Jeman Park

Jeman Park

Auto-generated profile, based on publicly available information

Jeman Park

AI Computing Reasearch Laboratory, Electronics and Telecommunications Research Institute

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 May 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
JLJemin Lee
Jemin Lee
YKYongin Kwon
Yongin Kwon
SPSihyeong Park
Sihyeong Park
MYMisun Yu
Misun Yu
JPJeman Park
Jeman Park
HSHwanjun Song
Hwanjun Song
Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation. However, the high computational requirements of ViTs hinder their widespread implementation. To address this issue, researchers have proposed efficient hybrid transformer architectures that combine convolutional and transformer layers with optimized attention computation of linear complexity. Additionally, post-training quantization has been proposed as a means of mitigating computational demands. For mobile devices, achieving optimal acceleration for ViTs necessitates the strategic integration of quantization techniques and efficient hybrid transformer structures. However, no prior investigation has applied quantization to efficient hybrid transformers. In this paper, we discover that applying existing post-training quantization (PTQ) methods for ViTs to efficient hybrid transformers leads to a drastic accuracy drop, attributed to the four following challenges: (i) highly dynamic ranges, (ii) zero-point overflow, (iii) diverse normalization, and (iv) limited model parameters (≤5M). To overcome these challenges, we propose a new post-training quantization method, which is the first to quantize efficient hybrid ViTs (MobileViTv1, MobileViTv2, Mobile-Former, EfficientFormerV1, EfficientFormerV2). We achieve a significant improvement of 17.73% for 8-bit and 29.75% for 6-bit on average, respectively, compared with existing PTQ methods (EasyQuant, FQ-ViT, PTQ4ViT, and RepQ-ViT). We plan to release our code at https://gitlab.com/ones-ai/q-hyvit.


1 March 2015 in Advanced Science Letters
Verified
Journal Article
Closed access
SCSungryung Cho
Sungryung Cho
SCSungmoon Chung
Sungmoon Chung
WLWooyeob Lee
Wooyeob Lee
IJInwhee Joe
Inwhee Joe
JPJeman Park
Jeman Park
WKWontae Kim
Wontae Kim

26 September 2025 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
YKYongin Kwon
Yongin Kwon
JCJoohyoung Cha
Joohyoung Cha
SOSehyeon Oh
Sehyeon Oh
MYMisun Yu
Misun Yu
JPJeman Park
Jeman Park
JLJemin Lee
Jemin Lee
Recent deep learning compilers commonly adopt auto-tuning approaches that search for the optimal kernel configuration in tensor programming from scratch, requiring tens of hours per operation and neglecting crucial optimization factors for parallel computing on asymmetric multicore processors. Meanwhile, hand-optimized inference libraries from hardware vendors provide high performance but lack the flexibility and automation needed for emerging models. To close this gap, we propose Luthier , which significantly narrows the search space by selecting the best kernel from existing inference libraries, and also employs cost model-based profiling to quickly determine the most efficient workload distribution for parallel computing. As a result, Luthier achieves up to 2.0x faster execution on convolution-based vision models and transformer-based language models (BERT, GPT) on both CPUs and GPUs, while reducing average tuning time by 95% compared with ArmNN, AutoTVM, Ansor, ONNXRuntime, and TFLite.

1 January 2015
Verified
Book Chapter
Closed access
PDF file
WLWooyeob Lee
Wooyeob Lee
SCSungmoon Chung
Sungmoon Chung
SCSungryung Cho
Sungryung Cho
IJInwhee Joe
Inwhee Joe
JPJeman Park
Jeman Park