Entities · Models
DiT
8 articles tagged with this entity.
-
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
-
Rethinking Conditional Generation for Underwater Salient Object Detection
-
RefAlign: Representation Alignment for Reference-to-Video Generation
-
Making Time Editable in Video Diffusion Transformers
-
PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
-
Improving Visual Representation Alignment Generation with GRPO
-
GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation
-
Chreode: A Cell World Model for One-Step Temporal Dynamics and Perturbation Prediction