Copertina

Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ma, Xuran, Liu, Yexin, Liu, Yaofu, Wu, Xianfeng, Zheng, Mingzhe, Wang, Zihao, Lim, Ser-Nam, Yang, Harry
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention
di: Zheng, Mingzhe, et al.
Pubblicazione: (2025)

VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention
di: Zheng, Mingzhe, et al.
Pubblicazione: (2024)

LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization
di: Wu, Xianfeng, et al.
Pubblicazione: (2025)

Temporal Regularization Makes Your Video Generator Stronger
di: Chen, Harold Haodong, et al.
Pubblicazione: (2025)

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

CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation
di: Zheng, Mingzhe, et al.
Pubblicazione: (2025)

AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
di: Liu, Yexin, et al.
Pubblicazione: (2025)

Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse
di: Liu, Hao, et al.
Pubblicazione: (2026)

Towards Chunk-Wise Generation for Long Videos
di: Zhang, Siyang, et al.
Pubblicazione: (2024)

Learning Latent Proxies for Controllable Single-Image Relighting
di: Zheng, Haoze, et al.
Pubblicazione: (2026)

Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning
di: Chen, Harold Haodong, et al.
Pubblicazione: (2024)

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding
di: Shu, Yan, et al.
Pubblicazione: (2025)

AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse
di: Yu, Zichao, et al.
Pubblicazione: (2025)

Video Decomposition Prior: A Methodology to Decompose Videos into Layers
di: Shrivastava, Gaurav, et al.
Pubblicazione: (2024)

Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
di: Chen, Harold Haodong, et al.
Pubblicazione: (2025)

InvarDiff: Cross-Scale Invariance Caching for Accelerated Diffusion Models
di: Wu, Zihao
Pubblicazione: (2025)

Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View
di: Wu, Xianzu, et al.
Pubblicazione: (2025)

AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
di: Fang, Pengjun, et al.
Pubblicazione: (2026)

Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising
di: Wang, Yifan, et al.
Pubblicazione: (2025)

Sortblock: Similarity-Aware Feature Reuse for Diffusion Model
di: Chen, Hanqi, et al.
Pubblicazione: (2025)

FluxShard: Motion-Aware Feature Cache Reuse for Collaborative Video Analytics in Mobile Edge Computing
di: Guan, Xiuxian, et al.
Pubblicazione: (2026)

OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models
di: Chu, Huanpeng, et al.
Pubblicazione: (2025)

KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse
di: Yang, Huan, et al.
Pubblicazione: (2025)

RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse
di: Geng, Yingsheng, et al.
Pubblicazione: (2026)

DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses
di: Pang, Yatian, et al.
Pubblicazione: (2024)

Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward
di: Xu, Xiaogang, et al.
Pubblicazione: (2025)

Fast Encoding and Decoding for Implicit Video Representation
di: Chen, Hao, et al.
Pubblicazione: (2024)

SAR Despeckling via Regional Denoising Diffusion Probabilistic Model
di: Hu, Xuran, et al.
Pubblicazione: (2024)

CacheClip: Accelerating RAG with Effective KV Cache Reuse
di: Yang, Bin, et al.
Pubblicazione: (2025)

Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop
di: Qian, Zhaofang, et al.
Pubblicazione: (2024)

Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly
di: Liu, Yexin, et al.
Pubblicazione: (2024)

What can Off-the-Shelves Large Multi-Modal Models do for Dynamic Scene Graph Generation?
di: Cui, Xuanming, et al.
Pubblicazione: (2025)

Efficient Remote KV Cache Reuse with GPU-native Video Codec
di: Mi, Liang, et al.
Pubblicazione: (2026)

Delta Activations: A Representation for Finetuned Large Language Models
di: Xu, Zhiqiu, et al.
Pubblicazione: (2025)

Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning
di: Park, Dongmin, et al.
Pubblicazione: (2024)

Perturbation on Feature Coalition: Towards Interpretable Deep Neural Networks
di: Hu, Xuran, et al.
Pubblicazione: (2024)

BOOKAGENT: Orchestrating Safety-Aware Visual Narratives via Multi-Agent Cognitive Calibration
di: Gao, Bo, et al.
Pubblicazione: (2026)

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
di: Zou, Chang, et al.
Pubblicazione: (2026)

DiReCT: Disentangled Regularization of Contrastive Trajectories for Physics-Refined Video Generation
di: Meyarian, Abolfazl, et al.
Pubblicazione: (2026)

Adaptive KV Cache Reuse for Fast Long-Context LLM Serving
di: li, Fei, et al.
Pubblicazione: (2026)