Cover Image

PureKV: Plug-and-Play KV Cache Optimization with Spatial-Temporal Sparse Attention for Vision-Language Large Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Zhonghua, Li, Kunxi, Zhou, Yiyun, Liu, Sihao, Wang, Zhaode, lv, Chengfei, Zhang, Shengyu
Format:	Preprint
Published:	2025
Subjects:	Multimedia
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

FlowMM: Cross-Modal Information Flow Guided KV Cache Merging for Efficient Multimodal Context Inference
by: Li, Kunxi, et al.
Published: (2025)

RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction
by: Liu, Sihao, et al.
Published: (2026)

MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
by: Li, Kunxi, et al.
Published: (2025)

FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression Framework
by: Zhu, Jianian, et al.
Published: (2025)

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

GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting
by: Yu, Hongyun, et al.
Published: (2024)

V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval
by: Kim, Donghyuk, et al.
Published: (2025)

SonicVisionLM: Playing Sound with Vision Language Models
by: Xie, Zhifeng, et al.
Published: (2024)

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

Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation
by: Guo, Hongming, et al.
Published: (2024)

SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding
by: Sun, Luoyi, et al.
Published: (2026)

SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions
by: Tu, Jinzhe, et al.
Published: (2026)

PiGW: A Plug-in Generative Watermarking Framework
by: Ma, Rui, et al.
Published: (2024)

Rethinking Vision Transformer for Large-Scale Fine-Grained Image Retrieval
by: Jiang, Xin, et al.
Published: (2025)

Can Multimodal Large Language Models Understand Spatial Relations?
by: Liu, Jingping, et al.
Published: (2025)

Efficient Transformer-Based Piano Transcription With Sparse Attention Mechanisms
by: Wei, Weixing, et al.
Published: (2025)

Quizzard@INOVA Challenge 2025 -- Track A: Plug-and-Play Technique in Interleaved Multi-Image Model
by: Cuong, Dinh Viet, et al.
Published: (2025)

Scene Graph Generation with Role-Playing Large Language Models
by: Chen, Guikun, et al.
Published: (2024)

Identity-Aware Vision-Language Model for Explainable Face Forgery Detection
by: Xu, Junhao, et al.
Published: (2025)

Segmentation-Based Attention Entropy: Detecting and Mitigating Object Hallucinations in Large Vision-Language Models
by: Song, Jiale, et al.
Published: (2026)

Not All Attention is Needed: Parameter and Computation Efficient Transfer Learning for Multi-modal Large Language Models
by: Wu, Qiong, et al.
Published: (2024)

VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
by: Bian, Yuxuan, et al.
Published: (2025)

ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Capability for Large Vision-Language Models
by: Liu, Shuo, et al.
Published: (2024)

Multimodal Emotion Recognition with Large Language Models
by: Zhang, Hongrui, et al.
Published: (2026)

FlexCache: Flexible Approximate Cache System for Video Diffusion
by: Sun, Desen, et al.
Published: (2024)

Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
by: Fazli, Mehrdad, et al.
Published: (2025)

ChartAdapter: Large Vision-Language Model for Chart Summarization
by: Xu, Peixin, et al.
Published: (2024)

Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation
by: Yang, Sicheng, et al.
Published: (2025)

COPA: Efficient Vision-Language Pre-training Through Collaborative Object- and Patch-Text Alignment
by: Jiang, Chaoya, et al.
Published: (2023)

MAO: Efficient Model-Agnostic Optimization of Prompt Tuning for Vision-Language Models
by: Li, Haoyang, et al.
Published: (2025)

Interest-Aware Joint Caching, Computing, and Communication Optimization for Mobile VR Delivery in MEC Networks
by: Fu, Baojie, et al.
Published: (2024)

SVD: Spatial Video Dataset
by: Izadimehr, M. H., et al.
Published: (2025)

Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models
by: Wu, Qiong, et al.
Published: (2024)

Sparse Attention across Multiple-context KV Cache
by: Cao, Ziyi, et al.
Published: (2025)

XRFlux: Virtual Reality Benchmark for Edge Caching Systems
by: Alfares, Nader, et al.
Published: (2024)

TSC-PCAC: Voxel Transformer and Sparse Convolution Based Point Cloud Attribute Compression for 3D Broadcasting
by: Guo, Zixi, et al.
Published: (2024)

EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models
by: Du, Mengfei, et al.
Published: (2024)

Multi-source Knowledge Enhanced Graph Attention Networks for Multimodal Fact Verification
by: Cao, Han, et al.
Published: (2024)

SoMeLVLM: A Large Vision Language Model for Social Media Processing
by: Zhang, Xinnong, et al.
Published: (2024)