Imagen de Portada

PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sun, Fengyuan, Chen, Hui, Xu, Xinhao, Zheng, Dandan, Chen, Jingdong, Zhou, Jun, Han, Jungong, Ding, Guiguang
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
por: Sun, Fengyuan, et al.
Publicado: (2025)

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

FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing
por: Tang, Zihan, et al.
Publicado: (2026)

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

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

Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving
por: Zeng, Hui, et al.
Publicado: (2025)

LSNet: See Large, Focus Small
por: Wang, Ao, et al.
Publicado: (2025)

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

Titanus: Enabling KV Cache Pruning and Quantization On-the-Fly for LLM Acceleration
por: Chen, Peilin, et al.
Publicado: (2025)

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence
por: Lyu, Mengyao, et al.
Publicado: (2024)

Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models
por: Li, Sijie, et al.
Publicado: (2026)

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

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

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

CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing
por: Wang, Rui, et al.
Publicado: (2025)

CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference
por: Wu, Guanlong, et al.
Publicado: (2026)

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

PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
por: Chitty-Venkata, Krishna Teja, et al.
Publicado: (2025)

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

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

RAP: KV-Cache Compression via RoPE-Aligned Pruning
por: Xin, Jihao, et al.
Publicado: (2026)

Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference
por: Joo, Donghyeon, et al.
Publicado: (2025)

Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models
por: Ye, Weihao, et al.
Publicado: (2024)

SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
por: Liao, Huanxuan, et al.
Publicado: (2025)

NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models
por: Li, Shengrui, et al.
Publicado: (2024)

Tracking and Segmenting Anything in Any Modality
por: Zhang, Tianlu, et al.
Publicado: (2025)

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

YOLOE: Real-Time Seeing Anything
por: Wang, Ao, et al.
Publicado: (2025)

Pruning Large Language Models with Semi-Structural Adaptive Sparse Training
por: Huang, Weiyu, et al.
Publicado: (2024)

SimMLM: A Simple Framework for Multi-modal Learning with Missing Modality
por: Li, Sijie, et al.
Publicado: (2025)

LongHalQA: Long-Context Hallucination Evaluation for MultiModal Large Language Models
por: Qiu, Han, et al.
Publicado: (2024)

Adaptive Pruning for Large Language Models with Structural Importance Awareness
por: Zheng, Haotian, et al.
Publicado: (2024)

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

Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization
por: Chrysostomou, George, et al.
Publicado: (2023)

UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs
por: Xiong, Yizhe, et al.
Publicado: (2025)

YOLOv10: Real-Time End-to-End Object Detection
por: Wang, Ao, et al.
Publicado: (2024)

Sample-aware Adaptive Structured Pruning for Large Language Models
por: Kong, Jun, et al.
Publicado: (2025)

Temporal Scaling Law for Large Language Models
por: Xiong, Yizhe, et al.
Publicado: (2024)

Deterministic Differentiable Structured Pruning for Large Language Models
por: Huang, Weiyu, et al.
Publicado: (2026)

Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning
por: Lyu, Mengyao, et al.
Publicado: (2025)