Omit references to the index or number of the sub-images, such as (xx), left, right, etc.3. There might be a common prefix or suffix caption shared among all sub-images at the beginning, end, or within the caption. Please incorporate the prefix or suffix into each sub-image's caption. If one subcaption contains context for multiple other subcaptions, add that context to each of the relevant subcaptions.4. The final output should be in JSON format, with an outer field'subcaptions', with a value that is a list of'subfigure' and'subcaption' dictionaries.5. If a subfigure contains more nested figures, i.e. subfigure (A) contains references to (left) and (right), add a field called "location" that stores the "left" or "right".6. If there are no references to sub-images, give a single subcaption with label "A".User Prompt:You are a research paper processor which splits the captions of figures into sub-captions that correspond with subfigures.System Prompt:"(a) H&E image of a breast tumor tissue. Fluorescently labeled markers superimposed as green color on the H&E image, (b) \u03b2-catenin, (c) pan-keratin, and (d) smooth muscle \u03b1-actin, markers.":{"subcaptions":

Clinical reasoning in medicine is a hypothesis-driven process where physicians refine diagnoses from limited information through targeted history, physical examination, and diagnostic investigations. In contrast, current medical benchmarks for large language models (LLMs) primarily assess knowledge recall through single-turn questions, where complete clinical information is provided upfront. To address this gap, we introduce VivaBench, a multi-turn benchmark that evaluates sequential clinical reasoning in LLM agents. Our dataset comprises 1152 physiciancurated clinical vignettes structured as interactive scenarios that simulate a viva voce examination in medical training, requiring agents to actively probe for relevant findings, select appropriate investigations, and synthesize information across multiple steps to reach a diagnosis. We evaluated several state-of-the-art LLMs and found that while models demonstrate competence in diagnosing conditions within well-described clinical presentations, their performance degrades significantly when required to navigate diagnostic uncertainty. Our analysis identified several failure modes that mirror common issues in clinical practice, including: (1) fixation on initial hypotheses, (2) excessive investigation ordering, (3) premature diagnostic closure, and (4) missing critical conditions. These patterns reveal fundamental limitations in how current LLMs manage uncertainty and gather information sequentially. Through VivaBench, we provide a standardized benchmark for evaluating conversational medical AI systems for real-world clinical decision support. Beyond medical applications, we contribute to the larger corpus of research on agentic AI by demonstrating how sequential reasoning trajectories can diverge in complex decision-making environments.

Accurate polyp sizing during endoscopy is crucial for cancer risk assessment but is hindered by subjective methods and inadequate datasets lacking integrated 2D appearance, 3D structure, and real-world size information. We introduce PolypSense3D, the first multi-source benchmark dataset specifically targeting depth-aware polyp size measurement. It uniquely integrates over 43,000 frames from virtual simulations, physical phantoms, and clinical sequences, providing synchronized RGB, dense/sparse depth, segmentation masks, camera parameters, and millimeter-scale size labels derived via a novel forceps-assisted in-vivo annotation technique. To establish its value, we benchmark state-of-the-art segmentation and depth estimation models. Results quantify significant domain gaps between simulated/phantom and clinical data and reveal substantial error propagation from perception stages to final size estimation, with the best fully automated pipelines achieving an average Mean Absolute Error (MAE) of 0.95 mm on the clinical data subset. Publicly released under CCBY-SA 4.0 with code and evaluation protocols, PolypSense3D offers a standardized platform to accelerate research in robust, clinically relevant quantitative endoscopic vision.

Recent advances in false discovery rate (FDR)-controlled feature selection methods have improved reliability by effectively limiting false positives, making them wellsuited for complex applications. A popular FDR-controlled framework called data splitting uses the "mirror statistics" to select features. However, we find that the unit variance assumption on mirror statistics could potentially limit the feature selection power. To address this, we generalize the mirror statistics in the Gaussian mirror framework and introduce a new approach called "generalized Gaussian mirror" (G2M), which adaptively learns the variance and forms new test statistics. We demonstrate both theoretically and empirically that the proposed test statistics achieve higher power than those of Gaussian mirror and data splitting. Comparisons with other FDR-controlled frameworks on synthetic, semi-synthetic, and real datasets highlight the superior performance of the G2M method in achieving higher power while maintaining FDR control. These findings suggest the potential for the G2M method for practical applications in real-world problems. Code is available at: https://github.com/skyve2012/G2M.

Large language models (LLMs) have achieved significant performance progress in various natural language processing applications. However, LLMs still struggle to meet the strict requirements for accuracy and reliability in the medical field and face many challenges in clinical applications. Existing clinical diagnostic evaluation benchmarks for evaluating medical agents powered by LLMs have severe limitations. Firstly, most existing medical evaluation benchmarks face the risk of data leakage or contamination.

Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets to support applications in fields such as healthcare, finance, and law. These fine-tuning datasets often have sensitive and confidential dataset-level properties -- such as patient demographics or disease prevalence--that are not intended to be revealed. While prior work has studied property inference attacks on discriminative models (e.g., image classification models) and generative models (e.g., GANs for image data), it remains unclear if such attacks transfer to LLMs. In this work, we introduce PropInfer, a benchmark task for evaluating property inference in LLMs under two fine-tuning paradigms: question-answering and chat-completion. Built on the ChatDoctor dataset, our benchmark includes a range of property types and task configurations. We further propose two tailored attacks: a prompt-based generation attack and a shadow-model attack leveraging word frequency signals.

PanTS is a large-scale, multi-institutional dataset curated to advance research in pancreatic CT analysis. It contains 36,390 CT scans from 145 medical centers, with expert-validated, voxel-wise annotations of over 993,000 anatomical structures, covering pancreatic tumors, pancreas head, body, and tail, and 24 surrounding anatomical structures such as vascular/skeletal structures and abdominal/thoracic organs. Each scan includes metadata such as patient age, sex, diagnosis, contrast phase, in-plane spacing, slice thickness, etc. AI models trained on PanTS achieve significantly better performance in pancreatic tumor detection, localization, and segmentation than those trained on existing public datasets. Our analysis indicates that these gains are directly attributable to the 16 larger-scale tumor annotations and indirectly supported by the 24 additional surrounding anatomical structures. As the largest and most comprehensive resource of its kind, PanTS offers a new benchmark for developing and evaluating AI models in pancreatic CT analysis.

Endoscopic procedures are essential for diagnosing and treating internal diseases, and multi-modal large language models (MLLMs) are increasingly applied to assist in endoscopy analysis. However, current benchmarks are limited, as they typically cover specific endoscopic scenarios and a small set of clinical tasks, failing to capture the real-world diversity of endoscopic scenarios and the full range of skills needed in clinical workflows. To address these issues, we introduce EndoBench, the first comprehensive benchmark specifically designed to assess MLLMs across the full spectrum of endoscopic practice with multi-dimensional capacities. EndoBench encompasses 4 distinct endoscopic scenarios, 12 specialized clinical tasks with 12 secondary subtasks, and 5 levels of visual prompting granularities, resulting in 6,832 rigorously validated VQA pairs from 21 diverse datasets. Our multi-dimensional evaluation framework mirrors the clinical workflow--spanning anatomical recognition, lesion analysis, spatial localization, and surgical operations--to holistically gauge the perceptual and diagnostic abilities of MLLMs in realistic scenarios. We benchmark 23 state-of-the-art models, including generalpurpose, medical-specialized, and proprietary MLLMs, and establish human clinician performance as a reference standard. Our extensive experiments reveal: (1) proprietary MLLMs outperform open-source and medical-specialized models overall, but still trail human experts; (2) medical-domain supervised fine-tuning substantially boosts task-specific accuracy; and (3) model performance remains sensitive to prompt format and clinical task complexity. EndoBench establishes a new standard for evaluating and advancing MLLMs in endoscopy, highlighting both progress and persistent gaps between current models and expert clinical reasoning. We publicly release our benchmark and code.

Multi-class tissue-type classification of colorectal cancer (CRC) histopathologic images is a significant step in the development of downstream machine learning models for diagnosis and treatment planning. However, publicly available CRC datasets used to build tissue classifiers often suffer from insufficient morphologic diversity, class imbalance, and low-quality image tiles, limiting downstream model performance and generalizability. To address this research gap, we introduce STARC-9 (STAnford coloRectal Cancer), a large-scale dataset for multi-class tissue classification. STARC-9 comprises 630,000 histopathologic image tiles uniformly sampled across nine clinically relevant tissue classes (each represented by 70,000 tiles), systematically extracted from hematoxylin & eosin-stained whole-slide images (WSI) from 200 CRC patients at the Stanford University School of Medicine. To construct STARC-9, we propose a novel framework, DeepCluster++, consisting of two primary steps to ensure diversity within each tissue class, followed by pathologist verification.

Simultaneous Localization and Mapping (SLAM) systems typically assume static, distant illumination; however, many real-world scenarios, such as endoscopy, subterranean robotics, and search & rescue in collapsed environments, require agents to operate with a co-located light and camera in the absence of external lighting. In such cases, dynamic near-field lighting introduces strong, view-dependent shading that significantly degrades SLAM performance. We introduce Near-Field Lighting Bundle Adjustment Loss (NFL-BA) which explicitly models near-field lighting as a part of Bundle Adjustment loss and enables better performance for scenes captured with dynamic lighting. NFL-BA can be integrated into neural rendering-based SLAM systems with implicit or explicit scene representations. Our evaluations mainly focus on endoscopy procedure where SLAM can enable autonomous navigation, guidance to unsurveyed regions, blindspot detections, and 3D visualizations, which can significantly improve patient outcomes and endoscopy experience for both physicians and patients. Replacing Photometric Bundle Adjustment loss of SLAM systems with NFL-BA leads to significant improvement in camera tracking, 37% for MonoGS and 14% for EndoGSLAM, and leads to state-of-the-art camera tracking and mapping performance on the C3VD colonoscopy dataset. Further evaluation on indoor scenes captured with phone camera with flashlight turned on, also demonstrate significant improvement in SLAM performance due to NFL-BA.