Image de couverture de livre

Modality-Aware Zero-Shot Pruning and Sparse Attention for Efficient Multimodal Edge Inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sui, Yueyuan, Mohapatra, Payal, Eldenk, Doğaç, Yang, Haodong, Zhang, Yiting, Zhang, Haoyan, Zhu, Qi, Xia, Stephen
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series
par: Mohapatra, Payal, et autres
Publié: (2025)

Attention Drift: What Autoregressive Speculative Decoding Models Learn
par: Eldenk, Doğaç, et autres
Publié: (2026)

UNIFERENCE: A Discrete Event Simulation Framework for Developing Distributed AI Models
par: Eldenk, Doğaç, et autres
Publié: (2026)

Incidents During Microservice Decomposition: A Case Study
par: Eldenk, Doğaç, et autres
Publié: (2025)

EmboAlign: Aligning Video Generation with Compositional Constraints for Zero-Shot Manipulation
par: Zhang, Gehao, et autres
Publié: (2026)

MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs
par: Xu, Hongjun, et autres
Publié: (2025)

SparseDVFS: Sparse-Aware DVFS for Energy-Efficient Edge Inference
par: Zhang, Ziyang, et autres
Publié: (2026)

Phase-driven Domain Generalizable Learning for Nonstationary Time Series
par: Mohapatra, Payal, et autres
Publié: (2024)

ElastiFormer: Learned Redundancy Reduction in Transformer via Self-Distillation
par: Liu, Junzhang, et autres
Publié: (2024)

Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs
par: Mohapatra, Payal, et autres
Publié: (2025)

Missingness-resilient Video-enhanced Multimodal Disfluency Detection
par: Mohapatra, Payal, et autres
Publié: (2024)

MoA-Off: Adaptive Heterogeneous Modality-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
par: Yang, Zheming, et autres
Publié: (2025)

TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech Super Resolution and Enhancement on Mobile and Wearable Platforms
par: Sui, Yueyuan, et autres
Publié: (2024)

MSAO: Adaptive Modality Sparsity-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
par: Yang, Zheming, et autres
Publié: (2026)

Environment-Aware Dynamic Pruning for Pipelined Edge Inference
par: O'Quinn, Austin, et autres
Publié: (2025)

Timestep-Aware Block Masking for Efficient Diffusion Model Inference
par: He, Haodong, et autres
Publié: (2026)

ASAP: Attention-Shift-Aware Pruning for Efficient LVLM Inference
par: Pathak, Surendra, et autres
Publié: (2026)

OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition
par: Zhang, Stephen, et autres
Publié: (2024)

ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models
par: Zhang, Pu, et autres
Publié: (2025)

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference
par: Li, Bo, et autres
Publié: (2026)

Guest Editors´ Introduction. Electronic Document Interoperability in eBusiness and eGovernment Applications
par: Asuman Dogac
Publié: (2008)

Multimodal Graph-Based Variational Mixture of Experts Network for Zero-Shot Multimodal Information Extraction
par: Zhou, Baohang, et autres
Publié: (2025)

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
par: Liu, Zheyuan, et autres
Publié: (2025)

SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
par: Wang, Hanrui, et autres
Publié: (2020)

Graph Neural Network-based Multi-agent Reinforcement Learning for Resilient Distributed Coordination of Multi-Robot Systems
par: Goeckner, Anthony, et autres
Publié: (2024)

CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning
par: Li, Yanshu, et autres
Publié: (2025)

Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference
par: Yan, Siyuan, et autres
Publié: (2025)

DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems
par: Guo, Qi, et autres
Publié: (2026)

Hyperbolic Multimodal Generative Representation Learning for Generalized Zero-Shot Multimodal Information Extraction
par: Zhou, Baohang, et autres
Publié: (2026)

TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification
par: Pandey, Akash, et autres
Publié: (2026)

AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity
par: Zhang, Yu, et autres
Publié: (2025)

Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
par: Wang, Hongjie, et autres
Publié: (2023)

Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention
par: Xiao, Emily, et autres
Publié: (2025)

Communication-Efficient Multi-Modal Edge Inference via Uncertainty-Aware Distributed Learning
par: Zhao, Hang, et autres
Publié: (2026)

EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models
par: Xing, Xingrun, et autres
Publié: (2025)

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning
par: Zhang, Xiao, et autres
Publié: (2025)

CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference
par: Wu, Guanlong, et autres
Publié: (2026)

XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge
par: Zhang, Yu, et autres
Publié: (2025)

Where Relevance Emerges: A Layer-Wise Study of Internal Attention for Zero-Shot Re-Ranking
par: Chen, Haodong, et autres
Publié: (2026)

MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention
par: Yaras, Can, et autres
Publié: (2025)