Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers

Kanghyun Baek, Jaihyun Lew, Chaehun Shin, Jungbeom Lee, Sungroh Yoon, in Proceedings of the International Conference on Machine Learning (ICML), Seoul, Korea, July 2026.
preprint link

10 July 2026

Conference

Newer Post Contextualized Visual Personalization in Vision-Language Models Older Post R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning