{"total":395,"rows":[{"id":"2111.05849","title":"Advances in Neural Rendering","created":"2021-11-10","cited_by_count":365,"area":null},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316,"area":null},{"id":"2106.10934","title":"GRAND: Graph Neural Diffusion","created":"2021-06-21","cited_by_count":258,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149,"area":null},{"id":"2304.11127","title":"Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance","created":"2023-04-21","cited_by_count":147,"area":null},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146,"area":null},{"id":"2110.09443","title":"Beltrami Flow and Neural Diffusion on Graphs","created":"2021-10-18","cited_by_count":84,"area":null},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81,"area":null},{"id":"2307.03694","title":"Scalable Membership Inference Attacks via Quantile Regression","created":"2023-07-07","cited_by_count":65,"area":"safety"},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"area":null},{"id":"2305.08252","title":"Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity","created":"2023-05-14","cited_by_count":56,"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":"2103.04850","title":"Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding","created":"2021-03-08","cited_by_count":50,"area":null},{"id":"2406.09997","title":"Towards Scalable and Versatile Weight Space Learning","created":"2024-06-14","cited_by_count":41,"area":null},{"id":"2302.11419","title":"Aligned Diffusion Schr\\\"odinger Bridges","created":"2023-02-22","cited_by_count":38,"area":null},{"id":"2207.07888","title":"SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks","created":"2022-07-16","cited_by_count":37,"area":null},{"id":"2505.14183","title":"ThinkSwitcher: When to Think Hard, When to Think Fast","created":"2025-05-20","cited_by_count":37,"area":"lr"},{"id":"2110.14771","title":"ABIDES-Gym: Gym Environments for Multi-Agent Discrete Event Simulation and Application to Financial Markets","created":"2021-10-27","cited_by_count":36,"area":null},{"id":"2402.14989","title":"Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data","created":"2024-02-22","cited_by_count":36,"area":null},{"id":"2402.14547","title":"OmniPred: Language Models as Universal Regressors","created":"2024-02-22","cited_by_count":34,"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":"2106.07887","title":"Credit Assignment in Neural Networks through Deep Feedback Control","created":"2021-06-15","cited_by_count":29,"area":null},{"id":"2110.04383","title":"Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations","created":"2021-10-08","cited_by_count":29,"area":null},{"id":"2305.12127","title":"DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training","created":"2023-05-20","cited_by_count":29,"area":null},{"id":"2310.08381","title":"AutoVP: An Automated Visual Prompting Framework and Benchmark","created":"2023-10-12","cited_by_count":29,"area":null},{"id":"2111.02275","title":"Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data","created":"2021-11-03","cited_by_count":28,"area":null},{"id":"2307.01680","title":"Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation","created":"2023-07-04","cited_by_count":28,"area":null},{"id":"2502.02582","title":"Open Materials Generation with Stochastic Interpolants","created":"2025-02-04","cited_by_count":28,"area":"diffusion"},{"id":"2403.19390","title":"Checkpoint Merging via Bayesian Optimization in LLM Pretraining","created":"2024-03-28","cited_by_count":27,"area":null},{"id":"2403.09110","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","created":"2024-03-14","cited_by_count":26,"area":"deeprl"},{"id":"2107.08861","title":"VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2303.15103","title":"Contrastive Learning Is Spectral Clustering On Similarity Graph","created":"2023-03-27","cited_by_count":25,"area":null},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","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":"2206.05833","title":"COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition","created":"2022-06-12","cited_by_count":22,"area":null},{"id":"2204.10022","title":"Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions","created":"2022-04-21","cited_by_count":20,"area":null},{"id":"2304.14343","title":"LibCity: A Unified Library Towards Efficient and Comprehensive Urban Spatial-Temporal Prediction","created":"2023-04-27","cited_by_count":20,"area":null},{"id":"2406.17720","title":"BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity","created":"2024-06-25","cited_by_count":20,"area":null},{"id":"2504.08201","title":"Neural Encoding and Decoding at Scale","created":"2025-04-11","cited_by_count":20,"area":null},{"id":"2301.11989","title":"Practical Differentially Private Hyperparameter Tuning with Subsampling","created":"2023-01-27","cited_by_count":19,"area":null},{"id":"2310.08910","title":"Scalarization for Multi-Task and Multi-Domain Learning at Scale","created":"2023-10-13","cited_by_count":19,"area":null},{"id":"2206.02107","title":"Interpretable Mixture of Experts","created":"2022-06-05","cited_by_count":17,"area":"moe"},{"id":"2204.05103","title":"Transformer-Based Self-Supervised Learning for Emotion Recognition","created":"2022-04-08","cited_by_count":16,"area":null},{"id":"2303.06470","title":"Prefix-Tree Decoding for Predicting Mass Spectra from Molecules","created":"2023-03-11","cited_by_count":16,"area":null},{"id":"2309.08859","title":"Rethinking Learning Rate Tuning in the Era of Large Language Models","created":"2023-09-16","cited_by_count":16,"area":"lr"},{"id":"2111.15341","title":"ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds","created":"2021-11-30","cited_by_count":15,"area":null},{"id":"2304.13174","title":"Dynamic Datasets and Market Environments for Financial Reinforcement Learning","created":"2023-04-25","cited_by_count":15,"area":null},{"id":"2104.01677","title":"A contrastive rule for meta-learning","created":"2021-04-04","cited_by_count":14,"area":null},{"id":"2205.13748","title":"Auto-PINN: Understanding and Optimizing Physics-Informed Neural Architecture","created":"2022-05-27","cited_by_count":14,"area":null},{"id":"2207.03574","title":"Demystifying the Adversarial Robustness of Random Transformation Defenses","created":"2022-06-18","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":"2408.11527","title":"The Vizier Gaussian Process Bandit Algorithm","created":"2024-08-21","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":"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":"2208.10967","title":"The Value of Out-of-Distribution Data","created":"2022-08-23","cited_by_count":12,"area":null},{"id":"2210.12936","title":"Selecting and Composing Learning Rate Policies for Deep Neural Networks","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2509.12178","title":"All that structure matches does not glitter","created":"2025-09-15","cited_by_count":12,"area":null},{"id":"2112.00298","title":"Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modeling","created":"2021-12-01","cited_by_count":11,"area":null},{"id":"2306.00854","title":"Spatio-Angular Convolutions for Super-resolution in Diffusion MRI","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2307.11432","title":"An Analysis of Multi-Agent Reinforcement Learning for Decentralized Inventory Control Systems","created":"2023-07-21","cited_by_count":11,"area":null},{"id":"2401.07049","title":"Quantum Denoising Diffusion Models","created":"2024-01-13","cited_by_count":11,"area":"diffusion"},{"id":"2403.02290","title":"Koopman-Assisted Reinforcement Learning","created":"2024-03-04","cited_by_count":11,"area":"deeprl"},{"id":"2110.02827","title":"Colmena: Scalable Machine-Learning-Based Steering of Ensemble Simulations for High Performance Computing","created":"2021-10-06","cited_by_count":10,"area":null},{"id":"2205.11438","title":"Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2207.12872","title":"Generalized Probabilistic U-Net for medical image segementation","created":"2022-07-26","cited_by_count":10,"area":null},{"id":"2207.14742","title":"Graph Neural Networks for Channel Decoding","created":"2022-07-29","cited_by_count":10,"area":null},{"id":"2311.01446","title":"Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulation","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2110.15288","title":"Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction","created":"2021-10-28","cited_by_count":9,"area":null},{"id":"2211.14411","title":"c-TPE: Tree-structured Parzen Estimator with Inequality Constraints for Expensive Hyperparameter Optimization","created":"2022-11-26","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":"2303.16633","title":"Targeted Adversarial Attacks on Wind Power Forecasts","created":"2023-03-29","cited_by_count":9,"area":null},{"id":"2310.14757","title":"SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research","created":"2023-10-23","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":"2106.15883","title":"Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2202.11954","title":"XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learning","created":"2022-02-24","cited_by_count":8,"area":null},{"id":"2204.06643","title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","created":"2022-04-13","cited_by_count":8,"area":null},{"id":"2210.12903","title":"Gallery Filter Network for Person Search","created":"2022-10-24","cited_by_count":8,"area":null},{"id":"2309.01230","title":"lfads-torch: A modular and extensible implementation of latent factor analysis via dynamical systems","created":"2023-09-03","cited_by_count":8,"area":null},{"id":"2310.17668","title":"Fine tuning Pre trained Models for Robustness Under Noisy Labels","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2410.10190","title":"Language Model Embeddings Can Be Sufficient for Bayesian Optimization","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2602.00424","title":"Open Materials Generation with Inference-Time Reinforcement Learning","created":"2026-01-31","cited_by_count":8,"area":"deeprl"},{"id":"2102.02344","title":"Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Models","created":"2021-02-03","cited_by_count":7,"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":"2111.12689","title":"A stacked deep convolutional neural network to predict the remaining useful life of a turbofan engine","created":"2021-11-24","cited_by_count":7,"area":null},{"id":"2112.04607","title":"Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning","created":"2021-12-08","cited_by_count":7,"area":null},{"id":"2201.03448","title":"BITES: Balanced Individual Treatment Effect for Survival data","created":"2022-01-05","cited_by_count":7,"area":null},{"id":"2202.05352","title":"Domain Adversarial Training: A Game Perspective","created":"2022-02-10","cited_by_count":7,"area":null},{"id":"2303.12306","title":"Understanding Expressivity of GNN in Rule Learning","created":"2023-03-22","cited_by_count":7,"area":null},{"id":"2305.15881","title":"Generative Adversarial Reduced Order Modelling","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2410.12052","title":"Skill-LLM: Repurposing General-Purpose LLMs for Skill Extraction","created":"2024-10-15","cited_by_count":7,"area":null},{"id":"2505.16115","title":"A Generic Framework for Conformal Fairness","created":"2025-05-22","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":"2107.06469","title":"Model-Parallel Model Selection for Deep Learning Systems","created":"2021-07-14","cited_by_count":6,"area":null},{"id":"2110.15084","title":"Using Non-Linear Causal Models to Study Aerosol-Cloud Interactions in the Southeast Pacific","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2111.04260","title":"Personalized Benchmarking with the Ludwig Benchmarking Toolkit","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2205.01081","title":"Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review","created":"2022-04-29","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":"2212.03771","title":"Expressive architectures enhance interpretability of dynamics-based neural population models","created":"2022-12-07","cited_by_count":6,"area":null}],"next_cursor":"100"}