Imagen de Portada

Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lu, Jiacheng, Zhu, Haoyi, Yi, Sipei, Xie, Enze, Li, Yu, Zhuo, Cheng
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation
por: Xiao, Yang, et al.
Publicado: (2025)

Vid2World: Crafting Video Diffusion Models to Interactive World Models
por: Huang, Siqiao, et al.
Publicado: (2025)

iVideoGPT: Interactive VideoGPTs are Scalable World Models
por: Wu, Jialong, et al.
Publicado: (2024)

Interactive World Simulator for Robot Policy Training and Evaluation
por: Wang, Yixuan, et al.
Publicado: (2026)

Astra: General Interactive World Model with Autoregressive Denoising
por: Zhu, Yixuan, et al.
Publicado: (2025)

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
por: Lin, Shanchuan, et al.
Publicado: (2025)

FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity
por: Tang, Jian, et al.
Publicado: (2026)

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

Face-to-Face: A Video Dataset for Multi-Person Interaction Modeling
por: Chu, Ernie, et al.
Publicado: (2026)

MotionStream: Real-Time Video Generation with Interactive Motion Controls
por: Shin, Joonghyuk, et al.
Publicado: (2025)

Training-Free Test-Time Adaptation with Brownian Distance Covariance in Vision-Language Models
por: Zhang, Yi, et al.
Publicado: (2026)

PAN: A World Model for General, Interactable, and Long-Horizon World Simulation
por: PAN Team, et al.
Publicado: (2025)

SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration
por: Li, Zekun, et al.
Publicado: (2026)

PEEKABOO: Interactive Video Generation via Masked-Diffusion
por: Jain, Yash, et al.
Publicado: (2023)

IPR-1: Interactive Physical Reasoner
por: Zhang, Mingyu, et al.
Publicado: (2025)

LVSA: Training-Free Sparse Attention for Long Video Diffusion
por: Glorian, Gael, et al.
Publicado: (2026)

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
por: Wu, Yecheng, et al.
Publicado: (2024)

Accelerating Diffusion Sampling with Optimized Time Steps
por: Xue, Shuchen, et al.
Publicado: (2024)

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
por: Zhang, Jintao, et al.
Publicado: (2025)

Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model Acceleration
por: Wei, Yuanxin, et al.
Publicado: (2025)

VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs
por: Yuan, Haoran, et al.
Publicado: (2026)

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
por: Pan, Zizheng, et al.
Publicado: (2024)

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
por: Pan, Jiayi, et al.
Publicado: (2025)

SceneFoundry: Generating Interactive Infinite 3D Worlds
por: Chen, ChunTeng, et al.
Publicado: (2026)

SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models
por: Lu, Mingyu, et al.
Publicado: (2026)

$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
por: Santos, Saul, et al.
Publicado: (2025)

Learning to Generate Rigid Body Interactions with Video Diffusion Models
por: Romero, David, et al.
Publicado: (2025)

db-SP: Accelerating Sparse Attention for Visual Generative Models with Dual-Balanced Sequence Parallelism
por: Chen, Siqi, et al.
Publicado: (2025)

Streamlined Photoacoustic Image Processing with Foundation Models: A Training-Free Solution
por: Deng, Handi, et al.
Publicado: (2024)

Training-Free Multi-View Extension of IC-Light for Textual Position-Aware Scene Relighting
por: Ye, Jiangnan, et al.
Publicado: (2025)

WorldCache: Content-Aware Caching for Accelerated Video World Models
por: Nawaz, Umair, et al.
Publicado: (2026)

AVID: Adapting Video Diffusion Models to World Models
por: Rigter, Marc, et al.
Publicado: (2024)

WorldEval: World Model as Real-World Robot Policies Evaluator
por: Li, Yaxuan, et al.
Publicado: (2025)

Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality
por: Xu, Yuan, et al.
Publicado: (2025)

InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
por: Huang, Zhe, et al.
Publicado: (2024)

Scaling Face Interaction Graph Networks to Real World Scenes
por: Lopez-Guevara, Tatiana, et al.
Publicado: (2024)

VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
por: Li, Xinhao, et al.
Publicado: (2024)

Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling
por: Qi, Han, et al.
Publicado: (2025)

Training-Free Acceleration of ViTs with Delayed Spatial Merging
por: Heo, Jung Hwan, et al.
Publicado: (2023)

WorldPack: Compressed Memory Improves Spatial Consistency in Video World Modeling
por: Oshima, Yuta, et al.
Publicado: (2025)