{"total":81,"rows":[{"id":"2103.00710","title":"Towards Personalized Federated Learning","created":"2021-03-01","cited_by_count":464,"area":null},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2304.10970","title":"Can GPT-4 Perform Neural Architecture Search?","created":"2023-04-21","cited_by_count":74,"area":null},{"id":"2102.01063","title":"Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition","created":"2021-02-01","cited_by_count":73,"area":null},{"id":"2103.12424","title":"BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search","created":"2021-03-23","cited_by_count":63,"area":null},{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56,"area":null},{"id":"2106.10784","title":"iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients","created":"2021-06-21","cited_by_count":51,"area":null},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37,"area":null},{"id":"2102.07954","title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","created":"2021-02-16","cited_by_count":36,"area":null},{"id":"2206.14532","title":"Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?","created":"2022-06-29","cited_by_count":32,"area":"distill"},{"id":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29,"area":"distill"},{"id":"2512.11130","title":"Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching","created":"2025-12-11","cited_by_count":28,"area":"distill"},{"id":"2109.15099","title":"PP-LCNet: A Lightweight CPU Convolutional Neural Network","created":"2021-09-17","cited_by_count":27,"area":null},{"id":"2105.06047","title":"Compatibility-aware Heterogeneous Visual Search","created":"2021-05-13","cited_by_count":23,"area":null},{"id":"2201.06227","title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing","created":"2022-01-17","cited_by_count":22,"area":null},{"id":"2303.07129","title":"AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments","created":"2023-03-13","cited_by_count":19,"area":null},{"id":"2108.00386","title":"WAS-VTON: Warping Architecture Search for Virtual Try-on Network","created":"2021-08-01","cited_by_count":18,"area":null},{"id":"2411.19146","title":"Puzzle: Distillation-Based NAS for Inference-Optimized LLMs","created":"2024-11-28","cited_by_count":17,"area":null},{"id":"2109.07222","title":"EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation","created":"2021-09-15","cited_by_count":15,"area":"distill"},{"id":"2108.09671","title":"Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift","created":"2021-08-22","cited_by_count":14,"area":null},{"id":"2112.10652","title":"HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet","created":"2021-12-20","cited_by_count":14,"area":null},{"id":"2303.02165","title":"DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network","created":"2023-03-05","cited_by_count":14,"area":null},{"id":"2104.00597","title":"One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking","created":"2021-04-01","cited_by_count":12,"area":null},{"id":"2302.05666","title":"Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels","created":"2023-02-11","cited_by_count":12,"area":"distill"},{"id":"2403.07134","title":"COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization","created":"2024-03-11","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":"2104.08702","title":"Reconsidering CO2 emissions from Computer Vision","created":"2021-04-18","cited_by_count":9,"area":null},{"id":"2107.00254","title":"AdaXpert: Adapting Neural Architecture for Growing Data","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2204.05941","title":"Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search","created":"2022-04-12","cited_by_count":9,"area":null},{"id":"2205.08119","title":"ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks","created":"2022-05-17","cited_by_count":8,"area":null},{"id":"2201.09724","title":"Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image Retrieval","created":"2022-01-24","cited_by_count":7,"area":null},{"id":"2301.06393","title":"$\\beta$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search","created":"2023-01-16","cited_by_count":7,"area":null},{"id":"2109.10060","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","created":"2021-09-21","cited_by_count":6,"area":null},{"id":"2210.07271","title":"BLOX: Macro Neural Architecture Search Benchmark and Algorithms","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2111.13204","title":"BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule","created":"2021-11-25","cited_by_count":5,"area":null},{"id":"2209.13139","title":"Searching a High-Performance Feature Extractor for Text Recognition Network","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2410.00350","title":"Efficient Training of Large Vision Models via Advanced Automated Progressive Learning","created":"2024-09-06","cited_by_count":5,"area":"diffusion"},{"id":"2206.11239","title":"FedorAS: Federated Architecture Search under system heterogeneity","created":"2022-06-22","cited_by_count":4,"area":null},{"id":"2207.07267","title":"ScaleNet: Searching for the Model to Scale","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2210.07634","title":"Pareto-aware Neural Architecture Generation for Diverse Computational Budgets","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2306.09295","title":"Neural Fine-Tuning Search for Few-Shot Learning","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2307.08300","title":"ShiftNAS: Improving One-shot NAS via Probability Shift","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2309.06047","title":"Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2311.04943","title":"MathNAS: If Blocks Have a Role in Mathematical Architecture Design","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2311.04950","title":"Lightweight Diffusion Models with Distillation-Based Block Neural Architecture Search","created":"2023-11-08","cited_by_count":4,"area":"diffusion"},{"id":"2403.01326","title":"DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions","created":"2024-03-02","cited_by_count":4,"area":null},{"id":"2103.07009","title":"Learning by Teaching, with Application to Neural Architecture Search","created":"2021-03-11","cited_by_count":3,"area":null},{"id":"2107.07173","title":"Scene-adaptive Knowledge Distillation for Sequential Recommendation via Differentiable Architecture Search","created":"2021-07-15","cited_by_count":3,"area":"distill"},{"id":"2111.03555","title":"AUTOKD: Automatic Knowledge Distillation Into A Student Architecture Family","created":"2021-11-05","cited_by_count":3,"area":"distill"},{"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":"2210.17180","title":"Automated Dominative Subspace Mining for Efficient Neural Architecture Search","created":"2022-10-31","cited_by_count":3,"area":null},{"id":"2301.12443","title":"Pipe-BD: Pipelined Parallel Blockwise Distillation","created":"2023-01-29","cited_by_count":3,"area":null},{"id":"2103.16889","title":"Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2204.03916","title":"A Survey of Supernet Optimization and its Applications: Spatial and Temporal Optimization for Neural Architecture Search","created":"2022-04-08","cited_by_count":2,"area":null},{"id":"2301.08092","title":"RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation","created":"2023-01-19","cited_by_count":2,"area":"distill"},{"id":"2303.08360","title":"Knowledge Distillation from Single to Multi Labels: an Empirical Study","created":"2023-03-15","cited_by_count":2,"area":"distill"},{"id":"2311.18451","title":"How Much Is Hidden in the NAS Benchmarks? Few-Shot Adaptation of a NAS Predictor","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2312.14200","title":"Efficient Architecture Search via Bi-level Data Pruning","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2207.04821","title":"Long-term Reproducibility for Neural Architecture Search","created":"2022-07-11","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":"2303.08308","title":"SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2311.13169","title":"SiGeo: Sub-One-Shot NAS via Information Theory and Geometry of Loss Landscape","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2407.20062","title":"SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation","created":"2024-07-29","cited_by_count":1,"area":"distill"},{"id":"2409.17566","title":"Flexiffusion: Segment-wise Neural Architecture Search for Flexible Denoising Schedule","created":"2024-09-26","cited_by_count":1,"area":"diffusion"},{"id":"2506.02488","title":"Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models","created":"2025-06-03","cited_by_count":1,"area":"diffusion"},{"id":"2511.21136","title":"Efficient Training for Human Video Generation with Entropy-Guided Prioritized Progressive Learning","created":"2025-11-26","cited_by_count":1,"area":"diffusion"},{"id":"2104.11522","title":"Conditional super-network weights","created":"2021-04-23","cited_by_count":0,"area":null},{"id":"2107.04324","title":"Mutually-aware Sub-Graphs Differentiable Architecture Search","created":"2021-07-09","cited_by_count":0,"area":null},{"id":"2107.07331","title":"A Light-weight Deep Human Activity Recognition Algorithm Using Multi-knowledge Distillation","created":"2021-07-06","cited_by_count":0,"area":"distill"},{"id":"2108.09996","title":"MS-DARTS: Mean-Shift Based Differentiable Architecture Search","created":"2021-08-23","cited_by_count":0,"area":null},{"id":"2303.01913","title":"Bespoke: A Block-Level Neural Network Optimization Framework for Low-Cost Deployment","created":"2023-03-03","cited_by_count":0,"area":null},{"id":"2308.15003","title":"Generative Model for Models: Rapid DNN Customization for Diverse Tasks and Resource Constraints","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2309.14670","title":"DONNAv2 -- Lightweight Neural Architecture Search for Vision tasks","created":"2023-09-26","cited_by_count":0,"area":null},{"id":"2310.15074","title":"MGAS: Multi-Granularity Architecture Search for Trade-Off Between Model Effectiveness and Efficiency","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2312.16046","title":"AdaNAS: Adaptively Post-processing with Self-supervised Neural Architecture Search for Ensemble Rainfall Forecasts","created":"2023-12-26","cited_by_count":0,"area":null},{"id":"2401.12350","title":"Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2504.20080","title":"DNAD: Differentiable Neural Architecture Distillation","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2511.21122","title":"Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2607.01387","title":"Bi-NAS: Towards Effective and Personalized Explanation for Recommender Systems via Bi-Level Neural Architecture Search","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.23752","title":"Too much of a good thing -- when knowledge distillation promotes overfitting, and how to avoid it","created":"2026-08-24","cited_by_count":0,"area":"distill"}],"next_cursor":null}