{"total":20,"rows":[{"id":"2102.00650","title":"Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective","created":"2021-02-01","cited_by_count":119,"area":"distill"},{"id":"2204.04588","title":"Robust Cross-Modal Representation Learning with Progressive Self-Distillation","created":"2022-04-10","cited_by_count":55,"area":"distill"},{"id":"2104.00676","title":"Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study","created":"2021-04-01","cited_by_count":51,"area":"distill"},{"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":"2402.11148","title":"Knowledge Distillation Based on Transformed Teacher Matching","created":"2024-02-17","cited_by_count":37,"area":"distill"},{"id":"2206.14532","title":"Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?","created":"2022-06-29","cited_by_count":32,"area":"distill"},{"id":"2103.13811","title":"Student Network Learning via Evolutionary Knowledge Distillation","created":"2021-03-23","cited_by_count":30,"area":"distill"},{"id":"2106.01489","title":"Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge","created":"2021-06-02","cited_by_count":9,"area":"distill"},{"id":"2210.13459","title":"Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation","created":"2022-10-22","cited_by_count":9,"area":"distill"},{"id":"2102.10780","title":"Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation","created":"2021-02-22","cited_by_count":5,"area":"distill"},{"id":"2211.03946","title":"Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study","created":"2022-11-08","cited_by_count":5,"area":"distill"},{"id":"2210.12427","title":"Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model","created":"2022-10-22","cited_by_count":4,"area":"distill"},{"id":"2305.12074","title":"DisCo: Distilled Student Models Co-training for Semi-supervised Text Mining","created":"2023-05-20","cited_by_count":4,"area":"distill"},{"id":"2507.00012","title":"Towards Undistillable Models by Minimizing Conditional Mutual Information","created":"2025-06-13","cited_by_count":3,"area":"distill"},{"id":"2602.12687","title":"Trust the uncertain teacher: distilling dark knowledge via calibrated uncertainty","created":"2026-02-13","cited_by_count":2,"area":"distill"},{"id":"2304.08878","title":"Deep Collective Knowledge Distillation","created":"2023-04-18","cited_by_count":0,"area":"distill"},{"id":"2505.14124","title":"Intra-class Patch Swap for Self-Distillation","created":"2025-05-20","cited_by_count":0,"area":"distill"},{"id":"2510.16076","title":"BPL: Bias-adaptive Preference Distillation Learning for Recommender System","created":"2025-10-17","cited_by_count":0,"area":"distill"},{"id":"2510.19223","title":"Enhancing Graph Neural Networks: A Mutual Learning Approach","created":"2025-10-22","cited_by_count":0,"area":"distill"},{"id":"2607.15467","title":"ADS-C: Antidistillation Sampling for Classification","created":"2026-07-16","cited_by_count":0,"area":"distill"}],"next_cursor":null}