{"total":1321,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649,"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":"2106.06935","title":"Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction","created":"2021-06-13","cited_by_count":275,"area":null},{"id":"2111.14973","title":"MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction","created":"2021-11-29","cited_by_count":246,"area":null},{"id":"2205.10343","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","created":"2022-05-20","cited_by_count":230,"area":null},{"id":"2109.02369","title":"Point-Based Neural Rendering with Per-View Optimization","created":"2021-09-06","cited_by_count":190,"area":null},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2104.09459","title":"A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups","created":"2021-04-19","cited_by_count":187,"area":null},{"id":"2109.00179","title":"Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds","created":"2021-09-01","cited_by_count":180,"area":null},{"id":"2202.13013","title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","created":"2022-02-25","cited_by_count":179,"area":null},{"id":"2110.03336","title":"Frame Averaging for Invariant and Equivariant Network Design","created":"2021-10-07","cited_by_count":168,"area":null},{"id":"2110.03753","title":"From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness","created":"2021-10-07","cited_by_count":155,"area":null},{"id":"2110.02910","title":"Equivariant Subgraph Aggregation Networks","created":"2021-10-06","cited_by_count":154,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2106.05304","title":"Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline","created":"2021-06-09","cited_by_count":145,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2110.13197","title":"Nested Graph Neural Networks","created":"2021-10-25","cited_by_count":137,"area":null},{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133,"area":null},{"id":"2104.00563","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","created":"2021-02-19","cited_by_count":131,"area":null},{"id":"2108.11482","title":"ETA Prediction with Graph Neural Networks in Google Maps","created":"2021-08-25","cited_by_count":130,"area":null},{"id":"2106.06610","title":"Scalars are universal: Equivariant machine learning, structured like classical physics","created":"2021-06-11","cited_by_count":127,"area":null},{"id":"2106.13264","title":"You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks","created":"2021-06-24","cited_by_count":127,"area":null},{"id":"2107.13048","title":"Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks","created":"2021-07-27","cited_by_count":124,"area":null},{"id":"2112.09992","title":"Weisfeiler and Leman go Machine Learning: The Story so far","created":"2021-12-18","cited_by_count":122,"area":null},{"id":"2102.11533","title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","created":"2021-02-23","cited_by_count":120,"area":null},{"id":"2305.19420","title":"What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization","created":"2023-05-30","cited_by_count":118,"area":null},{"id":"2206.11140","title":"Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries","created":"2022-06-22","cited_by_count":112,"area":null},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109,"area":null},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109,"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":"2205.15659","title":"The CLRS Algorithmic Reasoning Benchmark","created":"2022-05-31","cited_by_count":106,"area":null},{"id":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102,"area":null},{"id":"2202.03772","title":"Particle Transformer for Jet Tagging","created":"2022-02-08","cited_by_count":98,"area":null},{"id":"2201.11969","title":"Approximately Equivariant Networks for Imperfectly Symmetric Dynamics","created":"2022-01-28","cited_by_count":97,"area":null},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95,"area":null},{"id":"2106.06345","title":"Proximal Optimal Transport Modeling of Population Dynamics","created":"2021-06-11","cited_by_count":93,"area":null},{"id":"2102.10333","title":"Provably Strict Generalisation Benefit for Equivariant Models","created":"2021-02-20","cited_by_count":91,"area":null},{"id":"2106.05609","title":"GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings","created":"2021-06-10","cited_by_count":90,"area":null},{"id":"2205.13328","title":"How Powerful are K-hop Message Passing Graph Neural Networks","created":"2022-05-26","cited_by_count":90,"area":null},{"id":"2102.04776","title":"Generative Models as Distributions of Functions","created":"2021-02-09","cited_by_count":89,"area":null},{"id":"2203.17030","title":"Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks","created":"2022-03-31","cited_by_count":88,"area":null},{"id":"2102.07835","title":"Topological Graph Neural Networks","created":"2021-02-15","cited_by_count":87,"area":null},{"id":"2410.04803","title":"Timer-XL: Long-Context Transformers for Unified Time Series Forecasting","created":"2024-10-07","cited_by_count":87,"area":null},{"id":"2301.08210","title":"Everything is Connected: Graph Neural Networks","created":"2023-01-19","cited_by_count":85,"area":null},{"id":"2110.09443","title":"Beltrami Flow and Neural Diffusion on Graphs","created":"2021-10-18","cited_by_count":84,"area":null},{"id":"2109.07103","title":"Automatic Symmetry Discovery with Lie Algebra Convolutional Network","created":"2021-09-15","cited_by_count":83,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2102.13303","title":"Graph-based Semi-supervised Learning: A Comprehensive Review","created":"2021-02-26","cited_by_count":79,"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":"2110.13715","title":"ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs","created":"2021-10-26","cited_by_count":78,"area":null},{"id":"2404.14197","title":"SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion","created":"2024-04-22","cited_by_count":76,"area":null},{"id":"2112.01388","title":"Residual Pathway Priors for Soft Equivariance Constraints","created":"2021-12-02","cited_by_count":75,"area":null},{"id":"2301.13105","title":"Generalization on the Unseen, Logic Reasoning and Degree Curriculum","created":"2023-01-30","cited_by_count":73,"area":null},{"id":"2405.11643","title":"Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology","created":"2024-05-19","cited_by_count":72,"area":null},{"id":"2302.14040","title":"Permutation Equivariant Neural Functionals","created":"2023-02-27","cited_by_count":70,"area":null},{"id":"2502.03349","title":"Robust Autonomy Emerges from Self-Play","created":"2025-02-05","cited_by_count":67,"area":null},{"id":"2110.00577","title":"Reconstruction for Powerful Graph Representations","created":"2021-10-01","cited_by_count":65,"area":null},{"id":"2203.16797","title":"When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning","created":"2022-03-31","cited_by_count":65,"area":null},{"id":"2107.05768","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2107.01959","title":"Universal Approximation of Functions on Sets","created":"2021-07-05","cited_by_count":62,"area":null},{"id":"2105.07029","title":"Learning a Universal Template for Few-shot Dataset Generalization","created":"2021-05-14","cited_by_count":61,"area":null},{"id":"2111.02329","title":"Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods","created":"2021-11-03","cited_by_count":61,"area":null},{"id":"2204.07697","title":"Theory of Graph Neural Networks: Representation and Learning","created":"2022-04-16","cited_by_count":61,"area":null},{"id":"2206.14262","title":"Supervised Training of Conditional Monge Maps","created":"2022-06-28","cited_by_count":61,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58,"area":null},{"id":"2102.03247","title":"GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set","created":"2021-02-05","cited_by_count":57,"area":null},{"id":"2312.04501","title":"Graph Metanetworks for Processing Diverse Neural Architectures","created":"2023-12-07","cited_by_count":57,"area":null},{"id":"2305.11141","title":"Clifford Group Equivariant Neural Networks","created":"2023-05-18","cited_by_count":55,"area":null},{"id":"2111.04006","title":"A Review of Location Encoding for GeoAI: Methods and Applications","created":"2021-11-07","cited_by_count":54,"area":null},{"id":"2305.18846","title":"Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation","created":"2023-05-30","cited_by_count":54,"area":null},{"id":"2102.08898","title":"Few-shot Conformal Prediction with Auxiliary Tasks","created":"2021-02-17","cited_by_count":53,"area":null},{"id":"2502.14546","title":"Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks","created":"2025-02-20","cited_by_count":53,"area":null},{"id":"2106.10800","title":"Lossy Compression for Lossless Prediction","created":"2021-06-21","cited_by_count":52,"area":null},{"id":"2210.09974","title":"Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks","created":"2022-10-18","cited_by_count":52,"area":null},{"id":"2305.13546","title":"Neural Functional Transformers","created":"2023-05-22","cited_by_count":52,"area":null},{"id":"2112.03769","title":"Machine Learning in the Search for New Fundamental Physics","created":"2021-12-07","cited_by_count":50,"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":"2206.03992","title":"Neural Diffusion Processes","created":"2022-06-08","cited_by_count":50,"area":null},{"id":"2305.15871","title":"Learning Robust Statistics for Simulation-based Inference under Model Misspecification","created":"2023-05-25","cited_by_count":48,"area":null},{"id":"2202.11097","title":"Message passing all the way up","created":"2022-02-22","cited_by_count":47,"area":null},{"id":"2204.07548","title":"Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation","created":"2022-04-15","cited_by_count":47,"area":null},{"id":"2207.06680","title":"Equivariant Hypergraph Diffusion Neural Operators","created":"2022-07-14","cited_by_count":47,"area":null},{"id":"2304.04757","title":"A new perspective on building efficient and expressive 3D equivariant graph neural networks","created":"2023-04-07","cited_by_count":47,"area":null},{"id":"2203.10800","title":"Graph Neural Networks for Wireless Communications: From Theory to Practice","created":"2022-03-21","cited_by_count":46,"area":null},{"id":"2103.02535","title":"Style-based Point Generator with Adversarial Rendering for Point Cloud Completion","created":"2021-03-03","cited_by_count":45,"area":null},{"id":"2107.01614","title":"Survey: Leakage and Privacy at Inference Time","created":"2021-07-04","cited_by_count":44,"area":null},{"id":"2310.10553","title":"TacticAI: an AI assistant for football tactics","created":"2023-10-16","cited_by_count":44,"area":null},{"id":"2109.06024","title":"Formalizing and Estimating Distribution Inference Risks","created":"2021-09-13","cited_by_count":43,"area":null},{"id":"2403.05618","title":"OmniJet-$\\alpha$: The first cross-task foundation model for particle physics","created":"2024-03-08","cited_by_count":43,"area":null},{"id":"2106.02668","title":"Emergent Communication of Generalizations","created":"2021-06-04","cited_by_count":42,"area":null},{"id":"2302.00236","title":"Generative Adversarial Symmetry Discovery","created":"2023-02-01","cited_by_count":42,"area":null},{"id":"2204.07178","title":"Relaxing Equivariance Constraints with Non-stationary Continuous Filters","created":"2022-04-14","cited_by_count":41,"area":null},{"id":"2210.05062","title":"Relational Attention: Generalizing Transformers for Graph-Structured Tasks","created":"2022-10-11","cited_by_count":41,"area":null},{"id":"2103.01710","title":"Autobahn: Automorphism-based Graph Neural Nets","created":"2021-03-02","cited_by_count":39,"area":null},{"id":"2202.07559","title":"Unsupervised Learning of Group Invariant and Equivariant Representations","created":"2022-02-15","cited_by_count":39,"area":null},{"id":"2211.02590","title":"Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion","created":"2022-11-04","cited_by_count":39,"area":null},{"id":"2404.12484","title":"Neural Methods for Amortized Inference","created":"2024-04-18","cited_by_count":39,"area":null},{"id":"2106.01908","title":"You Never Cluster Alone","created":"2021-06-03","cited_by_count":38,"area":null}],"next_cursor":"100"}