{"total":160,"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":"2108.04392","title":"Rethinking Architecture Selection in Differentiable NAS","created":"2021-08-10","cited_by_count":92,"area":null},{"id":"2104.01177","title":"How Powerful are Performance Predictors in Neural Architecture Search?","created":"2021-04-02","cited_by_count":90,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78,"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":"2301.11300","title":"ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2106.15098","title":"Molecule Generation by Principal Subgraph Mining and Assembling","created":"2021-06-29","cited_by_count":54,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2402.11137","title":"TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks","created":"2024-02-17","cited_by_count":47,"area":null},{"id":"2201.13396","title":"NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy","created":"2022-01-31","cited_by_count":36,"area":null},{"id":"2103.05471","title":"Contrastive Neural Architecture Search with Neural Architecture Comparators","created":"2021-03-08","cited_by_count":34,"area":null},{"id":"2107.00860","title":"Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets","created":"2021-07-02","cited_by_count":33,"area":null},{"id":"2102.04040","title":"LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search","created":"2021-02-08","cited_by_count":28,"area":null},{"id":"2102.10490","title":"Stronger NAS with Weaker Predictors","created":"2021-02-21","cited_by_count":28,"area":null},{"id":"2109.00817","title":"NASI: Label- and Data-agnostic Neural Architecture Search at Initialization","created":"2021-09-02","cited_by_count":28,"area":null},{"id":"2101.11342","title":"Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search","created":"2021-01-27","cited_by_count":27,"area":null},{"id":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2203.15207","title":"Generalizing Few-Shot NAS with Gradient Matching","created":"2022-03-29","cited_by_count":25,"area":null},{"id":"2206.09811","title":"Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search","created":"2022-06-20","cited_by_count":23,"area":null},{"id":"2102.05610","title":"Searching for Fast Model Families on Datacenter Accelerators","created":"2021-02-10","cited_by_count":22,"area":null},{"id":"2110.10423","title":"ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies","created":"2021-10-20","cited_by_count":22,"area":null},{"id":"2102.07108","title":"CATE: Computation-aware Neural Architecture Encoding with Transformers","created":"2021-02-14","cited_by_count":21,"area":null},{"id":"2307.01998","title":"Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities","created":"2023-07-05","cited_by_count":21,"area":null},{"id":"2108.12821","title":"Analyzing and Mitigating Interference in Neural Architecture Search","created":"2021-08-29","cited_by_count":20,"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":"2201.09785","title":"Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search","created":"2022-01-24","cited_by_count":17,"area":null},{"id":"2210.06545","title":"GULP: a prediction-based metric between representations","created":"2022-10-12","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":"2303.07065","title":"MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID","created":"2023-03-13","cited_by_count":16,"area":null},{"id":"2203.08734","title":"Learning Where To Look -- Generative NAS is Surprisingly Efficient","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2503.17286","title":"Offline Model-Based Optimization: Comprehensive Review","created":"2025-03-21","cited_by_count":15,"area":null},{"id":"2106.09309","title":"Layer Folding: Neural Network Depth Reduction using Activation Linearization","created":"2021-06-17","cited_by_count":14,"area":null},{"id":"2303.01980","title":"Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecycle","created":"2023-02-05","cited_by_count":14,"area":null},{"id":"2403.06020","title":"Multi-conditioned Graph Diffusion for Neural Architecture Search","created":"2024-03-09","cited_by_count":14,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2211.08024","title":"NAR-Former: Neural Architecture Representation Learning towards Holistic Attributes Prediction","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2409.12255","title":"Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2108.01265","title":"Memorize, Factorize, or be Na\\\"ive: Learning Optimal Feature Interaction Methods for CTR Prediction","created":"2021-08-03","cited_by_count":12,"area":null},{"id":"2206.01520","title":"A Survey on Computationally Efficient Neural Architecture Search","created":"2022-06-03","cited_by_count":12,"area":null},{"id":"2404.16551","title":"Surprisingly Strong Performance Prediction with Neural Graph Features","created":"2024-04-25","cited_by_count":11,"area":null},{"id":"2108.04541","title":"Accelerating Evolutionary Neural Architecture Search via Multi-Fidelity Evaluation","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2108.11014","title":"iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization","created":"2021-08-25","cited_by_count":10,"area":null},{"id":"2209.10091","title":"Variational Inference for Infinitely Deep Neural Networks","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2309.02064","title":"MvFS: Multi-view Feature Selection for Recommender System","created":"2023-09-05","cited_by_count":10,"area":null},{"id":"2403.12821","title":"FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer","created":"2024-03-19","cited_by_count":10,"area":null},{"id":"2103.13253","title":"Learning Versatile Neural Architectures by Propagating Network Codes","created":"2021-03-24","cited_by_count":9,"area":null},{"id":"2104.08702","title":"Reconsidering CO2 emissions from Computer Vision","created":"2021-04-18","cited_by_count":9,"area":null},{"id":"2106.06799","title":"Zero-Cost Operation Scoring in Differentiable Architecture Search","created":"2021-06-12","cited_by_count":9,"area":null},{"id":"2108.08019","title":"RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving","created":"2021-08-18","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":"2206.06292","title":"MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing","created":"2022-06-13","cited_by_count":9,"area":null},{"id":"2206.06620","title":"Slimmable Domain Adaptation","created":"2022-06-14","cited_by_count":9,"area":null},{"id":"2102.06599","title":"Neural Architecture Search as Program Transformation Exploration","created":"2021-02-12","cited_by_count":8,"area":null},{"id":"2103.01495","title":"Task-Adaptive Neural Network Search with Meta-Contrastive Learning","created":"2021-03-02","cited_by_count":8,"area":null},{"id":"2104.05309","title":"Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2205.05844","title":"Bi-level Alignment for Cross-Domain Crowd Counting","created":"2022-05-12","cited_by_count":8,"area":null},{"id":"2502.04573","title":"Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer","created":"2025-02-06","cited_by_count":8,"area":null},{"id":"2103.12827","title":"Fisher Task Distance and Its Application in Neural Architecture Search","created":"2021-03-23","cited_by_count":7,"area":null},{"id":"2108.11105","title":"Lightweight Monocular Depth with a Novel Neural Architecture Search Method","created":"2021-08-25","cited_by_count":7,"area":null},{"id":"2208.06064","title":"Mixed-Precision Neural Networks: A Survey","created":"2022-08-11","cited_by_count":7,"area":null},{"id":"2301.09231","title":"GP-NAS-ensemble: a model for NAS Performance Prediction","created":"2023-01-23","cited_by_count":7,"area":null},{"id":"2306.10792","title":"NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2308.07760","title":"Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2105.11694","title":"FNAS: Uncertainty-Aware Fast Neural Architecture Search","created":"2021-05-25","cited_by_count":6,"area":null},{"id":"2106.08505","title":"Dynamically Grown Generative Adversarial Networks","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2111.04670","title":"Approximate Neural Architecture Search via Operation Distribution Learning","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2205.15254","title":"Pooling Revisited: Your Receptive Field is Suboptimal","created":"2022-05-30","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":"2306.05031","title":"Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations","created":"2023-06-08","cited_by_count":6,"area":null},{"id":"2105.04885","title":"Graph-based Neural Architecture Search with Operation Embeddings","created":"2021-05-11","cited_by_count":5,"area":null},{"id":"2110.13570","title":"Learning Graph Representation of Person-specific Cognitive Processes from Audio-visual Behaviours for Automatic Personality Recognition","created":"2021-10-26","cited_by_count":5,"area":null},{"id":"2201.12725","title":"Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2211.15155","title":"GraphPNAS: Learning Distribution of Good Neural Architectures via Deep Graph Generative Models","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2305.14065","title":"Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2309.09507","title":"Pruning Large Language Models via Accuracy Predictor","created":"2023-09-18","cited_by_count":5,"area":null},{"id":"2402.02105","title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","created":"2024-02-03","cited_by_count":5,"area":null},{"id":"2402.03480","title":"Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2403.05064","title":"Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision","created":"2024-03-08","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":"2406.02056","title":"CAP: A Context-Aware Neural Predictor for NAS","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2505.07300","title":"L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2104.09048","title":"Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS","created":"2021-04-19","cited_by_count":4,"area":null},{"id":"2106.02229","title":"Differentiable Architecture Search for Reinforcement Learning","created":"2021-06-04","cited_by_count":4,"area":null},{"id":"2206.05625","title":"Exploring the Intersection between Neural Architecture Search and Continual Learning","created":"2022-06-11","cited_by_count":4,"area":null},{"id":"2206.11239","title":"FedorAS: Federated Architecture Search under system heterogeneity","created":"2022-06-22","cited_by_count":4,"area":null},{"id":"2306.03387","title":"ColdNAS: Search to Modulate for User Cold-Start Recommendation","created":"2023-06-06","cited_by_count":4,"area":null},{"id":"2403.07591","title":"Robustifying and Boosting Training-Free Neural Architecture Search","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2409.09085","title":"HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning","created":"2024-09-11","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":"2110.08562","title":"BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements","created":"2021-10-16","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":"2302.00932","title":"Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS \"Cold-Start\"","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2304.08498","title":"Ranking Loss and Sequestering Learning for Reducing Image Search Bias in Histopathology","created":"2023-04-15","cited_by_count":3,"area":null},{"id":"2411.15731","title":"Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2503.02978","title":"Integrating Predictive and Generative Capabilities by Latent Space Design via the DKL-VAE Model","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2507.00880","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","created":"2025-07-01","cited_by_count":3,"area":null},{"id":"2103.07018","title":"Interleaving Learning, with Application to Neural Architecture Search","created":"2021-03-12","cited_by_count":2,"area":null},{"id":"2106.02738","title":"Encoder-Decoder Neural Architecture Optimization for Keyword Spotting","created":"2021-06-04","cited_by_count":2,"area":null}],"next_cursor":"100"}