collaborators

6 papers

cs.LG2025

TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation

Jaeho Kim, Seulki Lee

Unsupervised domain adaptation (UDA) for time series data remains a critical challenge in deep learning, with traditional pseudo-labeling strategies failing to capture temporal pat…

cs.AI2025

Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards

Jaeho Kim, Yunseok Lee, Seulki Lee

The peer review process in major artificial intelligence (AI) conferences faces unprecedented challenges with the surge of paper submissions (exceeding 10,000 submissions per venue…

cs.CV2025

On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices

Bosung Kim, Kyuhwan Lee, Isu Jeong +3

We present On-device Sora, the first model training-free solution for diffusion-based on-device text-to-video generation that operates efficiently on smartphone-grade devices. To a…

cs.CV2025

On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices

Bosung Kim, Kyuhwan Lee, Isu Jeong +3

We present On-device Sora, the first model training-free solution for diffusion-based on-device text-to-video generation that operates efficiently on smartphone-grade devices. To a…

cs.LG2024

SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization

Kwangryeol Park, Seulki Lee

We propose SMMF (Square-Matricized Momentum Factorization), a memory-efficient optimizer that reduces the memory requirement of the widely used adaptive learning rate optimizers, s…

cs.CV2024

Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks

Jaewook Lee, Yoel Park, Seulki Lee

In this paper, we introduce a memory-efficient CNN (convolutional neural network), which enables resource-constrained low-end embedded and IoT devices to perform on-device vision t…