Yu-Jia Hu

This paper proposes SVEET, a framework that requires merely training on a pretrained bidirectional video diffusion model but supports high-quality streaming video editing in an auto-regressive fashion and proposes a decoupled training scheme that explicitly enforces the orthogonality between the optimization directions of video controllability and model causality.

GPTKB 2.0 achieves the unprecedented feat of creating a million-scale knowledge base directly from LLMs, complete with disambiguated entities and relations.

Linear attention models can now achieve SOTA controllable generation performance, thanks to a new gated conditioning module that overcomes the limitations of ControlNet-style approaches.