Cover Image

Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jia, Fu, Xiaomeng, Peng, Xurui, Chen, Weifeng, Zheng, Youwei, Zhao, Tianyu, Wang, Jiexi, Chen, Fangmin, Wang, Xing, So, Hayden Kwok-Hay
Format:	Preprint
Published:	2026
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

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

Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models
by: Yan, Chenqian, et al.
Published: (2024)

SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features
by: Wang, Song, et al.
Published: (2023)

A Composable Dynamic Sparse Dataflow Architecture for Efficient Event-based Vision Processing on FPGA
by: Gao, Yizhao, et al.
Published: (2024)

Co-designing a Sub-millisecond Latency Event-based Eye Tracking System with Submanifold Sparse CNN
by: Zhang, Baoheng, et al.
Published: (2024)

Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation
by: Luo, Jiayi, et al.
Published: (2026)

Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion
by: Liu, Songwei, et al.
Published: (2025)

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
by: Mao, Xiaofeng, et al.
Published: (2026)

TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture
by: Wu, Jiajun, et al.
Published: (2024)

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

Model Will Tell: Training Membership Inference for Diffusion Models
by: Fu, Xiaomeng, et al.
Published: (2024)

XL3M: A Training-free Framework for LLM Length Extension Based on Segment-wise Inference
by: Wang, Shengnan, et al.
Published: (2024)

Training-free Stylized Text-to-Image Generation with Fast Inference
by: Ma, Xin, et al.
Published: (2025)

Lifecycle Cost-Effectiveness Modeling for Redundancy-Enhanced Multi-Chiplet Architectures
by: Liu, Zizhen, et al.
Published: (2026)

Training-free Camera Control for Video Generation
by: Hou, Chen, 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)

tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
by: Wang, Chen, et al.
Published: (2026)

Federated Quantum-Train Long Short-Term Memory for Gravitational Wave Signal
by: Liu, Chen-Yu, et al.
Published: (2025)

GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference
by: Zeng, Chao, et al.
Published: (2024)

Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation
by: Han, Yizhao, et al.
Published: (2026)

VideoMerge: Towards Training-free Long Video Generation
by: Zhang, Siyang, et al.
Published: (2025)

MedHorizon: Towards Long-context Medical Video Understanding in the Wild
by: Du, Bodong, et al.
Published: (2026)

Training-free Motion Factorization for Compositional Video Generation
by: Wang, Zixuan, et al.
Published: (2026)

Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing
by: Wang, Zhu, et al.
Published: (2025)

ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
by: Peng, Xurui, et al.
Published: (2025)

Memory Management and Contextual Consistency for Long-Running Low-Code Agents
by: Xu, Jiexi
Published: (2025)

How to Train Long-Context Language Models (Effectively)
by: Gao, Tianyu, et al.
Published: (2024)

Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
by: So, Junhyuk, et al.
Published: (2025)

Progressive Supernet Training for Efficient Visual Autoregressive Modeling
by: Chen, Xiaoyue, et al.
Published: (2025)

From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding
by: Sun, Guangyu, et al.
Published: (2025)

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
by: Kim, Sunghwan, et al.
Published: (2026)

TVG: A Training-free Transition Video Generation Method with Diffusion Models
by: Zhang, Rui, et al.
Published: (2024)

SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
by: Jain, Jitesh, et al.
Published: (2025)

WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
by: Liu, Junteng, et al.
Published: (2025)

Training-free Online Video Step Grounding
by: Zanella, Luca, et al.
Published: (2025)

DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference
by: Zhou, Jiajun, et al.
Published: (2023)

LightCtrl: Training-free Controllable Video Relighting
by: Peng, Yizuo, et al.
Published: (2026)

Tasa: Thermal-aware 3D-Stacked Architecture Design with Bandwidth Sharing for LLM Inference
by: He, Siyuan, et al.
Published: (2025)

Quantum-Train Long Short-Term Memory: Application on Flood Prediction Problem
by: Lin, Chu-Hsuan Abraham, et al.
Published: (2024)

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