6 papers · 1 filter
Early Failure Detection and Intervention in Video Diffusion Models
Kwon Byung-Ki, Sohwi Lim, Nam Hyeon-Woo +2
Text-to-video (T2V) diffusion models have rapidly advanced, yet generations still occasionally fail in practice, such as low text-video alignment or low perceptual quality. Since d…
Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching
Wonseok Choi, Sohwi Lim, Nam Hyeon-Woo +4
Instance-level image retrieval aims to find images containing the same object as a given query, despite variations in size, position, or appearance. To address this challenging tas…
RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models
Moon Ye-Bin, Roy Miles, Tae-Hyun Oh +2
Image retouching not only enhances visual quality but also serves as a means of expressing personal preferences and emotions. However, existing learning-based approaches require la…
VLM's Eye Examination: Instruct and Inspect Visual Competency of Vision Language Models
Nam Hyeon-Woo, Moon Ye-Bin, Wonseok Choi +2
Vision language models (VLMs) have shown promising reasoning capabilities across various benchmarks; however, our understanding of their visual perception remains limited. In this…
BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models
Moon Ye-Bin, Nam Hyeon-Woo, Wonseok Choi +1
Vision language models (VLMs) perceive the world through a combination of a visual encoder and a large language model (LLM). The visual encoder, pre-trained on large-scale vision-t…
SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems
Moon Ye-Bin, Nam Hyeon-Woo, Wonseok Choi +3
Data imbalance in training data often leads to biased predictions from trained models, which in turn causes ethical and social issues. A straightforward solution is to carefully cu…