3 papers
cs.AI2026
Calibrating Teacher--Student Discrepancy for On-Policy Distillation
Qiangqiang He, Jin Li, MingCai Chen
On-policy distillation (OPD) improves reasoning models by learning the token-level discrepancy between a stronger teacher and an on-policy student. However, this discrepancy does n…
cs.CV2026
UniJEPA: A Unified Joint-Embedding Predictive Architecture for Task-Agnostic Visual World Modeling
An Lanji, Dawei Liu, Jin Li +3
Joint-Embedding Predictive Architectures (JEPAs) have emerged as a principled framework for self-supervised learning of world models in compact latent spaces, yet existing methods…
cs.CV2026
DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning
An Lanji, Dawei Liu, Jin Li +3
Tool-integrated vision-language agents have made remarkable progress on compositional and multi-step visual reasoning. Yet their outputs frequently exhibit unfaithfulness: the stat…