{"total":191,"rows":[{"id":"2111.05849","title":"Advances in Neural Rendering","created":"2021-11-10","cited_by_count":365,"area":null},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2109.06716","title":"HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO","created":"2021-09-14","cited_by_count":112,"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":"2208.06102","title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training","created":"2022-08-12","cited_by_count":79,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2109.03670","title":"YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimization","created":"2021-09-08","cited_by_count":62,"area":null},{"id":"2106.03027","title":"Model Zoo: A Growing \"Brain\" That Learns Continually","created":"2021-06-06","cited_by_count":54,"area":null},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39,"area":null},{"id":"2206.07438","title":"Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview","created":"2022-06-15","cited_by_count":37,"area":null},{"id":"2302.05738","title":"Cross-Modal Fine-Tuning: Align then Refine","created":"2023-02-11","cited_by_count":34,"area":null},{"id":"2110.05668","title":"NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks","created":"2021-10-12","cited_by_count":32,"area":null},{"id":"2306.12370","title":"PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning","created":"2023-06-21","cited_by_count":31,"area":null},{"id":"2302.05499","title":"CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition","created":"2023-02-10","cited_by_count":30,"area":null},{"id":"2404.16795","title":"In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization","created":"2024-04-25","cited_by_count":26,"area":null},{"id":"2210.16913","title":"Revisiting Simple Regret: Fast Rates for Returning a Good Arm","created":"2022-10-30","cited_by_count":25,"area":null},{"id":"2411.02796","title":"Specialized Foundation Models Struggle to Beat Supervised Baselines","created":"2024-11-05","cited_by_count":24,"area":null},{"id":"2310.05055","title":"FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis","created":"2023-10-08","cited_by_count":23,"area":null},{"id":"2203.08212","title":"AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2104.08166","title":"Automatic Termination for Hyperparameter Optimization","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2111.03602","title":"NAS-Bench-x11 and the Power of Learning Curves","created":"2021-11-05","cited_by_count":20,"area":null},{"id":"2105.01015","title":"Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization","created":"2021-05-03","cited_by_count":19,"area":null},{"id":"2204.07554","title":"Efficient Architecture Search for Diverse Tasks","created":"2022-04-15","cited_by_count":18,"area":null},{"id":"2202.09774","title":"Supervising the Multi-Fidelity Race of Hyperparameter Configurations","created":"2022-02-20","cited_by_count":15,"area":null},{"id":"2105.10762","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","created":"2021-05-22","cited_by_count":14,"area":null},{"id":"2203.00330","title":"Machine Learning for Particle Flow Reconstruction at CMS","created":"2022-03-01","cited_by_count":14,"area":null},{"id":"2404.02112","title":"ImageNot: A contrast with ImageNet preserves model rankings","created":"2024-04-02","cited_by_count":14,"area":null},{"id":"2201.06834","title":"Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale","created":"2022-01-18","cited_by_count":13,"area":null},{"id":"2207.06940","title":"PASHA: Efficient HPO and NAS with Progressive Resource Allocation","created":"2022-07-14","cited_by_count":13,"area":null},{"id":"2312.10308","title":"Event-Based Contrastive Learning for Medical Time Series","created":"2023-12-16","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":"2106.09204","title":"An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models","created":"2021-06-17","cited_by_count":12,"area":null},{"id":"2108.13122","title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","created":"2021-08-30","cited_by_count":12,"area":null},{"id":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2412.07820","title":"Hyperband-based Bayesian Optimization for Black-box Prompt Selection","created":"2024-12-10","cited_by_count":10,"area":null},{"id":"2206.11791","title":"Open-source FPGA-ML codesign for the MLPerf Tiny Benchmark","created":"2022-06-23","cited_by_count":9,"area":null},{"id":"2301.13287","title":"MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2310.20458","title":"Machine learning detects terminal singularities","created":"2023-10-31","cited_by_count":9,"area":null},{"id":"2112.10644","title":"Self-attention Presents Low-dimensional Knowledge Graph Embeddings for Link Prediction","created":"2021-12-20","cited_by_count":8,"area":null},{"id":"2110.10461","title":"Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation","created":"2021-10-20","cited_by_count":7,"area":null},{"id":"2409.08439","title":"Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space","created":"2024-09-13","cited_by_count":7,"area":null},{"id":"2101.03221","title":"Machine learning classification of non-Markovian noise disturbing quantum dynamics","created":"2021-01-08","cited_by_count":6,"area":null},{"id":"2104.07391","title":"RIANN -- A Robust Neural Network Outperforms Attitude Estimation Filters","created":"2021-04-15","cited_by_count":6,"area":null},{"id":"2111.06495","title":"FairAutoML: Embracing Unfairness Mitigation in AutoML","created":"2021-11-11","cited_by_count":6,"area":null},{"id":"2207.00479","title":"Asynchronous Decentralized Bayesian Optimization for Large Scale Hyperparameter Optimization","created":"2022-07-01","cited_by_count":6,"area":null},{"id":"2211.01454","title":"Speeding up NAS with Adaptive Subset Selection","created":"2022-11-02","cited_by_count":6,"area":null},{"id":"2301.05079","title":"Deep learning enhanced noise spectroscopy of a spin qubit environment","created":"2023-01-12","cited_by_count":6,"area":null},{"id":"2306.07761","title":"Multi-Fidelity Multi-Armed Bandits Revisited","created":"2023-06-13","cited_by_count":6,"area":null},{"id":"2307.15422","title":"Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?","created":"2023-07-28","cited_by_count":6,"area":null},{"id":"2311.09480","title":"Show Your Work with Confidence: Confidence Bands for Tuning Curves","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2402.09638","title":"Multi-Fidelity Methods for Optimization: A Survey","created":"2024-02-15","cited_by_count":6,"area":null},{"id":"2501.06669","title":"Challenging reaction prediction models to generalize to novel chemistry","created":"2025-01-11","cited_by_count":6,"area":null},{"id":"2512.19927","title":"The Seismic Wavefield Common Task Framework","created":"2025-12-22","cited_by_count":6,"area":null},{"id":"2607.18235","title":"Automated Discovery Has No Universally Superior Harness","created":"2026-07-20","cited_by_count":6,"area":null},{"id":"2106.02352","title":"COLD: Concurrent Loads Disaggregator for Non-Intrusive Load Monitoring","created":"2021-06-04","cited_by_count":5,"area":null},{"id":"2202.04487","title":"Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget","created":"2022-02-09","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":"2311.16834","title":"FocusLearn: Fully-Interpretable, High-Performance Modular Neural Networks for Time Series","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2404.04111","title":"The Unreasonable Effectiveness Of Early Discarding After One Epoch In Neural Network Hyperparameter Optimization","created":"2024-04-05","cited_by_count":5,"area":null},{"id":"2405.00319","title":"Data Augmentation Policy Search for Long-Term Forecasting","created":"2024-05-01","cited_by_count":5,"area":null},{"id":"2605.05683","title":"Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2108.02479","title":"HyperJump: Accelerating HyperBand via Risk Modelling","created":"2021-08-05","cited_by_count":4,"area":null},{"id":"2111.14756","title":"Automated Benchmark-Driven Design and Explanation of Hyperparameter Optimizers","created":"2021-11-29","cited_by_count":4,"area":null},{"id":"2205.11048","title":"GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Model","created":"2022-05-23","cited_by_count":4,"area":null},{"id":"2207.07475","title":"Stable Invariant Models via Koopman Spectra","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2212.12478","title":"Image Classification with Small Datasets: Overview and Benchmark","created":"2022-12-23","cited_by_count":4,"area":null},{"id":"2305.00094","title":"Latent Dynamics Networks (LDNets): learning the intrinsic dynamics of spatio-temporal processes","created":"2023-04-28","cited_by_count":4,"area":null},{"id":"2305.07625","title":"Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2306.01436","title":"Multi-Objective Population Based Training","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2309.06782","title":"Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors","created":"2023-09-13","cited_by_count":4,"area":null},{"id":"2310.08177","title":"Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2402.17440","title":"Principled Architecture-aware Scaling of Hyperparameters","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2406.19892","title":"Automatic register identification for the open web using multilingual deep learning","created":"2024-06-28","cited_by_count":4,"area":null},{"id":"2409.18749","title":"TensorSocket: Shared Data Loading for Deep Learning Training","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2506.15881","title":"T-SHRED: Symbolic Regression for Regularization and Model Discovery with Transformer Shallow Recurrent Decoders","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2108.06959","title":"WikiChurches: A Fine-Grained Dataset of Architectural Styles with Real-World Challenges","created":"2021-08-16","cited_by_count":3,"area":null},{"id":"2108.12941","title":"RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations","created":"2021-08-30","cited_by_count":3,"area":null},{"id":"2110.08633","title":"Hydra: A System for Large Multi-Model Deep Learning","created":"2021-10-16","cited_by_count":3,"area":null},{"id":"2111.00513","title":"Automated Hyperparameter Optimization Challenge at CIKM 2021 AnalyticCup","created":"2021-10-31","cited_by_count":3,"area":null},{"id":"2204.09603","title":"Comparing Deep Reinforcement Learning Algorithms in Two-Echelon Supply Chains","created":"2022-04-20","cited_by_count":3,"area":null},{"id":"2211.00376","title":"Automated Imbalanced Learning","created":"2022-11-01","cited_by_count":3,"area":null},{"id":"2306.15628","title":"Machine-learning based noise characterization and correction on neutral atoms NISQ devices","created":"2023-06-27","cited_by_count":3,"area":null},{"id":"2310.11478","title":"ASP: Automatic Selection of Proxy dataset for efficient AutoML","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2402.19090","title":"Best Arm Identification with Resource Constraints","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2502.01916","title":"Generalizable and Fast Surrogates: Model Predictive Control of Articulated Soft Robots using Physics-Informed Neural Networks","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2504.18072","title":"A Model Zoo on Phase Transitions in Neural Networks","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2506.06143","title":"carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2508.12681","title":"Adaptive Model-Predictive Control of a Soft Continuum Robot Using a Physics-Informed Neural Network Based on Cosserat Rod Theory","created":"2025-08-18","cited_by_count":3,"area":null},{"id":"2109.13561","title":"A Strong Baseline for the VIPriors Data-Efficient Image Classification Challenge","created":"2021-09-28","cited_by_count":2,"area":null},{"id":"2111.15317","title":"AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop","created":"2021-11-30","cited_by_count":2,"area":null},{"id":"2201.09603","title":"Performance Analysis of Electrical Machines Using a Hybrid Data- and Physics-Driven Model","created":"2022-01-24","cited_by_count":2,"area":null},{"id":"2206.05530","title":"Memorization-Dilation: Modeling Neural Collapse Under Label Noise","created":"2022-06-11","cited_by_count":2,"area":null},{"id":"2210.04971","title":"Multi-step Planning for Automated Hyperparameter Optimization with OptFormer","created":"2022-10-10","cited_by_count":2,"area":null},{"id":"2304.12067","title":"Renate: A Library for Real-World Continual Learning","created":"2023-04-24","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":"2309.01226","title":"Saturn: An Optimized Data System for Large Model Deep Learning Workloads","created":"2023-09-03","cited_by_count":2,"area":null},{"id":"2310.05572","title":"A Simple and Robust Framework for Cross-Modality Medical Image Segmentation applied to Vision Transformers","created":"2023-10-09","cited_by_count":2,"area":null},{"id":"2310.14963","title":"Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens","created":"2023-10-23","cited_by_count":2,"area":null}],"next_cursor":"100"}