{"total":37,"rows":[{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633,"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":"2106.02898","title":"Dynamic Resolution Network","created":"2021-06-05","cited_by_count":31,"area":null},{"id":"2102.10490","title":"Stronger NAS with Weaker Predictors","created":"2021-02-21","cited_by_count":28,"area":null},{"id":"2106.15941","title":"Augmented Shortcuts for Vision Transformers","created":"2021-06-30","cited_by_count":19,"area":null},{"id":"2203.14577","title":"Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?","created":"2022-03-28","cited_by_count":18,"area":null},{"id":"2208.04321","title":"Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment","created":"2022-08-08","cited_by_count":17,"area":null},{"id":"2107.13153","title":"Homogeneous Architecture Augmentation for Neural Predictor","created":"2021-07-28","cited_by_count":14,"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":"2206.01520","title":"A Survey on Computationally Efficient Neural Architecture Search","created":"2022-06-03","cited_by_count":12,"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":"2102.11382","title":"Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity","created":"2021-02-22","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":"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":"2402.02105","title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","created":"2024-02-03","cited_by_count":5,"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":"2210.07634","title":"Pareto-aware Neural Architecture Generation for Diverse Computational Budgets","created":"2022-10-14","cited_by_count":4,"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":"2302.13020","title":"DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning","created":"2023-02-25","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":"2211.05950","title":"CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks","created":"2022-11-11","cited_by_count":2,"area":null},{"id":"2506.04001","title":"CARL: Causality-guided Architecture Representation Learning for an Interpretable Performance Predictor","created":"2025-06-04","cited_by_count":2,"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":"2209.06626","title":"NAAP-440 Dataset and Baseline for Neural Architecture Accuracy Prediction","created":"2022-09-14","cited_by_count":1,"area":null},{"id":"2506.05869","title":"Loss Functions for Predictor-based Neural Architecture Search","created":"2025-06-06","cited_by_count":1,"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":"2203.02086","title":"WPNAS: Neural Architecture Search by jointly using Weight Sharing and Predictor","created":"2022-03-04","cited_by_count":0,"area":null},{"id":"2210.14460","title":"PredNAS: A Universal and Sample Efficient Neural Architecture Search Framework","created":"2022-10-26","cited_by_count":0,"area":null},{"id":"2211.12419","title":"Accuracy Prediction for NAS Acceleration using Feature Selection and Extrapolation","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2402.05821","title":"Guided Evolution with Binary Discriminators for ML Program Search","created":"2024-02-08","cited_by_count":0,"area":null},{"id":"2506.02623","title":"SiamNAS: Siamese Surrogate Model for Dominance Relation Prediction in Multi-objective Neural Architecture Search","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2506.07735","title":"Language Embedding Meets Dynamic Graph: A New Exploration for Neural Architecture Representation Learning","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2609.12418","title":"RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.01317","title":"Prediction-powered Neural Architecture Search","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15307","title":"FENAS: A Few-Shot Meta-Ensembling Framework for Efficient Neural Architecture Search with Synergized Zero-Cost Proxies","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.16822","title":"DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}