{"total":25,"rows":[{"id":"2410.16215","title":"Pre-training Distillation for Large Language Models: A Design Space Exploration","created":"2024-10-21","cited_by_count":27,"area":"distill"},{"id":"2505.04560","title":"ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\\alpha$-$\\beta$-Divergence","created":"2025-05-07","cited_by_count":23,"area":"distill"},{"id":"2412.08139","title":"Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation","created":"2024-12-11","cited_by_count":19,"area":"distill"},{"id":"2511.02833","title":"In Good GRACEs: Principled Teacher Selection for Knowledge Distillation","created":"2025-11-04","cited_by_count":5,"area":"distill"},{"id":"2411.08937","title":"Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head","created":"2024-11-13","cited_by_count":4,"area":"distill"},{"id":"2507.15911","title":"Local Dense Logit Relations for Enhanced Knowledge Distillation","created":"2025-07-21","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":"2412.11788","title":"Neural Collapse Inspired Knowledge Distillation","created":"2024-12-16","cited_by_count":2,"area":"distill"},{"id":"2503.09030","title":"Adaptive Temperature Based on Logits Correlation in Knowledge Distillation","created":"2025-03-12","cited_by_count":2,"area":"distill"},{"id":"2506.18244","title":"Dual-Forward Path Teacher Knowledge Distillation: Bridging the Capacity Gap Between Teacher and Student","created":"2025-06-23","cited_by_count":2,"area":"distill"},{"id":"2407.12073","title":"Relational Representation Distillation","created":"2024-07-16","cited_by_count":1,"area":"distill"},{"id":"2411.10693","title":"Multi-perspective Contrastive Logit Distillation","created":"2024-11-16","cited_by_count":1,"area":"distill"},{"id":"2504.20108","title":"Swapped Logit Distillation via Bi-level Teacher Alignment","created":"2025-04-27","cited_by_count":1,"area":"distill"},{"id":"2605.20357","title":"Consistently Informative Soft-Label Temperature for Knowledge Distillation","created":"2026-05-19","cited_by_count":1,"area":"distill"},{"id":"2407.11802","title":"Discriminative and Consistent Representation Distillation","created":"2024-07-16","cited_by_count":0,"area":"distill"},{"id":"2505.08170","title":"MoKD: Multi-Task Optimization for Knowledge Distillation","created":"2025-05-13","cited_by_count":0,"area":"distill"},{"id":"2508.04539","title":"TopKD: Top-scaled Knowledge Distillation","created":"2025-08-06","cited_by_count":0,"area":"distill"},{"id":"2509.12553","title":"iCD: A Implicit Clustering Distillation Mathod for Structural Information Mining","created":"2025-09-16","cited_by_count":0,"area":"distill"},{"id":"2511.10942","title":"Heterogeneous Complementary Distillation","created":"2025-11-14","cited_by_count":0,"area":"distill"},{"id":"2601.01484","title":"SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines","created":"2026-01-04","cited_by_count":0,"area":"distill"},{"id":"2602.01265","title":"BicKD: Bilateral Contrastive Knowledge Distillation","created":"2026-02-01","cited_by_count":0,"area":"distill"},{"id":"2605.26246","title":"The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works","created":"2026-05-25","cited_by_count":0,"area":"distill"},{"id":"2607.08776","title":"A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions","created":"2026-05-05","cited_by_count":0,"area":"distill"},{"id":"2608.29099","title":"Temperature-Adaptive Transformed Teacher Matching","created":"2026-08-29","cited_by_count":0,"area":"distill"},{"id":"2609.36734","title":"Distilling What Matters: Confidence-Aware Selective Distillation for Large Language Models","created":"2026-09-29","cited_by_count":0,"area":"distill"}],"next_cursor":null}