4 citations · 5 across the 5 of their papers we have counts for
7 papers
Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation
Daeun Kim, Junwha Hong, Changhun Oh +3
Autoregressive image generation has emerged as a paradigm for multimodal AI systems due to its compatibility with transformer-based LLM serving infrastructures. However, generating…
Isotropic Embedding Perturbations for Robust Vision Language Encoders
Hyesong Choi, Daeun Kim, Song Park +5
Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandErase, and DropPath, offer stro…
Comparison of Image Processing Models in Quark Gluon Jet Classification
Daeun Kim, Jiwon Lee, Wonjun Jeong +6
Quark-gluon discrimination provides a useful test case for studying how different machine-learning architectures learn the spatial structure of QCD radiation. In this work, we comp…
Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse
Jinwoo Hwang, Daeun Kim, Sangyeop Lee +8
Recently, Video-Language Models (VideoLMs) have demonstrated remarkable capabilities, offering significant potential for flexible and powerful video query systems. These models typ…
MixDiT: Accelerating Image Diffusion Transformer Inference with Mixed-Precision MX Quantization
Daeun Kim, Jinwoo Hwang, Changhun Oh +1
Diffusion Transformer (DiT) has driven significant progress in image generation tasks. However, DiT inferencing is notoriously compute-intensive and incurs long latency even on dat…
Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models
Hyesong Choi, Daeun Kim, Sungmin Cha +2
In this work, we dive deep into the impact of additive noise in pre-training deep networks. While various methods have attempted to use additive noise inspired by the success of la…
CoVA: Exploiting Compressed-Domain Analysis to Accelerate Video Analytics
Jinwoo Hwang, Minsu Kim, Daeun Kim +5
Modern retrospective analytics systems leverage cascade architecture to mitigate bottleneck for computing deep neural networks (DNNs). However, the existing cascades suffer two lim…