{"total":151,"rows":[{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404,"area":null},{"id":"2404.07143","title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","created":"2024-04-10","cited_by_count":200,"area":null},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150,"area":null},{"id":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2206.08948","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","created":"2022-06-17","cited_by_count":60,"area":null},{"id":"2210.04242","title":"Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning","created":"2022-10-09","cited_by_count":60,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2201.03230","title":"Swin Transformer for Fast MRI","created":"2022-01-10","cited_by_count":56,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"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":"2102.05281","title":"Biomedical Question Answering: A Survey of Approaches and Challenges","created":"2021-02-10","cited_by_count":46,"area":null},{"id":"2204.09455","title":"Simplicial Attention Networks","created":"2022-04-20","cited_by_count":41,"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":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37,"area":null},{"id":"2101.04109","title":"Explain and Predict, and then Predict Again","created":"2021-01-11","cited_by_count":29,"area":null},{"id":"2110.06206","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","created":"2021-10-12","cited_by_count":27,"area":null},{"id":"2309.02138","title":"Generalized Simplicial Attention Neural Networks","created":"2023-09-05","cited_by_count":27,"area":null},{"id":"2310.10837","title":"Approximating Two-Layer Feedforward Networks for Efficient Transformers","created":"2023-10-16","cited_by_count":27,"area":null},{"id":"2102.03147","title":"Learning Conjoint Attentions for Graph Neural Nets","created":"2021-02-05","cited_by_count":26,"area":null},{"id":"2102.04754","title":"Bayesian Transformer Language Models for Speech Recognition","created":"2021-02-09","cited_by_count":22,"area":null},{"id":"2203.07485","title":"Simplicial Attention Neural Networks","created":"2022-03-14","cited_by_count":21,"area":null},{"id":"2505.16270","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","created":"2025-05-22","cited_by_count":21,"area":null},{"id":"2204.03503","title":"Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers","created":"2022-03-11","cited_by_count":20,"area":null},{"id":"2103.06541","title":"Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality","created":"2021-03-11","cited_by_count":17,"area":null},{"id":"2211.03796","title":"Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy","created":"2022-11-07","cited_by_count":17,"area":null},{"id":"2202.00909","title":"CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving","created":"2022-02-02","cited_by_count":16,"area":null},{"id":"2104.04041","title":"CLVSA: A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets","created":"2021-04-08","cited_by_count":15,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2103.05930","title":"AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing","created":"2021-03-10","cited_by_count":14,"area":null},{"id":"2210.12381","title":"S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention","created":"2022-10-22","cited_by_count":14,"area":null},{"id":"2212.06933","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2101.06883","title":"CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering","created":"2021-01-18","cited_by_count":12,"area":null},{"id":"2112.13310","title":"Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence","created":"2021-12-26","cited_by_count":12,"area":null},{"id":"2206.04246","title":"SwinCheX: Multi-label classification on chest X-ray images with transformers","created":"2022-06-09","cited_by_count":12,"area":null},{"id":"2207.04044","title":"kMaX-DeepLab: k-means Mask Transformer","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2307.12775","title":"Is attention all you need in medical image analysis? A review","created":"2023-07-24","cited_by_count":12,"area":null},{"id":"2102.12550","title":"Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning","created":"2021-02-24","cited_by_count":11,"area":null},{"id":"2403.11894","title":"From Explainable to Interpretable Deep Learning for Natural Language Processing in Healthcare: How Far from Reality?","created":"2024-03-18","cited_by_count":11,"area":null},{"id":"2405.13718","title":"Next-token prediction capacity: general upper bounds and a lower bound for transformers","created":"2024-05-22","cited_by_count":11,"area":null},{"id":"2112.11540","title":"Mixed Precision of Quantization of Transformer Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2409.18454","title":"Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications","created":"2024-09-27","cited_by_count":10,"area":null},{"id":"2203.02898","title":"Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents","created":"2022-03-06","cited_by_count":9,"area":null},{"id":"2311.14294","title":"Decouple Content and Motion for Conditional Image-to-Video Generation","created":"2023-11-24","cited_by_count":9,"area":null},{"id":"2405.15926","title":"Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2105.13061","title":"The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition","created":"2021-05-27","cited_by_count":8,"area":null},{"id":"2205.01592","title":"Conditional $\\beta$-VAE for De Novo Molecular Generation","created":"2022-05-01","cited_by_count":8,"area":null},{"id":"2508.08435","title":"Fast weight programming and linear transformers: from machine learning to neurobiology","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2103.02746","title":"Malware Classification Using Long Short-Term Memory Models","created":"2021-03-03","cited_by_count":7,"area":null},{"id":"2107.01983","title":"Gradient Importance Learning for Incomplete Observations","created":"2021-07-05","cited_by_count":7,"area":null},{"id":"2108.11117","title":"GlassNet: Label Decoupling-based Three-stream Neural Network for Robust Image Glass Detection","created":"2021-08-25","cited_by_count":7,"area":null},{"id":"2212.06735","title":"POPNASv3: a Pareto-Optimal Neural Architecture Search Solution for Image and Time Series Classification","created":"2022-12-13","cited_by_count":7,"area":null},{"id":"2306.09626","title":"PAtt-Lite: Lightweight Patch and Attention MobileNet for Challenging Facial Expression Recognition","created":"2023-06-16","cited_by_count":7,"area":null},{"id":"2503.15978","title":"A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli","created":"2025-03-20","cited_by_count":7,"area":null},{"id":"2101.09645","title":"Multi-Task Time Series Forecasting With Shared Attention","created":"2021-01-24","cited_by_count":6,"area":null},{"id":"2103.09656","title":"Set-to-Sequence Methods in Machine Learning: a Review","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2210.07715","title":"Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learning","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2302.01488","title":"Perfect is the enemy of test oracle","created":"2023-02-03","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":"2104.11571","title":"AttWalk: Attentive Cross-Walks for Deep Mesh Analysis","created":"2021-04-23","cited_by_count":5,"area":null},{"id":"2109.02716","title":"Vision Transformers For Weeds and Crops Classification Of High Resolution UAV Images","created":"2021-09-06","cited_by_count":5,"area":null},{"id":"2112.11438","title":"Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":5,"area":null},{"id":"2209.09245","title":"Interpreting the Mechanism of Synergism for Drug Combinations Using Attention-Based Hierarchical Graph Pooling","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2210.16101","title":"A Generic Shared Attention Mechanism for Various Backbone Neural Networks","created":"2022-10-27","cited_by_count":5,"area":null},{"id":"2305.10845","title":"TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Model","created":"2023-05-18","cited_by_count":5,"area":null},{"id":"2310.15586","title":"Detecting Intentional AIS Shutdown in Open Sea Maritime Surveillance Using Self-Supervised Deep Learning","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2402.00299","title":"Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2101.05018","title":"Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition","created":"2021-01-13","cited_by_count":4,"area":null},{"id":"2104.02879","title":"Adapting Speaker Embeddings for Speaker Diarisation","created":"2021-04-07","cited_by_count":4,"area":null},{"id":"2110.09665","title":"Ensemble ALBERT on SQuAD 2.0","created":"2021-10-19","cited_by_count":4,"area":null},{"id":"2110.10916","title":"Exploiting Inter-pixel Correlations in Unsupervised Domain Adaptation for Semantic Segmentation","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2112.12001","title":"DA-FDFtNet: Dual Attention Fake Detection Fine-tuning Network to Detect Various AI-Generated Fake Images","created":"2021-12-22","cited_by_count":4,"area":null},{"id":"2207.04293","title":"Attention and Self-Attention in Random Forests","created":"2022-07-09","cited_by_count":4,"area":null},{"id":"2208.08599","title":"Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition","created":"2022-08-18","cited_by_count":4,"area":null},{"id":"2301.04605","title":"Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions","created":"2023-01-11","cited_by_count":4,"area":null},{"id":"2303.07537","title":"Fractional dynamics foster deep learning of COPD stage prediction","created":"2023-03-13","cited_by_count":4,"area":null},{"id":"2409.17661","title":"A Fuzzy-based Approach to Predict Human Interaction by Functional Near-Infrared Spectroscopy","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2409.19518","title":"KODA: A Data-Driven Recursive Model for Time Series Forecasting and Data Assimilation using Koopman Operators","created":"2024-09-29","cited_by_count":4,"area":null},{"id":"2410.19256","title":"Spatioformer: A Geo-encoded Transformer for Large-Scale Plant Species Richness Prediction","created":"2024-10-25","cited_by_count":4,"area":null},{"id":"2103.06915","title":"On Improving Deep Learning Trace Analysis with System Call Arguments","created":"2021-03-11","cited_by_count":3,"area":null},{"id":"2208.13259","title":"Bayesian Neural Network Language Modeling for Speech Recognition","created":"2022-08-28","cited_by_count":3,"area":null},{"id":"2210.10965","title":"IDM-Follower: A Model-Informed Deep Learning Method for Long-Sequence Car-Following Trajectory Prediction","created":"2022-10-20","cited_by_count":3,"area":null},{"id":"2301.02773","title":"Building a Parallel Corpus and Training Translation Models Between Luganda and English","created":"2023-01-07","cited_by_count":3,"area":null},{"id":"2306.07115","title":"Exploring Attention Mechanisms for Multimodal Emotion Recognition in an Emergency Call Center Corpus","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2101.00389","title":"Multitask Learning for Class-Imbalanced Discourse Classification","created":"2021-01-02","cited_by_count":2,"area":null},{"id":"2105.01705","title":"Attention-based Stylisation for Exemplar Image Colourisation","created":"2021-05-04","cited_by_count":2,"area":null},{"id":"2105.09681","title":"Bidirectional LSTM-CRF Attention-based Model for Chinese Word Segmentation","created":"2021-05-20","cited_by_count":2,"area":null},{"id":"2108.02915","title":"LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching","created":"2021-08-06","cited_by_count":2,"area":null},{"id":"2110.01655","title":"VTAMIQ: Transformers for Attention Modulated Image Quality Assessment","created":"2021-10-04","cited_by_count":2,"area":null},{"id":"2112.07259","title":"TopNet: Learning from Neural Topic Model to Generate Long Stories","created":"2021-12-14","cited_by_count":2,"area":null},{"id":"2112.10068","title":"Lerna: Transformer Architectures for Configuring Error Correction Tools for Short- and Long-Read Genome Sequencing","created":"2021-12-19","cited_by_count":2,"area":null},{"id":"2201.10274","title":"Multi-channel Attentive Graph Convolutional Network With Sentiment Fusion For Multimodal Sentiment Analysis","created":"2022-01-25","cited_by_count":2,"area":null},{"id":"2204.03827","title":"IA-GCN: Interactive Graph Convolutional Network for Recommendation","created":"2022-04-08","cited_by_count":2,"area":null},{"id":"2211.03666","title":"Application of Graph Neural Networks and graph descriptors for graph classification","created":"2022-11-07","cited_by_count":2,"area":null},{"id":"2309.06004","title":"TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer","created":"2023-09-12","cited_by_count":2,"area":null},{"id":"2405.04515","title":"A Transformer with Stack Attention","created":"2024-05-07","cited_by_count":2,"area":null},{"id":"2408.00921","title":"Automatic Pull Request Description Generation Using LLMs: A T5 Model Approach","created":"2024-08-01","cited_by_count":2,"area":null}],"next_cursor":"100"}