{"total":350,"rows":[{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982,"area":null},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680,"area":null},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311,"area":null},{"id":"2104.02395","title":"Ensemble deep learning: A review","created":"2021-04-06","cited_by_count":284,"area":null},{"id":"2305.03053","title":"ZipIt! Merging Models from Different Tasks without Training","created":"2023-05-04","cited_by_count":179,"area":null},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151,"area":null},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"area":"safety"},{"id":"2109.09881","title":"Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation","created":"2021-09-20","cited_by_count":116,"area":null},{"id":"2106.11642","title":"Repulsive Deep Ensembles are Bayesian","created":"2021-06-22","cited_by_count":104,"area":null},{"id":"2402.01694","title":"ARGS: Alignment as Reward-Guided Search","created":"2024-01-23","cited_by_count":103,"area":"alignment"},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2102.10472","title":"Learning Neural Network Subspaces","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2410.11287","title":"Process Reward Model with Q-Value Rankings","created":"2024-10-15","cited_by_count":80,"area":"lr"},{"id":"2101.08482","title":"Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning","created":"2021-01-21","cited_by_count":78,"area":null},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77,"area":null},{"id":"2411.11919","title":"VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation","created":"2024-11-18","cited_by_count":73,"area":"mllm"},{"id":"2310.04415","title":"Why Do We Need Weight Decay in Modern Deep Learning?","created":"2023-10-06","cited_by_count":72,"area":null},{"id":"2110.03051","title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","created":"2021-10-06","cited_by_count":71,"area":null},{"id":"2312.09241","title":"TinyGSM: achieving >80% on GSM8k with small language models","created":"2023-12-14","cited_by_count":70,"area":"lr"},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67,"area":null},{"id":"2202.06985","title":"Deep Ensembles Work, But Are They Necessary?","created":"2022-02-14","cited_by_count":63,"area":null},{"id":"2102.01929","title":"Regularization Strategy for Point Cloud via Rigidly Mixed Sample","created":"2021-02-03","cited_by_count":59,"area":null},{"id":"2307.15615","title":"A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond","created":"2023-07-28","cited_by_count":55,"area":null},{"id":"2312.06353","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","created":"2023-12-11","cited_by_count":55,"area":null},{"id":"2210.09184","title":"Packed-Ensembles for Efficient Uncertainty Estimation","created":"2022-10-17","cited_by_count":49,"area":null},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48,"area":null},{"id":"2103.04514","title":"Nondeterminism and Instability in Neural Network Optimization","created":"2021-03-08","cited_by_count":48,"area":null},{"id":"2101.08387","title":"A Survey on Ensemble Learning under the Era of Deep Learning","created":"2021-01-21","cited_by_count":47,"area":null},{"id":"2106.14568","title":"Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity","created":"2021-06-28","cited_by_count":44,"area":null},{"id":"2312.02158","title":"PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness","created":"2023-12-04","cited_by_count":42,"area":null},{"id":"2210.06458","title":"Efficient Knowledge Distillation from Model Checkpoints","created":"2022-10-12","cited_by_count":37,"area":"distill"},{"id":"2508.12880","title":"Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models","created":"2025-08-18","cited_by_count":36,"area":"diffusion"},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2111.11108","title":"Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version","created":"2021-11-22","cited_by_count":35,"area":null},{"id":"2310.14230","title":"A comprehensive survey on deep active learning in medical image analysis","created":"2023-10-22","cited_by_count":35,"area":null},{"id":"2209.08928","title":"UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup","created":"2022-09-19","cited_by_count":34,"area":null},{"id":"2208.11866","title":"NeuralUQ: A comprehensive library for uncertainty quantification in neural differential equations and operators","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2406.12585","title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","created":"2024-06-18","cited_by_count":33,"area":null},{"id":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32,"area":null},{"id":"2204.02488","title":"Discovering and forecasting extreme events via active learning in neural operators","created":"2022-04-05","cited_by_count":32,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2106.16004","title":"What can linear interpolation of neural network loss landscapes tell us?","created":"2021-06-30","cited_by_count":28,"area":null},{"id":"2303.09055","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","created":"2023-03-16","cited_by_count":28,"area":null},{"id":"2307.03217","title":"Quantification of Uncertainty with Adversarial Models","created":"2023-07-06","cited_by_count":28,"area":null},{"id":"2603.12228","title":"Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights","created":"2026-03-12","cited_by_count":28,"area":null},{"id":"2206.14502","title":"RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness","created":"2022-06-29","cited_by_count":27,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2101.09815","title":"Annealed Stein Variational Gradient Descent","created":"2021-01-24","cited_by_count":26,"area":null},{"id":"2201.00519","title":"Stochastic Weight Averaging Revisited","created":"2022-01-03","cited_by_count":26,"area":null},{"id":"2202.11091","title":"Efficient and Differentiable Conformal Prediction with General Function Classes","created":"2022-02-22","cited_by_count":26,"area":null},{"id":"2105.03193","title":"Network Pruning That Matters: A Case Study on Retraining Variants","created":"2021-05-07","cited_by_count":25,"area":null},{"id":"2112.06334","title":"DPICT: Deep Progressive Image Compression Using Trit-Planes","created":"2021-12-12","cited_by_count":25,"area":null},{"id":"2206.00050","title":"FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation","created":"2022-05-31","cited_by_count":24,"area":null},{"id":"2307.13813","title":"How to Scale Your EMA","created":"2023-07-25","cited_by_count":24,"area":null},{"id":"2103.15254","title":"Bayesian Deep Basis Fitting for Depth Completion with Uncertainty","created":"2021-03-29","cited_by_count":23,"area":null},{"id":"2302.10164","title":"Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts","created":"2023-02-20","cited_by_count":23,"area":null},{"id":"2106.07451","title":"Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions","created":"2021-06-14","cited_by_count":21,"area":null},{"id":"2106.10760","title":"On Stein Variational Neural Network Ensembles","created":"2021-06-20","cited_by_count":21,"area":null},{"id":"2303.05715","title":"Context-Based Trit-Plane Coding for Progressive Image Compression","created":"2023-03-10","cited_by_count":21,"area":null},{"id":"2308.12965","title":"POCO: 3D Pose and Shape Estimation with Confidence","created":"2023-08-24","cited_by_count":21,"area":null},{"id":"2205.13532","title":"Selective Prediction via Training Dynamics","created":"2022-05-26","cited_by_count":20,"area":null},{"id":"2306.16788","title":"Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging","created":"2023-06-29","cited_by_count":20,"area":null},{"id":"2404.00653","title":"Dual DETRs for Multi-Label Temporal Action Detection","created":"2024-03-31","cited_by_count":20,"area":null},{"id":"2405.14438","title":"LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks","created":"2024-05-23","cited_by_count":20,"area":null},{"id":"2412.00205","title":"Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation","created":"2024-11-29","cited_by_count":20,"area":"diffusion"},{"id":"2110.03360","title":"Sparse MoEs meet Efficient Ensembles","created":"2021-10-07","cited_by_count":19,"area":null},{"id":"2211.09981","title":"Weighted Ensemble Self-Supervised Learning","created":"2022-11-18","cited_by_count":19,"area":null},{"id":"2212.06278","title":"Efficient Bayesian Uncertainty Estimation for nnU-Net","created":"2022-12-12","cited_by_count":19,"area":null},{"id":"2202.09826","title":"Continual Learning Beyond a Single Model","created":"2022-02-20","cited_by_count":18,"area":null},{"id":"2304.01973","title":"ERM++: An Improved Baseline for Domain Generalization","created":"2023-04-04","cited_by_count":18,"area":null},{"id":"2304.03981","title":"Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification","created":"2023-04-08","cited_by_count":18,"area":null},{"id":"2203.08881","title":"Hyperbolic Uncertainty Aware Semantic Segmentation","created":"2022-03-16","cited_by_count":17,"area":null},{"id":"2306.08693","title":"Integrating Uncertainty Awareness into Conformalized Quantile Regression","created":"2023-06-14","cited_by_count":17,"area":null},{"id":"2310.11451","title":"Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective","created":"2023-10-17","cited_by_count":17,"area":null},{"id":"2402.16828","title":"Training Neural Networks from Scratch with Parallel Low-Rank Adapters","created":"2024-02-26","cited_by_count":17,"area":null},{"id":"2111.13280","title":"Efficient Self-Ensemble for Semantic Segmentation","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2201.09699","title":"EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients","created":"2022-01-24","cited_by_count":16,"area":null},{"id":"2404.04933","title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2104.11667","title":"Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structure","created":"2021-04-23","cited_by_count":15,"area":null},{"id":"2108.00080","title":"A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms","created":"2021-07-30","cited_by_count":15,"area":null},{"id":"2203.08878","title":"Layer Ensembles: A Single-Pass Uncertainty Estimation in Deep Learning for Segmentation","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2204.03145","title":"DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors","created":"2022-04-07","cited_by_count":15,"area":null},{"id":"2303.01311","title":"Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation","created":"2023-03-02","cited_by_count":15,"area":null},{"id":"2407.13771","title":"Training-Free Model Merging for Multi-target Domain Adaptation","created":"2024-07-18","cited_by_count":15,"area":null},{"id":"2105.06747","title":"Troubleshooting Blind Image Quality Models in the Wild","created":"2021-05-14","cited_by_count":14,"area":null},{"id":"2305.06473","title":"Securing Distributed SGD against Gradient Leakage Threats","created":"2023-05-10","cited_by_count":14,"area":null},{"id":"2306.16817","title":"Improving Online Continual Learning Performance and Stability with Temporal Ensembles","created":"2023-06-29","cited_by_count":14,"area":null},{"id":"2202.11782","title":"Prune and Tune Ensembles: Low-Cost Ensemble Learning With Sparse Independent Subnetworks","created":"2022-02-23","cited_by_count":13,"area":null},{"id":"2210.11803","title":"Revisiting Checkpoint Averaging for Neural Machine Translation","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2212.03868","title":"Deep Learning for Brain Age Estimation: A Systematic Review","created":"2022-12-07","cited_by_count":13,"area":null},{"id":"2104.00597","title":"One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking","created":"2021-04-01","cited_by_count":12,"area":null},{"id":"2109.07628","title":"Connecting Low-Loss Subspace for Personalized Federated Learning","created":"2021-09-16","cited_by_count":12,"area":null},{"id":"2206.10011","title":"When Does Re-initialization Work?","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2207.13325","title":"SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding","created":"2022-07-27","cited_by_count":12,"area":null},{"id":"2106.14662","title":"Improving Uncertainty Calibration of Deep Neural Networks via Truth Discovery and Geometric Optimization","created":"2021-06-25","cited_by_count":11,"area":null},{"id":"2112.13316","title":"Efficient Diversity-Driven Ensemble for Deep Neural Networks","created":"2021-12-26","cited_by_count":11,"area":null},{"id":"2202.01943","title":"PSO-PINN: Physics-Informed Neural Networks Trained with Particle Swarm Optimization","created":"2022-02-04","cited_by_count":11,"area":null},{"id":"2208.10842","title":"Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost","created":"2022-08-23","cited_by_count":11,"area":null},{"id":"2301.12378","title":"Towards Inference Efficient Deep Ensemble Learning","created":"2023-01-29","cited_by_count":11,"area":null}],"next_cursor":"100"}