Yang Liu

Other people with similar names: Yang Janet Liu (Georgetown University; 刘洋), Yang Liu (Tsinghua), Yang Liu (Fudan), Yang Liu (BIGAI), Yang Liu, Yang Liu (Hunan), Yang Liu, Yang Liu (3M Health Information Systems), Yang Liu, Yang Liu, Yang Liu (UC Santa Cruz), Yang Liu (South China University of Technology), Yang Liu, Yang Liu (NTU), Yang Liu (Sun Yat-sen University), Yang Liu (North Carolina Central University), Yang Liu (Beijing Language and Culture University), Yang Liu (National University of Defense Technology), Yang Liu (Edinburgh Ph.D., Microsoft), Yang Liu (University of Helsinki), Yang Liu (The Chinese University of Hong Kong (Shenzhen)), Yang Liu (刘扬) (刘扬; Ph.D Purdue; ICSI, Dallas, Facebook, Liulishuo, Amazon), Yang Liu (刘洋) (刘洋; ICT, Tsinghua, Beijing Academy of Artificial Intelligence), Yang Liu (Microsoft Cognitive Services Research), Yang Liu (刘扬) (Peking University), Yang Liu (Samsung Research Center Beijing), Yang Liu (Tianjin University, China), Yang Liu (Univ. of Michigan, UC Santa Cruz), Yang Liu (Wilfrid Laurier University)

Unverified author pages with similar names: Yang Liu

2026

We introduce SPUR, a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images. SPUR features three key innovations: (1) Panel-Level Fine-Grained Perception: evaluating the visual perception of multimodal large language models (MLLMs) across three dimensions (numerical, morphological, and information localization) on six fine-grained panel types; (2) Cross-Panel Relation Understanding: utilizing complex images with an average of 14.3 panels per sample to evaluate MLLMs’ ability to decipher intricate cross-panel relations; (3) Expert-Level Reasoning: assessment of qualitative and quantitative reasoning across five experimental paradigms to determine if models can infer conclusions from evidence as human experts do. Comprehensive evaluation of 20 MLLMs and four multimodal Chain-of-Thought (MCoT) methods reveals that current models fall significantly short of the expert-level requirements for scientific image interpretation, underscoring a critical bottleneck in AI for Science (AI4S) research.