{"total":170,"rows":[{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491,"area":null},{"id":"2104.08315","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","created":"2021-04-16","cited_by_count":263,"area":null},{"id":"2101.08231","title":"Word Alignment by Fine-tuning Embeddings on Parallel Corpora","created":"2021-01-20","cited_by_count":186,"area":null},{"id":"2210.15191","title":"Truncation Sampling as Language Model Desmoothing","created":"2022-10-27","cited_by_count":123,"area":null},{"id":"2106.03760","title":"DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning","created":"2021-06-07","cited_by_count":115,"area":"moe"},{"id":"2106.01613","title":"NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning","created":"2021-06-03","cited_by_count":88,"area":null},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88,"area":null},{"id":"2106.00085","title":"Language Model Evaluation Beyond Perplexity","created":"2021-05-31","cited_by_count":78,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2305.15805","title":"Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers","created":"2023-05-25","cited_by_count":67,"area":null},{"id":"2108.04718","title":"Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation","created":"2021-08-10","cited_by_count":65,"area":null},{"id":"2204.09331","title":"NFormer: Robust Person Re-identification with Neighbor Transformer","created":"2022-04-20","cited_by_count":57,"area":null},{"id":"2302.06461","title":"A Study on ReLU and Softmax in Transformer","created":"2023-02-13","cited_by_count":53,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2406.16747","title":"Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers","created":"2024-06-24","cited_by_count":52,"area":null},{"id":"2112.02962","title":"DANets: Deep Abstract Networks for Tabular Data Classification and Regression","created":"2021-12-06","cited_by_count":50,"area":null},{"id":"2410.01104","title":"Softmax is not Enough (for Sharp Size Generalisation)","created":"2024-10-01","cited_by_count":46,"area":null},{"id":"2101.08543","title":"Boost then Convolve: Gradient Boosting Meets Graph Neural Networks","created":"2021-01-21","cited_by_count":44,"area":null},{"id":"2309.12673","title":"On Sparse Modern Hopfield Model","created":"2023-09-22","cited_by_count":42,"area":null},{"id":"2104.07012","title":"Sparse Attention with Linear Units","created":"2021-04-14","cited_by_count":41,"area":null},{"id":"2312.17346","title":"STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction","created":"2023-12-28","cited_by_count":35,"area":null},{"id":"2210.01941","title":"SIMPLE: A Gradient Estimator for $k$-Subset Sampling","created":"2022-10-04","cited_by_count":34,"area":null},{"id":"2212.10502","title":"A Measure-Theoretic Characterization of Tight Language Models","created":"2022-12-20","cited_by_count":33,"area":null},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2107.01830","title":"ARM-Net: Adaptive Relation Modeling Network for Structured Data","created":"2021-07-05","cited_by_count":24,"area":null},{"id":"2212.09171","title":"Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data","created":"2022-12-18","cited_by_count":21,"area":null},{"id":"2404.03830","title":"BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model","created":"2024-04-04","cited_by_count":21,"area":null},{"id":"2506.16640","title":"Long-Context Generalization with Sparse Attention","created":"2025-06-19","cited_by_count":21,"area":null},{"id":"2204.10810","title":"Learning to Scaffold: Optimizing Model Explanations for Teaching","created":"2022-04-22","cited_by_count":20,"area":null},{"id":"2305.16174","title":"From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module","created":"2023-05-25","cited_by_count":19,"area":null},{"id":"2312.17241","title":"Compact Neural Graphics Primitives with Learned Hash Probing","created":"2023-12-28","cited_by_count":19,"area":null},{"id":"2407.17097","title":"Towards Robust Knowledge Tracing Models via k-Sparse Attention","created":"2024-07-24","cited_by_count":19,"area":null},{"id":"2410.23126","title":"Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes","created":"2024-10-30","cited_by_count":19,"area":null},{"id":"2307.03749","title":"On the Efficacy of Sampling Adapters","created":"2023-07-07","cited_by_count":17,"area":null},{"id":"2203.02034","title":"Data-Efficient and Interpretable Tabular Anomaly Detection","created":"2022-03-03","cited_by_count":15,"area":null},{"id":"2108.01988","title":"Sparse Continuous Distributions and Fenchel-Young Losses","created":"2021-08-04","cited_by_count":14,"area":null},{"id":"2109.12188","title":"Predicting Attention Sparsity in Transformers","created":"2021-09-24","cited_by_count":13,"area":null},{"id":"2402.13725","title":"Sparse and Structured Hopfield Networks","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2204.03084","title":"Knowledge Infused Decoding","created":"2022-04-06","cited_by_count":12,"area":null},{"id":"2502.12082","title":"AdaSplash: Adaptive Sparse Flash Attention","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2103.10291","title":"Smoothing and Shrinking the Sparse Seq2Seq Search Space","created":"2021-03-18","cited_by_count":11,"area":null},{"id":"2112.00298","title":"Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modeling","created":"2021-12-01","cited_by_count":11,"area":null},{"id":"2305.03515","title":"GradTree: Learning Axis-Aligned Decision Trees with Gradient Descent","created":"2023-05-05","cited_by_count":11,"area":null},{"id":"2309.17130","title":"GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2305.00135","title":"Joint Sensing, Communication, and AI: A Trifecta for Resilient THz User Experiences","created":"2023-04-29","cited_by_count":10,"area":null},{"id":"2501.18537","title":"Loss Functions and Operators Generated by f-Divergences","created":"2025-01-30","cited_by_count":10,"area":null},{"id":"2207.08548","title":"GANDALF: Gated Adaptive Network for Deep Automated Learning of Features","created":"2022-07-18","cited_by_count":9,"area":null},{"id":"2405.18906","title":"Language Generation with Strictly Proper Scoring Rules","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2405.18979","title":"MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2508.08369","title":"Scaled-Dot-Product Attention as One-Sided Entropic Optimal Transport","created":"2025-08-11","cited_by_count":8,"area":"deeprl"},{"id":"2107.09729","title":"What Do You Get When You Cross Beam Search with Nucleus Sampling?","created":"2021-07-20","cited_by_count":7,"area":null},{"id":"2207.07212","title":"Attention, Filling in The Gaps for Generalization in Routing Problems","created":"2022-07-14","cited_by_count":7,"area":null},{"id":"2302.10903","title":"Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks","created":"2023-02-11","cited_by_count":7,"area":null},{"id":"2307.12198","title":"NCART: Neural Classification and Regression Tree for Tabular Data","created":"2023-07-23","cited_by_count":7,"area":null},{"id":"2503.07677","title":"PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity","created":"2025-03-10","cited_by_count":7,"area":"diffusion"},{"id":"2104.11026","title":"MeSIN: Multilevel Selective and Interactive Network for Medication Recommendation","created":"2021-04-22","cited_by_count":6,"area":null},{"id":"2110.14182","title":"Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models","created":"2021-10-27","cited_by_count":6,"area":null},{"id":"2401.04579","title":"A Deep Network for Explainable Prediction of Non-Imaging Phenotypes using Anatomical Multi-View Data","created":"2024-01-09","cited_by_count":6,"area":null},{"id":"2511.20102","title":"SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2601.17089","title":"GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing","created":"2026-01-23","cited_by_count":6,"area":"mllm"},{"id":"2207.09228","title":"Image Super-Resolution with Deep Dictionary","created":"2022-07-19","cited_by_count":5,"area":null},{"id":"2403.13351","title":"OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning","created":"2024-03-20","cited_by_count":5,"area":null},{"id":"2405.00568","title":"Powering In-Database Dynamic Model Slicing for Structured Data Analytics","created":"2024-05-01","cited_by_count":5,"area":"moe"},{"id":"2406.01189","title":"MultiMax: Sparse and Multi-Modal Attention Learning","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2406.02322","title":"A Survey of Transformer Enabled Time Series Synthesis","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2408.08761","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","created":"2024-08-16","cited_by_count":5,"area":"deeprl"},{"id":"2505.18698","title":"MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2601.12145","title":"Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2109.04983","title":"A Neural Tangent Kernel Perspective of Infinite Tree Ensembles","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2408.09624","title":"Attention is a smoothed cubic spline","created":"2024-08-19","cited_by_count":4,"area":null},{"id":"2408.11598","title":"Improving Calibration by Relating Focal Loss, Temperature Scaling, and Properness","created":"2024-08-21","cited_by_count":4,"area":null},{"id":"2409.07131","title":"Reranking Laws for Language Generation: A Communication-Theoretic Perspective","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2510.13681","title":"How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2605.18753","title":"DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2111.06832","title":"Speeding Up Entmax","created":"2021-11-12","cited_by_count":3,"area":null},{"id":"2206.11054","title":"S2RL: Do We Really Need to Perceive All States in Deep Multi-Agent Reinforcement Learning?","created":"2022-06-20","cited_by_count":3,"area":null},{"id":"2302.01581","title":"Learning to Decouple Complex Systems","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2405.02074","title":"A Federated Learning Benchmark on Tabular Data: Comparing Tree-Based Models and Neural Networks","created":"2024-05-03","cited_by_count":3,"area":null},{"id":"2408.13361","title":"NeurCAM: Interpretable Neural Clustering via Additive Models","created":"2024-08-23","cited_by_count":3,"area":null},{"id":"2412.15922","title":"RiTTA: Modeling Event Relations in Text-to-Audio Generation","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2508.12801","title":"Maximum Score Routing For Mixture-of-Experts","created":"2025-08-18","cited_by_count":3,"area":"moe"},{"id":"2511.00907","title":"Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2604.15180","title":"AdaSplash-2: Faster Differentiable Sparse Attention","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2604.15614","title":"Flexible Empowerment at Reasoning with Extended Best-of-N Sampling","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2108.02658","title":"Sparse Communication via Mixed Distributions","created":"2021-08-05","cited_by_count":2,"area":null},{"id":"2201.00490","title":"Learning with Latent Structures in Natural Language Processing: A Survey","created":"2022-01-03","cited_by_count":2,"area":null},{"id":"2205.12904","title":"Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel","created":"2022-05-25","cited_by_count":2,"area":null},{"id":"2209.15176","title":"Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition","created":"2022-09-30","cited_by_count":2,"area":null},{"id":"2408.07245","title":"q-exponential family for policy optimization","created":"2024-08-14","cited_by_count":2,"area":"deeprl"},{"id":"2502.08363","title":"Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2502.14773","title":"Sparse Activations as Conformal Predictors","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2601.22766","title":"Sparse Attention as Compact Kernel Regression","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.08216","title":"Entropy-Generated Attention Beyond Softmax and Entmax: Kaniadakis and Reciprocal-Symmetric Abe Operators","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2604.14925","title":"Improving Sparse Autoencoder with Dynamic Attention","created":"2026-04-16","cited_by_count":2,"area":"mechinterp"},{"id":"2104.00755","title":"Reconciling the Discrete-Continuous Divide: Towards a Mathematical Theory of Sparse Communication","created":"2021-04-01","cited_by_count":1,"area":null},{"id":"2106.01440","title":"Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models","created":"2021-06-01","cited_by_count":1,"area":null},{"id":"2106.07047","title":"Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models","created":"2021-06-13","cited_by_count":1,"area":null},{"id":"2210.03122","title":"Temporal Spatial Decomposition and Fusion Network for Time Series Forecasting","created":"2022-10-06","cited_by_count":1,"area":null},{"id":"2211.15924","title":"Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CT","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2304.03202","title":"SLM: End-to-end Feature Selection via Sparse Learnable Masks","created":"2023-04-06","cited_by_count":1,"area":null}],"next_cursor":"100"}