structured-attention

PerceptionDLM introduces a multimodal diffusion language model that enables parallel region perception via structured attention masking and efficient prompting, achieving faster inference without sacrificing caption quality. Experiments show competitive performance with substantial speed improvements for multi-region perception tasks.

OneHOI is a unified diffusion transformer framework that consolidates human-object interaction (HOI) generation and editing into a single conditional denoising process using relational modeling and structured attention mechanisms. The approach achieves state-of-the-art results across both HOI generation and editing tasks with support for multiple control modalities.