{"total":312,"rows":[{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396,"area":null},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2106.00908","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","created":"2021-06-02","cited_by_count":555,"area":null},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222,"area":null},{"id":"2103.04628","title":"Personalized Federated Learning using Hypernetworks","created":"2021-03-08","cited_by_count":212,"area":null},{"id":"2109.06590","title":"High-Fidelity GAN Inversion for Image Attribute Editing","created":"2021-09-14","cited_by_count":197,"area":null},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172,"area":null},{"id":"2405.15682","title":"The Road Less Scheduled","created":"2024-05-24","cited_by_count":163,"area":null},{"id":"2111.03186","title":"EditGAN: High-Precision Semantic Image Editing","created":"2021-11-04","cited_by_count":156,"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":"2102.12145","title":"GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator","created":"2021-02-24","cited_by_count":148,"area":null},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"area":null},{"id":"2104.05833","title":"Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization","created":"2021-04-12","cited_by_count":141,"area":null},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137,"area":null},{"id":"2106.02584","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","created":"2021-06-04","cited_by_count":113,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2202.03772","title":"Particle Transformer for Jet Tagging","created":"2022-02-08","cited_by_count":98,"area":null},{"id":"2203.07918","title":"GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting","created":"2022-03-15","cited_by_count":94,"area":null},{"id":"2102.02754","title":"Only a Matter of Style: Age Transformation Using a Style-Based Regression Model","created":"2021-02-04","cited_by_count":92,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2108.08367","title":"SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation","created":"2021-08-18","cited_by_count":88,"area":null},{"id":"2112.00719","title":"HyperInverter: Improving StyleGAN Inversion via Hypernetwork","created":"2021-12-01","cited_by_count":85,"area":null},{"id":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81,"area":null},{"id":"2304.03571","title":"$\\beta$-Variational autoencoders and transformers for reduced-order modelling of fluid flows","created":"2023-04-07","cited_by_count":77,"area":null},{"id":"2204.14244","title":"CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification","created":"2022-04-29","cited_by_count":65,"area":null},{"id":"2102.07448","title":"OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving","created":"2021-02-15","cited_by_count":57,"area":null},{"id":"2209.14981","title":"Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging","created":"2022-09-29","cited_by_count":54,"area":null},{"id":"2103.05032","title":"Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning","created":"2021-03-08","cited_by_count":52,"area":null},{"id":"2303.15743","title":"HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation","created":"2023-03-28","cited_by_count":49,"area":null},{"id":"2406.01581","title":"Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit","created":"2024-06-03","cited_by_count":46,"area":null},{"id":"2205.13648","title":"A Unified Analysis of Federated Learning with Arbitrary Client Participation","created":"2022-05-26","cited_by_count":45,"area":null},{"id":"2204.12454","title":"Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images","created":"2022-04-26","cited_by_count":43,"area":null},{"id":"2208.00237","title":"RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation","created":"2022-07-30","cited_by_count":43,"area":null},{"id":"2208.06661","title":"SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimation","created":"2022-08-13","cited_by_count":41,"area":null},{"id":"2210.01620","title":"SAM as an Optimal Relaxation of Bayes","created":"2022-10-04","cited_by_count":41,"area":null},{"id":"2303.13497","title":"TriPlaneNet: An Encoder for EG3D Inversion","created":"2023-03-23","cited_by_count":41,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2102.03897","title":"Self-supervised driven consistency training for annotation efficient histopathology image analysis","created":"2021-02-07","cited_by_count":39,"area":null},{"id":"2105.01848","title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML","created":"2021-05-05","cited_by_count":39,"area":null},{"id":"2110.00175","title":"DualNet: Continual Learning, Fast and Slow","created":"2021-10-01","cited_by_count":39,"area":null},{"id":"2203.07932","title":"Style Transformer for Image Inversion and Editing","created":"2022-03-15","cited_by_count":37,"area":null},{"id":"2405.15459","title":"Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions","created":"2024-05-24","cited_by_count":37,"area":null},{"id":"2303.12326","title":"Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding","created":"2023-03-22","cited_by_count":35,"area":null},{"id":"2203.10339","title":"Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation","created":"2022-03-19","cited_by_count":34,"area":null},{"id":"2303.11162","title":"Picture that Sketch: Photorealistic Image Generation from Abstract Sketches","created":"2023-03-20","cited_by_count":34,"area":null},{"id":"2104.07661","title":"E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion","created":"2021-04-15","cited_by_count":33,"area":null},{"id":"2104.00615","title":"Physics-informed neural networks for the shallow-water equations on the sphere","created":"2021-04-01","cited_by_count":32,"area":null},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2203.02645","title":"Acceleration of Federated Learning with Alleviated Forgetting in Local Training","created":"2022-03-05","cited_by_count":29,"area":null},{"id":"2207.08082","title":"CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement","created":"2022-07-17","cited_by_count":29,"area":null},{"id":"2103.13111","title":"MIcro-Surgical Anastomose Workflow recognition challenge report","created":"2021-03-24","cited_by_count":28,"area":null},{"id":"2206.13424","title":"Benchopt: Reproducible, efficient and collaborative optimization benchmarks","created":"2022-06-27","cited_by_count":27,"area":null},{"id":"2503.09799","title":"Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo","created":"2025-03-12","cited_by_count":27,"area":null},{"id":"2104.04420","title":"SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras","created":"2021-04-09","cited_by_count":25,"area":null},{"id":"2407.03575","title":"DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification","created":"2024-07-04","cited_by_count":25,"area":null},{"id":"2507.20016","title":"FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging","created":"2025-07-26","cited_by_count":25,"area":null},{"id":"2104.15023","title":"Post-training deep neural network pruning via layer-wise calibration","created":"2021-04-30","cited_by_count":24,"area":null},{"id":"2106.13731","title":"Ranger21: a synergistic deep learning optimizer","created":"2021-06-25","cited_by_count":22,"area":null},{"id":"2303.01500","title":"Dropout Reduces Underfitting","created":"2023-03-02","cited_by_count":21,"area":null},{"id":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20,"area":null},{"id":"2211.03186","title":"Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning","created":"2022-11-06","cited_by_count":19,"area":null},{"id":"2206.00664","title":"Hopular: Modern Hopfield Networks for Tabular Data","created":"2022-06-01","cited_by_count":18,"area":null},{"id":"2211.11448","title":"Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint","created":"2022-11-21","cited_by_count":18,"area":null},{"id":"2401.13536","title":"Finetuning Foundation Models for Joint Analysis Optimization","created":"2024-01-24","cited_by_count":18,"area":null},{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"area":null},{"id":"2201.13011","title":"On the Power-Law Hessian Spectrums in Deep Learning","created":"2022-01-31","cited_by_count":16,"area":null},{"id":"2305.15121","title":"Beyond Individual Input for Deep Anomaly Detection on Tabular Data","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2404.00498","title":"94% on CIFAR-10 in 3.29 Seconds on a Single GPU","created":"2024-03-30","cited_by_count":16,"area":null},{"id":"2106.06038","title":"Modeling Hierarchical Structures with Continuous Recursive Neural Networks","created":"2021-06-10","cited_by_count":15,"area":null},{"id":"2205.14338","title":"Object-wise Masked Autoencoders for Fast Pre-training","created":"2022-05-28","cited_by_count":15,"area":null},{"id":"2101.11302","title":"Multilingual and cross-lingual document classification: A meta-learning approach","created":"2021-01-27","cited_by_count":14,"area":null},{"id":"2102.13644","title":"Surgical Visual Domain Adaptation: Results from the MICCAI 2020 SurgVisDom Challenge","created":"2021-02-26","cited_by_count":14,"area":null},{"id":"2205.06672","title":"Local Attention Graph-based Transformer for Multi-target Genetic Alteration Prediction","created":"2022-05-13","cited_by_count":14,"area":null},{"id":"2409.15727","title":"LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation","created":"2024-09-24","cited_by_count":14,"area":null},{"id":"2501.05534","title":"OmniJet-${\\alpha}_C$: Learning point cloud calorimeter simulations using generative transformers","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2508.01908","title":"Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models","created":"2025-08-03","cited_by_count":14,"area":null},{"id":"2103.00243","title":"Searching for Robustness: Loss Learning for Noisy Classification Tasks","created":"2021-02-27","cited_by_count":13,"area":null},{"id":"2109.00953","title":"TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing prediction","created":"2021-09-02","cited_by_count":13,"area":null},{"id":"2208.10002","title":"TransNet: Category-Level Transparent Object Pose Estimation","created":"2022-08-22","cited_by_count":13,"area":null},{"id":"2301.12549","title":"Unlocking Deterministic Robustness Certification on ImageNet","created":"2023-01-29","cited_by_count":13,"area":null},{"id":"2404.00357","title":"Revisiting Random Weight Perturbation for Efficiently Improving Generalization","created":"2024-03-30","cited_by_count":13,"area":null},{"id":"2405.03140","title":"TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning","created":"2024-05-06","cited_by_count":12,"area":null},{"id":"2102.08431","title":"Complex Momentum for Optimization in Games","created":"2021-02-16","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":"2105.01846","title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex","created":"2021-05-05","cited_by_count":10,"area":null},{"id":"2304.11744","title":"SketchXAI: A First Look at Explainability for Human Sketches","created":"2023-04-23","cited_by_count":10,"area":null},{"id":"2310.10089","title":"Over-the-Air Federated Learning and Optimization","created":"2023-10-16","cited_by_count":10,"area":null},{"id":"2310.15047","title":"Implicit meta-learning may lead language models to trust more reliable sources","created":"2023-10-23","cited_by_count":10,"area":null},{"id":"2105.12763","title":"An Online Learning System for Wireless Charging Alignment using Surround-view Fisheye Cameras","created":"2021-05-26","cited_by_count":9,"area":null},{"id":"2105.14426","title":"ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX","created":"2021-05-30","cited_by_count":9,"area":null},{"id":"2106.03242","title":"Highlighting the Importance of Reducing Research Bias and Carbon Emissions in CNNs","created":"2021-06-06","cited_by_count":9,"area":null},{"id":"2110.10640","title":"OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data","created":"2021-10-20","cited_by_count":9,"area":null},{"id":"2111.10192","title":"An Expectation-Maximization Perspective on Federated Learning","created":"2021-11-19","cited_by_count":9,"area":null},{"id":"2202.13808","title":"DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2306.07684","title":"Lookaround Optimizer: $k$ steps around, 1 step average","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2402.09240","title":"Switch EMA: A Free Lunch for Better Flatness and Sharpness","created":"2024-02-14","cited_by_count":9,"area":null},{"id":"2404.03632","title":"Reference-Based 3D-Aware Image Editing with Triplanes","created":"2024-04-04","cited_by_count":9,"area":null},{"id":"2108.02768","title":"Learning to Elect","created":"2021-08-05","cited_by_count":8,"area":null},{"id":"2112.13826","title":"Last-Iterate Convergence of Saddle-Point Optimizers via High-Resolution Differential Equations","created":"2021-12-27","cited_by_count":8,"area":null},{"id":"2205.14955","title":"AttentionCode: Ultra-Reliable Feedback Codes for Short-Packet Communications","created":"2022-05-30","cited_by_count":8,"area":null}],"next_cursor":"100"}