Chunyi Peng

Distilling explicit, reward-guided skills into VLMs without the student model ever seeing the skills themselves unlocks superior multimodal performance.

Irrelevant text distractors cripple mixed-modality retrieval performance more than images, revealing a text modality preference that degrades performance in a V-shaped curve.

Despite high report quality, many models falter in citation accuracy and claim construction, exposing a disconnect between surface-level performance and deep reasoning skills.