论文检索

Matteo Baldoni, Cristina Baroglio, Monica Bucciarelli, Sara Capecchi, Leonardo Castellani, Elena Gandolfi, Francesco Ianì, Elisa Marengo, Roberto Micalizio

Theory of mind refers to the attribution of mental states that humans ascribe to other humans or objects (such as computer-based systems). Recently, the attribution of mental states has been investigated toward Artificial Intelligence (AI) as a basic manner to capture people's engagement toward it, and people's perception about AI social skills and AI capabilities. In line with this idea, mental state attribution can be used as an indirect measure of students' understanding of AI functioning, and in particular of the kind of interactions students may have with AI systems. Too often is the case of people using generative AI systems in ways that exceed their actual ways of functioning. In our study, children of age in the range 9-12 were involved in one-shot unplugged activities concerning data and models. The unplugged activities were not aimed at teaching the theory of Machine Learning, but rather they were designed so as to provide awareness on some basic mechanisms and help developing a correct use of tools that are becoming more and more present in everyday life. This paper introduces the activities and reports the results that were achieved.

Muhammad Azeem, Hoang D. Nguyen, Rosane Minghim

Artificial intelligence offers powerful methods for audio processing and analysis. Still, complex workflows and the required programming skills often limit access for students and domain experts, such as marine bioacousticians and soundscape ecologists. We present "AI EcoSound Tutor", a code-free and interactive tool that lowers these barriers by allowing users to construct and explore a complete AI pipeline for audio data analysis. Starting from raw recordings, users can choose from various feature extraction techniques (MFCC, OpenL3), apply dimensionality reduction methods (PCA, t-SNE, UMAP), and optionally perform unsupervised clustering (K-Means, GMM,HDBSCAN). The results are displayed with an interactive 2D visualisation where the user can compare multiple plots by employing various techniques, including PCA and t-SNE. Interactive plots enable the selection of points or clusters of interest, allowing exploration of spectrograms within the desired frequency range, and playing an audio clip corresponding to the selected points. An integrated "Help" feature provides explanations of each method (i.e., what it is, how it works, and its practical use in different domains, such as bioacoustics), fostering both conceptual understanding and useful skill acquisition as learning outcomes. For precomputed features or embeddings, this tool also supports training and evaluating a variety of machine learning models, providing visual feedback on the results. By merging accessibility, interactivity, pedagogy, and domain relevance, our application demystifies AI methods for interdisciplinary education and supporting research in audio analysis.

Cornelius O Adejoro, Oghenemaro Anuyah, Ali Raza, Karla Badillo-Urquiola, Tom Yeh

With artificial intelligence (AI) becoming more present in ed- ucation globally, it is essential to consider how cultural con- texts shape teachers’ perspectives, an understanding that sup- ports more inclusive and sustainable learning systems. This study draws on the African philosophy of Ubuntu to frame our cross-cultural investigation of how children conceptu- alize AI through the lens of their teachers. We conducted semi-structured interviews with twelve middle school teach- ers in Nigeria and the United States, asking them to interpret AI-themed essays written by students. These teacher reflec- tions revealed differing educational priorities, cultural val- ues, and infrastructural realities: U.S. educators’ interpreta- tions centered on personal development and future careers, while Nigerian teachers highlighted students’ focus on fam- ily, community well-being, and practical societal challenges. Nigerian participants also pointed to the need for improved infrastructure (e.g., electricity, internet), broader AI literacy, and education policies that reflect local needs. Our findings il- lustrate how culturally grounded worldviews, such as Ubuntu, shape interpretations of AI and its role in society, and sug- gest that AI education is never culturally neutral. We argue that AI literacy initiatives must be designed not only to teach technical skills but also to support educational sustainability, defined here as inclusive, resilient, and culturally responsive learning systems capable of evolving within diverse contexts. We offer actionable recommendations for the HCI commu- nity to co-design AI education tools that foreground collec- tive well-being, foster global digital citizenship, and reduce epistemic exclusion in the development of future technolo- gies.

Mehdi Yekrangi, Houssem Chatbri, Claudia Beatrice Chianella, Owen O'Neill

The increasing adoption of large language models in the fi-nancial sector introduces significant challenges related to the handling of sensitive financial information (SFI). Existing general-purpose content safety solutions, or guardrails, often fall short in detecting domain-specific risks inherent in finan-cial data processing. This study addresses these gaps by de-veloping a comprehensive taxonomy of SFI, grounded in globally recognized financial, information security, and AI governance standards. Leveraging this taxonomy, we synthe-sized an extensive dataset encompassing diverse categories of SFI and trained GARD (Generative Adversarial network Risk Detection) model to detect sensitive content in both in-puts and outputs of GenAI systems within the financial do-main. Our evaluation compared GARD against commercial guardrail solutions, including the OpenAI Moderation API and Microsoft Azure Content Safety (ACS). The results demonstrated that while commercial solutions maintained high precision, their recall was substantially lower, indicating many risky instances went undetected. In contrast, our model achieved a recall score of 0.98, significantly outperforming the benchmarks and enhancing SFI detection. These findings underscore the necessity of domain-specific guardrails tai-lored to the financial sector to ensure robust AI safety and compliance. In conclusion, this work contributes (1) A de-tailed taxonomy of SFI tailored for GenAI applications, (2) A comprehensive synthetic dataset that encompasses a wide range of sensitive topics relevant to the domain and (3) A high-performance risk detection model that can be deployed independently or alongside existing solutions to improve con-tent safety in financial services. This approach promotes trust, mitigates financial, legal, and reputational risks, and supports the responsible adoption of GenAI technologies in sensitive domains.

Yuze Sun, Wentao Luo, Yanfei Xiang, Jiancheng Pan, Jiahao Li, Quan Zhang, Xiaomeng Huang

With the growing role of artificial intelligence in climate and weather research, efficient model training and inference are in high demand. Current models like FourCastNet and AI-GOMS depend heavily on GPUs, limiting hardware independence, especially for Chinese domestic hardware and frameworks. To address this issue, we present a framework for migrating large-scale atmospheric and oceanic models from PyTorch to MindSpore and optimizing for Chinese chips, and evaluating their performance against GPUs. The framework focuses on software-hardware adaptation, memory optimization, and parallelism. Furthermore, the model's performance is evaluated across multiple metrics, including training speed, inference speed, model accuracy, and energy efficiency, with comparisons against GPU-based implementations. Experimental results demonstrate that the migration and optimization process preserves the models' original accuracy while significantly reducing system dependencies and improving operational efficiency by leveraging Chinese chips as a viable alternative for scientific computing. This work provides valuable insights and practical guidance for leveraging Chinese domestic chips and frameworks in atmospheric and oceanic AI model development, offering a pathway toward greater technological independence.

Nitin Gupta, Pallav Koppisetti, Kausik Lakkaraju, Biplav Srivastava

The rapid proliferation of Generative AI (GenAI) into diverse, high-stakes domains necessitates robust and reproducible evaluation methods. However, practitioners often resort to ad-hoc, non-standardized scripts, as common metrics are often unsuitable for specialized, structured outputs (e.g., automated plans, time-series) or holistic comparison across modalities (e.g., text, audio, and image). This fragmentation hinders comparability and slows AI system development. To address this challenge, we present GAICo (Generative AI Comparator): a deployed, open-source Python library that streamlines and standardizes GenAI output comparison. GAICo provides a unified, extensible framework supporting a comprehensive suite of reference-based metrics for unstructured text, specialized structured data formats, and multimedia (images, audio). Its architecture features a high-level API for rapid, end-to-end analysis, from multi-model comparison to visualization and reporting, alongside direct metric access for granular control. We demonstrate GAICo's utility through a detailed case study evaluating and debugging complex, multi-modal AI Travel Assistant pipelines. GAICo empowers AI researchers and developers to efficiently assess system performance, make evaluation reproducible, improve development velocity, and ultimately build more trustworthy AI systems, aligning with the goal of moving faster and safer in AI deployment. Since its release on PyPI in Jun 2025, the tool has been downloaded over 16K times, across versions, by Dec 2025, demonstrating growing community interest.

Ziming Dai, Tuo Zhang, Fei Gao, Xingyi Cai, Xiaofei Wang, Cheng Zhang, Wenyu Wang, Chengjie Zang

The growing industrial demand for customized and cost-efficient large language models (LLMs) is fueled by the rise of vertical, domain-specific tasks and the need to optimize performance under constraints such as latency and budget. Knowledge distillation, as an efficient model compression and transfer technique, offers a feasible solution. However, existing distillation frameworks often require manual intervention and struggle to meet such complex user-defined distillation requirements. To bridge this gap, we propose Stratos, an end-to-end LLM distillation pipeline that automates server/model selection, knowledge distillation, and deployment in distributed cloud environments. Given user-defined constraints on model performance and system budget, Stratos automatically selects Pareto-optimal servers, dynamically matches teacher–student pairs, and adapts distillation strategies based on task complexity to optimize cloud hosting. Experiments show that Stratos produces a student model that achieves four times the accuracy of its GPT-4o teacher baseline on a rare, domain-specific Mahjong reasoning task with reverse synthetic data and knowledge injection. Moreover, it achieves reduced latency and cost without compromising accuracy. These results highlight its promise for vertical-domain LLM deployment.

Yupeng Zhuo, Eddie Zhang, Xiangchen Yu, Aditya Pachpande, Andrew W. Kirkpatrick, Jessica Mckee, Juan Wachs

We introduce Trauma THOMPSON, a dataset and suite of benchmarks designed to accelerate the development of AI-powered copilots for real-time decision-making in emergency and resource-limited medical settings. This work proposes a method to address a critical bottleneck for future deployment: models trained on simulations may not perform well in the real world. The dataset features 3,717 unscripted, first-person video clips of five emergency procedures, uniquely including "just-in-time" (JIT) interventions that mirror the improvisational nature of field medicine. To obtain realistic patient data without ethical issues and identity concerns that medical data often encounter, we also propose TraumaGen, a novel framework for generating photorealistic patient and wound images from manikins while preserving clinical context. We establish benchmarks for action recognition, anticipation, and visual question answering (VQA), evaluating state-of-the-art models to demonstrate the challenges and potential of our dataset. By focusing on realism and improvisation, Trauma THOMPSON provides a crucial resource and a clear path toward developing and validating robust AI assistants for future deployment in real-world emergency care.

Julian Zhong-Nan Zhang, Yang Yu

The reliable deployment of reinforcement learning (RL) for real-world algorithmic trading is critically hindered by the ``simulation-to-reality gap.'' Standard industry backtesting on static historical data ignores market impact—the feedback loop where an agent's trades influence price dynamics—leading to strategies that are fragile and untrustworthy in live markets. To solve this significant problem, we present a novel and emerging application of AI: a framework for building an interactive, responsive market simulator. Our system first uses imitation learning (IL) to automatically train an ensemble of agents, each learning a distinct trading strategy from a different historical market regime (e.g., bull, bear). This creates a data-driven proxy for a diverse population of real-world traders. We then deploy an innovative Action Synthesis Network to synthesize the actions of this ensemble, generating a realistic, synthetic price trajectory that endogenously models the market's reaction to trades. This interactive environment is then used to train a final RL policy. We evaluate our system on NASDAQ-100 (QQQ) data, and the results demonstrate strong potential for deployment. The RL policy trained in our responsive simulator achieves significantly more robust performance, exhibiting superior downside protection during market downturns compared to various traditional baselines. This application provides a scalable and technically sound methodology for building more realistic training environments, presenting a clear path toward the development and eventual deployment of more resilient and effective algorithmic trading strategies.

Xu Wang, Jiaju Kang, Puyu Han, Zeyu Ai, Luqi Gong

Long-form science fiction generation demands rigorous maintenance of narrative coherence across evolving plots, character dynamics, and speculative world-building. We propose Octopus, an entropy-controlled neural framework with persistent memory-context binding that addresses these challenges through two key innovations: 1) dynamic entropy regulation balancing creativity and structural stability via narrative divergence thresholds, and 2) hierarchical memory architecture preserving character states, plot events, and scientific rules over 10K+ token spans. Evaluations across 12 sci-fi subgenres demonstrate Octopus's superiority over GPT-4 and ReAlign baselines, achieving 15.2% higher coherence scores (SciClarity) and 62% fewer contextual contradictions in extended narratives. Human evaluations confirm its effectiveness in maintaining speculative logic (4.7/5 vs. 3.1/5 baseline) while preserving creative diversity. The framework resolves the "hard sci-fi paradox" of enforcing scientific rigor without compromising narrative flexibility, establishing new capabilities for AI-assisted cross-media universe development.

Qixin Wang, Dawei Wang, Kun Chen, Yaowei Hu, Puneet Girdhar, Ruoteng Wang, Aadesh Gupta, Chaitanya Devella, Wenlai Guo, Shangwen Huang 等

In recent years, recommendation systems have evolved from providing a single list of recommendations to offering a comprehensive suite of topic-focused services. To better accomplish this task, conversational recommendation systems (CRS) have progressed from basic retrieval-augmented LLM generation to agentic systems with advanced reasoning and self-correction capabilities. However, agentic systems come with notable response latency—a longstanding challenge for conversational recommendation systems. To balance the trade-off between handling complex queries and minimizing latency, we propose AdaptJobRec, the first conversational job recommendation system that leverages autonomous agent to integrate personalized recommendation algorithm tools. The system employs a user query complexity identification mechanism to minimize response latency. For straightforward queries, the agent directly selects the appropriate tool for rapid responses. For complex queries, the agent uses the memory processing module to filter chat history for relevant content, then passes the results to the intelligent task decomposition planner, and finally executes the tasks using personalized recommendation tools. Evaluation on Walmart’s real-world career recommendation scenarios demonstrates that AdaptJobRec reduces average response latency by up to 53.3\% compared to competitive baselines, while significantly improving recommendation accuracy.

Chibuike E. Ugwu, Roschelle Fritz, Diane J. Cook, Jana Doppa

Urinary tract infection (UTI) flare-ups pose a significant health risk for older adults with chronic conditions. These infections often go unnoticed until they become severe, making early detection through innovative smart home technologies crucial. Traditional machine learning (ML) approaches relying on simple binary classification for UTI detection offer limited utility to nurses and practitioners as they lack insight into prediction uncertainty, hindering informed clinical decision-making. This paper presents a clinician-in-the-loop (CIL) smart home system that leverages ambient sensor data to extract meaningful behavioral markers, train robust predictive ML models, and calibrate them to enable uncertainty-aware decision support. The system incorporates a statistically valid uncertainty quantification method called Conformal-Calibrated Interval (CCI), which quantifies uncertainty and abstains from making predictions ("I don’t know") when the ML model's confidence is low. Evaluated on real-world data from eight smart homes, our method outperforms baseline methods in recall and other classification metrics while maintaining the lowest abstention proportion and interval width. A survey of 42 nurses confirms that our system's outputs are valuable for guiding clinical decision-making, underscoring their practical utility in improving informed decisions and effectively managing UTIs and other condition flare-ups in older adults.

Gregory Hok Tjoan Go, Khang Ly, Anders Søgaard, Seyed Amin Tabatabaei, Maarten de Rijke, Xinyi Chen

The rapid growth of scientific publications has made it increasingly difficult to keep literature reviews comprehensive and up-to-date. Though prior work has focused on automating retrieval and screening, the writing phase of systematic reviews remains largely under-explored, especially with regard to readability and factual accuracy. To address this, we present LiRA (Literature Review Agents), a multi-agent collaborative workflow which emulates the human literature review process. LiRA utilizes specialized agents for content outlining, subsection writing, editing, and reviewing, producing cohesive and comprehensive review articles. Evaluated on SciReviewGen and a proprietary ScienceDirect dataset, LiRA outperforms current baselines such as AutoSurvey and MASS-Survey in writing and citation quality, while maintaining competitive similarity to human-written reviews. We further evaluate LiRA in real-world scenarios using document retrieval and assess its robustness to reviewer model variation. Our findings highlight the potential of agentic LLM workflows, even without domain-specific tuning, to improve the reliability and usability of automated scientific writing.

Arpit Tiwari, Bhavuk Singhal, Anshu Aditya, Aryan Tiwari, Shubham Jain, Debashis Mukherjee, Debdoot Mukherjee

In e-commerce logistics, accurate geospatial clustering is essential for optimizing resource allocation, manpower planning, and delivery network design. However, existing density-based clustering approaches, particularly their reliance on heuristic parameter tuning, have been underexplored in datasets with significant density variations, limiting robustness and scalability. This study presents an unsupervised framework that extends DBSCAN by leveraging Gaussian Mixture Models (GMM). First, we propose a method that systematically identifies suitable clustering scales through statistical modeling. Second, the approach iteratively applies DBSCAN to extract clusters from dense to sparse regions, overcoming single-parameter limitations. Finally, we validate the method through large-scale offline experiments using data from over 200 last-mile dispatch centers (LMDC). The results demonstrate the framework’s effectiveness in identifying heterogeneous geographic demand patterns and supporting workforce planning and operational benchmarking. This framework provides a scalable solution to a critical challenge in e-commerce logistics, offering a valuable reference for strategic and operational decision-making.

Budhitama Subagdja, Shanthoshigaa D, Ah-Hwee Tan, Iris Rawtaer

This paper introduces a novel system for in-home cognitive health assessment using ambient sensors and a machine learning technology that can robustly detect mild cognitive impairment (MCI) despite limited available data. The learned model can explain the aspects of individuals' daily lives led to the prediction, while reliably predicting MCI, providing more insights to healthcare workers for further clinical interventions. We developed the robust transparent machine learning model, based on fusion adaptive resonance theory (Fusion ART) neural network to learn individuals' daily patterns of activity from continuous sensor data in terms of a suite of digital biomarkers reflecting four key domains: physical, daily activity, cognitive engagement, and sleep patterns. Based on a longitudinal study of over one hundred participants, deployed with non-intrusive sensors in their homes to undergo parallel clinical evaluation across a period of five years, our model successfully identified individuals with MCI, achieving high predictive accuracy regardless the noisy and sparse availability of data. As a transparent neural network, the learned model can also be interpreted as classification rules to distinguish MCI from normal cognition (NC) cases based on the digital biomarkers. These results demonstrate that passively collected, sensor-derived digital biomarkers can be leveraged to indicate cognitive status and potentially providing clinically meaningful insights on the impairment conditions. We also discuss the practical challenges and lessons learned from this real-world deployment to inform future large-scale implementations of such AI-driven health monitoring systems.

Chathurangi Shyalika, Aryaman Sharma, Fadi El Kalach, Utkarshani Jaimini, Cory Henson, Ramy Harik, Amit Sheth

Modern manufacturing environments demand not only accurate predictions but also interpretable insights to process anomalies, root causes, and potential interventions. Existing AI systems often function as isolated black boxes, lacking the seamless integration of prediction, explanation, and causal reasoning required for a unified decision-support solution. This fragmentation limits their trustworthiness and practical utility in high-stakes industrial environments. In this work, we present CausalTrace, a neurosymbolic causal analysis module integrated into the SmartPilot industrial CoPilot. CausalTrace performs data-driven causal analysis enriched by industrial ontologies and knowledge graphs, including advanced functions such as causal discovery, counterfactual reasoning, and root cause analysis (RCA). It supports real-time operator interaction and is designed to complement existing agents by offering transparent, explainable decision support. We conducted a comprehensive evaluation of CausalTrace using multiple causal assessment methods and the C3AN framework (i.e. Custom, Compact, Composite AI with Neurosymbolic Integration), which spans principles of robustness, intelligence, and trustworthiness. In an academic rocket assembly testbed, CausalTrace achieved substantial agreement with domain experts (ROUGE-1: 0.91 in ontology QA) and strong RCA performance (MAP@3: 94%, PR@2: 97%, MRR: 0.92, Jaccard: 0.92). It also attained 4.59/5 in the C3AN evaluation, demonstrating precision and reliability for live deployment.

Segev Shlomov, Alon Oved, Sami Marreed, Ido Levy, Offer Akrabi, Avi Yaeli, Łukasz Strąk, Elizabeth Koumpan, Yinon Goldshtein, Eilam Shapira 等

Agents are rapidly advancing in automating digital work, but enterprises face a harder challenge: moving beyond prototypes to deployed systems that deliver measurable business value. This path is complicated by fragmented frameworks, slow development, and the absence of standardized evaluation practices. Generalist agents have emerged as a promising direction, excelling on academic benchmarks and offering flexibility across tasks, applications, and modalities. Yet, evidence of their use in enterprise settings remains limited. This paper reports IBM’s experience developing and piloting the Computer Using Generalist Agent (CUGA). CUGA adopts a hierarchical planner--executor architecture with strong analytical foundations, achieving state-of-the-art performance on AppWorld and WebArena. Beyond benchmarks, it was evaluated in a Business-Process-Outsourcing talent acquisition pilot, addressing enterprise requirements for scalability, auditability, safety, and governance. In preliminary evaluations, CUGA approached the accuracy of specialized agents while suggesting reductions in development time and cost. We provide early evidence that generalist agents can operate at enterprise scale, distill key technical and organizational lessons, and outline requirements for transitioning research-grade architectures like CUGA into enterprise-ready systems.

Benedikt Schlereth-Groh, Sakir Furkan Yöndem, Ramin Tavakoli Kolagari

Reinforcement Learning (RL) has shown significant promise in developing autonomous navigation algorithms for complex environments. However, the direct application of RL policies trained in simulation to real-world scenarios often faces challenges due to the reality gap. This paper proposes a two-stage system incorporating a segmentation strategy and a bird’s-eye-view (BEV) representation to mitigate the domain gap between simulation and reality. In the first stage, the segmentation transforms sensor data into a simplified and interpretable representation of the surrounding area, facilitating transferability across different deployments. In the second stage, the agent navigates through the BEV map, which can be trained using a vectorized simulation environment---a setup that runs multiple parallel instances of the environment to provide a wide range of training scenarios. This vectorization enables rapid exposure to varied environmental conditions, thereby accelerating and diversifying the training of a deep RL agent to achieve optimal navigation behaviors while maintaining high-speed, in-bound trajectories. The segmentation is crucial because it supports generalization of the learned policy across different robotic platforms. The contribution of this paper lies in combining real-time semantic segmentation with a bird’s-eye-view navigation policy, resulting in a transferable and scalable framework for real-world deployment of RL-based navigation agents. Experimental results demonstrate that agents trained with this methodology exhibit robust navigation performance and adaptability in both simulated and real-world environments, validating the efficacy of combining vectorized simulation with real-world segmentation for practical robotic navigation.

Uttam Rao, Madhav Marathe

Bibliometric and science-of-science studies have yielded valuable insights into co-authorship and citation networks, yet most analyses rely on static datasets and limited relation types. We introduce a multi-agent AI architecture that orchestrates specialized large language model (LLM) agents (ingestion, extraction, disambiguation, integration, and analysis) to build and query a comprehensive knowledge graph. Ingestion agents unify data from diverse sources such as OpenAlex, ORCID, ROR, USPTO, and custom web scrapers. Extraction agents harness LLMs to parse unstructured text. Disambiguation agents combine rule-based heuristics with LLM reasoning to resolve ambiguous authors and institutions. Integration agents assemble and cache a provenance-rich graph. An analysis agent translates natural language questions into graph queries and interprets results. This end-to-end pipeline produces a rich graph schema spanning authors, institutions, publications, patents, grants, topics, and temporal relations. Researcher mobility and knowledge diffusion are then modeled as timed automata, where each researcher node’s institutional transitions and accumulated attributes (such as publications, collaborators, and topic expertise) enable dynamic temporal reasoning. Results show that our multi-agent, graph-based system consistently outperforms standalone LLMs and research agents on complex temporal queries, entity disambiguation accuracy, and cross-entity reasoning while maintaining competitive efficiency. These capabilities position the system as a foundation for real-time, LLM-assisted knowledge analysis platforms that can support science policy, research evaluation, and meta-scientific inquiry.

Md Masudur Rahman, Mohamed El Masry, Gayle Gordillo, Juan Wachs

In emerging clinical applications such as ultrasound-based burn assessment, the lack of domain-specific data presents a significant challenge for developing robust AI systems. Vision-language models (VLMs) have shown strong performance in general computer vision tasks, yet their application to medical imaging remains limited, particularly due to insufficient reasoning capabilities and the scarcity of high-quality training data. We introduce AURA (Automated Unified Reasoning for Burn Assessment), a multi-modal approach that integrates pre-trained VLMs with symbolic first-order logic (FOL) reasoning to improve diagnostic accuracy and interpretability in this data-limited setting. For this study, we collected real-patient data over a one-year period at a U.S. burn center, performing all experiments in a real clinical setting to ensure practical relevance. The dataset includes both conventional B-Mode ultrasound and Tissue Doppler Imaging (TDI), with TDI introduced here for the first time in burn assessment, underscoring the emerging nature of this work. Beyond burn severity classification, we assess the system’s ability to produce expert-level surgical insight directly from imaging data. On the retrospective dataset, it achieves up to 93% accuracy in surgical classification and 87% in fine-grained burn depth prediction, comparable to expert-informed predictions and substantially exceeding the 70% accuracy of traditional visual inspection by human experts. These results, obtained from a novel multi-modal dataset collected in a real clinical burn center setting, highlight the potential of this approach to improve decision-making in burn care. To further support future deployment, we demonstrate a prototype integration with an Electronic Medical Record (EMR) system that aligns with clinical workflows and supports scalable, real-world implementation.