Cover Image

DeltaLLM: A Training-Free Framework Exploiting Temporal Sparsity for Efficient Edge LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qi, Jiawen, Gao, Chang, Ren, Zhaochun, Chen, Qinyu
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Signal Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DeltaDPD: Exploiting Dynamic Temporal Sparsity in Recurrent Neural Networks for Energy-Efficient Wideband Digital Predistortion
by: Wu, Yizhuo, et al.
Published: (2025)

TCN-DPD: Parameter-Efficient Temporal Convolutional Networks for Wideband Digital Predistortion
by: Duan, Huanqiang, et al.
Published: (2025)

Structure-Aware Multimodal LLM Framework for Trustworthy Near-Field Beam Prediction
by: Li, Mengyuan, et al.
Published: (2026)

OpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital Predistortion
by: Wu, Yizhuo, et al.
Published: (2025)

SignalLLM: A General-Purpose LLM Agent Framework for Automated Signal Processing
by: Ke, Junlong, et al.
Published: (2025)

E2CAR: An Efficient 2D-CNN Framework for Real-Time EEG Artifact Removal on Edge Devices
by: Liu, Haoliang, et al.
Published: (2026)

Bridging 6G IoT and AI: LLM-Based Efficient Approach for Physical Layer's Optimization Tasks
by: Mehmood, Ahsan, et al.
Published: (2026)

Distributed Integrated Sensing and Edge AI Exploiting Prior Information
by: Dong, Biao, et al.
Published: (2025)

DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights
by: Mikaelyan, Liana, et al.
Published: (2025)

Training-Free Message Passing for Learning on Hypergraphs
by: Tang, Bohan, et al.
Published: (2024)

Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions
by: Gao, Xiaoxue, et al.
Published: (2025)

ECG Semantic Integrator (ESI): A Foundation ECG Model Pretrained with LLM-Enhanced Cardiological Text
by: Yu, Han, et al.
Published: (2024)

Leveraging LLM Agents for Automated Optimization Modeling for SASP Problems: A Graph-RAG based Approach
by: Pan, Tianpeng, et al.
Published: (2025)

Jointly Modeling Spatio-Temporal Features of Tactile Signals for Action Classification
by: Lin, Jimmy, et al.
Published: (2024)

Exploiting sparse structures and synergy designs to advance situational awareness of electrical power grid
by: Li, Shimiao
Published: (2024)

When NPUs Are Not Always Faster: A Stage-Level Analysis of Mobile LLM Inference
by: Li, Pu, et al.
Published: (2026)

Adaptive End-to-End Transceiver Design for NextG Pilot-Free and CP-Free Wireless Systems
by: Cheng, Jiaming, et al.
Published: (2025)

CLSP-REQA: A Real-Time Quality-Aware Closed-Loop Seizure Prediction Framework with Mamba-BiLSTM and Confidence-Gated Intervention
by: Chen, Mufeng, et al.
Published: (2026)

Variational Inference of Structured Line Spectra Exploiting Group-Sparsity
by: Möderl, Jakob, et al.
Published: (2023)

Collaborative Edge AI Inference over Cloud-RAN
by: Zhang, Pengfei, et al.
Published: (2024)

CSIYOLO: An Intelligent CSI-based Scatter Sensing Framework for Integrated Sensing and Communication Systems
by: Zhang, Xudong, et al.
Published: (2025)

A Lightweight Human Pose Estimation Approach for Edge Computing-Enabled Metaverse with Compressive Sensing
by: Hieu, Nguyen Quang, et al.
Published: (2024)

Building Semantic Communication System via Molecules: An End-to-End Training Approach
by: Cheng, Yukun, et al.
Published: (2024)

Towards 6G Native-AI Edge Networks: A Semantic-Aware and Agentic Intelligence Paradigm
by: Feng, Chenyuan, et al.
Published: (2025)

Augmenting Channel Simulator and Semi- Supervised Learning for Efficient Indoor Positioning
by: Li, Yupeng, et al.
Published: (2024)

Unsupervised Attention-Based Multi-Source Domain Adaptation Framework for Drift Compensation in Electronic Nose Systems
by: Zhang, Wenwen, et al.
Published: (2024)

A Learnable SIM Paradigm: Fundamentals, Training Techniques, and Applications
by: Wang, Hetong, et al.
Published: (2026)

LLM-Empowered Resource Allocation in Wireless Communications Systems
by: Lee, Woongsup, et al.
Published: (2024)

MP-DPD: Low-Complexity Mixed-Precision Neural Networks for Energy-Efficient Digital Predistortion of Wideband Power Amplifiers
by: Wu, Yizhuo, et al.
Published: (2024)

RadioGAT: A Joint Model-based and Data-driven Framework for Multi-band Radiomap Reconstruction via Graph Attention Networks
by: Li, Xiaojie, et al.
Published: (2024)

Prompting Large Language Models for Training-Free Non-Intrusive Load Monitoring
by: Xue, Junyu, et al.
Published: (2025)

AMSnet-KG: A Netlist Dataset for LLM-based AMS Circuit Auto-Design Using Knowledge Graph RAG
by: Shi, Yichen, et al.
Published: (2024)

RadioLLM: Introducing Large Language Model into Cognitive Radio via Hybrid Prompt and Token Reprogrammings
by: Chen, Shuai, et al.
Published: (2025)

Invited Paper: Feature-to-Classifier Co-Design for Mixed-Signal Smart Flexible Wearables for Healthcare at the Extreme Edge
by: Shatta, Maha, et al.
Published: (2025)

Energy-Efficient Learning-Based Beamforming for ISAC-Enabled V2X Networks
by: Shang, Chen, et al.
Published: (2025)

Advancing Air Quality Monitoring: TinyML-Based Real-Time Ozone Prediction with Cost-Effective Edge Devices
by: Ken, Huam Ming, et al.
Published: (2025)

Learning to Focus: CSI-Free Hierarchical MARL for Reconfigurable Reflectors
by: Le, Hieu, et al.
Published: (2026)

An Exploratory Assessment of LLM's Potential Toward Flight Trajectory Reconstruction Analysis
by: Zhang, Qilei, et al.
Published: (2024)

Digital Twin Enabled Site Specific Channel Precoding: Over the Air CIR Inference
by: Haider, Majumder, et al.
Published: (2025)

PITN: Physics-Informed Temporal Networks for Cuffless Blood Pressure Estimation
by: Wang, Rui, et al.
Published: (2024)