{"total":76,"rows":[{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169,"area":null},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61,"area":null},{"id":"2203.13471","title":"Non-Probability Sampling Network for Stochastic Human Trajectory Prediction","created":"2022-03-25","cited_by_count":46,"area":null},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2101.08467","title":"CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification","created":"2021-01-21","cited_by_count":38,"area":null},{"id":"2110.12007","title":"When to Prune? A Policy towards Early Structural Pruning","created":"2021-10-22","cited_by_count":38,"area":null},{"id":"2108.13041","title":"Auto-Split: A General Framework of Collaborative Edge-Cloud AI","created":"2021-08-30","cited_by_count":30,"area":null},{"id":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20,"area":null},{"id":"2211.13955","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","created":"2022-11-25","cited_by_count":20,"area":null},{"id":"2101.08809","title":"PyGlove: Symbolic Programming for Automated Machine Learning","created":"2021-01-21","cited_by_count":19,"area":null},{"id":"2110.08616","title":"GradSign: Model Performance Inference with Theoretical Insights","created":"2021-10-16","cited_by_count":19,"area":null},{"id":"2102.10301","title":"Towards Accurate and Compact Architectures via Neural Architecture Transformer","created":"2021-02-20","cited_by_count":17,"area":null},{"id":"2306.14306","title":"Adaptive Sharpness-Aware Pruning for Robust Sparse Networks","created":"2023-06-25","cited_by_count":17,"area":null},{"id":"2310.18329","title":"Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices","created":"2023-10-19","cited_by_count":17,"area":null},{"id":"2106.08630","title":"HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning","created":"2021-06-16","cited_by_count":16,"area":null},{"id":"2110.00337","title":"PhiNets: a scalable backbone for low-power AI at the edge","created":"2021-10-01","cited_by_count":16,"area":null},{"id":"2111.10007","title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","created":"2021-11-19","cited_by_count":15,"area":null},{"id":"2104.00031","title":"NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization","created":"2021-03-31","cited_by_count":13,"area":null},{"id":"2102.08619","title":"Rethinking Co-design of Neural Architectures and Hardware Accelerators","created":"2021-02-17","cited_by_count":12,"area":null},{"id":"2211.02206","title":"Soft Masking for Cost-Constrained Channel Pruning","created":"2022-11-04","cited_by_count":12,"area":null},{"id":"2107.10624","title":"LANA: Latency Aware Network Acceleration","created":"2021-07-12","cited_by_count":11,"area":"distill"},{"id":"2103.13253","title":"Learning Versatile Neural Architectures by Propagating Network Codes","created":"2021-03-24","cited_by_count":9,"area":null},{"id":"2401.13330","title":"NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks","created":"2024-01-24","cited_by_count":9,"area":null},{"id":"2110.10811","title":"HALP: Hardware-Aware Latency Pruning","created":"2021-10-20","cited_by_count":8,"area":null},{"id":"2111.01203","title":"One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search","created":"2021-11-01","cited_by_count":8,"area":null},{"id":"2112.02086","title":"Data-Free Neural Architecture Search via Recursive Label Calibration","created":"2021-12-03","cited_by_count":8,"area":null},{"id":"2203.06810","title":"Automated Learning for Deformable Medical Image Registration by Jointly Optimizing Network Architectures and Objective Functions","created":"2022-03-14","cited_by_count":8,"area":null},{"id":"2109.07582","title":"Pareto-wise Ranking Classifier for Multi-objective Evolutionary Neural Architecture Search","created":"2021-09-14","cited_by_count":7,"area":null},{"id":"2111.11581","title":"Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration","created":"2021-11-22","cited_by_count":7,"area":null},{"id":"2209.15560","title":"Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge Distillation","created":"2022-09-30","cited_by_count":7,"area":"distill"},{"id":"2306.02459","title":"Multi-Predict: Few Shot Predictors For Efficient Neural Architecture Search","created":"2023-06-04","cited_by_count":6,"area":null},{"id":"2103.11833","title":"AutoSpace: Neural Architecture Search with Less Human Interference","created":"2021-03-22","cited_by_count":5,"area":null},{"id":"2111.15106","title":"MAPLE: Microprocessor A Priori for Latency Estimation","created":"2021-11-30","cited_by_count":5,"area":null},{"id":"2208.06820","title":"Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation","created":"2022-08-14","cited_by_count":5,"area":null},{"id":"2210.01384","title":"Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2212.03965","title":"CODEBench: A Neural Architecture and Hardware Accelerator Co-Design Framework","created":"2022-12-07","cited_by_count":5,"area":null},{"id":"2303.13121","title":"DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filter","created":"2023-03-23","cited_by_count":5,"area":null},{"id":"2406.01414","title":"CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2111.12299","title":"EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search","created":"2021-11-24","cited_by_count":4,"area":null},{"id":"2204.04918","title":"When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2204.12950","title":"MAPLE-Edge: A Runtime Latency Predictor for Edge Devices","created":"2022-04-27","cited_by_count":3,"area":null},{"id":"2207.05321","title":"Bi-fidelity Evolutionary Multiobjective Search for Adversarially Robust Deep Neural Architectures","created":"2022-07-12","cited_by_count":3,"area":null},{"id":"2505.12523","title":"Energy-Aware Deep Learning on Resource-Constrained Hardware","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2109.02909","title":"BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables","created":"2021-09-07","cited_by_count":2,"area":null},{"id":"2203.12412","title":"U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search","created":"2022-03-23","cited_by_count":2,"area":null},{"id":"2301.04502","title":"Pruning Compact ConvNets for Efficient Inference","created":"2023-01-11","cited_by_count":2,"area":null},{"id":"2303.13745","title":"EdgeTran: Co-designing Transformers for Efficient Inference on Mobile Edge Platforms","created":"2023-03-24","cited_by_count":2,"area":null},{"id":"2401.16760","title":"One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2607.06922","title":"Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2101.11800","title":"AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications","created":"2021-01-28","cited_by_count":1,"area":null},{"id":"2107.08815","title":"Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data","created":"2021-07-16","cited_by_count":1,"area":null},{"id":"2107.11170","title":"Bias Loss for Mobile Neural Networks","created":"2021-07-23","cited_by_count":1,"area":null},{"id":"2109.05432","title":"Prioritized Subnet Sampling for Resource-Adaptive Supernet Training","created":"2021-09-12","cited_by_count":1,"area":null},{"id":"2110.05842","title":"Across-Task Neural Architecture Search via Meta Learning","created":"2021-10-12","cited_by_count":1,"area":null},{"id":"2110.10876","title":"Evolving Transferable Neural Pruning Functions","created":"2021-10-21","cited_by_count":1,"area":null},{"id":"2203.13921","title":"A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural Accelerators","created":"2022-03-25","cited_by_count":1,"area":null},{"id":"2208.10498","title":"Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey","created":"2022-08-22","cited_by_count":1,"area":null},{"id":"2210.02620","title":"Inference Latency Prediction at the Edge","created":"2022-10-06","cited_by_count":1,"area":null},{"id":"2304.06393","title":"Learning Accurate Performance Predictors for Ultrafast Automated Model Compression","created":"2023-04-13","cited_by_count":1,"area":null},{"id":"2305.14403","title":"Layer-adaptive Structured Pruning Guided by Latency","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2406.00291","title":"Multi-Objective Neural Architecture Search by Learning Search Space Partitions","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2409.01089","title":"CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2412.00724","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2607.08013","title":"Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2102.10435","title":"MHDeep: Mental Health Disorder Detection System based on Body-Area and Deep Neural Networks","created":"2021-02-20","cited_by_count":0,"area":null},{"id":"2108.03001","title":"Learning to Rank Ace Neural Architectures via Normalized Discounted Cumulative Gain","created":"2021-08-06","cited_by_count":0,"area":null},{"id":"2203.15408","title":"AutoCoMet: Smart Neural Architecture Search via Co-Regulated Shaping Reinforcement","created":"2022-03-29","cited_by_count":0,"area":null},{"id":"2209.11785","title":"Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search","created":"2022-09-23","cited_by_count":0,"area":null},{"id":"2301.01758","title":"An Ensemble Mobile-Cloud Computing Method for Affordable and Accurate Glucometer Readout","created":"2023-01-04","cited_by_count":0,"area":null},{"id":"2306.05021","title":"Mixed-TD: Efficient Neural Network Accelerator with Layer-Specific Tensor Decomposition","created":"2023-06-08","cited_by_count":0,"area":null},{"id":"2310.07940","title":"Cost-Driven Hardware-Software Co-Optimization of Machine Learning Pipelines","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2311.05827","title":"AccEPT: An Acceleration Scheme for Speeding Up Edge Pipeline-parallel Training","created":"2023-11-10","cited_by_count":0,"area":null},{"id":"2402.13525","title":"MatchNAS: Optimizing Edge AI in Sparse-Label Data Contexts via Automating Deep Neural Network Porting for Mobile Deployment","created":"2024-02-21","cited_by_count":0,"area":null},{"id":"2501.16397","title":"THOR: A Generic Energy Estimation Approach for On-Device Training","created":"2025-01-27","cited_by_count":0,"area":null},{"id":"2605.21560","title":"AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems","created":"2026-05-20","cited_by_count":0,"area":"agents"},{"id":"2607.09063","title":"EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}