{"total":131,"rows":[{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039,"area":null},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713,"area":null},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2402.00789","title":"Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces","created":"2024-02-01","cited_by_count":134,"area":"ssm"},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2401.13136","title":"The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts","created":"2024-01-23","cited_by_count":94,"area":"alignment"},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2301.11956","title":"On the Connection Between MPNN and Graph Transformer","created":"2023-01-27","cited_by_count":61,"area":null},{"id":"2407.16237","title":"OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection","created":"2024-07-23","cited_by_count":56,"area":null},{"id":"2305.10716","title":"A Survey on Time-Series Pre-Trained Models","created":"2023-05-18","cited_by_count":52,"area":null},{"id":"2304.04662","title":"SELFormer: Molecular Representation Learning via SELFIES Language Models","created":"2023-04-10","cited_by_count":40,"area":null},{"id":"2201.12438","title":"Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey","created":"2022-01-28","cited_by_count":38,"area":null},{"id":"2404.11553","title":"Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages","created":"2024-04-17","cited_by_count":38,"area":null},{"id":"2401.11969","title":"Claim Detection for Automated Fact-checking: A Survey on Monolingual, Multilingual and Cross-Lingual Research","created":"2024-01-22","cited_by_count":35,"area":null},{"id":"2306.10095","title":"AD-AutoGPT: An Autonomous GPT for Alzheimer's Disease Infodemiology","created":"2023-06-16","cited_by_count":34,"area":null},{"id":"2312.03014","title":"Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey","created":"2023-12-05","cited_by_count":34,"area":null},{"id":"2204.03873","title":"Spatial Transformer Network on Skeleton-based Gait Recognition","created":"2022-04-08","cited_by_count":33,"area":null},{"id":"2310.16570","title":"Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2401.04472","title":"A Survey on Efficient Federated Learning Methods for Foundation Model Training","created":"2024-01-09","cited_by_count":29,"area":null},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2302.10447","title":"Mask-guided BERT for Few Shot Text Classification","created":"2023-02-21","cited_by_count":25,"area":null},{"id":"2309.08836","title":"Bias and Fairness in Chatbots: An Overview","created":"2023-09-16","cited_by_count":20,"area":null},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"area":"offlinerl"},{"id":"2205.14912","title":"E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation","created":"2022-05-30","cited_by_count":19,"area":null},{"id":"2303.09461","title":"ChatGPT Participates in a Computer Science Exam","created":"2023-03-08","cited_by_count":19,"area":null},{"id":"2304.07880","title":"Sabi\\'a: Portuguese Large Language Models","created":"2023-04-16","cited_by_count":19,"area":null},{"id":"2112.09685","title":"Neuromorphic Camera Denoising using Graph Neural Network-driven Transformers","created":"2021-12-17","cited_by_count":15,"area":null},{"id":"2310.03030","title":"GPT-MolBERTa: GPT Molecular Features Language Model for molecular property prediction","created":"2023-09-20","cited_by_count":14,"area":null},{"id":"2311.05884","title":"Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems","created":"2023-11-10","cited_by_count":14,"area":null},{"id":"2304.01246","title":"Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT","created":"2023-04-03","cited_by_count":13,"area":null},{"id":"2309.06799","title":"When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System","created":"2023-09-13","cited_by_count":13,"area":null},{"id":"2403.00826","title":"LLMGuard: Guarding Against Unsafe LLM Behavior","created":"2024-02-27","cited_by_count":13,"area":null},{"id":"2404.03021","title":"Blessing or curse? A survey on the Impact of Generative AI on Fake News","created":"2024-04-03","cited_by_count":12,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2201.05613","title":"The Dark Side of the Language: Pre-trained Transformers in the DarkNet","created":"2022-01-14","cited_by_count":10,"area":null},{"id":"2403.17410","title":"On permutation-invariant neural networks","created":"2024-03-26","cited_by_count":10,"area":null},{"id":"2405.12452","title":"Prompt-Based Spatio-Temporal Graph Transfer Learning","created":"2024-05-21","cited_by_count":10,"area":null},{"id":"2306.17170","title":"An Overview on Generative AI at Scale with Edge-Cloud Computing","created":"2023-06-02","cited_by_count":9,"area":null},{"id":"2402.00699","title":"PeaTMOSS: A Dataset and Initial Analysis of Pre-Trained Models in Open-Source Software","created":"2024-02-01","cited_by_count":9,"area":null},{"id":"2411.02941","title":"A Mamba Foundation Model for Time Series Forecasting","created":"2024-11-05","cited_by_count":9,"area":"ssm"},{"id":"2204.10365","title":"Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2207.10032","title":"Detecting Harmful Online Conversational Content towards LGBTQIA+ Individuals","created":"2022-06-15","cited_by_count":8,"area":null},{"id":"2211.14425","title":"PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations","created":"2022-11-26","cited_by_count":8,"area":null},{"id":"2305.06472","title":"ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2402.08450","title":"Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products","created":"2024-02-13","cited_by_count":8,"area":null},{"id":"2507.15905","title":"Foundation Models and Transformers for Anomaly Detection: A Survey","created":"2025-07-21","cited_by_count":8,"area":null},{"id":"2510.10182","title":"A Survey of Inductive Reasoning for Large Language Models","created":"2025-10-11","cited_by_count":8,"area":"lr"},{"id":"2108.12177","title":"Offensive Language Identification in Low-resourced Code-mixed Dravidian languages using Pseudo-labeling","created":"2021-08-27","cited_by_count":6,"area":null},{"id":"2408.05326","title":"A Psychology-based Unified Dynamic Framework for Curriculum Learning","created":"2024-08-09","cited_by_count":6,"area":null},{"id":"2204.07056","title":"A Comparative Evaluation Of Transformer Models For De-Identification Of Clinical Text Data","created":"2022-03-25","cited_by_count":5,"area":null},{"id":"2302.01984","title":"PSST! Prosodic Speech Segmentation with Transformers","created":"2023-02-03","cited_by_count":5,"area":null},{"id":"2303.00613","title":"Diffusing Graph Attention","created":"2023-03-01","cited_by_count":5,"area":null},{"id":"2305.09438","title":"MPI-rical: Data-Driven MPI Distributed Parallelism Assistance with Transformers","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2305.14649","title":"A Joint Time-frequency Domain Transformer for Multivariate Time Series Forecasting","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2403.04882","title":"Efficient High-Resolution Time Series Classification via Attention Kronecker Decomposition","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2405.16669","title":"Low-resourced Languages and Online Knowledge Repositories: A Need-Finding Study","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2310.12936","title":"A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2311.04368","title":"Evaluating multiple large language models in pediatric ophthalmology","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2507.20443","title":"Provable In-Context Learning of Nonlinear Regression with Transformers","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2208.05596","title":"Finding Reusable Machine Learning Components to Build Programming Language Processing Pipelines","created":"2022-08-11","cited_by_count":3,"area":null},{"id":"2211.14732","title":"Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challenges","created":"2022-11-27","cited_by_count":3,"area":null},{"id":"2212.14040","title":"HeartBEiT: Vision Transformer for Electrocardiogram Data Improves Diagnostic Performance at Low Sample Sizes","created":"2022-12-13","cited_by_count":3,"area":null},{"id":"2308.09693","title":"A Lightweight Transformer for Faster and Robust EBSD Data Collection","created":"2023-08-18","cited_by_count":3,"area":null},{"id":"2404.00950","title":"AISPACE at SemEval-2024 task 8: A Class-balanced Soft-voting System for Detecting Multi-generator Machine-generated Text","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2503.15220","title":"Entity-aware Cross-lingual Claim Detection for Automated Fact-checking","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2512.02720","title":"StockMem: An Event-Reflection Memory Framework for Stock Forecasting","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2512.07178","title":"ContextualSHAP : Enhancing SHAP Explanations Through Contextual Language Generation","created":"2025-12-08","cited_by_count":3,"area":null},{"id":"2203.07216","title":"A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification","created":"2022-03-14","cited_by_count":2,"area":null},{"id":"2203.13151","title":"Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic masking","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2205.10687","title":"Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Understanding","created":"2022-05-21","cited_by_count":2,"area":null},{"id":"2210.05470","title":"Block Format Error Bounds and Optimal Block Size Selection","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2306.01376","title":"DSHGT: Dual-Supervisors Heterogeneous Graph Transformer -- A pioneer study of using heterogeneous graph learning for detecting software vulnerabilities","created":"2023-06-02","cited_by_count":2,"area":null},{"id":"2306.10419","title":"Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptation","created":"2023-06-17","cited_by_count":2,"area":null},{"id":"2310.04017","title":"PGraphDTA: Improving Drug Target Interaction Prediction using Protein Language Models and Contact Maps","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2311.17128","title":"Vulnerability Analysis of Transformer-based Optical Character Recognition to Adversarial Attacks","created":"2023-11-28","cited_by_count":2,"area":null},{"id":"2312.02220","title":"QuantAttack: Exploiting Dynamic Quantization to Attack Vision Transformers","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2403.15822","title":"Computational Sentence-level Metrics Predicting Human Sentence Comprehension","created":"2024-03-23","cited_by_count":2,"area":null},{"id":"2405.03989","title":"A Method for Parsing and Vectorization of Semi-structured Data used in Retrieval Augmented Generation","created":"2024-05-07","cited_by_count":2,"area":"rag"},{"id":"2405.05136","title":"Integrating LSTM and BERT for Long-Sequence Data Analysis in Intelligent Tutoring Systems","created":"2024-04-24","cited_by_count":2,"area":null},{"id":"2408.15077","title":"MMASD+: A Novel Dataset for Privacy-Preserving Behavior Analysis of Children with Autism Spectrum Disorder","created":"2024-08-27","cited_by_count":2,"area":null},{"id":"2505.06917","title":"Non-Stationary Time Series Forecasting Based on Fourier Analysis and Cross Attention Mechanism","created":"2025-05-11","cited_by_count":2,"area":null},{"id":"2505.20048","title":"Synthetic Time Series Forecasting with Transformer Architectures: Extensive Simulation Benchmarks","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2208.02402","title":"Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models","created":"2022-08-04","cited_by_count":1,"area":null},{"id":"2209.08206","title":"Selective Token Generation for Few-shot Natural Language Generation","created":"2022-09-17","cited_by_count":1,"area":null},{"id":"2212.11455","title":"Understanding Postpartum Parents' Experiences via Two Digital Platforms","created":"2022-12-22","cited_by_count":1,"area":null},{"id":"2305.09948","title":"HICO-DET-SG and V-COCO-SG: New Data Splits for Evaluating the Systematic Generalization Performance of Human-Object Interaction Detection Models","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2306.00409","title":"Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2401.11972","title":"Synergizing Machine Learning & Symbolic Methods: A Survey on Hybrid Approaches to Natural Language Processing","created":"2024-01-22","cited_by_count":1,"area":null},{"id":"2401.16736","title":"Engineering A Large Language Model From Scratch","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2407.00648","title":"LegalTurk Optimized BERT for Multi-Label Text Classification and NER","created":"2024-06-30","cited_by_count":1,"area":null},{"id":"2408.11336","title":"FATE: Focal-modulated Attention Encoder for Multivariate Time-series Forecasting","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2412.19928","title":"Assessing Text Classification Methods for Cyberbullying Detection on Social Media Platforms","created":"2024-12-27","cited_by_count":1,"area":null},{"id":"2504.20666","title":"SFi-Former: Sparse Flow Induced Attention for Graph Transformer","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2505.02655","title":"SCFormer: Structured Channel-wise Transformer with Cumulative Historical State for Multivariate Time Series Forecasting","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2505.11586","title":"The Ripple Effect: On Unforeseen Complications of Backdoor Attacks","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2507.06538","title":"Few-shot Learning on AMS Circuits and Its Application to Parasitic Capacitance Prediction","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2111.04507","title":"Ontology-based question answering over corporate structured data","created":"2021-11-08","cited_by_count":0,"area":null},{"id":"2111.11159","title":"Investigating Cross-Linguistic Gender Bias in Hindi-English Across Domains","created":"2021-11-22","cited_by_count":0,"area":null}],"next_cursor":"100"}