Image de couverture de livre

What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lin, Hangyu, Wen, Chao, Xu, Chengming, Gao, Jianxiong, Zhang, Jiangning, Hu, Xiaobin, Fu, Yanwei
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing
par: Huang, Xijie, et autres
Publié: (2026)

FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on
par: Jiang, Boyuan, et autres
Publié: (2024)

ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model
par: Xu, Chengming, et autres
Publié: (2024)

A Generalization Theory of Cross-Modality Distillation with Contrastive Learning
par: Lin, Hangyu, et autres
Publié: (2024)

DiVE: DiT-based Video Generation with Enhanced Control
par: Jiang, Junpeng, et autres
Publié: (2024)

DiT4Edit: Diffusion Transformer for Image Editing
par: Feng, Kunyu, et autres
Publié: (2024)

DiffFAE: Advancing High-fidelity One-shot Facial Appearance Editing with Space-sensitive Customization and Semantic Preservation
par: Wang, Qilin, et autres
Publié: (2024)

Insert Anything: Image Insertion via In-Context Editing in DiT
par: Song, Wensong, et autres
Publié: (2025)

StrandDesigner: Towards Practical Strand Generation with Sketch Guidance
par: Zhang, Na, et autres
Publié: (2025)

Lumina-Video: Efficient and Flexible Video Generation with Multi-scale Next-DiT
par: Liu, Dongyang, et autres
Publié: (2025)

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

Making Your Dreams A Reality: Decoding the Dreams into a Coherent Video Story from fMRI Signals
par: Fu, Yanwei, et autres
Publié: (2025)

S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation
par: Zhao, Lin, et autres
Publié: (2026)

LongVie 2: Multimodal Controllable Ultra-Long Video World Model
par: Gao, Jianxiong, et autres
Publié: (2025)

XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
par: Chen, Bowen, et autres
Publié: (2025)

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
par: Zhou, Zihan, et autres
Publié: (2025)

Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping
par: Zhou, Chao, et autres
Publié: (2026)

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

CustAny: Customizing Anything from A Single Example
par: Kong, Lingjie, et autres
Publié: (2024)

VITON-DiT: Learning In-the-Wild Video Try-On from Human Dance Videos via Diffusion Transformers
par: Zheng, Jun, et autres
Publié: (2024)

DiT-JSCC: Rethinking Deep JSCC with Diffusion Transformers and Semantic Representations
par: Tan, Kailin, et autres
Publié: (2026)

SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment
par: Sun, Yanxiao, et autres
Publié: (2025)

DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training
par: Tan, Xin, et autres
Publié: (2025)

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
par: Lyu, Hengye, et autres
Publié: (2026)

VividPose: Advancing Stable Video Diffusion for Realistic Human Image Animation
par: Wang, Qilin, et autres
Publié: (2024)

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation
par: Yang, Lianwei, et autres
Publié: (2025)

IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment
par: Chen, Yinan, et autres
Publié: (2025)

MaterialPicker: Multi-Modal DiT-Based Material Generation
par: Ma, Xiaohe, et autres
Publié: (2024)

VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models
par: Xiaobin, Hu, et autres
Publié: (2025)

Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
par: Wang, Xiaoce, et autres
Publié: (2026)

Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation
par: Tan, Weipeng, et autres
Publié: (2025)

AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation
par: Wang, Kai, et autres
Publié: (2024)

DiP: Taming Diffusion Models in Pixel Space
par: Chen, Zhennan, et autres
Publié: (2025)

Collaborative Face Experts Fusion in Video Generation: Boosting Identity Consistency Across Large Face Poses
par: Wang, Yuji, et autres
Publié: (2025)

SVFR: A Unified Framework for Generalized Video Face Restoration
par: Wang, Zhiyao, et autres
Publié: (2025)

HiMat: DiT-based Ultra-High Resolution SVBRDF Generation
par: Wang, Zixiong, et autres
Publié: (2025)

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

Modeling Spatiotemporal Neural Frames for High Resolution Brain Dynamic
par: Qu, Wanying, et autres
Publié: (2026)

HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads
par: Xu, Yu, et autres
Publié: (2024)

LaVin-DiT: Large Vision Diffusion Transformer
par: Wang, Zhaoqing, et autres
Publié: (2024)