{"total":121,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2206.02647","title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","created":"2022-06-06","cited_by_count":359,"area":null},{"id":"2103.02438","title":"Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design","created":"2021-03-03","cited_by_count":106,"area":null},{"id":"2106.06345","title":"Proximal Optimal Transport Modeling of Population Dynamics","created":"2021-06-11","cited_by_count":93,"area":null},{"id":"2103.15619","title":"SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data","created":"2021-03-29","cited_by_count":78,"area":null},{"id":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2206.03996","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","created":"2022-06-08","cited_by_count":58,"area":null},{"id":"2103.12413","title":"Neural ODE Processes","created":"2021-03-23","cited_by_count":57,"area":null},{"id":"2111.10510","title":"Bayesian Learning via Neural Schr\\\"odinger-F\\\"ollmer Flows","created":"2021-11-20","cited_by_count":56,"area":null},{"id":"2102.08898","title":"Few-shot Conformal Prediction with Auxiliary Tasks","created":"2021-02-17","cited_by_count":53,"area":null},{"id":"2203.00585","title":"Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology","created":"2022-03-01","cited_by_count":50,"area":null},{"id":"2308.15474","title":"A General-Purpose Self-Supervised Model for Computational Pathology","created":"2023-08-29","cited_by_count":42,"area":null},{"id":"2106.01908","title":"You Never Cluster Alone","created":"2021-06-03","cited_by_count":38,"area":null},{"id":"2205.15463","title":"Few-Shot Diffusion Models","created":"2022-05-30","cited_by_count":38,"area":"diffusion"},{"id":"2106.03593","title":"Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2303.07502","title":"Meta-learning approaches for few-shot learning: A survey of recent advances","created":"2023-03-13","cited_by_count":25,"area":null},{"id":"2111.05326","title":"The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning","created":"2021-11-09","cited_by_count":23,"area":null},{"id":"2209.00517","title":"The Neural Process Family: Survey, Applications and Perspectives","created":"2022-09-01","cited_by_count":23,"area":null},{"id":"2209.11820","title":"Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learning","created":"2022-09-23","cited_by_count":23,"area":null},{"id":"2106.16245","title":"How to Train Your MAML to Excel in Few-Shot Classification","created":"2021-06-30","cited_by_count":22,"area":null},{"id":"2110.09140","title":"Learning Prototype-oriented Set Representations for Meta-Learning","created":"2021-10-18","cited_by_count":19,"area":null},{"id":"2111.03144","title":"Amortized Variational Inference for Simple Hierarchical Models","created":"2021-11-04","cited_by_count":19,"area":null},{"id":"2101.02523","title":"Few-Shot Learning with Class Imbalance","created":"2021-01-07","cited_by_count":18,"area":null},{"id":"2102.02274","title":"Neural Recursive Belief States in Multi-Agent Reinforcement Learning","created":"2021-02-03","cited_by_count":18,"area":null},{"id":"2106.06326","title":"TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation","created":"2021-06-11","cited_by_count":17,"area":null},{"id":"2107.00197","title":"Few-Shot Learning with a Strong Teacher","created":"2021-07-01","cited_by_count":16,"area":null},{"id":"2204.05449","title":"Neural Processes with Stochastic Attention: Paying more attention to the context dataset","created":"2022-04-11","cited_by_count":16,"area":null},{"id":"2209.01501","title":"Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions","created":"2022-09-03","cited_by_count":14,"area":null},{"id":"2303.08557","title":"Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey","created":"2023-03-15","cited_by_count":14,"area":null},{"id":"2402.07594","title":"Zero-shot Imputation with Foundation Inference Models for Dynamical Systems","created":"2024-02-12","cited_by_count":13,"area":null},{"id":"2504.08934","title":"Long Context In-Context Compression by Getting to the Gist of Gisting","created":"2025-04-11","cited_by_count":13,"area":"inference"},{"id":"2106.06410","title":"What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data","created":"2021-06-11","cited_by_count":10,"area":null},{"id":"2107.13467","title":"Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation","created":"2021-07-28","cited_by_count":10,"area":null},{"id":"2301.11722","title":"Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?","created":"2023-01-27","cited_by_count":10,"area":"diffusion"},{"id":"2502.11744","title":"FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation","created":"2025-02-17","cited_by_count":10,"area":"offlinerl"},{"id":"2103.06386","title":"Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning","created":"2021-03-10","cited_by_count":9,"area":null},{"id":"2205.10370","title":"Diversity vs. Recognizability: Human-like generalization in one-shot generative models","created":"2022-05-20","cited_by_count":9,"area":null},{"id":"2207.09759","title":"Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition","created":"2022-07-20","cited_by_count":9,"area":null},{"id":"2308.02877","title":"Meta-learning in healthcare: A survey","created":"2023-08-05","cited_by_count":9,"area":null},{"id":"2308.06382","title":"Phoneme Hallucinator: One-shot Voice Conversion via Set Expansion","created":"2023-08-11","cited_by_count":9,"area":null},{"id":"2109.14120","title":"Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness","created":"2021-09-29","cited_by_count":8,"area":null},{"id":"2211.16632","title":"Hierarchical Transformer for Survival Prediction Using Multimodality Whole Slide Images and Genomics","created":"2022-11-29","cited_by_count":8,"area":null},{"id":"2310.18713","title":"Episodic Multi-Task Learning with Heterogeneous Neural Processes","created":"2023-10-28","cited_by_count":8,"area":null},{"id":"2110.02529","title":"On the Importance of Firth Bias Reduction in Few-Shot Classification","created":"2021-10-06","cited_by_count":7,"area":null},{"id":"2208.01573","title":"Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning","created":"2022-08-02","cited_by_count":7,"area":null},{"id":"2208.10559","title":"Transductive Decoupled Variational Inference for Few-Shot Classification","created":"2022-08-22","cited_by_count":7,"area":null},{"id":"2305.06114","title":"Few-shot Action Recognition via Intra- and Inter-Video Information Maximization","created":"2023-05-10","cited_by_count":7,"area":null},{"id":"2308.06942","title":"Approximating Human-Like Few-shot Learning with GPT-based Compression","created":"2023-08-14","cited_by_count":7,"area":null},{"id":"2309.04452","title":"Postprocessing of Ensemble Weather Forecasts Using Permutation-invariant Neural Networks","created":"2023-09-08","cited_by_count":7,"area":null},{"id":"2502.19049","title":"In-Context Learning of Stochastic Differential Equations with Foundation Inference Models","created":"2025-02-26","cited_by_count":7,"area":null},{"id":"2103.09656","title":"Set-to-Sequence Methods in Machine Learning: a Review","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2110.12279","title":"SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation","created":"2021-10-23","cited_by_count":6,"area":null},{"id":"2511.05924","title":"DiScoFormer: Plug-In Density and Score Estimation with Transformers","created":"2025-11-08","cited_by_count":6,"area":null},{"id":"2104.09011","title":"Few-shot Learning for Topic Modeling","created":"2021-04-19","cited_by_count":5,"area":null},{"id":"2202.12795","title":"Equilibrium Aggregation: Encoding Sets via Optimization","created":"2022-02-25","cited_by_count":5,"area":null},{"id":"2206.11573","title":"Few-Shot Non-Parametric Learning with Deep Latent Variable Model","created":"2022-06-23","cited_by_count":5,"area":null},{"id":"2402.01399","title":"A Probabilistic Model Behind Self-Supervised Learning","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2101.05018","title":"Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition","created":"2021-01-13","cited_by_count":4,"area":null},{"id":"2309.00380","title":"Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectives","created":"2023-09-01","cited_by_count":4,"area":"moe"},{"id":"2501.09705","title":"Practical Continual Forgetting for Pre-trained Vision Models","created":"2025-01-16","cited_by_count":4,"area":null},{"id":"2505.18150","title":"Generative Distribution Embeddings: Lifting autoencoders to the space of distributions for multiscale representation learning","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2102.03776","title":"Hyperparameter Optimization with Differentiable Metafeatures","created":"2021-02-07","cited_by_count":3,"area":null},{"id":"2102.06083","title":"Partially Observed Exchangeable Modeling","created":"2021-02-11","cited_by_count":3,"area":null},{"id":"2104.09650","title":"Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks","created":"2021-04-19","cited_by_count":3,"area":null},{"id":"2107.08305","title":"PICASO: Permutation-Invariant Cascaded Attentional Set Operator","created":"2021-07-17","cited_by_count":3,"area":null},{"id":"2202.01940","title":"Distribution Embedding Networks for Generalization from a Diverse Set of Classification Tasks","created":"2022-02-04","cited_by_count":3,"area":null},{"id":"2208.04600","title":"IDNP: Interest Dynamics Modeling using Generative Neural Processes for Sequential Recommendation","created":"2022-08-09","cited_by_count":3,"area":null},{"id":"2311.10671","title":"Fuse It or Lose It: Deep Fusion for Multimodal Simulation-Based Inference","created":"2023-11-17","cited_by_count":3,"area":null},{"id":"2403.15123","title":"Quantification using Permutation-Invariant Networks based on Histograms","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2406.06079","title":"Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks","created":"2024-06-10","cited_by_count":3,"area":"diffusion"},{"id":"2502.12088","title":"Meta-Statistical Learning: Supervised Learning of Statistical Estimators","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2105.03781","title":"MetaKernel: Learning Variational Random Features with Limited Labels","created":"2021-05-08","cited_by_count":2,"area":null},{"id":"2201.11815","title":"Consolidated learning -- a domain-specific model-free optimization strategy with examples for XGBoost and MIMIC-IV","created":"2022-01-27","cited_by_count":2,"area":null},{"id":"2211.04670","title":"Distributional Shift Adaptation using Domain-Specific Features","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2301.13136","title":"Contrastive Meta-Learning for Partially Observable Few-Shot Learning","created":"2023-01-30","cited_by_count":2,"area":null},{"id":"2306.15169","title":"Exploiting Inferential Structure in Neural Processes","created":"2023-06-27","cited_by_count":2,"area":null},{"id":"2307.16005","title":"Enhancing Object Detection in Ancient Documents with Synthetic Data Generation and Transformer-Based Models","created":"2023-07-29","cited_by_count":2,"area":null},{"id":"2401.09966","title":"Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection","created":"2024-01-18","cited_by_count":2,"area":"lr"},{"id":"2403.15476","title":"Learning to Infer Generative Template Programs for Visual Concepts","created":"2024-03-20","cited_by_count":2,"area":null},{"id":"2406.17834","title":"Univariate Skeleton Prediction in Multivariate Systems Using Transformers","created":"2024-06-25","cited_by_count":2,"area":null},{"id":"2410.03892","title":"Towards Cost Sensitive Decision Making","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2504.01650","title":"Sparse Gaussian Neural Processes","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2510.19425","title":"Neural Variational Dropout Processes","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2104.05344","title":"How Sensitive are Meta-Learners to Dataset Imbalance?","created":"2021-04-12","cited_by_count":1,"area":null},{"id":"2106.15133","title":"Meta-learning for Matrix Factorization without Shared Rows or Columns","created":"2021-06-29","cited_by_count":1,"area":null},{"id":"2110.11664","title":"GCCN: Global Context Convolutional Network","created":"2021-10-22","cited_by_count":1,"area":null},{"id":"2306.11636","title":"SeFNet: Bridging Tabular Datasets with Semantic Feature Nets","created":"2023-06-20","cited_by_count":1,"area":null},{"id":"2401.12421","title":"AdaEmbed: Semi-supervised Domain Adaptation in the Embedding Space","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2402.03139","title":"Enhancing Neural Subset Selection: Integrating Background Information into Set Representations","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2405.17824","title":"mTREE: Multi-Level Text-Guided Representation End-to-End Learning for Whole Slide Image Analysis","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2411.04517","title":"Continuous Sign Language Recognition System using Deep Learning with MediaPipe Holistic","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2606.20538","title":"Multi-Task Bayesian In-Context Learning","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2101.00203","title":"B-SMALL: A Bayesian Neural Network approach to Sparse Model-Agnostic Meta-Learning","created":"2021-01-01","cited_by_count":0,"area":null},{"id":"2103.00684","title":"Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection","created":"2021-03-01","cited_by_count":0,"area":null},{"id":"2103.02265","title":"Meta-Learning with Variational Bayes","created":"2021-03-03","cited_by_count":0,"area":null},{"id":"2104.09231","title":"Visual analytics of set data for knowledge discovery and member selection support","created":"2021-04-04","cited_by_count":0,"area":null},{"id":"2105.00397","title":"OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation","created":"2021-05-02","cited_by_count":0,"area":null},{"id":"2107.02228","title":"Meta-learning Amidst Heterogeneity and Ambiguity","created":"2021-07-05","cited_by_count":0,"area":null},{"id":"2112.09752","title":"Set Twister for Single-hop Node Classification","created":"2021-12-17","cited_by_count":0,"area":null},{"id":"2205.09738","title":"AIGenC: An AI generalisation model via creativity","created":"2022-05-19","cited_by_count":0,"area":null}],"next_cursor":"100"}