Learning from the Self-future: On-policy Self-distillation for dLLMs
Paper • 2606.18195 • Published • 76
Zhang Tiantian
Sanyichangnuanyang
·
AI & ML interests
Reinforcement Learning, Continual Learning
Recent Activity
upvoted a paper 22 days ago
Learning from the Self-future: On-policy Self-distillation for dLLMs upvoted a paper about 1 year ago
Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal
Large Language ModelsOrganizations
None yet
upvoted a paper 22 days ago