{"total":125,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999,"area":null},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2104.02112","title":"Efficient Attentions for Long Document Summarization","created":"2021-04-05","cited_by_count":345,"area":null},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207,"area":null},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102,"area":null},{"id":"2203.10314","title":"Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds","created":"2022-03-19","cited_by_count":102,"area":null},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96,"area":null},{"id":"2108.08771","title":"Learning to Match Features with Seeded Graph Matching Network","created":"2021-08-19","cited_by_count":92,"area":null},{"id":"2102.04776","title":"Generative Models as Distributions of Functions","created":"2021-02-09","cited_by_count":89,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2312.07511","title":"A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems","created":"2023-12-12","cited_by_count":68,"area":null},{"id":"2107.01959","title":"Universal Approximation of Functions on Sets","created":"2021-07-05","cited_by_count":62,"area":null},{"id":"2205.15764","title":"SymFormer: End-to-end symbolic regression using transformer-based architecture","created":"2022-05-31","cited_by_count":59,"area":null},{"id":"2105.09511","title":"Medical Image Segmentation Using Squeeze-and-Expansion Transformers","created":"2021-05-20","cited_by_count":57,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2302.04931","title":"In-Context Learning with Many Demonstration Examples","created":"2023-02-09","cited_by_count":39,"area":null},{"id":"2106.01908","title":"You Never Cluster Alone","created":"2021-06-03","cited_by_count":38,"area":null},{"id":"2110.14416","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","created":"2021-10-27","cited_by_count":35,"area":null},{"id":"2410.05952","title":"Active Evaluation Acquisition for Efficient LLM Benchmarking","created":"2024-10-08","cited_by_count":35,"area":null},{"id":"2107.00860","title":"Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets","created":"2021-07-02","cited_by_count":33,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2211.10295","title":"Evaluating generative models in high energy physics","created":"2022-11-18","cited_by_count":31,"area":null},{"id":"2106.02346","title":"Provably Strict Generalisation Benefit for Invariance in Kernel Methods","created":"2021-06-04","cited_by_count":30,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","cited_by_count":28,"area":null},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2205.11404","title":"Variable-Input Deep Operator Networks","created":"2022-05-23","cited_by_count":25,"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":"2106.03898","title":"SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention","created":"2021-06-07","cited_by_count":18,"area":null},{"id":"2105.04037","title":"Graph Attention Networks with Positional Embeddings","created":"2021-05-09","cited_by_count":16,"area":null},{"id":"2212.14852","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","created":"2022-12-30","cited_by_count":16,"area":null},{"id":"2305.12689","title":"FIT: Far-reaching Interleaved Transformers","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2411.16680","title":"Quark: Real-time, High-resolution, and General Neural View Synthesis","created":"2024-11-25","cited_by_count":16,"area":null},{"id":"2104.06703","title":"Deep Permutation Equivariant Structure from Motion","created":"2021-04-14","cited_by_count":15,"area":null},{"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":"2207.02242","title":"State-Augmented Learnable Algorithms for Resource Management in Wireless Networks","created":"2022-07-05","cited_by_count":14,"area":null},{"id":"2208.10428","title":"Equivariant Hypergraph Neural Networks","created":"2022-08-22","cited_by_count":14,"area":null},{"id":"2304.06715","title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2106.08185","title":"Kernel Identification Through Transformers","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2107.14053","title":"Few-Shot and Continual Learning with Attentive Independent Mechanisms","created":"2021-07-29","cited_by_count":13,"area":null},{"id":"2205.14005","title":"RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation","created":"2022-05-24","cited_by_count":13,"area":null},{"id":"2211.11386","title":"PS-Transformer: Learning Sparse Photometric Stereo Network using Self-Attention Mechanism","created":"2022-11-21","cited_by_count":13,"area":null},{"id":"2305.15254","title":"Attention to Mean-Fields for Particle Cloud Generation","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2102.04438","title":"Improved Brain Age Estimation with Slice-based Set Networks","created":"2021-02-08","cited_by_count":11,"area":null},{"id":"2102.13419","title":"Iterative SE(3)-Transformers","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2110.02393","title":"Geometric Algebra Attention Networks for Small Point Clouds","created":"2021-10-05","cited_by_count":10,"area":null},{"id":"2203.13465","title":"CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification","created":"2022-03-25","cited_by_count":9,"area":null},{"id":"2204.03957","title":"Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition","created":"2022-04-08","cited_by_count":9,"area":null},{"id":"2104.10105","title":"Neural Networks for Learning Counterfactual G-Invariances from Single Environments","created":"2021-04-20","cited_by_count":8,"area":null},{"id":"2204.03065","title":"The Self-Optimal-Transport Feature Transform","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2212.11671","title":"Set-Transformer BeamsNet for AUV Velocity Forecasting in Complete DVL Outage Scenarios","created":"2022-12-22","cited_by_count":7,"area":null},{"id":"2301.04791","title":"Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction","created":"2023-01-12","cited_by_count":7,"area":null},{"id":"2305.10203","title":"Exploring the Space of Key-Value-Query Models with Intention","created":"2023-05-17","cited_by_count":7,"area":null},{"id":"2107.00801","title":"Meta-Learning for Relative Density-Ratio Estimation","created":"2021-07-02","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":"2202.11132","title":"Bag Graph: Multiple Instance Learning using Bayesian Graph Neural Networks","created":"2022-02-22","cited_by_count":6,"area":null},{"id":"2203.05285","title":"Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework","created":"2022-03-10","cited_by_count":6,"area":null},{"id":"2205.11718","title":"Semi-Parametric Inducing Point Networks and Neural Processes","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2206.09021","title":"Conditional Permutation Invariant Flows","created":"2022-06-17","cited_by_count":6,"area":null},{"id":"2209.09861","title":"ESTA: An Esports Trajectory and Action Dataset","created":"2022-09-20","cited_by_count":6,"area":null},{"id":"2210.08031","title":"Neural Attentive Circuits","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2211.09286","title":"Permutation-Invariant Tabular Data Synthesis","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2302.11533","title":"MONGOOSE: Path-wise Smooth Bayesian Optimisation via Meta-learning","created":"2023-02-22","cited_by_count":6,"area":null},{"id":"2606.26497","title":"Learning Probabilistic Filters with Strictly Proper Scoring Rules","created":"2026-06-25","cited_by_count":6,"area":null},{"id":"2104.08874","title":"Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction","created":"2021-04-18","cited_by_count":5,"area":null},{"id":"2108.10808","title":"Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation","created":"2021-08-24","cited_by_count":5,"area":null},{"id":"2109.12451","title":"Deciding Whether to Ask Clarifying Questions in Large-Scale Spoken Language Understanding","created":"2021-09-25","cited_by_count":5,"area":null},{"id":"2112.00775","title":"Routing with Self-Attention for Multimodal Capsule Networks","created":"2021-12-01","cited_by_count":5,"area":null},{"id":"2210.13319","title":"MARS: Meta-Learning as Score Matching in the Function Space","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2106.06210","title":"Learning to Pool in Graph Neural Networks for Extrapolation","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2205.12407","title":"Convolutional Neural Processes for Inpainting Satellite Images","created":"2022-05-24","cited_by_count":4,"area":null},{"id":"2205.15895","title":"From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2408.10709","title":"Variable Assignment Invariant Neural Networks for Learning Logic Programs","created":"2024-08-20","cited_by_count":4,"area":null},{"id":"2103.09764","title":"HAMIL: Hierarchical Aggregation-Based Multi-Instance Learning for Microscopy Image Classification","created":"2021-03-17","cited_by_count":3,"area":null},{"id":"2103.15330","title":"Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications","created":"2021-03-29","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":"2204.04913","title":"Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2210.00641","title":"DARTFormer: Finding The Best Type Of Attention","created":"2022-10-02","cited_by_count":3,"area":null},{"id":"2211.14905","title":"Multi-Modal Few-Shot Temporal Action Detection","created":"2022-11-27","cited_by_count":3,"area":null},{"id":"2506.16698","title":"SIDE: Semantic ID Embedding for effective learning from sequences","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2103.06676","title":"Inference for Generative Capsule Models","created":"2021-03-11","cited_by_count":2,"area":null},{"id":"2105.09378","title":"Robust partial Fourier reconstruction for diffusion-weighted imaging using a recurrent convolutional neural network","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2110.11987","title":"Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representations","created":"2021-10-22","cited_by_count":2,"area":null},{"id":"2202.08583","title":"Point cloud completion via structured feature maps using a feedback network","created":"2022-02-17","cited_by_count":2,"area":null},{"id":"2211.15136","title":"Collective Intelligence for 2D Push Manipulations with Mobile Robots","created":"2022-11-28","cited_by_count":2,"area":null},{"id":"2407.04513","title":"LayerShuffle: Enhancing Robustness in Vision Transformers by Randomizing Layer Execution Order","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2102.04683","title":"Meta-Learning for Koopman Spectral Analysis with Short Time-series","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2108.07533","title":"Investigating transformers in the decomposition of polygonal shapes as point collections","created":"2021-08-17","cited_by_count":1,"area":null},{"id":"2109.07253","title":"Integrating Sensing and Communication in Cellular Networks via NR Sidelink","created":"2021-09-15","cited_by_count":1,"area":null},{"id":"2111.08356","title":"On-Demand Unlabeled Personalized Federated Learning","created":"2021-11-16","cited_by_count":1,"area":null},{"id":"2202.05517","title":"Electricity Consumption Forecasting for Out-of-distribution Time-of-Use Tariffs","created":"2022-02-11","cited_by_count":1,"area":null},{"id":"2203.03385","title":"FloorGenT: Generative Vector Graphic Model of Floor Plans for Robotics","created":"2022-03-07","cited_by_count":1,"area":null}],"next_cursor":"100"}