement of Korean Math Word Problem Solving Using Labeled-Edge Information
여상엽
한국통신학회 종합 학술 발표회 (동계) 2023, pp.1063-1064 |
|
|
Conference
|
2022 |
Profiling-based ArmCL Optimal Schedule Search for Single-ISA Heterogeneous Multi-Core Architectures
차주형
대한전자공학회 학술 대회 (추계) 2022, pp.300-304 |
|
|
Conference
|
2022 |
CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution
Taeho Kim
European Conference on Computer Vision (ECCV) 2022 (LNCS 13680), pp.651-667 |
2 |
|
Journal
|
2022 |
Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment
Jemin Lee
Future Generation Computer Systems, v.132, pp.124-135 |
11 |
|
Conference
|
2021 |
Mixed-Precision Quantization via Glow Compiler Extension
이제민
대한임베디드공학회 학술 대회 (추계) 2021, pp.205-207 |
|
|
Conference
|
2021 |
Development of Scalable HLS based Deep Learning Accelerator
권용인
대한임베디드공학회 학술 대회 (추계) 2021, pp.247-249 |
|
|
Conference
|
2021 |
Performance Improvement of Neural-net Computation using Branch-Parallel Execution on Heterogeneous Processing Units
유미선
대한임베디드공학회 학술 대회 (추계) 2021, pp.257-260 |
|
|
Conference
|
2020 |
Accuracy Improvement of Quantized Neural Network Model Based on Operator Fusion for NPU
이제민
대한임베디드공학회 학술 대회 (추계) 2020, pp.1-4 |
|
|
Conference
|
2020 |
An Automatic C/C++ code Generation Framework for Deep Neural Network Deployment on Embedded Devices
유미선
한국 컴퓨터 종합 학술 대회 2020, pp.691-693 |
|
|
Conference
|
2020 |
Performance Improvement by Extending ISA of a HLS Based Deep Learning Accelerator
권용인
IEMEK Symposium on Embedded Technology (ISET) 2020, pp.46-49 |
|
|
Conference
|
2020 |
Profiling-based Graph Partitioning System for Multi-accelerator Deep Learning Compilers
유미선
IEMEK Symposium on Embedded Technology (ISET) 2020, pp.67-70 |
|
|
Conference
|
2020 |
Accelerating the Inference of CNN using Target-Independent Operator Fusion based on the Glow Compiler
이제민
IEMEK Symposium on Embedded Technology (ISET) 2020, pp.64-66 |
|
|
Conference
|
2020 |
Tiling and Scheduling: Machine code optimization for deep learning accelerators
권용인
한국 컴퓨터 종합 학술 대회 2020, pp.1-3 |
|
|
Conference
|
2020 |
Accelerating Object Detection for CPU using the Glow Compiler
이제민
한국 컴퓨터 종합 학술 대회 2020, pp.212-214 |
|
|