6 papers
Range Asymmetric Numeral Systems-Based Lightweight Intermediate Feature Compression for Split Computing of Deep Neural Networks
Mingyu Sung, Suhwan Im, Vikas Palakonda +1
Split computing distributes deep neural network inference between resource-constrained edge devices and cloud servers but faces significant communication bottlenecks when transmitt…
No Pose Estimation? No Problem: Pose-Agnostic and Instance-Aware Test-Time Adaptation for Monocular Depth Estimation
Mingyu Sung, Hyeonmin Choe, Il-Min Kim +2
Monocular depth estimation (MDE), inferring pixel-level depths in single RGB images from a monocular camera, plays a crucial and pivotal role in a variety of AI applications demand…
Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing
Mingyu Sung, Vikas Palakonda, Suhwan Im +4
Large language models (LLMs) have achieved near-human performance across diverse reasoning tasks, yet their deployment on resource-constrained Internet-of-Things (IoT) devices rema…
Why Should the Server Do It All?: A Scalable, Versatile, and Model-Agnostic Framework for Server-Light DNN Inference over Massively Distributed Clients via Training-Free Intermediate Feature Compression
Mingyu Sung, Suhwan Im, Daeho Bang +3
Modern DNNs often rely on edge-cloud model partitioning (MP), but widely used schemes fix shallow, static split points that underutilize edge compute and concentrate latency and en…
H2-Cache: A Novel Hierarchical Dual-Stage Cache for High-Performance Acceleration of Generative Diffusion Models
Mingyu Sung, Il-Min Kim, Sangseok Yun +1
Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising…
GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?
Mingyu Sung, Seungjae Ham, Kangwoo Kim +4
Image super-resolution(SR) is fundamental to many vision system-from surveillance and autonomy to document analysis and retail analytics-because recovering high-frequency details,…