3 papers
cs.CV2025
Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation
Subin Kim, Sangwoo Mo, Mamshad Nayeem Rizve +4
Achieving precise alignment between user intent and generated visuals remains a central challenge in text-to-visual generation, as a single attempt often fails to produce the desir…
cs.CV2025
Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling
Subin Kim, Seoung Wug Oh, Jui-Hsien Wang +2
While recent advancements in text-to-video diffusion models enable high-quality short video generation from a single prompt, generating real-world long videos in a single pass rema…
cs.LG2024
Querying Easily Flip-flopped Samples for Deep Active Learning
Seong Jin Cho, Gwangsu Kim, Junghyun Lee +2
Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data. One effective selection strat…