Cover Image

KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Yingbing, Srikrishnan, Tharun Adithya, Reinhardt, Steven K., Chen, Deming
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

BlindSight: Harnessing Sparsity for Efficient Vision-Language Models
by: Srikrishnan, Tharun Adithya, et al.
Published: (2025)

AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference
by: Huang, Kai, et al.
Published: (2025)

STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models
by: Han, Yuhang, et al.
Published: (2026)

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

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

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

VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
by: Tu, Dezhan, et al.
Published: (2024)

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

Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models
by: Liu, Xuyang, et al.
Published: (2025)

Efficient Long-Horizon GUI Agents via Training-Free KV Cache Compression
by: Zhou, Bowen, et al.
Published: (2026)

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

Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach
by: Yang, Yaoxin, et al.
Published: (2025)

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

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
by: Su, Zunhai, et al.
Published: (2026)

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
by: Su, Zunhai, et al.
Published: (2026)

PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
by: Sun, Fengyuan, et al.
Published: (2025)

Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders
by: Wang, Yizhou, et al.
Published: (2025)

Dual-Signal Adaptive KV-Cache Optimization for Long-Form Video Understanding in Vision-Language Models
by: Sai, Vishnu, et al.
Published: (2026)

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

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

FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
by: Tong, Jintao, et al.
Published: (2025)

Make Your LVLM KV Cache More Lightweight
by: Chen, Xihao, et al.
Published: (2026)

TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge
by: Zhang, Shu-Hao, et al.
Published: (2025)

Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models
by: Chen, Xinyu, et al.
Published: (2025)

FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression
by: Li, Jianjian, et al.
Published: (2025)

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition
by: Hu, Youbing, et al.
Published: (2024)

Enhancing Vision Models for Text-Heavy Content Understanding and Interaction
by: TG, Adithya, et al.
Published: (2024)

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

Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers
by: Ma, Ji, et al.
Published: (2025)

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression
by: Hu, Lianyu, et al.
Published: (2025)

PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models
by: Meng, Yu, et al.
Published: (2025)

Empirical Recipes for Efficient and Compact Vision-Language Models
by: Huang, Jiabo, et al.
Published: (2026)

IBiT: Utilizing Inductive Biases to Create a More Data Efficient Attention Mechanism
by: Giri, Adithya
Published: (2025)

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

Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models
by: Long, Jiahuan, et al.
Published: (2025)

ESP-PCT: Enhanced VR Semantic Performance through Efficient Compression of Temporal and Spatial Redundancies in Point Cloud Transformers
by: Mei, Luoyu, et al.
Published: (2024)

Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion
by: Tuncer, Tuna, et al.
Published: (2026)

Task-Aware KV Compression For Cost-Effective Long Video Understanding
by: Qin, Minghao, et al.
Published: (2025)

LagKV: Lag-Relative Information of the KV Cache Tells Which Tokens Are Important
by: Liang, Manlai, et al.
Published: (2025)

HybridToken-VLM: Hybrid Token Compression for Vision-Language Models
by: Zhang, Jusheng, et al.
Published: (2025)