الباحثون

Feiyu Han

المنشورات 2

نسخة أولية وصول مفتوح

No Task Vector Is an Island: A Comprehensive Study on the Composability of Task Vectors from On-Policy Distillation

Jingang Zhou, Feiyu Han, Han Zhu وآخرون · 2026

Task vectors provide a simple mechanism for composing learned capabilities through model merging. However, the composability of task vectors produced by on-policy distillation (OPD) remains largely unexplored. OPD trains a student using teacher feedback on student-generated trajectories, yielding parameter updates that …

نسخة أولية وصول مفتوح

AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents

Yufan Liu, Shang Luo, Yang Liu وآخرون · 2026

Physical changes or sensing errors can invalidate embodied agents' task-relevant beliefs. AquaMend compares re-probing, rollback, and supported continuation on a probe-belief-action graph under an expected-loss objective covering sensing, physical recovery, and uncorrected failures. A joint posterior guides a one-step …

المؤلفون المشاركون