Large vision-language models (LVLMs) demonstrate strong performance in dermatology; however, evaluating diagnostic reasoning for rare conditions remains largely unexplored. Existing benchmarks focus on common diseases and assess only final accuracy, overlooking the clinical reasoning process, which is critical for complex cases. We address this gap by constructing DermCase, a long-context benchmark derived from peer-reviewed case reports. Our dataset contains 26,030 multi-modal image-text pairs and 6,354 clinically challenging cases, each annotated with comprehensive clinical information and step-by-step reasoning chains. To enable reliable evaluation, we establish DermLIP-based similarity metrics that achieve stronger alignment with dermatologists for assessing differential diagnosis quality. Benchmarking 22 leading LVLMs exposes significant deficiencies across diagnosis accuracy, differential diagnosis, and clinical reasoning. Fine-tuning experiments demonstrate that instruction tuning substantially improves performance while Direct Preference Optimization (DPO) yields minimal gains. Systematic error analysis further reveals critical limitations in current models' reasoning capabilities.

3D skeletal action recognition has emerged as a powerful alternative to traditional RGB and depth-based approaches, offering robustness to environmental variations, computational efficiency, and enhanced privacy. Despite remarkable progress, current research remains fragmented across diverse input representations and lacks evaluation under scenarios that reflect real-world challenges. This paper presents a representation-centric review of supervised skeletal action recognition, systematically categorizing state-of-the-art methods by their input feature types: joint coordinates, bone vectors, motion flows, and extended representations, and analyzing how these choices influence spatiotemporal modeling strategies. Building on the insights from this review, we introduce ANUBIS, a large-scale, challenging dataset designed to address critical gaps in existing benchmarks. ANUBIS incorporates multi-view recordings with back-view perspectives, complex multi-person interactions, fine-grained and violent actions, and contemporary social behaviors. We benchmark a diverse set of state-of-the-art models on ANUBIS and conduct an in-depth analysis of how different feature types affect recognition performance across 102 action categories. Our results show strong action-feature dependencies, highlight the limitations of na & iuml;ve multi-representational fusion, and point toward the need for task-aware, semantically aligned integration strategies. This work offers both a comprehensive foundation and a practical benchmarking resource, aiming to guide the next generation of robust, generalizable skeleton-based action recognition systems for complex real-world scenarios. The dataset, benchmarking framework, and code are available at https://yliu1082.github.io/ANUBIS/.

Plane geometry problem solving (PGPS) has recently gained significant attention as a benchmark to assess the multi-modal reasoning capabilities of large vision-language models. Despite the growing interest in PGPS, the research community still lacks a comprehensive overview that systematically synthesizes recent work in PGPS. To fill this gap, we present a survey of existing PGPS studies. We first categorize PGPS methods into an encoder-decoder framework and summarize the corresponding output formats used by their encoders and decoders. Subsequently, we classify and analyze these encoders and decoders according to their architectural designs. Finally, we outline major challenges and promising directions for future research. In particular, we discuss the hallucination issues arising during the encoding phase within encoder-decoder architectures, as well as the problem of data leakage in current PGPS benchmarks.

Clinical photographs play a vital role in conversational computer-aided diagnosis, particularly in dermatology. However, existing skin disease benchmarks contain limitations like insufficient dataset size, the sole presence of categorical labels, the lack of expert inspections, and limited diversity in annotations. To address these shortcomings, we introduce DermEVAL, a large-scale benchmark specifically designed to evaluate the performance of Multimodal Large Language Models (MLLMs) in dermatology. Our benchmark includes image-text pairs depicting 16 distinct skin diseases, featuring a total of 11,347 representative images drawn from various dermatological datasets, carefully selected and annotated with the guidance of dermatologists. DermEVAL enables two primary tasks: visual question answering (VQA) and medical report generation (MRG), designed to simulate real-world medical diagnostics. We evaluate the performance of MLLMs in dermatology using multiple metrics, including traditional metrics and GPT-4V-based assessments. Our results indicate that accurately diagnosing skin diseases remains challenging for state-of-the-art MLLMs. We also demonstrate that fine-tuning MLLMs using DermEVAL significantly improves their performance on dermatology-related image–text tasks.

The prevalence of vision-threatening eye diseases is a significant global burden, with many cases remaining undiagnosed or diagnosed too late for effective treatment. Large vision-language models (LVLMs) have the potential to assist in understanding anatomical information, diagnosing eye diseases, and drafting interpretations and follow-up plans, thereby reducing the burden on clinicians and improving access to eye care. However, limited benchmarks are available to assess LVLMs' performance in ophthalmology-specific applications. In this study, we introduce LMOD, a large-scale multimodal ophthalmology benchmark consisting of 21,993 instances across (1) five ophthalmic imaging modalities: optical coherence tomography, color fundus photographs, scanning laser ophthalmoscopy, lens photographs, and surgical scenes; (2) free-text, demographic, and disease biomarker information; and (3) primary ophthalmology-specific applications such as anatomical information understanding, disease diagnosis, and subgroup analysis. In addition, we benchmarked 13 state-of-the-art LVLM representatives from closed-source, open-source, and medical domains. The results demonstrate a significant performance drop for LVLMs in ophthalmology compared to other domains. Systematic error analysis further identified six major failure modes: misclassification, failure to abstain, inconsistent reasoning, hallucination, assertions without justification, and lack of domain-specific knowledge. In contrast, supervised neural networks specifically trained on these tasks as baselines demonstrated high accuracy. These findings underscore the pressing need for benchmarks in the development and validation of ophthalmology-specific LVLMs.

Vision-threatening eye diseases pose a major global health burden, with timely diagnosis limited by workforce shortages and restricted access to specialized care. While multimodal large language models (MLLMs) show promise for medical image interpretation, advancing MLLMs for ophthalmology is hindered by the lack of comprehensive benchmark datasets suitable for evaluating generative models. We present a large-scale multimodal ophthalmology benchmark comprising 32,633 instances with multi-granular annotations across 12 common ophthalmic conditions and 5 imaging modalities. The dataset integrates imaging, anatomical structures, demographics, and free-text annotations, supporting anatomical structure recognition, disease screening, disease staging, and demographic prediction for bias evaluation. This work extends our preliminary LMOD benchmark with three major enhancements: (1) nearly 50

Generative text-to-image models, such as Stable Diffusion, have demonstrated a remarkable ability to generate diverse, high-quality images. However, they are surprisingly inept when it comes to rendering human hands, which are often anatomically incorrect or reside in the "uncanny valley". In this paper, we propose a method HandCraft for restoring such malformed hands. This is achieved by automatically constructing masks and depth images for hands as conditioning signals using a parametric model, allowing a diffusion-based image editor to fix the hand's anatomy and adjust its pose while seamlessly integrating the changes into the original image, preserving pose, color, and style. Our plug-and-play hand restoration solution is compatible with existing pretrained diffusion models, and the restoration process facilitates adoption by eschewing any fine-tuning or training requirements for the diffusion models. We also contribute MalHand datasets that contain generated images with a wide variety of malformed hands in several styles for hand detector training and hand restoration benchmarking, and demonstrate through qualitative and quantitative evaluation that HandCraft not only restores anatomical correctness but also maintains the integrity of the overall image.

We introduce GeoDANO, a geometric vision-language model (VLM) with a domain-agnostic vision encoder, for solving plane geometry problems. Although VLMs have been employed for solving geometry problems, their ability to recognize geometric features remains insufficiently analyzed. To address this gap, we propose a benchmark that evaluates the recognition of visual geometric features, including primitives such as dots and lines, and relations such as orthogonality. Our preliminary study shows that vision encoders often used in general-purpose VLMs, e.g., OpenCLIP, fail to detect these features and struggle to generalize across domains. To overcome the limitation, we develop GeoCLIP, a CLIP-based model trained on synthetic geometric diagram–caption pairs. Benchmark results show that GeoCLIP outperforms existing vision encoders in recognizing geometric features. We then propose our VLM, GeoDANO, which augments GeoCLIP with a domain adaptation strategy for unseen diagram styles. GeoDANO outperforms specialized methods for plane geometry problems and GPT-4o on MathVerse. The implementation is available at https://github.com/ml-postech/GeoDANO.

Most existing graph neural networks (GNNs) learn node embeddings using the framework of message passing and aggregation. Such GNNs are incapable of learning relative positions between graph nodes within a graph. To empower GNNs with the awareness of node positions, some nodes are set as anchors. Then, using the distances from a node to the anchors, GNNs can infer relative positions between nodes. However, position-aware GNNs (P-GNNs) arbitrarily select anchors, leading to compromising position awareness and feature extraction. To eliminate this compromise, we demonstrate that selecting evenly distributed and asymmetric anchors is essential. On the other hand, we show that choosing anchors that can aggregate embeddings of all the nodes within a graph is NP-complete. Therefore, devising efficient optimal algorithms in a deterministic approach is practically not feasible. To ensure position awareness and bypass NP-completeness, we propose position-sensing GNNs (PSGNNs), learning how to choose anchors in a backpropagatable fashion. Experiments verify the effectiveness of PSGNNs against state-of-the-art GNNs, substantially improving performance on various synthetic and real-world graph datasets while enjoying stable scalability. Specifically, PSGNNs on average boost area under the curve (AUC) more than 14% for pairwise node classification and 18% for link prediction over the existing state-of-the-art position-aware methods. Our source code is publicly available at: https://github.com/ZhenyueQin/PSGNN.

In this paper, we present a novel benchmark for Emotion Recognition using facial landmarks extracted from realistic news videos. Traditional methods relying on RGB images are resource-intensive, whereas our approach with Facial Landmark Emotion Recognition (FLER) offers a simplified yet effective alternative. By leveraging Graph Neural Networks (GNNs) to analyze the geometric and spatial relationships of facial landmarks, our method enhances the understanding and accuracy of emotion recognition. We discuss the advancements and challenges in deep learning techniques for emotion recognition, particularly focusing on Graph Neural Networks (GNNs) and Transformers. Our experimental results demonstrate the viability and potential of our dataset as a benchmark, setting a new direction for future research in emotion recognition technologies. The codes and models are at: https://github.com/wangzhifengharrison/benchmark_real_news

Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing. Nonetheless, the potential of using visual prompts for emotion recognition in these models remains largely unexplored and untapped. Traditional methods in VLLMs struggle with spatial localization and often discard valuable global context. To address this problem, we propose a Set-of-Vision prompting (SoV) approach that enhances zero-shot emotion recognition by using spatial information, such as bounding boxes and facial landmarks, to mark targets precisely. SoV improves accuracy in face count and emotion categorization while preserving the enriched image context. Through a battery of experimentation and analysis of recent commercial or open-source VLLMs, we evaluate the SoV model's ability to comprehend facial expressions in natural environments. Our findings demonstrate the effectiveness of integrating spatial visual prompts into VLLMs for improving emotion recognition performance.

Skeleton sequences are lightweight and compact and thus are ideal candidates for action recognition on edge devices. Recent skeleton-based action recognition methods extract features from 3-D joint coordinates as spatial–temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance. The use of first-and second-order features, that is, joint and bone representations, has led to high accuracy. Nonetheless, many models are still confused by actions that have similar motion trajectories. To address these issues, we propose fusing higher-order features in the form of angular encoding (AGE) into modern architectures to robustly capture the relationships between joints and body parts. This simple fusion with popular spatial–temporal graph neural networks achieves new state-of-the-art accuracy in two large benchmarks, including NTU60 and NTU120, while employing fewer parameters and reduced run time. Our source code is publicly available at: https://github.com/ZhenyueQin/Angular-Skeleton-Encoding.

Background: Low-grade serous ovarian cancer is a low incidence type of ovarian cancer, and this study aimed to investigate the clinical features and effective treatment strategies that may influence its prognosis. Methods: We retrospectively examined the clinical characteristics of patients with a diagnosis of low-grade plasma ovarian cancer recorded in the Surveillance, Epidemiology, and End Results (SEER) database between 1988-2017. The Kaplan-Meier method and Cox regression proportional risk method were used to assess overall survival (OS). A column-wise model that could predict OS was constructed based on Cox proportional risk. Results: The study found that age, marital status, side, International Federation of Gynecology and Obstetrics (FIGO) stage, serum cancer antigen 125 (CA125), surgery, postoperative residual disease diameter and chemotherapy all significantly affected the prognosis of the disease. Among them, serum CA125, FIGO stage, surgery, postoperative residual disease diameter and chemotherapy were independent factors affecting prognosis. According to the nomogram, FIGO staging and prognosis of low-grade serous ovarian cancer (LGSOC) patients were the most significant, followed by surgery and chemotherapy, while age at presentation and chemotherapy had little effect on OS. Conclusion: The better prognosis of LGSOC is associated with surgery, surgical outcomes, chemotherapy, and early-stage patients. However, large sample studies are needed to further clarify whether patients with early serous ovarian cancer are suitable for fertility-sparing surgery, and whether chemotherapy and radiotherapy should be added in patients with advanced ovarian cancer.

Uterine fibroids are benign gynecologic tumors, and women aged between 30 to 50 years are known to have a high incidence of uterine fibroids. A growing number of pharmacotherapies and minimally invasive organ-preserving treatments have been designed and conducted over the past few years. However, there has not been any therapeutic drugs exhibiting an ideal therapeutic effect and low recurrence rate, such that the surgical treatment continues to be primarily employed in the actual clinical treatment. In general, surgical treatment has been performed as the organ-and fertility -preserving hysteroscopic or laparoscopic resections of the fibroids. Minimally invasive surgical equipment (e.g., hysteroscopy, traditional porous laparoscopy, trans-umbilical laparoscopy, transvaginal laparoscopy, as well as robot-assisted laparoscopy) has been extensively applied to clinical treatment. Compared with traditional laparotomy, minimally invasive surgical equipment is characterized by minimally invasive surgery, high efficiency and safety. As medical technology has been leaping forward, interventional therapy and radiofrequency ablation can also be employed for treating uterine fibroids. In accordance with the research progress worldwide, the current situation, limitations, and advantages of the treatment of uterine fibroids in patients with fertility requirements are reviewed in this study.

Emotion recognition is crucial for enhancing human-computer interaction. While traditional approaches largely depend on RGB images, our proposed Geometric-Aware Facial Landmark Emotion Recognition framework harnesses the geometric and spectral attributes of facial landmarks for emotion recognition. This work unfolds three key contributions: utilizing Graph Convolutional Networks to grasp the natural spatial relationships among facial landmarks, introducing distance-aware graph operations to accentuate the relational geometry, and employing spectral encodings to comprehend the frequency-based attributes of landmark positions. Through rigorous experiments on recognized datasets RAF-DB and KDEF, Our method surpasses baseline methods, demonstrating its effectiveness especially in high-resolution scenarios where detailed facial landmarks are apparent. The datasets curated for Facial Landmark Emotion Recognition will also be shared publicly as part of this work, offering a significant resource for the community. The encouraging results highlight the potential of geometric-aware analysis in propelling emotion recognition systems forward, opening avenues for further research in this evolving domain.

Teratomas often occur in the gonads, while Extragonadal mature cystic teratomas are reported occasionally, with the most common site being the omentum. Teratoma in the Douglas sac is extremely rare. we report a rare case of mature cystic Teratoma in the Douglas sac in a 71-year-old woman who underwent laparoscopic surgery. A cyst with a diameter of approximately 6 cm from Douglas was found during surgery, and the mass was separated from both ovaries. Microscopically, the cyst was a mature cystic teratoma that did not originate from the ovary.

子宫内膜异位症(EMs)是导致女性不孕的较为常见疾病之一.对于卵巢型EMs,腹腔镜手术可提高患者术后自然妊娠率.但EMs具有复发性高的特点,因此术后需药物长期管理,尤其对于有生育要求的女性患者,应选择既能抑制病灶复发,又不影响卵巢排卵的药物.目前研究表明,地屈孕酮是治疗剂量可减少EMs术后复发且不抑制排卵的唯一药物.本文报道两例卵巢型EMs患者在行腹腔镜卵巢子宫内膜异位囊肿剥除术后予地屈孕酮20 mg/d长周期(月经周期第5～25天)管理,均自然妊娠,且一名患者顺利分娩一名健康男婴,另一名患者仍继续妊娠中,未见患者及胎儿异常.随访结果提示地屈孕酮在管理EMs的同时不影响自然妊娠,可能是作为近期有生育计划的育龄期EMs患者术后长期管理的优选药物.

We introduce a pipeline to address anatomical inaccuracies in Stable Diffusion generated hand images. The initial step involves constructing a specialized dataset, focusing on hand anomalies, to train our models effectively. A finetuned detection model is pivotal for precise identification of these anomalies, ensuring targeted correction. Body pose estimation aids in understanding hand orientation and positioning, crucial for accurate anomaly correction. The integration of ControlNet and InstructPix2Pix facilitates sophisticated inpainting and pixel-level transformation, respectively. This dual approach allows for high-fidelity image adjustments. This comprehensive approach ensures the generation of images with anatomically accurate hands, closely resembling real-world appearances. Our experimental results demonstrate the pipeline's efficacy in enhancing hand image realism in Stable Diffusion outputs. We provide an online demo at https://fixhand.yiqun.io

目的 初步探讨以雌孕激素序贯疗法为基础的联合药物方案治疗不全流产的安全性和可行性.方法 回顾性分析 2021 年 3 月至 2022 年 5 月于南京医科大学附属常州第二人民医院确诊为不全流产的 9 例患者的临床资料.所有患者曾接受人工流产或引产术,术后经阴道超声检查提示宫腔内部分妊娠物残留,均进行雌孕激素序贯疗法联合米非司酮及中成药血府逐瘀胶囊治疗.观察 9 例患者用药期间血β-HCG 水平变化,经阴道超声检查宫腔妊娠物残余物大小,记录阴道流血、腹痛及药物不良反应发生情况等.结果 9 例患者在治疗期间均无明显的阴道流血及严重腹痛.7 例患者在用药 1 个周期(4 周)药物撤退性出血干净后行经阴道超声检查,提示宫腔内未见妊娠残余物,血β-HCG下降至正常范围;另 2 例患者分别于用药 2 个周期、4 个周期后治愈.用药期间 9 例患者中 2 例患者出现轻度恶心症状,1 例患者在用药第 4 周期时出现轻度乳房胀痛,其余 6 例患者均未见明显药物不良反应.1 例患者在治愈 1 个月后自然妊娠.结论 以雌孕激素序贯疗法为基础的联合药物方案治疗不全流产可能是安全可行的.