Cover Image

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Bo, Cui, Xinyu, Zhao, Jian, Wei, Tong, Zhang, Min-Ling
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
by: Luo, Jiayun, et al.
Published: (2025)

EDIT: Enhancing Vision Transformers by Mitigating Attention Sink through an Encoder-Decoder Architecture
by: Feng, Wenfeng, et al.
Published: (2025)

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

See What You Are Told: Visual Attention Sink in Large Multimodal Models
by: Kang, Seil, et al.
Published: (2025)

Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity
by: Tian, Jiahao, et al.
Published: (2026)

MAGI-1: Autoregressive Video Generation at Scale
by: ai, Sand., et al.
Published: (2025)

Direction-Aware Diagonal Autoregressive Image Generation
by: Xu, Yijia, et al.
Published: (2025)

A$^2$RD: Agentic Autoregressive Diffusion for Long Video Consistency
by: Long, Do Xuan, et al.
Published: (2026)

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding
by: Huang, De-An, et al.
Published: (2025)

Speculative Decoding for Autoregressive Video Generation
by: Hu, Yuezhou, et al.
Published: (2026)

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

Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
by: Cai, Peiliang, et al.
Published: (2026)

VFIMamba: Video Frame Interpolation with State Space Models
by: Zhang, Guozhen, et al.
Published: (2024)

One-Forcing: Towards Stable One-Step Autoregressive Video Generation
by: Feng, Jiaqi, et al.
Published: (2026)

TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation
by: Shaulov, Ariel, et al.
Published: (2026)

DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation
by: Yuan, Zhihang, et al.
Published: (2025)

Frame-Difference Guided Dynamic Region Perception for CLIP Adaptation in Text-Video Retrieval
by: Yu, Jiaao, et al.
Published: (2025)

Next Block Prediction: Video Generation via Semi-Autoregressive Modeling
by: Ren, Shuhuai, et al.
Published: (2025)

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

STORYANCHORS: Generating Consistent Multi-Scene Story Frames for Long-Form Narratives
by: Wang, Bo, et al.
Published: (2025)

Enhancing Long Video Question Answering with Scene-Localized Frame Grouping
by: Yang, Xuyi, et al.
Published: (2025)

Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
by: Yi, Jung, et al.
Published: (2025)

MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation
by: Chen, Ming, et al.
Published: (2025)

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

DAP: A Discrete-token Autoregressive Planner for Autonomous Driving
by: Ye, Bowen, et al.
Published: (2025)

VideoMAR: Autoregressive Video Generatio with Continuous Tokens
by: Yu, Hu, et al.
Published: (2025)

Motion-Aware Caching for Efficient Autoregressive Video Generation
by: Xu, Jing, et al.
Published: (2026)

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

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
by: Chen, Yiwen, et al.
Published: (2024)

Adaptive Greedy Frame Selection for Long Video Understanding
by: Huang, Yuning, et al.
Published: (2026)

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

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

UFO: Enhancing Diffusion-Based Video Generation with a Uniform Frame Organizer
by: Liu, Delong, et al.
Published: (2024)

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

KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding
by: Li, Zongyao, et al.
Published: (2025)

HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering
by: Ben-Ami, Dan, et al.
Published: (2026)

LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
by: Wang, Hanyu, et al.
Published: (2024)

MarDini: Masked Autoregressive Diffusion for Video Generation at Scale
by: Liu, Haozhe, et al.
Published: (2024)

Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning
by: Cao, Min, et al.
Published: (2025)

CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video
by: Li, Lingen, et al.
Published: (2026)