Cover Image

Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Hanmo, Xu, Chenghao, Yang, Xu, Chen, Xuan, Deng, Cheng
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

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

Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
by: Ji, Yicheng, et al.
Published: (2026)

AStF: Motion Style Transfer via Adaptive Statistics Fusor
by: Chen, Hanmo, et al.
Published: (2025)

Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning
by: Chen, Hanmo, et al.
Published: (2026)

AMS-KV: Adaptive KV Caching in Multi-Scale Visual Autoregressive Transformers
by: Xu, Boxun, et al.
Published: (2025)

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
by: Yesiltepe, Hidir, et al.
Published: (2026)

Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation
by: Chen, Jiayu, et al.
Published: (2026)

PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache
by: Li, Kunyang, et al.
Published: (2026)

Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling
by: Qin, Ziran, et al.
Published: (2025)

Decouple and Cache: KV Cache Construction for Streaming Video Understanding
by: Pang, Zhanzhong, et al.
Published: (2026)

StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression
by: Chen, Yilong, et al.
Published: (2025)

Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
by: Di, Shangzhe, et al.
Published: (2025)

Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
by: Gao, Kaifeng, et al.
Published: (2024)

StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion
by: Yang, Haoxin, et al.
Published: (2025)

FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
by: Luo, Xiangyang, et al.
Published: (2025)

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering
by: Xiao, Junbin, et al.
Published: (2026)

KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration
by: Zhang, Ruicheng, et al.
Published: (2026)

Perceive, Verify and Understand Long Video: Multi-Granular Perception and Active Verification via Interactive Agents
by: Li, Jiahua, et al.
Published: (2025)

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

CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion
by: Tang, Yolo Yunlong, et al.
Published: (2024)

Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models
by: Cheng, Tianle, et al.
Published: (2025)

When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning
by: Liu, Yang, et al.
Published: (2025)

Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models
by: Tao, Keda, et al.
Published: (2025)

Progressive Autoregressive Video Diffusion Models
by: Xie, Desai, et al.
Published: (2024)

MSC: Multi-Scale Spatio-Temporal Causal Attention for Autoregressive Video Diffusion
by: Xu, Xunnong, et al.
Published: (2024)

X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference
by: Zeng, Yixiao, et al.
Published: (2026)

Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
by: Liu, Kunhao, et al.
Published: (2025)

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

Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention
by: Samuel, Dvir, et al.
Published: (2026)

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
by: Zhang, Haowei, et al.
Published: (2026)

Saliency Guided Optimization of Diffusion Latents
by: Wang, Xiwen, et al.
Published: (2024)

AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization
by: Jiang, Zhonghua, et al.
Published: (2025)

HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling
by: Cederlund, Jonathan, et al.
Published: (2026)

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
by: Wang, Ao, et al.
Published: (2024)

CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs
by: Han, Insu, et al.
Published: (2025)

Cross-Self KV Cache Pruning for Efficient Vision-Language Inference
by: Pei, Xiaohuan, et al.
Published: (2024)

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
by: Yang, Yanlai, et al.
Published: (2025)

KV-Efficient VLA: A Method to Speed up Vision Language Models with RNN-Gated Chunked KV Cache
by: Xu, Wanshun, et al.
Published: (2025)

Segment Anything for Video: A Comprehensive Review of Video Object Segmentation and Tracking from Past to Future
by: Xu, Guoping, et al.
Published: (2025)

Trajectory-Consistent Calibration for Cache-Accelerated Diffusion Models
by: Liang, Mingyu, et al.
Published: (2026)