Harness-Zero：透過代理人即Harness進行Harness蒸餾
Harness-Zero: Harness Distillation via Agent-as-Harness
arXiv
1
Liang-Hsun Huang 許願
Attention to Mamba：跨架構蒸餾的配方
Attention to Mamba A Recipe for Cross-Architecture Distillation
arXiv
171
Teds Lin 許願
翻轉 TIDE：擴散大型語言模型的跨架構蒸餾
Turning the TIDE Cross-Architecture Distillation for Diffusion Large Language Models
arXiv
79
Liang-Hsun Huang 許願
如何微調推理模型？師生合作框架合成學生一致的 SFT 資料
How to Fine-Tune a Reasoning Model A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
arXiv
74
Teds Lin 許願
自蒸餾實現持續學習
Self-Distillation Enables Continual Learning
arXiv
103
kerg kerg 許願
Lightning OPD：利用離線同策略蒸餾實現大型推理模型的高效後訓練
Lightning OPD Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
arXiv
295
Teds Lin 許願