The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
Paper • 2512.19693 • Published • 67
weichenfan
weepiess2383
AI & ML interests
None yet
Recent Activity
liked a model about 3 hours ago
weepiess2383/UAE new activity about 3 hours ago
weepiess2383/UAE:Add pipeline tag and improve model card updated a model 1 day ago
weepiess2383/UAEOrganizations
authored a
paper 3 months ago
authored 3
papers about 1 year ago
Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models
Paper • 2501.08453 • Published • 1
CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
Paper • 2503.18886 • Published • 24
RepVideo: Rethinking Cross-Layer Representation for Video Generation
Paper • 2501.08994 • Published • 15
authored a
paper over 2 years ago