Cover Image

KV-Efficient VLA: A Method to Speed up Vision Language Models with RNN-Gated Chunked KV Cache

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Wanshun, Zhuang, Long, Shan, Lianlei
Format:	Preprint
Published:	2025
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

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

KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy
by: Huang, Yingbing, et al.
Published: (2026)

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

AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference
by: Huang, Kai, 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)

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
by: Zhang, Haowei, 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)

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

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

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

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

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

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

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

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

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

VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models
by: Zhang, Jianke, et al.
Published: (2026)

TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text
by: Lu, Songshuo, et al.
Published: (2024)

AMS-KV: Adaptive KV Caching in Multi-Scale Visual Autoregressive Transformers
by: Xu, Boxun, et al.
Published: (2025)

CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
by: Du, Fan, et al.
Published: (2026)

Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
by: Cai, Peiliang, et al.
Published: (2026)

VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation
by: Xu, Changhua, et al.
Published: (2026)

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

VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models
by: Ranjan, Ravi, et al.
Published: (2026)

NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding
by: Liu, Shiyu, et al.
Published: (2025)

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

ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
by: Wang, Xiyang, 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)

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
by: Chen, Peng, et al.
Published: (2025)

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

VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
by: Gao, Mingjian, et al.
Published: (2026)

VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
by: Wang, Chaoyang, et al.
Published: (2026)

ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations
by: Zhou, Yuhao, et al.
Published: (2026)

UrbanVLA: A Vision-Language-Action Model for Urban Micromobility
by: Li, Anqi, et al.
Published: (2025)

AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models
by: Rao, Zhifeng, et al.
Published: (2026)

SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and Planning
by: Dang, Chenxu, et al.
Published: (2026)

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

Test-Time Training with KV Binding Is Secretly Linear Attention
by: Liu, Junchen, et al.
Published: (2026)

Decouple and Cache: KV Cache Construction for Streaming Video Understanding
by: Pang, Zhanzhong, et al.
Published: (2026)