Submitted by
Liu
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Learning from the Self-future: On-policy Self-distillation for dLLMs
FutureSim: Replaying World Events to Evaluate Adaptive Agents
None defined yet.
Learning from the Self-future: On-policy Self-distillation for dLLMs
FutureSim: Replaying World Events to Evaluate Adaptive Agents