Though Large Vision-Language Models (LVLMs) are being actively explored in medicine, their ability to conduct complex real-world telemedicine consultations combining accurate diagnosis with professional dialogue remains underexplored. This paper presents 3MDBench (Medical Multimodal Multi-agent Dialogue Benchmark), an open-source framework for simulating and evaluating LVLM-driven telemedical consultations. 3MDBench simulates patient variability through temperament-based Patient Agent and evaluates diagnostic accuracy and dialogue quality via Assessor Agent. It includes 2996 cases across 34 diagnoses from real-world telemedicine interactions, combining textual and image-based data. The experimental study compares diagnostic strategies for widely used open and closed-source LVLMs. We demonstrate that multimodal dialogue with internal reasoning improves F1 score by 6.5% over non-dialogue settings, highlighting the importance of context-aware, information-seeking questioning. Moreover, injecting predictions from a diagnostic convolutional neural network into the LVLM's context boosts F1 by up to 20%. Source code is available at https://github.com/univanxx/3mdbench.

Rapid information access is vital during wildfires, yet traditional data sources are slow and costly. Social media offers real-time updates, but extracting relevant insights remains a challenge. In this work, we focus on multimodal wildfire social media data, which, although existing in current datasets, is currently underrepresented in Canadian contexts. We present WildFireCan-MMD, a new multimodal dataset of X posts from recent Canadian wildfires, annotated across twelve key themes. We evaluate zero-shot vision-language models on this dataset and compare their results with those of custom-trained and baseline classifiers. We show that while baseline methods and zero-shot prompting offer quick deployment, custom-trained models outperform them when labelled data is available. Our best-performing custom model reaches 84.48% f-score, outperforming VLMs and baseline classifiers. We also demonstrate how this model can be used to uncover trends during wildfires, through the collection and analysis of a large unlabeled dataset. Our dataset facilitates future research in wildfire response, and our findings highlight the importance of tailored datasets and task-specific training. Importantly, such datasets should be localized, as disaster response requirements vary across regions and contexts.

Multi-environment (M-En) networks integrate diverse traffic sources, including Internet of Things (IoT) and traditional computing systems, creating complex and evolving conditions for malicious traffic detection. Existing machine learning (ML)-based approaches, typically trained on static single-domain datasets, often fail to generalize across heterogeneous network environments. To address this gap, we develop a realistic Docker-NS3-based testbed that emulates both IoT and traditional traffic conditions, enabling the generation and capture of live, labeled network flows. The resulting M-En Dataset combines this traffic with curated public PCAP traces to provide comprehensive coverage of benign and malicious behaviors. Building on this foundation, we propose Multi-LF, a real-time continuous learning framework that combines a lightweight model (M1) for rapid detection with a deeper model (M2) for high-confidence refinement and adaptation. A confidence-based coordination mechanism enhances efficiency without compromising accuracy, while weight interpolation mitigates catastrophic forgetting during continuous updates. Features extracted at 1-second intervals capture fine-grained temporal patterns, enabling early recognition of evolving attack behaviors. Implemented and evaluated within the Docker-NS3 testbed on live traffic, Multi-LF achieves an accuracy of 0.999 while requiring human intervention for only 0.0026 percent of packets, demonstrating its effectiveness and practicality for real-time malicious traffic detection in heterogeneous network environments.

Large Foundation Models (LFMs), including multi-modal and generative models, promise to unlock new capabilities for next-generation Edge AI applications. However, performing inference with LFMs in resource-constrained and heterogeneous edge environments, such as Multi-access Edge Computing (MEC), presents significant challenges for workload orchestration due to time-varying network, compute, and storage conditions. In particular, current split inference strategies, which partition LFM layers across nodes, are not designed to adapt to fluctuating workloads, dynamic bandwidth conditions, or evolving privacy constraints in high-utilization MEC environments. In this work, we propose a novel adaptive split inference orchestration framework that elevates both the placement and partitioning of LFM layers to runtime-tunable variables. Specifically, our framework enables real-time, quality-of-service (QoS)-aware management of inference workloads by extending conventional orchestrators with three key services: (1) Capacity-aware workload distribution, which continuously profiles node resources and selects an optimal subset of MEC nodes; (2) Dynamic partition migration, which transparently relocates pre-cut LFM segments in response to changes in utilization or network conditions; (3) Real-time reconfiguration, which dynamically re-splits LFM layers to balance latency, throughput, and privacy. We formalize the joint placement-partitioning problem, outline a reference architecture and algorithmic workflow, and discuss applicability in representative smart city, V2X, and industrial edge scenarios.

This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1. Built on three core principles -- diversity, deliberative reasoning, and rigorous filtering -- STAR-1 aims to address the critical needs for safety alignment in LRMs. Specifically, we begin by integrating existing open-source safety datasets from diverse sources. Then, we curate safety policies to generate policy-grounded deliberative reasoning samples. Lastly, we apply a GPT-4o-based safety scoring system to select training examples aligned with best practices. Experimental results show that fine-tuning LRMs with STAR-1 leads to an average 40% improvement in safety performance across four benchmarks, while only incurring a marginal decrease (e.g., an average of 1.1%) in reasoning ability measured across five reasoning tasks. Extensive ablation studies further validate the importance of our design principles in constructing STAR-1 and analyze its efficacy across both LRMs and traditional LLMs. Our project page is https://ucsc-vlaa.github.io/STAR-1.

Common knowledge is crucial for safe group coordination. In its absence, humans must rely on shared knowledge, which is inherently limited in depth and therefore prone to coordination failures, because any finite-order knowledge attribution allows for an even higher order attribution that may change what is known by whom. In three separate experiments involving 802 participants, we investigate the extent to which humans can differentiate between common knowledge and nth-order shared knowledge. We designed a two-person coordination game with imperfect information to simplify the recursive game structure and higher-order uncertainties into a relatable everyday scenario. In this game, coordination for the highest payoff requires a specific fact to be common knowledge between players. However, this fact cannot become common knowledge in the game. The fact can at most be nth-order shared knowledge for some n. Our findings reveal that even at quite shallow depths of shared knowledge (low values of n), players behave as though they possess common knowledge, and claim similar levels of certainty in their actions, despite incurring significant penalties when falsely assuming guaranteed coordination. We term this phenomenon 'the curse of shared knowledge'. It arises either from the players' inability to distinguish between higher-order shared knowledge and common knowledge, or from their implicit assumption that their co-player cannot make this distinction.

Large language models (LLMs) increasingly operate in social contexts, motivating analysis of how they express and shift moral judgments. In this work, we investigate the moral response of LLMs to persona role-play, prompting a LLM to assume a specific character. Using the Moral Foundations Questionnaire (MFQ), we introduce a benchmark that quantifies two properties: moral susceptibility and moral robustness, defined from the variability of MFQ scores across and within personas, respectively. We find that, for moral robustness, model family accounts for most of the variance, while model size shows no systematic effect. The Claude family is, by a significant margin, the most robust, followed by Gemini and GPT-4 models, with other families exhibiting lower robustness. In contrast, moral susceptibility exhibits a mild family effect but a clear within-family size effect, with larger variants being more susceptible. Moreover, robustness and susceptibility are positively correlated, an association that is more pronounced at the family level. Additionally, we present moral foundation profiles for models without persona role-play and for personas averaged across models. Together, these analyses provide a systematic view of how persona conditioning shapes moral behavior in large language models.

The evolution of mathematics has been guided in part by interestingness. From researchers choosing which problems to tackle next, to students deciding which ones to engage with, people's choices are often guided by judgments about how interesting or challenging problems are likely to be. As AI systems, such as LLMs, increasingly participate in mathematics with people -- whether for advanced research or education -- it becomes important to understand how well their judgments align with human ones. Our work examines this alignment through two empirical studies of human and LLM assessment of mathematical interestingness and difficulty, spanning a range of mathematical experience. We study two groups: participants from a crowdsourcing platform and International Math Olympiad competitors. We show that while many LLMs appear to broadly agree with human notions of interestingness, they mostly do not capture the distribution observed in human judgments. Moreover, most LLMs only somewhat align with why humans find certain math problems interesting, showing weak correlation with human-selected interestingness rationales. Together, our findings highlight both the promises and limitations of current LLMs in capturing human interestingness judgments for mathematical AI thought partnerships.

We present Large Sign Language Models (LSLM), a novel framework for translating 3D American Sign Language (ASL) by leveraging Large Language Models (LLMs) as the backbone, which can benefit hearing-impaired individuals' virtual communication. Unlike existing sign language recognition methods that rely on 2D video, our approach directly utilizes 3D sign language data to capture rich spatial, gestural, and depth information in 3D scenes. This enables more accurate and resilient translation, enhancing digital communication accessibility for the hearing-impaired community. Beyond the task of ASL translation, our work explores the integration of complex, embodied multimodal languages into the processing capabilities of LLMs, moving beyond purely text-based inputs to broaden their understanding of human communication. We investigate both direct translation from 3D gesture features to text and an instruction-guided setting where translations can be modulated by external prompts, offering greater flexibility. This work provides a foundational step toward inclusive, multimodal intelligent systems capable of understanding diverse forms of language.

Mastering fine-grained visual recognition, essential in many expert domains, can require that specialists undergo years of dedicated training. Modeling the progression of such expertize in humans remains challenging, and accurately inferring a human learner's knowledge state is a key step toward understanding visual learning. We introduce CleverBirds, a large-scale knowledge tracing benchmark for fine-grained bird species recognition. Collected by the citizen-science platform eBird, it offers insight into how individuals acquire expertize in complex fine-grained classification. More than 40,000 participants have engaged in the quiz, answering over 17 million multiple-choice questions spanning over 10,000 bird species, with long-range learning patterns across an average of 400 questions per participant. We release this dataset to support the development and evaluation of new methods for visual knowledge tracing. We show that tracking learners' knowledge is challenging, especially across participant subgroups and question types, with different forms of contextual information offering varying degrees of predictive benefit. CleverBirds is among the largest benchmark of its kind, offering a substantially higher number of learnable concepts. With it, we hope to enable new avenues for studying the development of visual expertize over time and across individuals.