Xiaojing Zhang

Xinna Lin, Siqi Ma, Junjie Shan et al.

Pursuing artificial intelligence for biomedical science, a.k.a. AI Scientist, draws increasing attention, where one common approach is to build a copilot agent driven by Large Language Models (LLMs). However, to evaluate such systems, people either rely on direct Question-Answering (QA) to the LLM itself, or in a biomedical experimental manner. How to precisely benchmark biomedical agents from an AI Scientist perspective remains largely unexplored. To this end, we draw inspiration from one most important abilities of scientists, understanding the literature, and introduce BioKGBench. In contrast to traditional evaluation benchmark that only focuses on factual QA, where the LLMs are known to have hallucination issues, we first disentangle "Understanding Literature" into two atomic abilities, i) "Understanding" the unstructured text from research papers by performing scientific claim verification, and ii) Ability to interact with structured Knowledge-Graph Question-Answering (KGQA) as a form of "Literature" grounding. We then formulate a novel agent task, dubbed KGCheck, using KGQA and domain-based Retrieval-Augmented Generation (RAG) to identify the factual errors of existing large-scale knowledge graph databases. We collect over two thousand data for two atomic tasks and 225 high-quality annotated data for the agent task. Surprisingly, we discover that state-of-the-art agents, both daily scenarios and biomedical ones, have either failed or inferior performance on our benchmark. We then introduce a simple yet effective baseline, dubbed BKGAgent. On the widely used popular knowledge graph, we discover over 90 factual errors which provide scenarios for agents to make discoveries and demonstrate the effectiveness of our approach. The code and data are available at https://github.com/westlake-autolab/BioKGBench.

Qianxi Fu, Youngjoon Suh, Xiaojing Zhang et al.

Phase change plays a critical role in thermal management systems, yet quantitative characterization of multiphase heat transfer remains limited by the challenges of measuring temperature fields in chaotic, rapidly evolving flow regimes. While computational methods offer spatiotemporal resolution in idealized cases, replicating complex experimental conditions remains prohibitively difficult. Here, we present a data-driven framework that leverages a conditional generative adversarial network (CGAN) to infer temperature fields from geometric phase contours in a canonical pool boiling configuration where advanced data collection techniques are restricted. Using high-speed imaging data and simulation-informed training, our model demonstrates the ability to reconstruct temperature fields with errors below 6%. We further show that standard data augmentation strategies are effective in enhancing both accuracy and physical plausibility of the predicted maps across both simulation and experimental datasets when precise physical constraints are not applicable. Our results highlight the potential of deep generative models to bridge the gap between observable multiphase phenomena and underlying thermal transport, offering a powerful approach to augment and interpret experimental measurements in complex two-phase systems.