Image de couverture de livre

EdgeInfinite-Instruct: Bridging SFT-Based Optimization and NPU-Level Efficiency for Edge Devices

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Jiyu, Lim, Poh Seng, Peng, Shuang, Luo, Daxiong, Foo, JungHau, Deep, Yap, Jie, Timothy Lee Jun, Wen, Kelvin Teh Kae, Yang, Fan, Feng, Danyu, Chen, Hao-Yun, Chen, Peng-Wen, Li, Fangyuan, Chen, Xiaoxin, Mun, Wong Wai
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices
par: Chen, Jiyu, et autres
Publié: (2025)

P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats
par: Chen, Yuzong, et autres
Publié: (2025)

Superhydrophobic Solar‐to‐Thermal Materials Toward Cutting‐Edge Applications
par: Shan Li, et autres
Publié: (2024)

Edge-Wise Graph-Instructed Neural Networks
par: Della Santa, Francesco, et autres
Publié: (2024)

eIQ Neutron: Redefining Edge-AI Inference with Integrated NPU and Compiler Innovations
par: Bamberg, Lennart, et autres
Publié: (2025)

Chiral Valley Edge States
par: Liu, Jian-Wei, et autres
Publié: (2025)

Edge‐Connectivity Between Edge‐Ends of Infinite Graphs
par: Leandro Aurichi, et autres
Publié: (2025)

Edge‐AI Driven Gamification in Engineering Education for Improving Student Engagement
par: Kiran Deep Singh, et autres
Publié: (2025)

RingAda: Pipelining Large Model Fine-Tuning on Edge Devices with Scheduled Layer Unfreezing
par: Li, Liang, et autres
Publié: (2025)

DMSA: A Decentralized Microservice Architecture for Edge Networks
par: Chen, Yuang, et autres
Publié: (2025)

Edge Deployment of Small Language Models, a comprehensive comparison of CPU, GPU and NPU backends
par: Prieto, Pablo, et autres
Publié: (2025)

Recall: Empowering Multimodal Embedding for Edge Devices
par: Cai, Dongqi, et autres
Publié: (2024)

Parallel Imports and Product Quality in the Presence of Price Control
par: Chin‐Sheng Chen, et autres
Publié: (2025)

Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-play Neural Network Toolbox Enabling Edge Deployment
par: Wu, Jiaqi, et autres
Publié: (2024)

TIGER: Text-Instructed 3D Gaussian Retrieval and Coherent Editing
par: Xu, Teng, et autres
Publié: (2024)

LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load
par: Tummalapalli, Pranay, et autres
Publié: (2026)

Space-ground Fluid AI for 6G Edge Intelligence
par: Chen, Qian, et autres
Publié: (2024)

Learning to Adapt SFT Data for Better Reasoning Generalization
par: Sun, Lisong, et autres
Publié: (2026)

AuroraEdge-V-2B: A Faster And Stronger Edge Visual Large Language Model
par: Chen, Xiang
Publié: (2026)

Collaborative Edge AI Inference over Cloud-RAN
par: Zhang, Pengfei, et autres
Publié: (2024)

Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
par: Peng, Ruiying, et autres
Publié: (2026)

T-Edge: Trusted Heterogeneous Edge Computing
par: Shen, Jiamin, et autres
Publié: (2024)

Sequential Bayesian Optimal Experimental Design in Infinite Dimensions via Policy Gradient Reinforcement Learning
par: Shen, Kaichen, et autres
Publié: (2026)

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference
par: Chen, Chun-Ting, et autres
Publié: (2025)

Personalized Federated Distillation Assisted Vehicle Edge Caching Strategy
par: Li, Xun, et autres
Publié: (2025)

Anderson Localization for Schrödinger Operators with Monotone Potentials Generated by the Doubling Map
par: Peng, Yuanyuan, et autres
Publié: (2026)

Towards Efficient Multi-Scale Deformable Attention on NPU
par: Huang, Chenghuan, et autres
Publié: (2025)

Energy-Efficient Federated Edge Learning For Small-Scale Datasets in Large IoT Networks
par: Xie, Haihui, et autres
Publié: (2026)

GraphEdge: Dynamic Graph Partition and Task Scheduling for GNNs Computing in Edge Network
par: Xiao, Wenjing, et autres
Publié: (2025)

Multidimensional coherent spectroscopy of correlated lattice systems
par: Chen, Jiyu, et autres
Publié: (2024)

Efficient Polarization Demosaicking via Low-cost Edge-aware and Inter-channel Correlation
par: Liu, Guangsen, et autres
Publié: (2024)

Optimizing Edge Active Sites via Intrinsic In‐Plane Iridium Deficiency in Layered Iridium Oxides for Oxygen Evolution Electrocatalysis
par: Lina Wang, et autres
Publié: (2024)

An imperceptible connection between the Clebsch--Gordan coefficients of $U_q(\mathfrak{sl}_2)$ and the Terwilliger algebras of Grassmann graphs
par: Huang, Hau-Wen
Publié: (2023)

Verma modules and finite-dimensional irreducible modules of the universal Askey--Wilson algebra at roots of unity
par: Huang, Hau-Wen
Publié: (2024)

A way to treat dual Hahn polynomials as Racah polynomials via the theory of Leonard pairs
par: Huang, Hau-Wen
Publié: (2025)

The Askey--Wilson algebras, the Lie algebra $\mathfrak{so}_{3}$, and their fermionic realizations
par: Huang, Hau-Wen
Publié: (2025)

SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference
par: Chen, Qian, et autres
Publié: (2025)

Improved Streaming Edge Coloring
par: Chechik, Shiri, et autres
Publié: (2025)

Full‐Stokes Polarization Bifocal Plane Metasurface with Bright‐Field and Edge‐Enhanced Imaging
par: Peng Zhou, et autres
Publié: (2025)

Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations
par: Liu, Zijie, et autres
Publié: (2025)