{"total":102,"rows":[{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260,"area":null},{"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":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2111.14213","title":"Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning","created":"2021-11-28","cited_by_count":114,"area":null},{"id":"2108.04392","title":"Rethinking Architecture Selection in Differentiable NAS","created":"2021-08-10","cited_by_count":92,"area":null},{"id":"2110.03825","title":"Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks","created":"2021-10-07","cited_by_count":74,"area":null},{"id":"2203.01665","title":"$\\beta$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search","created":"2022-03-03","cited_by_count":64,"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":"2106.10784","title":"iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients","created":"2021-06-21","cited_by_count":51,"area":null},{"id":"2403.16187","title":"ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models","created":"2024-03-24","cited_by_count":36,"area":null},{"id":"2206.00820","title":"NIPQ: Noise proxy-based Integrated Pseudo-Quantization","created":"2022-06-02","cited_by_count":35,"area":null},{"id":"2108.01289","title":"AdvRush: Searching for Adversarially Robust Neural Architectures","created":"2021-08-03","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":"2303.00466","title":"ASP: Learn a Universal Neural Solver!","created":"2023-03-01","cited_by_count":27,"area":null},{"id":"2509.16105","title":"DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning","created":"2025-09-19","cited_by_count":26,"area":"moe"},{"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":"2102.07108","title":"CATE: Computation-aware Neural Architecture Encoding with Transformers","created":"2021-02-14","cited_by_count":21,"area":null},{"id":"2109.05749","title":"Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning","created":"2021-09-13","cited_by_count":19,"area":null},{"id":"2110.04743","title":"ZARTS: On Zero-order Optimization for Neural Architecture Search","created":"2021-10-10","cited_by_count":18,"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":"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":"2210.07998","title":"$\\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells","created":"2022-10-14","cited_by_count":15,"area":null},{"id":"2305.02423","title":"PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer","created":"2023-05-03","cited_by_count":15,"area":null},{"id":"2106.04784","title":"Accelerating Neural Architecture Search via Proxy Data","created":"2021-06-09","cited_by_count":14,"area":null},{"id":"2202.07242","title":"Neural Architecture Search for Dense Prediction Tasks in Computer Vision","created":"2022-02-15","cited_by_count":12,"area":null},{"id":"2404.12467","title":"Towards Multi-modal Transformers in Federated Learning","created":"2024-04-18","cited_by_count":12,"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":"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":"2208.05271","title":"Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation","created":"2022-08-10","cited_by_count":9,"area":null},{"id":"2112.03552","title":"Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training","created":"2021-12-07","cited_by_count":8,"area":null},{"id":"2108.11939","title":"Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2109.02533","title":"Neural Ensemble Search via Bayesian Sampling","created":"2021-09-06","cited_by_count":7,"area":null},{"id":"2208.00791","title":"Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search","created":"2022-08-01","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":"2510.04655","title":"FT-MDT: Extracting Decision Trees from Medical Texts via a Novel Low-rank Adaptation Method","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2105.06369","title":"Neighborhood-Aware Neural Architecture Search","created":"2021-05-13","cited_by_count":6,"area":null},{"id":"2109.12425","title":"L$^{2}$NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning","created":"2021-09-25","cited_by_count":6,"area":null},{"id":"2111.06353","title":"Learning from Mistakes -- A Framework for Neural Architecture Search","created":"2021-11-11","cited_by_count":6,"area":null},{"id":"2202.02142","title":"Deep invariant networks with differentiable augmentation layers","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2302.05629","title":"Improving Differentiable Architecture Search via Self-Distillation","created":"2023-02-11","cited_by_count":6,"area":"distill"},{"id":"2507.15836","title":"Optimizing Canaries for Privacy Auditing with Metagradient Descent","created":"2025-07-21","cited_by_count":6,"area":"safety"},{"id":"2111.13204","title":"BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule","created":"2021-11-25","cited_by_count":5,"area":null},{"id":"2209.01688","title":"On the Privacy Risks of Cell-Based NAS Architectures","created":"2022-09-04","cited_by_count":5,"area":null},{"id":"2304.02845","title":"Robust Neural Architecture Search","created":"2023-04-06","cited_by_count":5,"area":null},{"id":"2304.05405","title":"Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search","created":"2023-04-11","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":"2312.12648","title":"IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importance","created":"2023-12-19","cited_by_count":5,"area":null},{"id":"2106.02229","title":"Differentiable Architecture Search for Reinforcement Learning","created":"2021-06-04","cited_by_count":4,"area":null},{"id":"2107.03719","title":"Bag of Tricks for Neural Architecture Search","created":"2021-07-08","cited_by_count":4,"area":null},{"id":"2109.12426","title":"Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search","created":"2021-09-25","cited_by_count":4,"area":null},{"id":"2109.15273","title":"DAAS: Differentiable Architecture and Augmentation Policy Search","created":"2021-09-30","cited_by_count":4,"area":null},{"id":"2208.08835","title":"Differentiable Architecture Search with Random Features","created":"2022-08-18","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":"2409.14433","title":"OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strength","created":"2024-09-22","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":"2211.08666","title":"Revisiting Training-free NAS Metrics: An Efficient Training-based Method","created":"2022-11-16","cited_by_count":3,"area":null},{"id":"2302.05632","title":"Operation-level Progressive Differentiable Architecture Search","created":"2023-02-11","cited_by_count":3,"area":null},{"id":"2305.08611","title":"GeNAS: Neural Architecture Search with Better Generalization","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2307.04443","title":"Search-time Efficient Device Constraints-Aware Neural Architecture Search","created":"2023-07-10","cited_by_count":3,"area":null},{"id":"2601.17921","title":"ShapLoRA: Allocation of Low-rank Adaption on Large Language Models via Shapley Value Inspired Importance Estimation","created":"2026-01-25","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":"2107.02451","title":"Integrating Large Circular Kernels into CNNs through Neural Architecture Search","created":"2021-07-06","cited_by_count":2,"area":null},{"id":"2107.11500","title":"$\\mu$DARTS: Model Uncertainty-Aware Differentiable Architecture Search","created":"2021-07-24","cited_by_count":2,"area":null},{"id":"2108.06822","title":"CONet: Channel Optimization for Convolutional Neural Networks","created":"2021-08-15","cited_by_count":2,"area":null},{"id":"2207.06968","title":"DASS: Differentiable Architecture Search for Sparse neural networks","created":"2022-07-14","cited_by_count":2,"area":null},{"id":"2306.06852","title":"Rethink DARTS Search Space and Renovate a New Benchmark","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2306.06858","title":"Robustifying DARTS by Eliminating Information Bypass Leakage via Explicit Sparse Regularization","created":"2023-06-12","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":"2503.10404","title":"Architecture-Aware Minimization (A$^2$M): How to Find Flat Minima in Neural Architecture Search","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2503.11159","title":"Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2101.04028","title":"Unchain the Search Space with Hierarchical Differentiable Architecture Search","created":"2021-01-11","cited_by_count":1,"area":null},{"id":"2203.06474","title":"Optimizer Amalgamation","created":"2022-03-12","cited_by_count":1,"area":null},{"id":"2211.10105","title":"$\\alpha$ DARTS Once More: Enhancing Differentiable Architecture Search by Masked Image Modeling","created":"2022-11-18","cited_by_count":1,"area":null},{"id":"2306.06855","title":"Small Temperature is All You Need for Differentiable Architecture Search","created":"2023-06-12","cited_by_count":1,"area":null},{"id":"2306.11982","title":"Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2307.06005","title":"DDNAS: Discretized Differentiable Neural Architecture Search for Text Classification","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2411.06098","title":"Revisiting Long-Tailed Learning: Insights from an Architectural Perspective","created":"2024-11-09","cited_by_count":1,"area":null},{"id":"2504.16306","title":"Regularizing Differentiable Architecture Search with Smooth Activation","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2104.10450","title":"Making Differentiable Architecture Search less local","created":"2021-04-21","cited_by_count":0,"area":null},{"id":"2106.11542","title":"Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis","created":"2021-06-22","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":"2108.05647","title":"Is Differentiable Architecture Search truly a One-Shot Method?","created":"2021-08-12","cited_by_count":0,"area":null},{"id":"2108.09996","title":"MS-DARTS: Mean-Shift Based Differentiable Architecture Search","created":"2021-08-23","cited_by_count":0,"area":null},{"id":"2112.00275","title":"Learning from Mistakes based on Class Weighting with Application to Neural Architecture Search","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2205.06355","title":"Warm-starting DARTS using meta-learning","created":"2022-05-12","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":"2306.10098","title":"Differentiable Instruction Optimization for Cross-Task Generalization","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2403.14083","title":"emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2405.16610","title":"The devil is in discretization discrepancy. Robustifying Differentiable NAS with Single-Stage Searching Protocol","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2405.18042","title":"Visualizing the loss landscape of Self-supervised Vision Transformer","created":"2024-05-28","cited_by_count":0,"area":null},{"id":"2407.20279","title":"On Supernet Transfer Learning for Effective Task Adaptation","created":"2024-07-26","cited_by_count":0,"area":null},{"id":"2503.17994","title":"Instructing the Architecture Search for Spatial-temporal Sequence Forecasting with LLM","created":"2025-03-23","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":"2507.16533","title":"confopt: A Library for Implementation and Evaluation of Gradient-based One-Shot NAS Methods","created":"2025-07-22","cited_by_count":0,"area":null},{"id":"2511.00035","title":"Neural Architecture Search for global multi-step Forecasting of Energy Production Time Series","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2602.17700","title":"MIDAS: Mosaic Input-Specific Differentiable Architecture Search","created":"2026-02-06","cited_by_count":0,"area":null}],"next_cursor":"100"}