11 papers
Which Tokens to Merge? Diffusion Dynamics for Efficient Image Generation
SeungJu Cha, Ye-Chan Kim, HyunGee Kim +2
Token merging has emerged as an effective training-free strategy for accelerating diffusion models by reducing redundant token computation while minimizing generation degradation.…
Not Just a Subject: Capturing Adaptive Scene-Specific Variance for Visual Storytelling
SeungJu Cha, Ye-Chan Kim, Kwanyoung Lee +1
Recent advancements in diffusion models have significantly improved text-to-image generation, enabling their application to visual storytelling, where coherent image sequences are…
Beyond Pairwise Repulsion: Collective Diversity via Determinant Maximization in Diffusion Sampling
Kwanyoung Lee, SeungJu Cha, Yebin Ahn +2
Strong guidance in text-to-image (T2I) diffusion models concentrates sampling toward high-density modes of the conditional distribution, collapsing independently sampled noise vect…
Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning
Ye-Chan Kim, Seunghee Choi, SeungJu Cha +4
Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level captions per video. Recent work…
Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generation
Kwanyoung Lee, SeungJu Cha, Yebin Ahn +3
Diffusion-based text-to-image (T2I) models have made remarkable progress in generating photorealistic and semantically rich images. However, when the target concepts lie in low-den…
ADAPT: Attention Driven Adaptive Prompt Scheduling and InTerpolating Orthogonal Complements for Rare Concepts Generation
Kwanyoung Lee, Hyunwoo Oh, SeungJu Cha +2
Generating rare compositional concepts in text-to-image synthesis remains a challenge for diffusion models, particularly for attributes that are uncommon in the training data. Whil…
SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning
Ye-Chan Kim, SeungJu Cha, Si-Woo Kim +3
Weakly-Supervised Dense Video Captioning aims to localize and describe events in videos trained only on caption annotations, without temporal boundaries. Prior work introduced an i…
ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion
Sungho Koh, SeungJu Cha, Hyunwoo Oh +2
Text-to-image diffusion models often exhibit degraded performance when generating images beyond their training resolution. Recent training-free methods can mitigate this limitation…
CatchPhrase: EXPrompt-Guided Encoder Adaptation for Audio-to-Image Generation
Hyunwoo Oh, SeungJu Cha, Kwanyoung Lee +2
We propose CatchPhrase, a novel audio-to-image generation framework designed to mitigate semantic misalignment between audio inputs and generated images. While recent advances in m…
SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
Ye-Chan Kim, SeungJu Cha, Si-Woo Kim +2
Zero-shot domain adaptation is a method for adapting a model to a target domain without utilizing target domain image data. To enable adaptation without target images, existing stu…
VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness
SeungJu Cha, Kwanyoung Lee, Ye-Chan Kim +2
Recent large-scale text-to-image diffusion models generate photorealistic images but often struggle to accurately depict interactions between humans and objects due to their limite…