A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
Pixeldit proposes pixel-space diffusion transformers for image generation, eliminating the need for a pretrained autoencoder and its associated information loss.
Xu Wang, Kaixiang Yao, Miao Pan, et al.
Proposes ProVisE, a benchmark-agnostic framework to evaluate spatial cognition in image-generation models by parsing pixel-space outputs into structured predictions, and introduces SpatialGen-Bench for unified comparison with text-output VLMs.