Cover Image

Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tuncer, Tuna, Becker, Felix, Pfeil, Thomas
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Graphics Image and Video Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction
by: Wang, Runze, et al.
Published: (2026)

Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising
by: Bemana, Mojtaba, et al.
Published: (2024)

AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Content
by: Conde, Marcos V, et al.
Published: (2024)

Neural Graphics Texture Compression Supporting Random Access
by: Farhadzadeh, Farzad, et al.
Published: (2024)

NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation
by: Li, Sicheng, et al.
Published: (2024)

Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis
by: Guo, Shouchang, et al.
Published: (2022)

DrawVideo: Generating Long Video from Storyboard Keyframe Sketches
by: Xu, Chuanzhi, et al.
Published: (2026)

ColorVideoVDP: A visual difference predictor for image, video and display distortions
by: Mantiuk, Rafal K., et al.
Published: (2024)

Dispersed Structured Light for Hyperspectral 3D Imaging
by: Shin, Suhyun, et al.
Published: (2023)

Cascaded 3D Diffusion Models for Whole-body 3D 18-F FDG PET/CT synthesis from Demographics
by: Yoon, Siyeop, et al.
Published: (2025)

d-Sketch: Improving Visual Fidelity of Sketch-to-Image Translation with Pretrained Latent Diffusion Models without Retraining
by: Roy, Prasun, et al.
Published: (2025)

HDRT: A Large-Scale Dataset for Infrared-Guided HDR Imaging
by: Peng, Jingchao, et al.
Published: (2024)

EGGS: Edge Guided Gaussian Splatting for Radiance Fields
by: Gong, Yuanhao
Published: (2024)

Textured Gaussians for Enhanced 3D Scene Appearance Modeling
by: Chao, Brian, et al.
Published: (2024)

Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites
by: Ruan, Lingyan, et al.
Published: (2025)

PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism
by: Ye, Yuyan, et al.
Published: (2025)

VEIGAR: View-consistent Explicit Inpainting and Geometry Alignment for 3D object Removal
by: Do, Pham Khai Nguyen, et al.
Published: (2025)

ViPE: Video Pose Engine for 3D Geometric Perception
by: Huang, Jiahui, et al.
Published: (2025)

Multidimensional Compressed Sensing for Spectral Light Field Imaging
by: Cao, Wen, et al.
Published: (2024)

Learned Single-Pass Multitasking Perceptual Graphics for Immersive Displays
by: Yılmaz, Doğa, et al.
Published: (2024)

Bridging the Diagnostic Divide: Classical Computer Vision and Advanced AI methods for distinguishing ITB and CD through CTE Scans
by: Gupta, Shashwat, et al.
Published: (2024)

Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
by: Gu, Diandian, et al.
Published: (2026)

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
by: Wei, Huawei, et al.
Published: (2024)

VIS30K: A Collection of Figures and Tables from IEEE Visualization Conference Publications
by: Chen, Jian, et al.
Published: (2020)

Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior
by: Lee, Byeonghyeon, et al.
Published: (2024)

Biomedical Image Segmentation: A Systematic Literature Review of Deep Learning Based Object Detection Methods
by: Wahid, Fazli, et al.
Published: (2024)

Neural radiance fields-based holography [Invited]
by: Kang, Minsung, et al.
Published: (2024)

Processing HSV Colored Medical Images and Adapting Color Thresholds for Computational Image Analysis: a Practical Introduction to an open-source tool
by: Cai, Lie, et al.
Published: (2024)

COSMOS: Coherent Supergaussian Modeling with Spatial Priors for Sparse-View 3D Splatting
by: Jeong, Chaeyoung, et al.
Published: (2025)

Submillimeter-Accurate 3D Lumbar Spine Reconstruction from Biplanar X-Ray Images: Incorporating a Multi-Task Network and Landmark-Weighted Loss
by: Yu, Wanxin, et al.
Published: (2025)

Adaptively Placed Multi-Grid Scene Representation Networks for Large-Scale Data Visualization
by: Wurster, Skylar Wolfgang, et al.
Published: (2023)

SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces
by: Yang, Chuanxiang, et al.
Published: (2026)

Exploring Foundation Models for Synthetic Medical Imaging: A Study on Chest X-Rays and Fine-Tuning Techniques
by: da Silva, Davide Clode, et al.
Published: (2024)

Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
by: Han, Junlin, et al.
Published: (2024)

SGSST: Scaling Gaussian Splatting StyleTransfer
by: Galerne, Bruno, et al.
Published: (2024)

LiDAR-3DGS: LiDAR Reinforced 3D Gaussian Splatting for Multimodal Radiance Field Rendering
by: Lim, Hansol, et al.
Published: (2024)

Vector Representations of Vessel Trees
by: Batten, James, et al.
Published: (2025)

Universal Beta Splatting
by: Liu, Rong, et al.
Published: (2025)

Sea-Undistort: A Dataset for Through-Water Image Restoration in High Resolution Airborne Bathymetric Mapping
by: Kromer, Maximilian, et al.
Published: (2025)

Faster Projected GAN: Towards Faster Few-Shot Image Generation
by: Wang, Chuang, et al.
Published: (2024)