Image de couverture de livre

Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhou, Chao, Wei, Tianyi, Chen, Yiling, Zhou, Wenbo, Yu, Nenghai
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Multimedia
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer
par: Zhu, Rui, et autres
Publié: (2024)

UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
par: Wang, Xiang, et autres
Publié: (2025)

Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study
par: Sun, Xibo, et autres
Publié: (2024)

ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding
par: Zhang, Zhenxing, et autres
Publié: (2024)

Rethinking Multi-view Representation Learning via Distilled Disentangling
par: Ke, Guanzhou, et autres
Publié: (2024)

Untwisting RoPE: Frequency Control for Shared Attention in DiTs
par: Mikaeili, Aryan, et autres
Publié: (2026)

Cross Modal Fine-Grained Alignment via Granularity-Aware and Region-Uncertain Modeling
par: Liu, Jiale, et autres
Publié: (2025)

MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention
par: Wang, Tianyi, et autres
Publié: (2025)

FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing
par: Cai, Lingling, et autres
Publié: (2024)

Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling
par: Zhou, Chao, et autres
Publié: (2025)

DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation
par: Cai, Minghong, et autres
Publié: (2024)

Clean Image May be Dangerous: Data Poisoning Attacks Against Deep Hashing
par: Li, Shuai, et autres
Publié: (2025)

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
par: Tian, Yuchuan, et autres
Publié: (2024)

SpecFLASH: A Latent-Guided Semi-autoregressive Speculative Decoding Framework for Efficient Multimodal Generation
par: Wang, Zihua, et autres
Publié: (2025)

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
par: Chen, Liyang, et autres
Publié: (2025)

CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment
par: Liu, Yating, et autres
Publié: (2025)

Riemann-based Multi-scale Attention Reasoning Network for Text-3D Retrieval
par: Li, Wenrui, et autres
Publié: (2024)

Multi-scale Attention Guided Pose Transfer
par: Roy, Prasun, et autres
Publié: (2022)

Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioning
par: Song, Zijie, et autres
Publié: (2023)

Art2Mus: Artwork-to-Music Generation via Visual Conditioning and Large-Scale Cross-Modal Alignment
par: Rinaldi, Ivan, et autres
Publié: (2026)

Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment
par: Shan, Ziyu, et autres
Publié: (2024)

Regularizing Subspace Redundancy of Low-Rank Adaptation
par: Zhu, Yue, et autres
Publié: (2025)

DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization
par: Nguyen, Ngoc-Son, et autres
Publié: (2026)

Visual Grounding with Multi-modal Conditional Adaptation
par: Yao, Ruilin, et autres
Publié: (2024)

Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attention
par: Song, Shezheng, et autres
Publié: (2026)

Noisy-Correspondence Learning for Text-to-Image Person Re-identification
par: Qin, Yang, et autres
Publié: (2023)

A Hierarchical Compression Technique for 3D Gaussian Splatting Compression
par: Huang, He, et autres
Publié: (2024)

Inclusion 2024 Global Multimedia Deepfake Detection Challenge: Towards Multi-dimensional Face Forgery Detection
par: Zhang, Yi, et autres
Publié: (2024)

DepthGait: Multi-Scale Cross-Level Feature Fusion of RGB-Derived Depth and Silhouette Sequences for Robust Gait Recognition
par: Li, Xinzhu, et autres
Publié: (2025)

ByteNet: Rethinking Multimedia File Fragment Classification through Visual Perspectives
par: Liu, Wenyang, et autres
Publié: (2024)

Signal: Selective Interaction and Global-local Alignment for Multi-Modal Object Re-Identification
par: Liu, Yangyang, et autres
Publié: (2025)

PixCLIP: Achieving Fine-grained Visual Language Understanding via Any-granularity Pixel-Text Alignment Learning
par: Xiao, Yicheng, et autres
Publié: (2025)

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
par: Chow, Wei, et autres
Publié: (2025)

Textured mesh Quality Assessment using Geometry and Color Field Similarity
par: Yang, Kaifa, et autres
Publié: (2025)

PAME: Self-Supervised Masked Autoencoder for No-Reference Point Cloud Quality Assessment
par: Shan, Ziyu, et autres
Publié: (2024)

MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces
par: E, Shaojun, et autres
Publié: (2025)

Transcending Fusion: A Multi-Scale Alignment Method for Remote Sensing Image-Text Retrieval
par: Yang, Rui, et autres
Publié: (2024)

Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding
par: Bao, Guangyin, et autres
Publié: (2024)

ContextBLIP: Doubly Contextual Alignment for Contrastive Image Retrieval from Linguistically Complex Descriptions
par: Lin, Honglin, et autres
Publié: (2024)

POINTS1.5: Building a Vision-Language Model towards Real World Applications
par: Liu, Yuan, et autres
Publié: (2024)