{"total":15,"rows":[{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2401.16456","title":"SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design","created":"2024-01-29","cited_by_count":56,"area":null},{"id":"2308.11358","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","created":"2023-08-22","cited_by_count":36,"area":null},{"id":"2310.03294","title":"DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training","created":"2023-10-05","cited_by_count":29,"area":null},{"id":"2311.07621","title":"To Transformers and Beyond: Large Language Models for the Genome","created":"2023-11-13","cited_by_count":15,"area":null},{"id":"2406.05816","title":"Attention as a Hypernetwork","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2401.02789","title":"Large Language Models in Plant Biology","created":"2024-01-05","cited_by_count":8,"area":null},{"id":"2312.04556","title":"Large Language Models for Mathematicians","created":"2023-12-07","cited_by_count":7,"area":null},{"id":"2309.11587","title":"CATS: Conditional Adversarial Trajectory Synthesis for Privacy-Preserving Trajectory Data Publication Using Deep Learning Approaches","created":"2023-09-20","cited_by_count":6,"area":null},{"id":"2206.04803","title":"Detecting Anomalous Cryptocurrency Transactions: an AML/CFT Application of Machine Learning-based Forensics","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2107.02174","title":"What Makes for Hierarchical Vision Transformer?","created":"2021-07-05","cited_by_count":4,"area":null},{"id":"2606.01432","title":"Leaf Spectral Reflectance Prediction Using Multi-Head Attention Neural Networks","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2310.07347","title":"Fast-ELECTRA for Efficient Pre-training","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2506.09101","title":"Feature Shift Localization Network","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2610.13261","title":"Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}