Prompt-based essay writing is an effective and common way to assess students' critical thinking skills. Recent work has evaluated the impressive capabilities of Large Language Models (LLMs) on this task. However, most studies focus primarily on English. Those examining LLMs' performance in Chinese often rely on coarse-grained text quality metrics, overlooking the structural and rhetorical complexities of Chinese essays, particularly across diverse genres. We therefore propose EssayBench, a multi-genre benchmark specifically designed for Chinese essay writing, along with a fine-grained, genre-specific scoring framework that hierarchically aggregates scores to better align with human preferences. The dataset comprises 728 real-world prompts across four major genres (Argumentative, Narrative, Descriptive, and Expository), and includes both Open-Ended and Constrained types. Our evaluation protocol is validated through a comprehensive human agreement study. The results show that our protocol aligns well with human judgments, achieving a highest Spearman's correlation of 0.816 and outperforming coarse-grained evaluation methods by an average of 8.6\%. Finally, we benchmark 15 large LLMs, analyzing their strengths and limitations across genres and instruction types. We believe EssayBench offers a more reliable framework for evaluating Chinese essay generation and provides valuable insights for improving LLMs in this domain.

While reasoning-enhanced large language models perform strongly on English medical tasks, a persistent multilingual gap remains, with substantially weaker reasoning in local languages, limiting equitable global medical deployment. To bridge this gap, we introduce Med-CoReasoner, a language-informed co-reasoning framework that elicits parallel English and local-language reasoning, abstracts them into structured concepts, and integrates local clinical knowledge into an English logical scaffold via concept-level alignment and retrieval. This design combines the structural robustness of English reasoning with the practice-grounded expertise encoded in local languages. To evaluate multilingual medical reasoning beyond multiple-choice settings, we construct MultiMed-X, a benchmark covering seven languages with expert-annotated long-form question answering and natural language inference tasks, comprising 350 instances per language. Experiments across three benchmarks show that Med-CoReasoner improves multilingual reasoning performance by an average of 5%, with particularly substantial gains in low-resource languages. Moreover, model distillation and expert evaluation analysis further confirm that Med-CoReasoner produces clinically sound and culturally grounded reasoning traces.

Ding Xia, Xinyue Gui, Mark Colley, Fan Gao, Zhongyi Zhou, Dongyuan Li, Renhe Jiang, Takeo Igarashi. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Jianing Zhang, Runan Li, Honglin Pang, Ding Xia, Zhou Zhu, Qian Zhang, Chuntao Li, Xi Yang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Pedestrian–automated vehicle (AV) encounters in shared spaces often involve hesitation and ambiguity. Vehicle-mounted external human–machine interfaces (eHMIs) can help, but obscured or poorly timed communications create significant challenges. To address this, we present a mobile smart pole interaction unit (SPIU) with integrated cameras and LED displays, designed as a pedestrian-side system to deliver explicit cues (“WALK,” “STOP”). An in-the-wild evaluation of the SPIU (N = 21) using a four-factor analysis (CarBehavior, Mobility, eHMI, SPIU) showed that the SPIU improved understandability, trust, and perceived safety, and reduced workload compared with the baseline, with a combination (eHMI+SPIU) yielding the strongest results. Beyond these quantitative benefits, participants appreciated the mobility of the SPIU for its “clear” and “easy to decide” mediation. This work contributes to (1) a design and deployment framework for a mobile SPIU and (2) an in-the-wild evaluation protocol for pedestrian–AV interactions in nonsignalized spaces. Our work sparks discussions on real world evaluations involving detailed vehicle kinematics and accessible multimodality (e.g., audio), focusing on the role of personal robots as user-side eHMIs.

Field studies are irreplaceable but costly, time-consuming, and error-prone, which need careful preparation. Inspired by rapid-prototyping in manufacturing, we propose a fast, low-cost evaluation method using Vision-Language Model (VLM) personas to simulate outcomes comparable to field results. While LLMs show human-like reasoning and language capabilities, autonomous vehicle (AV)-pedestrian interaction requires spatial awareness, emotional empathy, and behavioral generation. This raises our research question: To what extent can VLM personas mimic human responses in field studies? We conducted parallel studies: 1) one real-world study with 20 participants, and 2) one video-study using 20 VLM personas, both on a street-crossing task. We compared their responses and interviewed five HCI researchers on potential applications. Results show that VLM personas mimic human response patterns (e.g., average crossing times of 5.25 s vs. 5.07 s) lack the behavioral variability and depth. They show promise for formative studies, field study preparation, and human data augmentation.

Seeking dietary guidance often requires navigating complex nutritional knowledge while considering individual health needs. To address this, we present HealthGenie, an interactive platform that leverages the interpretability of knowledge graphs (KGs) and the conversational power of large language models (LLMs) to deliver tailored dietary recommendations alongside integrated nutritional visualizations for fast, intuitive insights. Upon receiving a user query, HealthGenie performs intent refinement and maps user's needs to a curated nutritional knowledge graph. The system then retrieves and visualizes relevant subgraphs, while offering detailed, explainable recommendations. Users can interactively adjust preferences to further tailor results. A within-subject study and quantitative analysis show that HealthGenie reduces cognitive load and interaction effort while supporting personalized, health-aware decision-making.

Automated vehicles (AVs) are gradually becoming part of our daily lives. However, effective communication between road users and AVs remains a significant challenge. Although various external human-machine interfaces (eHMIs) have been developed to facilitate interactions, psychological factors, such as a lack of trust and inadequate emotional signaling, may still deter users from confidently engaging with AVs in certain contexts. To address this gap, we propose TailCue, an exploration of how tail-based eHMIs affect user interaction with AVs. We first investigated mappings between tail movements and emotional expressions from robotics and zoology, and accordingly developed a motion-emotion mapping scheme. A physical robotic tail was implemented, and specific tail motions were designed based on our scheme. An online, video-based user study with 21 participants was conducted. Our findings suggest that, although the intended emotions conveyed by the tail were not consistently recognized, open-ended feedback indicated that the tail motion needs to align with the scenarios and cues. Our result highlights the necessity of scenario-specific optimization to enhance tail-based eHMIs. Future work will refine tail movement strategies to maximize their effectiveness across diverse interaction contexts.

Surface-mount device (SMD) diodes offer compact size, light weight, and enhanced reliability over traditional diodes but demand higher precision and more complex manufacturing processes. While research often centers on environmental and material factors affecting electronic packaging reliability, the impact of manufacturing processes on device failure is less explored. This study simulates the pin bending process of an SMD diode, analyzing stress conditions on internal structures for two mold design schemes. The distinct geometric features of molds in the two schemes result in different mold motion patterns and contact locations during operation. Notably, comparative analysis reveals that Design Scheme 1 sustains 2.66-fold greater stress concentration in the heat sink structure while demonstrating 2.16-times elevated chip stress levels relative to Design Scheme 2. Through simulation analysis, in conjunction with real-world manufacturing conditions, the primary factors leading to device failure are identified. Under the influence of mold tolerances and processing errors, the chip stress in the SMD diode increases from 23.603 to 188.11 MPa, a value approximately eight times the original stress level. It is emphasized that dimensional tolerances in the production process significantly impact device reliability, and the design of molds must account for these variations. This research offers valuable theoretical insights into ensuring the reliability of pin bending for various SMD devices. Moreover, the simulation outcomes for the SMD diode contribute to a deeper understanding of the internal stresses encountered in other plastic devices during their pin bending stages.

Recently, stateless blockchains have been proposed to alleviate the storage overhead for nodes. A stateless blockchain achieves storage-consensus parallelism, where storage workloads are offloaded from on-chain consensus, enabling more resource-constraint nodes to participate in the consensus. However, existing stateless blockchains still suffer from limited throughput. In this paper, we present Porygon, a novel stateless blockchain with three-dimensional (3D) parallelism. First, Porygon separates the storage and consensus of transactions as the stateless blockchain, achieving the storage-consensus parallelism. This first-dimensional parallelism divides the processing of transactions into several stages and scales the network by supporting more nodes in the system. Based on such a design, we then propose a pipeline mechanism to achieve second-dimensional inter-block parallelism, where relevant stages of processing transactions are pipelined efficiently, thereby reducing transaction latency. Finally, Porygon presents a sharding mechanism to achieve third-dimensional inner-block parallelism. By sharding the executions of transactions of a block and adopting a lightweight cross-shard coordination mechanism, Porygon can effectively execute both intra-shard and cross-shard transactions, consequently achieving outstanding transaction throughput. We evaluate the performance of Porygon by extensive experiments on an implemented prototype and large-scale simulations. Compared with existing blockchains, Porygon boosts throughput by up to 20x, reduces network usage by more than 50%, and simultaneously requires only 5MB of storage consumption per node.

Human-centered AI aims to bridge the gap between machine decision-making and human understanding. However, even for classification tasks where deep neural networks have achieved superb performance, there are currently few methods that link humans and AI well, especially on domain-specific tasks. In this paper, we propose SpaceEditing, a 2D spatial layout tool that enables human users to interact with the latent space of deep neural networks. During the interaction process, the tool’s algorithm automatically processes user actions, providing feedback to the network and leveraging triplet loss to effectively learn from user-modified information. We evaluate SpaceEditing with three case studies: (1) an archaeology researcher uses a bronze dataset; (2) a deep learning researcher uses a garbage classification dataset; (3) six deep learning beginners use a head pose dataset. The experimental results demonstrate the effectiveness of our tool in integrating human knowledge and improving network performance.

The exact shape of intracranial aneurysms is critical in medical diagnosis and surgical planning. While voxel-based deep learning frameworks have been proposed for this segmentation task, their performance remains limited. In this study, we offer a two-step surface-based deep learning pipeline that achieves significantly better results. Our proposed model takes a surface model of an entire set of principal brain arteries containing aneurysms as input and returns aneurysm surfaces as output. A user first generates a surface model by manually specifying multiple thresholds for time-of-flight magnetic resonance angiography images. The system then samples small surface fragments from the entire set of brain arteries and classifies the surface fragments according to whether aneurysms are present using a point-based deep learning network (PointNet++). Finally, the system applies surface segmentation (SO-Net) to surface fragments containing aneurysms. We conduct a direct comparison of the segmentation performance of our proposed surface-based framework and an existing voxel-based method by counting voxels: our framework achieves a much higher Dice similarity (72%) than the prior approach (46%).

Machine learning (ML) has been extensively applied to model geohazards, yielding tremendous success. However, researchers and practitioners still face challenges in enhancing the reliability of ML models. In the present study, a systematic framework combining k-fold cross-validation (CV), metaheuristics (MHs), support vector regression (SVR), and Friedman and Nemenyi tests was proposed to improve the reliability and performance of geohazard modeling. The average normalized mean square error (NMSE) from k-fold CV sets was adopted as the fitness metric. Twenty of the most well-established MHs and the most recent MHs were adopted to tune the hyperparameters of SVR and were evaluated through nonparametric Friedman and post hoc Nemenyi tests to identify significant differences. Observations from a typical reservoir landslide were selected as a benchmark dataset, and the accuracy, robustness, computational time, and convergence speed of the MHs were compared. Significant performance differences among the twenty MHs were identified by Friedman and post hoc Nemenyi tests of the mean absolute error (MAE), root mean squared error (RMSE), Kling–Gupta efficiency (KGE), and computational time, with p values lower than 0.05. The comparison of results demonstrated that the multiverse optimizer (MVO) is among the highest-performing, most stable, and computationally efficient algorithms, providing superior performance to other methods, with nearly optimum values of the correlation coefficient (R), a low MAE (23.5086 versus 23.9360), a low mean RMSE (48.6946 versus 50.1882), and a high mean KGE (0.9803 versus 0.9893) in predicting the displacement of the Shuping landslide. This paper considerably enriches the literature regarding hyperparameter optimization algorithms and the enhancement of their reliability. In addition, Friedman and post hoc Nemenyi tests have the potential for evaluating and comparing various ML-based geohazard models.

Medicine is an important application area for deep learning models. Research in this field is a combination of medical expertise and data science knowledge. In this paper, instead of 2D medical images, we introduce an open-access 3D intracranial aneurysm dataset, IntrA, that makes the application of points-based and mesh-based classification and segmentation models available. Our dataset can be used to diagnose intracranial aneurysms and to extract the neck for a clipping operation in medicine and other areas of deep learning, such as normal estimation and surface reconstruction. We provide a large-scale benchmark of classification and part segmentation by testing state-of-the-art networks. We also discuss the performance of each method and demonstrate the challenges of our dataset. The published dataset can be accessed here: https://github.com/intra2d2019/IntrA.