Cover Image

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Yang, Sun, Zhicheng, Xu, Kun, Chen, Liwei, Jiang, Hao, Huang, Quzhe, Song, Chengru, Liu, Yuliang, Zhang, Di, Song, Yang, Gai, Kun, Mu, Yadong
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
by: Jin, Yang, et al.
Published: (2023)

Pyramidal Flow Matching for Efficient Video Generative Modeling
by: Jin, Yang, et al.
Published: (2024)

RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
by: Sun, Zhicheng, et al.
Published: (2024)

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations
by: Li, Jinghan, et al.
Published: (2025)

Harder Tasks Need More Experts: Dynamic Routing in MoE Models
by: Huang, Quzhe, et al.
Published: (2024)

Probing Multimodal Large Language Models for Global and Local Semantic Representations
by: Tao, Mingxu, et al.
Published: (2024)

ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation
by: Zhang, Xu, et al.
Published: (2026)

UniVideo: Unified Understanding, Generation, and Editing for Videos
by: Wei, Cong, et al.
Published: (2025)

DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies
by: Song, Wei, et al.
Published: (2025)

UNIC: Unified In-Context Video Editing
by: Ye, Zixuan, et al.
Published: (2025)

Generating Attribute-Aware Human Motions from Textual Prompt
by: Wang, Xinghan, et al.
Published: (2025)

SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation
by: Xu, Xuancheng, et al.
Published: (2025)

3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
by: Fang, Zhixue, et al.
Published: (2026)

Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
by: Liu, Zeyu, et al.
Published: (2026)

VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents
by: Wang, Feng, et al.
Published: (2026)

TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
by: Yao, Linli, et al.
Published: (2026)

TAFormer: A Unified Target-Aware Transformer for Video and Motion Joint Prediction in Aerial Scenes
by: Xu, Liangyu, et al.
Published: (2024)

Towards Scalable Pre-training of Visual Tokenizers for Generation
by: Yao, Jingfeng, et al.
Published: (2025)

Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning
by: Zhang, Long, et al.
Published: (2025)

AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation
by: Wang, Le, et al.
Published: (2025)

VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning
by: Cai, Minghong, et al.
Published: (2025)

Unified Video-Language Pre-training with Synchronized Audio
by: Mo, Shentong, et al.
Published: (2024)

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding
by: Wang, Xiangfeng, et al.
Published: (2025)

Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model
by: He, Xu, et al.
Published: (2024)

TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation
by: Li, Ruineng, et al.
Published: (2025)

GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving
by: Xu, Shaoqing, et al.
Published: (2024)

Video RWKV:Video Action Recognition Based RWKV
by: Yin, Zhuowen, et al.
Published: (2024)

UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation
by: Xu, Yiyan, et al.
Published: (2026)

FullDiT: Multi-Task Video Generative Foundation Model with Full Attention
by: Ju, Xuan, et al.
Published: (2025)

VINO: A Unified Visual Generator with Interleaved OmniModal Context
by: Chen, Junyi, et al.
Published: (2026)

Unified Gas-Kinetic Wave-Particle Method for Multiscale Flow Simulation of Partially Ionized Plasma
by: Pu, Zhigang, et al.
Published: (2024)

Edit-Your-Motion: Space-Time Diffusion Decoupling Learning for Video Motion Editing
by: Zuo, Yi, et al.
Published: (2024)

Wave-Particle Based Multiscale Modeling and Simulation of Non-equilibrium Turbulent Flows
by: Yang, Xiaojian, et al.
Published: (2025)

Wave Particle Turbulent Simulation of Spatially Developing Round Jets Using a Non Equilibrium Transport Model with a Mixing Length Characteristic Time Closure
by: Yang, Xiaojian, et al.
Published: (2026)

MEDN: Motion-Emotion Feature Decoupling Network for Micro-Expression Recognition
by: Hu, Chenxing, et al.
Published: (2026)

Code generation and runtime techniques for enabling data-efficient deep learning training on GPUs
by: Wu, Kun
Published: (2024)

Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
by: Shi, Chengshuai, et al.
Published: (2024)

UDC-VIT: A Real-World Video Dataset for Under-Display Cameras
by: Ahn, Kyusu, et al.
Published: (2025)

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
by: Yao, Linli, et al.
Published: (2025)

Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models
by: Qin, Mengxin, et al.
Published: (2026)