{"total":13,"rows":[{"id":"2104.02096","title":"Compressing Visual-linguistic Model via Knowledge Distillation","created":"2021-04-05","cited_by_count":86,"area":"distill"},{"id":"2109.08359","title":"Distilling Linguistic Context for Language Model Compression","created":"2021-09-17","cited_by_count":33,"area":"distill"},{"id":"2101.05938","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","created":"2021-01-15","cited_by_count":15,"area":"distill"},{"id":"2108.02598","title":"Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification","created":"2021-08-05","cited_by_count":14,"area":"distill"},{"id":"2209.03182","title":"On the Effectiveness of Compact Biomedical Transformers","created":"2022-09-07","cited_by_count":11,"area":"distill"},{"id":"2305.15032","title":"How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives","created":"2023-05-24","cited_by_count":9,"area":"distill"},{"id":"2106.05691","title":"Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation","created":"2021-06-10","cited_by_count":6,"area":"distill"},{"id":"2406.11022","title":"Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models","created":"2024-06-16","cited_by_count":3,"area":"distill"},{"id":"2411.00052","title":"Larger models yield better results? Streamlined severity classification of ADHD-related concerns using BERT-based knowledge distillation","created":"2024-10-30","cited_by_count":3,"area":"distill"},{"id":"2404.03196","title":"Okay, Let's Do This! Modeling Event Coreference with Generated Rationales and Knowledge Distillation","created":"2024-04-04","cited_by_count":2,"area":"distill"},{"id":"2411.11623","title":"Federated Incremental Named Entity Recognition","created":"2024-11-18","cited_by_count":2,"area":"distill"},{"id":"2301.11688","title":"Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?","created":"2023-01-27","cited_by_count":1,"area":"distill"},{"id":"2604.03110","title":"Multi-Aspect Knowledge Distillation for Language Model with Low-rank Factorization","created":"2026-04-03","cited_by_count":0,"area":"distill"}],"next_cursor":null}