{"total":172,"rows":[{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103,"area":null},{"id":"2106.06130","title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","created":"2021-06-11","cited_by_count":204,"area":null},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92,"area":null},{"id":"2508.10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","created":"2025-08-14","cited_by_count":82,"area":null},{"id":"2105.04949","title":"BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?","created":"2021-05-11","cited_by_count":56,"area":null},{"id":"2402.02769","title":"Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2102.04877","title":"Noisy Recurrent Neural Networks","created":"2021-02-09","cited_by_count":42,"area":null},{"id":"2212.10356","title":"Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis","created":"2022-12-20","cited_by_count":42,"area":null},{"id":"2402.01763","title":"When Large Language Models Meet Vector Databases: A Survey","created":"2024-01-30","cited_by_count":39,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2101.01761","title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","created":"2021-01-05","cited_by_count":35,"area":null},{"id":"2108.13421","title":"Recent advances for quantum classifiers","created":"2021-08-30","cited_by_count":35,"area":null},{"id":"2503.02453","title":"Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations","created":"2025-03-04","cited_by_count":35,"area":null},{"id":"2308.15985","title":"Vision-Based Traffic Accident Detection and Anticipation: A Survey","created":"2023-08-30","cited_by_count":31,"area":null},{"id":"2203.01593","title":"3D Human Motion Prediction: A Survey","created":"2022-03-03","cited_by_count":30,"area":null},{"id":"2109.01876","title":"Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting","created":"2021-09-04","cited_by_count":29,"area":null},{"id":"2112.04178","title":"Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition","created":"2021-12-08","cited_by_count":29,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2103.17182","title":"Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization","created":"2021-03-31","cited_by_count":28,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","cited_by_count":26,"area":null},{"id":"2210.03221","title":"PQLM -- Multilingual Decentralized Portable Quantum Language Model for Privacy Protection","created":"2022-10-06","cited_by_count":26,"area":null},{"id":"2210.15452","title":"Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity","created":"2022-10-20","cited_by_count":25,"area":null},{"id":"2103.00188","title":"Super-resolution-based Change Detection Network with Stacked Attention Module for Images with Different Resolutions","created":"2021-02-27","cited_by_count":23,"area":null},{"id":"2112.10992","title":"Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition","created":"2021-12-21","cited_by_count":23,"area":null},{"id":"2204.08771","title":"EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting","created":"2022-04-19","cited_by_count":22,"area":null},{"id":"2203.02281","title":"A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directions","created":"2022-03-03","cited_by_count":21,"area":null},{"id":"2112.03328","title":"Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2021-12-06","cited_by_count":20,"area":null},{"id":"2202.05126","title":"Deep Learning for Computational Cytology: A Survey","created":"2022-02-10","cited_by_count":20,"area":null},{"id":"2111.11051","title":"Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition","created":"2021-11-22","cited_by_count":19,"area":null},{"id":"2110.14109","title":"Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums","created":"2021-10-27","cited_by_count":15,"area":null},{"id":"2107.01671","title":"Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory","created":"2021-07-04","cited_by_count":14,"area":null},{"id":"2102.06329","title":"Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients","created":"2021-02-12","cited_by_count":13,"area":null},{"id":"2206.02806","title":"Quantum Neural Network Classifiers: A Tutorial","created":"2022-06-06","cited_by_count":13,"area":null},{"id":"2311.08223","title":"Improving Image Captioning via Predicting Structured Concepts","created":"2023-11-14","cited_by_count":13,"area":null},{"id":"2411.07660","title":"HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image Classification","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2106.09204","title":"An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models","created":"2021-06-17","cited_by_count":12,"area":null},{"id":"2108.02924","title":"Interpretable Visual Understanding with Cognitive Attention Network","created":"2021-08-06","cited_by_count":12,"area":null},{"id":"2307.11793","title":"Leveraging arbitrary mobile sensor trajectories with shallow recurrent decoder networks for full-state reconstruction","created":"2023-07-20","cited_by_count":12,"area":null},{"id":"2106.05506","title":"Brittle AI, Causal Confusion, and Bad Mental Models: Challenges and Successes in the XAI Program","created":"2021-06-10","cited_by_count":11,"area":null},{"id":"2109.04235","title":"EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformer","created":"2021-09-09","cited_by_count":11,"area":null},{"id":"2104.00772","title":"Low-Resource Language Modelling of South African Languages","created":"2021-04-01","cited_by_count":10,"area":null},{"id":"2104.03474","title":"Revisiting Simple Neural Probabilistic Language Models","created":"2021-04-08","cited_by_count":10,"area":null},{"id":"2109.07591","title":"On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation","created":"2021-09-15","cited_by_count":10,"area":null},{"id":"2111.00201","title":"A Comparative Review of Recent Few-Shot Object Detection Algorithms","created":"2021-10-30","cited_by_count":10,"area":null},{"id":"2401.05975","title":"End-to-end Learnable Clustering for Intent Learning in Recommendation","created":"2024-01-11","cited_by_count":10,"area":null},{"id":"2209.09545","title":"Graph Reasoning Transformer for Image Parsing","created":"2022-09-20","cited_by_count":9,"area":null},{"id":"2301.11495","title":"Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks","created":"2023-01-27","cited_by_count":9,"area":null},{"id":"2408.08338","title":"Activation Space Selectable Kolmogorov-Arnold Networks","created":"2024-08-15","cited_by_count":9,"area":null},{"id":"2402.18974","title":"Generating Graphs via Spectral Diffusion","created":"2024-02-29","cited_by_count":8,"area":null},{"id":"2408.05966","title":"Freehand Sketch Generation from Mechanical Components","created":"2024-08-12","cited_by_count":8,"area":null},{"id":"2204.03433","title":"Machine Learning-Enabled IoT Security: Open Issues and Challenges Under Advanced Persistent Threats","created":"2022-04-07","cited_by_count":7,"area":null},{"id":"2101.02766","title":"Active Screening for Recurrent Diseases: A Reinforcement Learning Approach","created":"2021-01-07","cited_by_count":6,"area":null},{"id":"2106.06960","title":"Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2021-06-13","cited_by_count":6,"area":null},{"id":"2207.04396","title":"Graph Generative Model for Benchmarking Graph Neural Networks","created":"2022-07-10","cited_by_count":6,"area":null},{"id":"2501.00659","title":"Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2102.07071","title":"Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2112.08733","title":"Self-Supervised Dynamic Graph Representation Learning via Temporal Subgraph Contrast","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2201.04207","title":"Fighting Money Laundering with Statistics and Machine Learning","created":"2022-01-11","cited_by_count":5,"area":null},{"id":"2203.03584","title":"Counter Hate Speech in Social Media: A Survey","created":"2022-02-21","cited_by_count":5,"area":null},{"id":"2304.04874","title":"ImageCaptioner$^2$: Image Captioner for Image Captioning Bias Amplification Assessment","created":"2023-04-10","cited_by_count":5,"area":null},{"id":"2404.09022","title":"Navigating the Landscape of Large Language Models: A Comprehensive Review and Analysis of Paradigms and Fine-Tuning Strategies","created":"2024-04-13","cited_by_count":5,"area":null},{"id":"2507.09834","title":"Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2603.05235","title":"Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2111.09503","title":"Blind VQA on 360{\\deg} Video via Progressively Learning from Pixels, Frames and Video","created":"2021-11-18","cited_by_count":4,"area":null},{"id":"2111.14067","title":"PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds","created":"2021-11-28","cited_by_count":4,"area":null},{"id":"2204.01662","title":"Evolving Neural Selection with Adaptive Regularization","created":"2022-04-04","cited_by_count":4,"area":null},{"id":"2204.02027","title":"A Survey on Dropout Methods and Experimental Verification in Recommendation","created":"2022-04-05","cited_by_count":4,"area":null},{"id":"2204.03125","title":"Deep transfer learning for system identification using long short-term memory neural networks","created":"2022-04-06","cited_by_count":4,"area":null},{"id":"2311.15200","title":"SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification","created":"2023-11-26","cited_by_count":4,"area":null},{"id":"2404.15289","title":"EEGDiR: Electroencephalogram denoising network for temporal information storage and global modeling through Retentive Network","created":"2024-03-20","cited_by_count":4,"area":null},{"id":"2105.10832","title":"Spectral Pruning for Recurrent Neural Networks","created":"2021-05-23","cited_by_count":3,"area":null},{"id":"2205.15146","title":"Batch Normalization Is Blind to the First and Second Derivatives of the Loss","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2207.01739","title":"Machine Learning in Access Control: A Taxonomy and Survey","created":"2022-07-04","cited_by_count":3,"area":null},{"id":"2207.08191","title":"Stroke-Based Autoencoders: Self-Supervised Learners for Efficient Zero-Shot Chinese Character Recognition","created":"2022-07-17","cited_by_count":3,"area":null},{"id":"2209.11680","title":"An Overview of Violence Detection Techniques: Current Challenges and Future Directions","created":"2022-09-21","cited_by_count":3,"area":null},{"id":"2303.12992","title":"A Survey of Historical Learning: Learning Models with Learning History","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2304.07711","title":"Obstacle-Transformer: A Trajectory Prediction Network Based on Surrounding Trajectories","created":"2023-04-16","cited_by_count":3,"area":null},{"id":"2309.02317","title":"A study on the impact of pre-trained model on Just-In-Time defect prediction","created":"2023-09-05","cited_by_count":3,"area":null},{"id":"2310.03243","title":"Sparse Deep Learning for Time Series Data: Theory and Applications","created":"2023-10-05","cited_by_count":3,"area":null},{"id":"2310.18926","title":"CHAIN: Exploring Global-Local Spatio-Temporal Information for Improved Self-Supervised Video Hashing","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2410.08224","title":"A Survey of Spatio-Temporal EEG data Analysis: from Models to Applications","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2101.09788","title":"Evaluating Models of Robust Word Recognition with Serial Reproduction","created":"2021-01-24","cited_by_count":2,"area":null},{"id":"2202.02170","title":"The Ecological Footprint of Neural Machine Translation Systems","created":"2022-02-04","cited_by_count":2,"area":null},{"id":"2203.01465","title":"Deep Q-network using reservoir computing with multi-layered readout","created":"2022-03-03","cited_by_count":2,"area":null},{"id":"2212.05178","title":"State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions","created":"2022-12-10","cited_by_count":2,"area":null},{"id":"2403.00832","title":"Explainable Session-based Recommendation via Path Reasoning","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2501.07925","title":"Phase of Flight Classification in Aviation Safety using LSTM, GRU, and BiLSTM: A Case Study with ASN Dataset","created":"2025-01-14","cited_by_count":2,"area":null},{"id":"2502.12298","title":"Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2502.16955","title":"MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2512.20094","title":"Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learning","created":"2025-12-23","cited_by_count":2,"area":null},{"id":"2103.08800","title":"Predicting Opioid Use Disorder from Longitudinal Healthcare Data using Multi-stream Transformer","created":"2021-03-16","cited_by_count":1,"area":null},{"id":"2103.11221","title":"Spatio-Temporal Data Mining for Aviation Delay Prediction","created":"2021-03-20","cited_by_count":1,"area":null},{"id":"2104.00385","title":"Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures","created":"2021-04-01","cited_by_count":1,"area":null},{"id":"2104.04255","title":"Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networks","created":"2021-04-09","cited_by_count":1,"area":null},{"id":"2105.12585","title":"Automatic Construction of Sememe Knowledge Bases via Dictionaries","created":"2021-05-26","cited_by_count":1,"area":null},{"id":"2105.12828","title":"Pouring Dynamics Estimation Using Gated Recurrent Units","created":"2021-05-08","cited_by_count":1,"area":null}],"next_cursor":"100"}