Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation
Yifu Luo, Chuang Ma, Zeyu Chen +3
On-policy Self-distillation (OPSD) has proven effective for post-training large language models by constructing a teacher conditioned on privileged references. However, existing ap…
cs.CL2026
Learning from the Self-future: On-policy Self-distillation for dLLMs
Yifu Luo, Zeyu Chen, Haoyu Wang +4
On-policy self-distillation (OPSD) has proven effective for post-training large language models (LLMs), yet its application to diffusion LLMs (dLLMs) remains unexplored. Existing O…