Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing 事件

Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing arXiv:2605.24674v1 Announce Type: new Abstract: Instruction-based video editing requires transforming a source video according to a natural-language instruction while preserving irrelevant content and remaining temporally coherent. We argue that existing Diffusion Transformer (DiT) editors struggle with this task for two structural reasons. First, conditioning signals are fed undifferentiated into all transformer