{"total":309,"rows":[{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491,"area":null},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2209.06243","title":"CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task","created":"2022-09-13","cited_by_count":207,"area":null},{"id":"2105.15183","title":"Efficient and Modular Implicit Differentiation","created":"2021-05-31","cited_by_count":203,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2307.13565","title":"Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities","created":"2023-07-25","cited_by_count":130,"area":null},{"id":"2210.15191","title":"Truncation Sampling as Language Model Desmoothing","created":"2022-10-27","cited_by_count":123,"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":"2309.11925","title":"Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task","created":"2023-09-21","cited_by_count":88,"area":null},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2106.07153","title":"Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods","created":"2021-06-14","cited_by_count":59,"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":"2103.06641","title":"Differentially Private Query Release Through Adaptive Projection","created":"2021-03-11","cited_by_count":52,"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":"2410.01104","title":"Softmax is not Enough (for Sharp Size Generalisation)","created":"2024-10-01","cited_by_count":46,"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":"2211.16887","title":"T2G-Former: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction","created":"2022-11-30","cited_by_count":41,"area":null},{"id":"2404.03827","title":"Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models","created":"2024-04-04","cited_by_count":38,"area":null},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36,"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":"2404.14994","title":"Transformers Can Represent $n$-gram Language Models","created":"2024-04-23","cited_by_count":32,"area":null},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2101.04109","title":"Explain and Predict, and then Predict Again","created":"2021-01-11","cited_by_count":29,"area":null},{"id":"2207.13513","title":"Learning with Combinatorial Optimization Layers: a Probabilistic Approach","created":"2022-07-27","cited_by_count":29,"area":null},{"id":"2211.13290","title":"SEAT: Stable and Explainable Attention","created":"2022-11-23","cited_by_count":25,"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":"2109.06619","title":"Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration","created":"2021-09-14","cited_by_count":24,"area":null},{"id":"2210.01802","title":"Alternating Differentiation for Optimization Layers","created":"2022-10-03","cited_by_count":22,"area":null},{"id":"2210.03454","title":"DABERT: Dual Attention Enhanced BERT for Semantic Matching","created":"2022-10-07","cited_by_count":21,"area":null},{"id":"2302.12530","title":"Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflicts","created":"2023-02-24","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":"2108.05682","title":"(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models' Performance","created":"2021-08-12","cited_by_count":20,"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":"2211.13955","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","created":"2022-11-25","cited_by_count":20,"area":null},{"id":"2411.18822","title":"RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data","created":"2024-11-27","cited_by_count":20,"area":null},{"id":"2109.04552","title":"SPECTRA: Sparse Structured Text Rationalization","created":"2021-09-09","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":"2402.02098","title":"Self-attention Networks Localize When QK-eigenspectrum Concentrates","created":"2024-02-03","cited_by_count":19,"area":null},{"id":"2405.17822","title":"Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action","created":"2024-05-28","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":"2106.02208","title":"BERTTune: Fine-Tuning Neural Machine Translation with BERTScore","created":"2021-06-04","cited_by_count":18,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2303.09728","title":"The Cascaded Forward Algorithm for Neural Network Training","created":"2023-03-17","cited_by_count":17,"area":null},{"id":"2410.01537","title":"Attention layers provably solve single-location regression","created":"2024-10-02","cited_by_count":17,"area":null},{"id":"2305.05964","title":"Interpretable Multimodal Misinformation Detection with Logic Reasoning","created":"2023-05-10","cited_by_count":16,"area":null},{"id":"2308.06262","title":"Foundation Model is Efficient Multimodal Multitask Model Selector","created":"2023-08-11","cited_by_count":16,"area":null},{"id":"2404.03900","title":"Nonparametric Modern Hopfield Models","created":"2024-04-05","cited_by_count":16,"area":null},{"id":"2101.06658","title":"Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution","created":"2021-01-17","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":"2103.06263","title":"Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution","created":"2021-03-10","cited_by_count":13,"area":null},{"id":"2109.12188","title":"Predicting Attention Sparsity in Transformers","created":"2021-09-24","cited_by_count":13,"area":null},{"id":"2212.13899","title":"Attentive Deep Neural Networks for Legal Document Retrieval","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2301.12047","title":"Backpropagation of Unrolled Solvers with Folded Optimization","created":"2023-01-28","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":"2106.01680","title":"Convergent Graph Solvers","created":"2021-06-03","cited_by_count":12,"area":null},{"id":"2109.04556","title":"Subword Mapping and Anchoring across Languages","created":"2021-09-09","cited_by_count":12,"area":null},{"id":"2211.01407","title":"On the Informativeness of Supervision Signals","created":"2022-11-02","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":"2504.16041","title":"Muon Optimizer Accelerates Grokking","created":"2025-04-22","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":"2304.01518","title":"Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation","created":"2023-04-04","cited_by_count":11,"area":null},{"id":"2305.15768","title":"High-Similarity-Pass Attention for Single Image Super-Resolution","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2410.03001","title":"Can Transformers Learn $n$-gram Language Models?","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2101.11520","title":"Supervised Tree-Wasserstein Distance","created":"2021-01-27","cited_by_count":10,"area":null},{"id":"2110.02667","title":"Attentive Walk-Aggregating Graph Neural Networks","created":"2021-10-06","cited_by_count":10,"area":null},{"id":"2201.13063","title":"NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments","created":"2022-01-31","cited_by_count":10,"area":null},{"id":"2203.11629","title":"On Neural Network Equivalence Checking using SMT Solvers","created":"2022-03-22","cited_by_count":10,"area":null},{"id":"2410.05506","title":"Privacy Vulnerabilities in Marginals-based Synthetic Data","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2410.06324","title":"Differentiation Through Black-Box Quadratic Programming Solvers","created":"2024-10-08","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":"2504.00927","title":"Multi-Token Attention","created":"2025-04-01","cited_by_count":10,"area":null},{"id":"2505.19371","title":"Foundations of Top-$k$ Decoding For Language Models","created":"2025-05-25","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":"2412.02254","title":"ProbPose: A Probabilistic Approach to 2D Human Pose Estimation","created":"2024-12-03","cited_by_count":9,"area":null},{"id":"2504.08959","title":"MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer","created":"2025-04-11","cited_by_count":9,"area":null},{"id":"2204.06517","title":"Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation","created":"2022-03-30","cited_by_count":8,"area":null},{"id":"2205.09589","title":"Learning Energy Networks with Generalized Fenchel-Young Losses","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2206.07235","title":"Training Discrete Deep Generative Models via Gapped Straight-Through Estimator","created":"2022-06-15","cited_by_count":8,"area":null},{"id":"2207.03902","title":"Interaction Pattern Disentangling for Multi-Agent Reinforcement Learning","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2306.04996","title":"T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification","created":"2023-06-08","cited_by_count":8,"area":null},{"id":"2309.16883","title":"The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing","created":"2023-09-28","cited_by_count":8,"area":null},{"id":"2405.14064","title":"Building a stable classifier with the inflated argmax","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2405.18906","title":"Language Generation with Strictly Proper Scoring Rules","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2406.12282","title":"SAGDFN: A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecasting","created":"2024-06-18","cited_by_count":8,"area":null},{"id":"2602.11779","title":"Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement Learning","created":"2026-02-12","cited_by_count":8,"area":null},{"id":"2104.05819","title":"Learning from Executions for Semantic Parsing","created":"2021-04-12","cited_by_count":7,"area":null},{"id":"2107.00594","title":"Pretext Tasks selection for multitask self-supervised speech representation learning","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2207.05205","title":"Scaling Novel Object Detection with Weakly Supervised Detection Transformers","created":"2022-07-11","cited_by_count":7,"area":null},{"id":"2208.03727","title":"Robust Multi-Object Tracking by Marginal Inference","created":"2022-08-07","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":"2410.06851","title":"Understanding Model Ensemble in Transferable Adversarial Attack","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2508.17821","title":"Limitations of Normalization in Attention Mechanism","created":"2025-08-25","cited_by_count":7,"area":null}],"next_cursor":"100"}