{"total":36,"rows":[{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491,"area":null},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296,"area":null},{"id":"2101.12609","title":"Open World Compositional Zero-Shot Learning","created":"2021-01-29","cited_by_count":101,"area":null},{"id":"2105.01017","title":"Learning Graph Embeddings for Open World Compositional Zero-Shot Learning","created":"2021-05-03","cited_by_count":49,"area":null},{"id":"2310.20501","title":"Neural Retrievers are Biased Towards LLM-Generated Content","created":"2023-10-31","cited_by_count":38,"area":null},{"id":"2403.05812","title":"Algorithmic progress in language models","created":"2024-03-09","cited_by_count":31,"area":null},{"id":"2402.06853","title":"History, Development, and Principles of Large Language Models-An Introductory Survey","created":"2024-02-10","cited_by_count":30,"area":null},{"id":"2501.04437","title":"Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions","created":"2025-01-08","cited_by_count":23,"area":null},{"id":"2307.14107","title":"Decoding ChatGPT: A Taxonomy of Existing Research, Current Challenges, and Possible Future Directions","created":"2023-07-26","cited_by_count":18,"area":null},{"id":"2106.16006","title":"Improving the Efficiency of Transformers for Resource-Constrained Devices","created":"2021-06-30","cited_by_count":12,"area":null},{"id":"2104.03474","title":"Revisiting Simple Neural Probabilistic Language Models","created":"2021-04-08","cited_by_count":10,"area":null},{"id":"2507.04636","title":"Put Teacher in Student's Shoes: Cross-Distillation for Ultra-compact Model Compression Framework","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2407.00935","title":"Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining","created":"2024-07-01","cited_by_count":7,"area":null},{"id":"2202.02212","title":"Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2304.02247","title":"Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy","created":"2023-04-05","cited_by_count":6,"area":null},{"id":"2410.00131","title":"Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2112.14472","title":"Temporal Attention Augmented Transformer Hawkes Process","created":"2021-12-29","cited_by_count":5,"area":null},{"id":"2110.08633","title":"Hydra: A System for Large Multi-Model Deep Learning","created":"2021-10-16","cited_by_count":3,"area":null},{"id":"2112.14479","title":"Universal Transformer Hawkes Process with Adaptive Recursive Iteration","created":"2021-12-29","cited_by_count":3,"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":"2312.15020","title":"Self-Admitted Technical Debt Detection Approaches: A Decade Systematic Review","created":"2023-12-19","cited_by_count":2,"area":null},{"id":"2410.01098","title":"Exploring Gen-AI applications in building research and industry: A review","created":"2024-10-01","cited_by_count":2,"area":null},{"id":"2202.13363","title":"Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation","created":"2022-02-27","cited_by_count":1,"area":null},{"id":"2305.14380","title":"Finding the Pillars of Strength for Multi-Head Attention","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2305.18553","title":"Controllable Path of Destruction","created":"2023-05-29","cited_by_count":1,"area":null},{"id":"2307.00213","title":"More for Less: Compact Convolutional Transformers Enable Robust Medical Image Classification with Limited Data","created":"2023-07-01","cited_by_count":1,"area":null},{"id":"2312.10925","title":"Delving Deeper Into Astromorphic Transformers","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2410.15620","title":"Acoustic Model Optimization over Multiple Data Sources: Merging and Valuation","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2103.06198","title":"Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling","created":"2021-03-10","cited_by_count":0,"area":null},{"id":"2105.03994","title":"Dispatcher: A Message-Passing Approach To Language Modelling","created":"2021-05-09","cited_by_count":0,"area":null},{"id":"2108.05490","title":"Attacks against Ranking Algorithms with Text Embeddings: a Case Study on Recruitment Algorithms","created":"2021-08-12","cited_by_count":0,"area":null},{"id":"2110.12855","title":"Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experience","created":"2021-10-25","cited_by_count":0,"area":null},{"id":"2305.11462","title":"Extending Memory for Language Modelling","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2402.06964","title":"NLP for Knowledge Discovery and Information Extraction from Energetics Corpora","created":"2024-02-10","cited_by_count":0,"area":null},{"id":"2402.15923","title":"Predicting Outcomes in Video Games with Long Short Term Memory Networks","created":"2024-02-24","cited_by_count":0,"area":null},{"id":"2601.09220","title":"From Hawkes Processes to Attention: Time-Modulated Mechanisms for Event Sequences","created":"2026-01-14","cited_by_count":0,"area":null}],"next_cursor":null}