OmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells
OmniVCBench is introduced, a figure-centric, source-traceable benchmark for the interpretation component of an AIVC, and AIVC-Judge is introduced, a task-conditioned MLLM-as-a-judge framework with category-specific, reference-aware rubrics for evaluating open-ended responses.
Man-Yu Li, Xun-Kai Li, Yong-Fu Xiong et al.
· 0 citations