{"total":20,"rows":[{"id":"2602.15260","title":"Fast and Effective On-policy Distillation from Reasoning Prefixes","created":"2026-02-16","cited_by_count":53,"area":"distill"},{"id":"2606.01249","title":"Trust Region On-Policy Distillation","created":"2026-05-31","cited_by_count":30,"area":"distill"},{"id":"2412.14964","title":"Efficient Knowledge Injection in LLMs via Self-Distillation","created":"2024-12-19","cited_by_count":24,"area":"distill"},{"id":"2608.04794","title":"Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation","created":"2026-08-05","cited_by_count":18,"area":"distill"},{"id":"2603.24596","title":"X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs","created":"2026-03-06","cited_by_count":16,"area":"distill"},{"id":"2505.19504","title":"DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation","created":"2025-05-26","cited_by_count":14,"area":"distill"},{"id":"2607.13124","title":"ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation","created":"2026-07-14","cited_by_count":8,"area":"distill"},{"id":"2607.01763","title":"Denser $\\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training","created":"2026-07-02","cited_by_count":7,"area":"distill"},{"id":"2609.02548","title":"Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs","created":"2026-09-02","cited_by_count":4,"area":"distill"},{"id":"2608.16320","title":"StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding","created":"2026-08-17","cited_by_count":2,"area":"distill"},{"id":"2609.23697","title":"Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation","created":"2026-09-20","cited_by_count":2,"area":"distill"},{"id":"2607.28026","title":"Contrastive Reinforced Policy Optimization via Privileged Self-Distillation","created":"2026-07-30","cited_by_count":1,"area":"distill"},{"id":"2602.01007","title":"Distilling Token-Trained Models into Byte-Level Models","created":"2026-02-01","cited_by_count":0,"area":"distill"},{"id":"2606.22942","title":"Understanding Knowledge Distillation in Post-Training: When It Helps and When It Fails","created":"2026-06-22","cited_by_count":0,"area":"distill"},{"id":"2609.15313","title":"Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy Distillation","created":"2026-09-14","cited_by_count":0,"area":"distill"},{"id":"2609.31900","title":"Understanding the Synergy between SFT, RLVR, and OPD in LLM Post-Training","created":"2026-09-25","cited_by_count":0,"area":"distill"},{"id":"2609.32493","title":"SoFT: Soft Targets for Generalizable LLM Fine-Tuning","created":"2026-09-26","cited_by_count":0,"area":"distill"},{"id":"2609.33711","title":"DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation","created":"2026-09-27","cited_by_count":0,"area":"distill"},{"id":"2610.03529","title":"Divergence controls entropy in distillation","created":"2026-10-02","cited_by_count":0,"area":"distill"},{"id":"2610.09639","title":"On-Policy Distillation Teaches New Skills but Not New Knowledge","created":"2026-10-07","cited_by_count":0,"area":"distill"}],"next_cursor":null}