Determining whether an image is AI-generated does not establish whether the situation it depicts is factually supported. We formulate Image Factuality Assessment: given an image and a generic verification instruction, a system returns a supported or refuted verdict with an evidence-grounded explanation. Without a suppl...
Zian Wang, Rui-Qi Liu, Zheng-Bo Zhang et al.· 0 citations
Proprietary language models exhibit strong reasoning and coding capabilities, but their output distributions are inaccessible, making fine-grained distillation methods that rely on teacher logits difficult to apply directly to black-box models. We observe that rich textual feedback from a black-box teacher can be treat...
On-policy distillation (OPD) applies token-level teacher supervision to student-generated trajectories, but this supervision is not always reliable. Existing methods use local confidence or teacher-student agreement to weight, filter, or truncate the sampled trajectory. These signals do not directly determine whether t...
Ximo Zhu, Rui-Qi Liu, Rong Wang et al.· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.