{"total":22,"rows":[{"id":"2311.07052","title":"Towards the Law of Capacity Gap in Distilling Language Models","created":"2023-11-13","cited_by_count":44,"area":"distill"},{"id":"2503.20083","title":"Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching","created":"2025-03-25","cited_by_count":41,"area":"distill"},{"id":"2203.08757","title":"Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation","created":"2022-03-16","cited_by_count":27,"area":"distill"},{"id":"2109.06243","title":"KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation","created":"2021-09-13","cited_by_count":20,"area":"distill"},{"id":"2201.10207","title":"SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training","created":"2022-01-25","cited_by_count":19,"area":"distill"},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2110.03334","title":"Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models","created":"2021-10-07","cited_by_count":15,"area":"distill"},{"id":"2206.07808","title":"Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems","created":"2022-06-15","cited_by_count":15,"area":"distill"},{"id":"2212.01188","title":"Improving Simultaneous Machine Translation with Monolingual Data","created":"2022-12-02","cited_by_count":13,"area":"distill"},{"id":"2606.09456","title":"Breaking the Tokenizer Barrier: On-Policy Distillation across Model Families","created":"2026-06-08","cited_by_count":9,"area":"distill"},{"id":"2303.10917","title":"Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition","created":"2023-03-20","cited_by_count":8,"area":"distill"},{"id":"2210.15184","title":"Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models","created":"2022-10-27","cited_by_count":5,"area":"distill"},{"id":"2403.01479","title":"Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation","created":"2024-03-03","cited_by_count":5,"area":"distill"},{"id":"2103.09903","title":"Transformer-based ASR Incorporating Time-reduction Layer and Fine-tuning with Self-Knowledge Distillation","created":"2021-03-17","cited_by_count":3,"area":"distill"},{"id":"2107.13689","title":"Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation","created":"2021-07-29","cited_by_count":3,"area":"distill"},{"id":"2401.11700","title":"Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers","created":"2024-01-22","cited_by_count":3,"area":"distill"},{"id":"2605.21699","title":"X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation","created":"2026-05-20","cited_by_count":2,"area":"distill"},{"id":"2110.10429","title":"Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach","created":"2021-10-20","cited_by_count":1,"area":"distill"},{"id":"2111.13284","title":"Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs","created":"2021-11-26","cited_by_count":1,"area":"distill"},{"id":"2311.11518","title":"Multi-teacher Distillation for Multilingual Spelling Correction","created":"2023-11-20","cited_by_count":1,"area":"distill"},{"id":"2507.21568","title":"Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages","created":"2025-07-29","cited_by_count":0,"area":"distill"},{"id":"2602.09691","title":"Is Knowledge Distillation Actually Greener? A Case Study in Machine Translation","created":"2026-02-10","cited_by_count":0,"area":"distill"}],"next_cursor":null}