Cover Image

FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Zihan, Shen, Leqi, Chen, Hui, Wang, Ao, Wan, Ben, Feng, Yan, Zhang, Ke, Zhao, Sicheng, Liu, Tongxuan, Ding, Guiguang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FastVID: Dynamic Density Pruning for Fast Video Large Language Models
by: Shen, Leqi, et al.
Published: (2025)

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
by: Sun, Fengyuan, 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)

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

OOCO: Latency-disaggregated Architecture for Online-Offline Co-locate LLM Serving
by: Wu, Siyu, et al.
Published: (2025)

CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs
by: Wang, Ao, et al.
Published: (2023)

KVzap: Fast, Adaptive, and Faithful KV Cache Pruning
by: Jegou, Simon, et al.
Published: (2026)

TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
by: Shen, Leqi, et al.
Published: (2024)

MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference
by: Wan, Zhongwei, et al.
Published: (2025)

DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
by: Shen, Leqi, et al.
Published: (2025)

LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs
by: Shen, Leqi, et al.
Published: (2025)

Towards Threshold-Free KV Cache Pruning
by: Ni, Xuanfan, et al.
Published: (2025)

Multimodal OCR: Parse Anything from Documents
by: Zheng, Handong, et al.
Published: (2026)

Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability
by: Hao, Tianxiang, et al.
Published: (2023)

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

Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle
by: Wang, Zihan, et al.
Published: (2026)

DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference
by: Dehghanighobadi, Zahra, et al.
Published: (2026)

OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
by: Gu, Yuzhe, et al.
Published: (2025)

FairKV: Balancing Per-Head KV Cache for Fast Multi-GPU Inference
by: Zhao, Bingzhe, et al.
Published: (2025)

FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
by: Liu, Guangda, et al.
Published: (2025)

KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference
by: Tian, Yuxuan, et al.
Published: (2025)

DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation
by: Mohammadshirazi, Ahmad, et al.
Published: (2024)

More is Better: Deep Domain Adaptation with Multiple Sources
by: Zhao, Sicheng, et al.
Published: (2024)

Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations
by: Liang, Yiwen, et al.
Published: (2025)

G-KV: Decoding-Time KV Cache Eviction with Global Attention
by: Liao, Mengqi, et al.
Published: (2025)

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs
by: Wang, Ao, et al.
Published: (2024)

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
by: Zhou, Xiabin, et al.
Published: (2024)

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
by: Liu, Xiang, et al.
Published: (2025)

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

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
by: Cai, Zefan, et al.
Published: (2025)

EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
by: Ji, Shiyu, et al.
Published: (2026)

FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration
by: Jo, Dongwon, et al.
Published: (2025)

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning
by: Guo, Hang, et al.
Published: (2025)

AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
by: Wang, Zhengren, et al.
Published: (2026)

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

MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm
by: Li, Zhang, et al.
Published: (2025)

RepViT-SAM: Towards Real-Time Segmenting Anything
by: Wang, Ao, et al.
Published: (2023)

LSNet: See Large, Focus Small
by: Wang, Ao, et al.
Published: (2025)

RepViT: Revisiting Mobile CNN From ViT Perspective
by: Wang, Ao, et al.
Published: (2023)

ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
by: Qi, Yanlin, et al.
Published: (2026)