Image de couverture de livre

LagKV: Lag-Relative Information of the KV Cache Tells Which Tokens Are Important

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liang, Manlai, Zhang, JiaMing, Li, Xiong, Li, Jinlong
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
par: Zhang, Haowei, et autres
Publié: (2026)

Lag-Relative Sparse Attention In Long Context Training
par: Liang, Manlai, et autres
Publié: (2025)

Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach
par: Yang, Yaoxin, et autres
Publié: (2025)

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering
par: Xiao, Junbin, et autres
Publié: (2026)

VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
par: Tu, Dezhan, et autres
Publié: (2024)

KV-Efficient VLA: A Method to Speed up Vision Language Models with RNN-Gated Chunked KV Cache
par: Xu, Wanshun, et autres
Publié: (2025)

STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models
par: Han, Yuhang, et autres
Publié: (2026)

Cross-Self KV Cache Pruning for Efficient Vision-Language Inference
par: Pei, Xiaohuan, et autres
Publié: (2024)

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
par: Yang, Yanlai, et autres
Publié: (2025)

Make Your LVLM KV Cache More Lightweight
par: Chen, Xihao, et autres
Publié: (2026)

KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy
par: Huang, Yingbing, et autres
Publié: (2026)

AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference
par: Huang, Kai, et autres
Publié: (2025)

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
par: Cai, Zefan, et autres
Publié: (2024)

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
par: Yesiltepe, Hidir, et autres
Publié: (2026)

Efficient Long-Horizon GUI Agents via Training-Free KV Cache Compression
par: Zhou, Bowen, et autres
Publié: (2026)

PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
par: Sun, Fengyuan, et autres
Publié: (2025)

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference
par: Wan, Zhongwei, et autres
Publié: (2024)

TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text
par: Lu, Songshuo, et autres
Publié: (2024)

AMS-KV: Adaptive KV Caching in Multi-Scale Visual Autoregressive Transformers
par: Xu, Boxun, et autres
Publié: (2025)

WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization
par: Tao, Wei, et autres
Publié: (2026)

CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation
par: Lin, Xiaolin, et autres
Publié: (2025)

FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing
par: Tang, Zihan, et autres
Publié: (2026)

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
par: Cai, Zefan, et autres
Publié: (2025)

Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models
par: Li, Zhang, et autres
Publié: (2023)

LFTR: Learning-Free Token Reduction for Multimodal Large Language Models
par: Zhao, Zihui, et autres
Publié: (2025)

StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression
par: Chen, Yilong, et autres
Publié: (2025)

Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
par: Ji, Yicheng, et autres
Publié: (2026)

Task-Aware KV Compression For Cost-Effective Long Video Understanding
par: Qin, Minghao, et autres
Publié: (2025)

Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration
par: Evangelista, Davide, et autres
Publié: (2026)

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression
par: Hu, Lianyu, et autres
Publié: (2025)

Test-Time Training with KV Binding Is Secretly Linear Attention
par: Liu, Junchen, et autres
Publié: (2026)

On the Limits of Token Reduction for Efficient Unified Vision Language Training
par: Chen, Siyi, et autres
Publié: (2026)

Where is the multimodal goal post? On the Ability of Foundation Models to Recognize Contextually Important Moments
par: Surikuchi, Aditya K, et autres
Publié: (2026)

KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction
par: Yuan, Aomufei, et autres
Publié: (2025)

Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos
par: Kalluri, Tarun, et autres
Publié: (2024)

G-KV: Decoding-Time KV Cache Eviction with Global Attention
par: Liao, Mengqi, et autres
Publié: (2025)

Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification
par: Qin, Minghao, et autres
Publié: (2025)

Dual-Signal Adaptive KV-Cache Optimization for Long-Form Video Understanding in Vision-Language Models
par: Sai, Vishnu, et autres
Publié: (2026)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
par: Zhong, Yiwu, et autres
Publié: (2024)

Text or Image? What is More Important in Cross-Domain Generalization Capabilities of Hate Meme Detection Models?
par: Aggarwal, Piush, et autres
Publié: (2024)