{"total":13,"rows":[{"id":"2303.04245","title":"How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding","created":"2023-03-07","cited_by_count":86,"area":null},{"id":"2209.11379","title":"Do Current Multi-Task Optimization Methods in Deep Learning Even Help?","created":"2022-09-23","cited_by_count":60,"area":null},{"id":"2312.01429","title":"Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars","created":"2023-12-03","cited_by_count":30,"area":null},{"id":"2212.07530","title":"Causes and Cures for Interference in Multilingual Translation","created":"2022-12-14","cited_by_count":23,"area":null},{"id":"2212.10551","title":"Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation","created":"2022-12-20","cited_by_count":21,"area":null},{"id":"2404.11201","title":"Neuron Specialization: Leveraging intrinsic task modularity for multilingual machine translation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2110.02600","title":"Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning","created":"2021-10-06","cited_by_count":16,"area":null},{"id":"2110.06997","title":"Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","created":"2021-10-13","cited_by_count":16,"area":null},{"id":"2505.17895","title":"DataRater: Meta-Learned Dataset Curation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2304.03216","title":"On the Pareto Front of Multilingual Neural Machine Translation","created":"2023-04-06","cited_by_count":7,"area":null},{"id":"2409.03303","title":"Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2205.15544","title":"Refining Low-Resource Unsupervised Translation by Language Disentanglement of Multilingual Model","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2407.05082","title":"DMTG: One-Shot Differentiable Multi-Task Grouping","created":"2024-07-06","cited_by_count":0,"area":null}],"next_cursor":null}