Jinpeng Wan

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multimodal models.

Introduces AlphaOracle, a human-workflow-inspired framework for deciphering undeciphered oracle bone script characters using a large digitized corpus, reducing analysis time and agreeing with expert interpretations.