Entity · paper

Appearance Pointers -- Multimodal Region Control of Diffusion Transformers

paperactiveprovisionalappearance-pointers-multimodal-region-control-of-diffusion-transformers-d18d57a5·1 events·first seen Jul 22, 2026

Aliases: Appearance Pointers -- Multimodal Region Control of Diffusion Transformers

Co-occurring entities

Linear Diffusion Transformer

More like this (12)

Sparse-structure Multimodal Diffusion Transformer Conditional Diffusion Transformer MDTransformer Representation-Conditioned Diffusion Models Signed-Permutation Coordinate Transport for RMSNorm Transformers Sequentially-Controlled Interactive Multi-Particle Flow-Maps Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers Phi4-Multimodal Variable-Width Transformers MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities Multimodal Clinical Challenge Point Linear Diffusion Transformer

Recent events (1)

5arXiv · cs.AI·Jul 22, 2026·source ↗

Appearance Pointers: Modality-Agnostic Regional Control for Diffusion Transformers

Researchers introduce 'appearance pointers,' compact tokens that enable precise regional control in Diffusion Transformers (DiTs) by aligning text or image inputs with user-specified spatial masks. A region correspondence network produces these tokens, refined via spatial aggregation, allowing multi-region guidance without retraining the base model or significantly increasing token load. The method claims to be the first modality-agnostic interface for localized multimodal control in DiTs, matching or surpassing modality-specific state-of-the-art methods across evaluated metrics.

Multimodal Progress Linear Diffusion Transformer Appearance Pointers -- Multimodal Region Control of Diffusion Transformers