A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Kuan Xing, Ye Wang, Changyi Gan, et al.
Atelier is a shortcut-aware control-state planning framework that improves artist-grounded text-to-image generation by explicitly modeling artistic intent and avoiding canonical style shortcuts.
Wenyi Hong, Ming Ding, Wendi Zheng, et al.
CogVideo is the first large-scale pretrained transformer for text-to-video generation, leveraging a pretrained text-to-image model to achieve state-of-the-art results.
Unknown
This paper introduces Make-a-video, a method for text-to-video generation that leverages text-to-image models and unsupervised video data, achieving state-of-the-art results without paired text-video data.
Unknown
Controlvideo introduces a training-free framework for controllable text-to-video generation by leveraging pre-trained text-to-image models.
Unknown
This paper investigates the broader applicability of compositional diffusion mechanisms, originally designed for long-horizon planning, to long-content generation tasks such as text-to-image.
Debottam Dutta, Jaehoon Hahm, Jianchong Chen, et al.
TILT is a training-free framework that improves compositional text-to-image generation by using a model-intrinsic reward to guide diffusion sampling toward joint concept presence.