Cover Image

Training-Free Efficient Video Generation via Dynamic Token Carving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yuechen, Xing, Jinbo, Xia, Bin, Liu, Shaoteng, Peng, Bohao, Tao, Xin, Wan, Pengfei, Lo, Eric, Jia, Jiaya
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers
by: Zhang, Yuechen, et al.
Published: (2025)

ControlNeXt: Powerful and Efficient Control for Image and Video Generation
by: Peng, Bohao, et al.
Published: (2024)

UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
by: Huang, Jiehui, et al.
Published: (2025)

Prompt Highlighter: Interactive Control for Multi-Modal LLMs
by: Zhang, Yuechen, et al.
Published: (2023)

DreamVE: Unified Instruction-based Image and Video Editing
by: Xia, Bin, et al.
Published: (2025)

Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
by: Li, Yanwei, et al.
Published: (2024)

GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning
by: Mou, Zhun, et al.
Published: (2025)

Scalable Language Model with Generalized Continual Learning
by: Peng, Bohao, et al.
Published: (2024)

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?
by: Qu, Tianyuan, et al.
Published: (2025)

DreamOmni: Unified Image Generation and Editing
by: Xia, Bin, et al.
Published: (2024)

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
by: Tan, Xudong, et al.
Published: (2025)

DreamOmni2: Multimodal Instruction-based Editing and Generation
by: Xia, Bin, et al.
Published: (2025)

LLMGA: Multimodal Large Language Model based Generation Assistant
by: Xia, Bin, et al.
Published: (2023)

Generative Video Propagation
by: Liu, Shaoteng, et al.
Published: (2024)

LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model
by: Yang, Senqiao, et al.
Published: (2023)

VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
by: Liu, Yuqi, et al.
Published: (2025)

KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
by: Song, Baiyang, et al.
Published: (2026)

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
by: Ji, Sihui, et al.
Published: (2025)

DreamOmni3: Scribble-based Editing and Generation
by: Xia, Bin, et al.
Published: (2025)

ConceptCarve: Dynamic Realization of Evidence
by: Caplan, Eylon, et al.
Published: (2025)

VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption
by: Zhong, Tianxiong, et al.
Published: (2025)

A General and Efficient Training for Transformer via Token Expansion
by: Huang, Wenxuan, et al.
Published: (2024)

Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
by: Li, Haodong, et al.
Published: (2026)

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
by: Wang, Chengyao, et al.
Published: (2025)

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
by: Peng, Bohao, et al.
Published: (2024)

GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding
by: Wang, Chengyao, et al.
Published: (2024)

MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens
by: Kim, Youngrae, et al.
Published: (2026)

Enhancing Micro Gesture Recognition for Emotion Understanding via Context-aware Visual-Text Contrastive Learning
by: Li, Deng, et al.
Published: (2024)

RL-GPT: Integrating Reinforcement Learning and Code-as-policy
by: Liu, Shaoteng, et al.
Published: (2024)

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
by: Yang, Senqiao, et al.
Published: (2025)

MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks
by: Li, Jingyao, et al.
Published: (2023)

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
by: Zhu, Haowei, et al.
Published: (2026)

TokenFLEX: Unified VLM Training for Flexible Visual Tokens Inference
by: Hu, Junshan, et al.
Published: (2025)

MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
by: Ji, Sihui, et al.
Published: (2025)

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
by: Zhong, Zhisheng, et al.
Published: (2024)

BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation
by: Wang, Ruotong, et al.
Published: (2025)

StreamGVE: Training-Free Video Editing via Few-Step Streaming Video Generation
by: Jiao, Guanlong, et al.
Published: (2026)

SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation
by: Liu, YaoYang, et al.
Published: (2026)

Training-free and Adaptive Sparse Attention for Efficient Long Video Generation
by: Xia, Yifei, et al.
Published: (2025)

Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing
by: Goel, Raghavv, et al.
Published: (2026)