Cover Image

CATP: Cross-Attention Token Pruning for Accuracy Preserved Multimodal Model Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liao, Ruqi, Zhao, Chuqing, Li, Jin, Feng, Weiqi, Lyu, Yi, Chen, Bingxian, Yang, Haochen
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning
by: Li, Yanshu, et al.
Published: (2025)

PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference
by: Zhang, Hao, et al.
Published: (2025)

Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification
by: Yun, Jungmin, et al.
Published: (2024)

Pruning Foundation Models for High Accuracy without Retraining
by: Zhao, Pu, et al.
Published: (2024)

Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion
by: Cheng, Zhen, et al.
Published: (2026)

Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
by: Son, Jaemin, et al.
Published: (2025)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
by: Taniguchi, Rei, et al.
Published: (2026)

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
by: Fu, Qichen, et al.
Published: (2024)

ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models
by: Chen, Hao, et al.
Published: (2025)

Saliency-driven Dynamic Token Pruning for Large Language Models
by: Tao, Yao, et al.
Published: (2025)

CATP: Confidence-Aware Token Pruning for Camouflaged Object Detection
by: Gao, Yuhan, et al.
Published: (2026)

Hey, That's My Data! Token-Only Dataset Inference in Large Language Models
by: Xiong, Chen, et al.
Published: (2025)

SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
by: Wang, Hanrui, et al.
Published: (2020)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
by: Zhong, Yiwu, et al.
Published: (2024)

PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding
by: Wang, Nan, et al.
Published: (2026)

Towards Lossless Token Pruning in Late-Interaction Retrieval Models
by: Zong, Yuxuan, et al.
Published: (2025)

PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality
by: Yu, Byeongho, et al.
Published: (2025)

SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval
by: Lin, Yueqian, et al.
Published: (2024)

PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
by: Zhang, Luan, et al.
Published: (2026)

Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models
by: Wu, Jialiang, et al.
Published: (2025)

Pruning Large Language Models by Identifying and Preserving Functional Networks
by: Liu, Yiheng, et al.
Published: (2025)

LFTR: Learning-Free Token Reduction for Multimodal Large Language Models
by: Zhao, Zihui, et al.
Published: (2025)

Self-Selected Attention Span for Accelerating Large Language Model Inference
by: Jin, Tian, et al.
Published: (2024)

MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens
by: Chen, Yu, et al.
Published: (2026)

COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens
by: Kwek, Eugene, et al.
Published: (2025)

AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation
by: Fang, Yixiong, et al.
Published: (2025)

EvoP: Robust LLM Inference via Evolutionary Pruning
by: Wu, Shangyu, et al.
Published: (2025)

Inference-Friendly Models With MixAttention
by: Rajput, Shashank, et al.
Published: (2024)

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
by: Li, Geng, et al.
Published: (2026)

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
by: Zhang, Shaolei, et al.
Published: (2025)

Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs
by: Jin, Yijie, et al.
Published: (2025)

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
by: Liao, Qilin, et al.
Published: (2025)

LaCo: Large Language Model Pruning via Layer Collapse
by: Yang, Yifei, et al.
Published: (2024)

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models
by: Wang, Zekun, et al.
Published: (2023)

Pruning General Large Language Models into Customized Expert Models
by: Zhao, Yirao, et al.
Published: (2025)

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

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
by: Qian, Chen, et al.
Published: (2025)

Adaptive Draft-Verification for Efficient Large Language Model Decoding
by: Liu, Xukun, et al.
Published: (2024)

DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration
by: Zhang, Hanzhi, et al.
Published: (2025)

AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph
by: Wang, Zhaowei, et al.
Published: (2023)