4 papers
Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models
Keuntae Kim, Mingyu Kang, Yong Suk Choi
Diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive (AR) LLMs. Recently, this paradigm has been extended to multimodal tasks, leading t…
LogoDiffuser: Training-Free Multilingual Logo Generation and Stylization via Letter-Aware Attention Control
Mingyu Kang, Hyein Seo, Yuna Jeong +2
Recent advances in text-to-image generation have been remarkable, but generating multilingual design logos that harmoniously integrate visual and textual elements remains a challen…
Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
Mingyu Kang, Yong Suk Choi
Text-to-image diffusion models have achieved remarkable success in generating high-quality and diverse images. Building on these advancements, diffusion models have also demonstrat…
Balancing Lexical and Semantic Quality in Abstractive Summarization
Jeewoo Sul, Yong Suk Choi
An important problem of the sequence-to-sequence neural models widely used in abstractive summarization is exposure bias. To alleviate this problem, re-ranking systems have been ap…