PPL
Yifan Yang
Papers (9)
Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model MergingNot All Disagreement Is Learnable: Token Teachability in On-Policy DistillationSkillOpt: Executive Strategy for Self-Evolving Agent SkillsFrom Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent SkillsComponent-Aware Structure-Preserving Style Transfer for Satellite Visual Sim2Real Data ConstructionVGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field PredictionEmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied AgentsGeometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-TrainingSOAR: Real-Time Joint Optimization of Order Allocation and Robot Scheduling in Robotic Mobile Fulfillment Systems