Imagen de Portada

Playing with Transformer at 30+ FPS via Next-Frame Diffusion

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheng, Xinle, He, Tianyu, Xu, Jiayi, Guo, Junliang, He, Di, Bian, Jiang
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

VidTok: A Versatile and Open-Source Video Tokenizer
por: Tang, Anni, et al.
Publicado: (2024)

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
por: Wu, Haoyu, et al.
Publicado: (2025)

MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft
por: Guo, Junliang, et al.
Publicado: (2025)

VidTwin: Video VAE with Decoupled Structure and Dynamics
por: Wang, Yuchi, et al.
Publicado: (2024)

InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation
por: Wang, Yuchi, et al.
Publicado: (2024)

Fast Autoregressive Video Generation with Diagonal Decoding
por: Ye, Yang, et al.
Publicado: (2025)

Luminark: Training-free, Probabilistically-Certified Watermarking for General Vision Generative Models
por: Xu, Jiayi, et al.
Publicado: (2026)

Overcoming Semantic Dilution in Transformer-Based Next Frame Prediction
por: Nguyen, Hy, et al.
Publicado: (2025)

Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory
por: Wu, Ruiqi, et al.
Publicado: (2026)

Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
por: Zhang, Wentao, et al.
Publicado: (2024)

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation
por: Inferix Team, et al.
Publicado: (2025)

Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach
por: Li, Jiayang, et al.
Publicado: (2025)

VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction
por: Ji, Longbin, et al.
Publicado: (2026)

Cut2Next: Generating Next Shot via In-Context Tuning
por: He, Jingwen, et al.
Publicado: (2025)

Video-GPT via Next Clip Diffusion
por: Zhuang, Shaobin, et al.
Publicado: (2025)

A Physical Coherence Benchmark for Evaluating Video Generation Models via Optical Flow-guided Frame Prediction
por: Chen, Yongfan, et al.
Publicado: (2025)

GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
por: Zhang, Xinjie, et al.
Publicado: (2024)

Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning
por: Zhang, Yu, et al.
Publicado: (2025)

Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generation
por: Cao, Yushe, et al.
Publicado: (2025)

Siamese Transformer Networks for Few-shot Image Classification
por: Jiang, Weihao, et al.
Publicado: (2024)

PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation
por: Jiang, Liyao, et al.
Publicado: (2024)

Free-Mask: A Novel Paradigm of Integration Between the Segmentation Diffusion Model and Image Editing
por: Gao, Bo, et al.
Publicado: (2024)

Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models
por: Jang, Sangwon, et al.
Publicado: (2025)

DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
por: Zhang, Peng, et al.
Publicado: (2026)

DDPM-MoCo: Advancing Industrial Surface Defect Generation and Detection with Generative and Contrastive Learning
por: He, Yangfan, et al.
Publicado: (2024)

Fostering Video Reasoning via Next-Event Prediction
por: Wang, Haonan, et al.
Publicado: (2025)

Detecting AI-Generated Video via Frame Consistency
por: Ma, Long, et al.
Publicado: (2024)

PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modeling
por: Ji, Haorui, et al.
Publicado: (2024)

Compositional 3D-aware Video Generation with LLM Director
por: Zhu, Hanxin, et al.
Publicado: (2024)

AR4D: Autoregressive 4D Generation from Monocular Videos
por: Zhu, Hanxin, et al.
Publicado: (2025)

DenseFormer: Learning Dense Depth Map from Sparse Depth and Image via Conditional Diffusion Model
por: Yuan, Ming, et al.
Publicado: (2025)

FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
por: Ge, Haonan, et al.
Publicado: (2025)

DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation
por: Cheng, Hanbo, et al.
Publicado: (2024)

Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
por: Wang, Xiaoce, et al.
Publicado: (2026)

Generative Pre-trained Autoregressive Diffusion Transformer
por: Zhang, Yuan, et al.
Publicado: (2025)

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
por: Zou, Chang, et al.
Publicado: (2024)

ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer
por: Han, Zhen, et al.
Publicado: (2024)

Mamba-FETrack: Frame-Event Tracking via State Space Model
por: Huang, Ju, et al.
Publicado: (2024)

GAIS: Frame-Level Gated Audio-Visual Integration with Semantic Variance-Scaled Perturbation for Text-Video Retrieval
por: Yang, Bowen, et al.
Publicado: (2025)

A Retrospective Systematic Study on Hierarchical Sparse Query Transformer-assisted Ultrasound Screening for Early Hepatocellular Carcinoma
por: She, Chaoyin, et al.
Publicado: (2025)