惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

U
Unit 42
V
V2EX
Martin Fowler
Martin Fowler
博
博客园 - Franky
P
Proofpoint News Feed
P
Palo Alto Networks Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
B
Blog
The Register - Security
The Register - Security
Latest news
Latest news
S
Security @ Cisco Blogs
Simon Willison's Weblog
Simon Willison's Weblog
Recorded Future
Recorded Future
大猫的无限游戏
大猫的无限游戏
M
Microsoft Research Blog - Microsoft Research
Scott Helme
Scott Helme
T
Tailwind CSS Blog
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Application and Cybersecurity Blog
Application and Cybersecurity Blog
T
True Tiger Recordings
有赞技术团队
有赞技术团队
I
Intezer
Cisco Talos Blog
Cisco Talos Blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
The GitHub Blog
The GitHub Blog
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
T
Tenable Blog
博
博客园 - 叶小钗
Hugging Face - Blog
Hugging Face - Blog
Hacker News: Ask HN
Hacker News: Ask HN
S
Security Archives - TechRepublic
F
Future of Privacy Forum
爱范儿
爱范儿
PCI Perspectives
PCI Perspectives
H
Help Net Security
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
T
The Blog of Author Tim Ferriss
MyScale Blog
MyScale Blog
N
Netflix TechBlog - Medium
罗
罗磊的独立博客
Apple Machine Learning Research
Apple Machine Learning Research
MongoDB | Blog
MongoDB | Blog
Security Latest
Security Latest
美
美团技术团队
博
博客园 - 三生石上(FineUI控件)
S
Schneier on Security
量
量子位
C
CERT Recently Published Vulnerability Notes
SecWiki News
SecWiki News

cs.LG updates on arXiv.org

Provable Joint Decontamination for Benchmarking Multiple Large Language Models Tabular foundation models for robust calibration of near-infrared chemical sensing data DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models Predicting Performance of Symbolic and Prompt Programs with Examples Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study Embedding-Based Federated Learning with Runtime Governance for Iron Deficiency Prediction Objective-Induced Bias and Search Dynamics in Multiobjective Unsupervised Feature Selection The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding Discovering Entity-Conditioned Lag Heterogeneity: A Lag-Gated Neural Audit Framework for Panel Time Series A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift Leveraging Self-Paced Curriculum Learning for Enhanced Modality Balance in Multimodal Conversational Emotion Recognition Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising Harnesses for Inference-Time Alignment over Execution Trajectories Double descent for least-squares interpolation on contaminated data: A simulation study TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation HealthCraft: A Reinforcement Learning Safety Environment for Emergency Medicine Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds OpenSeisML: Open Large-Scale Real Seismic and well-log Dataset for Generative AI ReversedQ: Opportunities for Faster Q-Learning in Episodic Online Reinforcement Learning Online Conformal Prediction with Corrupted Feedback TreeText-CTS: Compact, Source-Traceable Tree-Path Evidence for Irregular Clinical Time-Series Prediction SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning Mechanisms of Misgeneralization in Physical Sequence Modeling PACD-Net: Pseudo-Augmented Contrastive Distillation for Glycemic Control Estimation from SMBG OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning Nonlocal operator learning for fMRI encoding and decoding tasks LT2: Linear-Time Looped Transformers Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages Supervised Latent Restructuring for Small-Data Quantum Learning in Plant Phenomics LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series Quadratic Characterizations for Reachability Analysis of Neural Networks Score-Based Causal Discovery of Latent Variable Causal Models Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure? Robust Subspace-Constrained Quadratic Models for Low-Dimensional Structure Learning Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression A 10,000-Year Global Stochastic Tropical Cyclone Catalog with Wind-Dependent Track Transitions (WHITS) Modular Multimodal Classification Without Fine-Tuning: A Simple Compositional Approach TriForces: Augmenting Atomistic GNNs for Transferable Representations Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detection CASCADE Conformal Prediction: Uncertainty-Adaptive Prediction Intervals for Two-Stage Clinical Decision Support Unsupervised clustering and classification of upper limb EMG signals during functional movements: a data-driven REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak The General Theory of Localization Methods Neural Collapse by Design: Learning Class Prototypes on the Hypersphere Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning Deep Learning Surrogates for Emulating Stochastic Climate Tipping Dynamics Robust Recommendation from Noisy Implicit Feedback: A GMM-Weighted Bayes-label Transition Matrix Framework Decision-Path Patterns as Tree Reliability Signals: Path-based Adaptive Weighting for Random Forest Classification AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases ShapeBench: A Scalable Benchmark and Diagnostic Suite for Standardized Evaluation in Aerodynamic Shape Optimization WaveGraphNet: Physics-Consistent Guided-Wave Damage Localization through Coupled Inverse-Forward Graph Learning Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics Correcting Stochastic Update Bias in Preconditioned Language Model Optimizers Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels Group-Algebraic Tensors: Provably-optimal Equivariant Learning and Physical Symmetry Discovery Reinforcing Human Behavior Simulation via Verbal Feedback An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Spectral Souping: A Unified Framework for Online Preference Alignment Miller-Index-Based Latent Crystallographic Fracture Plane Reasoning with Vision-Language Models Causal Machine Learning Is Not a Panacea: A Roadmap for Observational Causal Inference in Health Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data Axiomatizing Neural Networks via Pursuit of Subspaces Training Language Agents to Learn from Experience Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates Dynamic Shapley Computation Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions Design for Manufacturing: A Manufacturability Knowledge-Integrated Reinforcement Learning Framework for Free-Form Pipe Routing in Aeroengines Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs Distributed Direct Preference Optimization Can Conversational XAI Improve User Performance? An Experimental Study Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions FusionCell: Cross-Attentive Fusion of Layout Geometry and Netlist Topology for Standard-Cell Performance Prediction ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity AirfoilGen: A valid-by-construction and performance-aware latent diffusion model for airfoil generation Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front Matryoshka Concept Bottleneck Models Latent Process Generator Matching Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers
AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems
Penglin Dai, · 2026-05-23 · via cs.LG updates on arXiv.org

View PDF HTML (experimental)

Abstract:Deploying neural networks on microcontroller units (MCUs) is critical for edge intelligence but remains challenging due to tight memory, storage, and computation constraints. Existing approaches, such as model compression and hardware-aware neural architecture search (HW-NAS), often depend on proxy metrics, incur high search cost, and do not fully bridge the gap between architecture design and verified deployment. This paper presents AutoMCU, a feasibility-first large language model (LLM)-based multi-agent system for automated neural network customization under MCU constraints. Given natural-language task requirements and hardware specifications, AutoMCU iteratively generates structured architecture candidates, filters infeasible designs through vendor toolchain feedback before training, evaluates feasible models under a controlled protocol, and verifies deployability through backend-grounded deployment analysis. AutoMCU includes two key mechanisms: 1) hardware-in-the-loop architecture generation for early elimination of undeployable candidates under RAM and Flash constraints, and 2) state-isolated multi-agent scheduling for stable coordination of proposal, training, evaluation, and deployment stages. Experiments on CIFAR-10 and CIFAR-100 under strict MCU constraints show that AutoMCU achieves competitive accuracy while reducing customization time to about 1--2 hours, compared with hundreds of GPU hours for representative MCU-oriented HW-NAS baselines. Comparisons with ColabNAS and the LLM-based NAS method GENIUS on NAS-Bench-201 further demonstrate the effectiveness and stability of AutoMCU. Real-device deployments on multiple STM32 microcontrollers validate its practical applicability to MCU-scale edge intelligence.
Subjects: Machine Learning (cs.LG)
Cite as: arXiv:2605.21560 [cs.LG]
  (or arXiv:2605.21560v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2605.21560

arXiv-issued DOI via DataCite

Submission history

From: Zijie Zhou [view email]
[v1] Wed, 20 May 2026 14:59:17 UTC (3,036 KB)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。