AI RESEARCH

Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier

arXiv CS.CV

ArXi:2603.20382v1 Announce Type: new In practical AI workflows, complex tasks often involve chaining multiple generative models, such as using a video or 3D generation model after a 2D image generator. However, distributional mismatches between the output of upstream models and the expected input of downstream models frequently degrade overall generation quality.