activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation

Junhyuk So, Hyunho Kook, Chaeyeon Jang +1

Autoregressive (AR) modeling has recently emerged as a promising new paradigm in visual generation, but its practical adoption is severely constrained by the slow inference speed o…

cs.CV2025

Grouped Speculative Decoding for Autoregressive Image Generation

Junhyuk So, Juncheol Shin, Hyunho Kook +1

Recently, autoregressive (AR) image models have demonstrated remarkable generative capabilities, positioning themselves as a compelling alternative to diffusion models. However, th…

cs.CV2025

PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models

Junhyuk So, Jiwoong Shin, Chaeyeon Jang +1

Recently, diffusion models have achieved significant advances in vision, text, and robotics. However, they still face slow generation speeds due to sequential denoising processes.…

cs.CV2025

FSPGD: Rethinking Black-box Attacks on Semantic Segmentation

Eun-Sol Park, MiSo Park, Seung Park +1

Transferability, the ability of adversarial examples crafted for one model to deceive other models, is crucial for black-box attacks. Despite advancements in attack methods for sem…

cs.CV2024

Diffusion Model Compression for Image-to-Image Translation

Geonung Kim, Beomsu Kim, Eunhyeok Park +1

As recent advances in large-scale Text-to-Image (T2I) diffusion models have yielded remarkable high-quality image generation, diverse downstream Image-to-Image (I2I) applications h…

cs.CV2024

FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models

Junhyuk So, Jungwon Lee, Eunhyeok Park

The substantial computational costs of diffusion models, especially due to the repeated denoising steps necessary for high-quality image generation, present a major obstacle to the…