Authors: Henrique Correia da Fonseca, Ant\'onio Fernandes, Zhao Song, Theodor Cimpeanu, Nataliya Balabanova, Adeela Bashir, Paolo Bova, Alessio Buscemi, Alessandro Di Stefano, Manh Hong Duong, Elias Fernandez Domingos, Ndidi Bianca Ogbo, Simon T. Powers, Daniele Proverbio, Zia Ush Shamszaman, Fernando P. Santos, The Anh Han, Marcus Krellner
Abstract: When developers of artificial intelligence (AI) products need to decide between profit and safety for the users, they likely choose profit. Untrustworthy AI technology must come packaged with tangible negative consequences. Here, we envisage those consequences as the loss of reputation caused by media coverage of their misdeeds, disseminated to the public. We explore whether media coverage has the potential to push AI creators into the production of safe products, enabling widespread adoption of AI technology. We created artificial populations of self-interested creators and users and studied them through the lens of evolutionary game theory. Our results reveal that media is indeed able to foster cooperation between creators and users, but not always. Cooperation does not evolve if the quality of the information provided by the media is not reliable enough, or if the costs of either accessing media or ensuring safety are too high. By shaping public perception and holding developers accountable, media emerges as a powerful soft regulator -- guiding AI safety even in the absence of formal government oversight.
Authors: Andrew Ferguson, Marisa LaFleur, Lars Ruthotto, Jesse Thaler, Yuan-Sen Ting, Pratyush Tiwary, Soledad Villar, E. Paulo Alves, Jeremy Avigad, Simon Billinge, Camille Bilodeau, Keith Brown, Emmanuel Candes, Arghya Chattopadhyay, Bingqing Cheng, Jonathan Clausen, Connor Coley, Andrew Connolly, Fred Daum, Sijia Dong, Chrisy Xiyu Du, Cora Dvorkin, Cristiano Fanelli, Eric B. Ford, Luis Manuel Frutos, Nicol\'as Garc\'ia Trillos, Cecilia Garraffo, Robert Ghrist, Rafael Gomez-Bombarelli, Gianluca Guadagni, Sreelekha Guggilam, Sergei Gukov, Juan B. Guti\'errez, Salman Habib, Johannes Hachmann, Boris Hanin, Philip Harris, Murray Holland, Elizabeth Holm, Hsin-Yuan Huang, Shih-Chieh Hsu, Nick Jackson, Olexandr Isayev, Heng Ji, Aggelos Katsaggelos, Jeremy Kepner, Yannis Kevrekidis, Michelle Kuchera, J. Nathan Kutz, Branislava Lalic, Ann Lee, Matt LeBlanc, Josiah Lim, Rebecca Lindsey, Yongmin Liu, Peter Y. Lu, Sudhir Malik, Vuk Mandic, Vidya Manian, Emeka P. Mazi, Pankaj Mehta, Peter Melchior, Brice M\'enard, Jennifer Ngadiuba, Stella Offner, Elsa Olivetti, Shyue Ping Ong, Christopher Rackauckas, Philippe Rigollet, Chad Risko, Philip Romero, Grant Rotskoff, Brett Savoie, Uros Seljak, David Shih, Gary Shiu, Dima Shlyakhtenko, Eva Silverstein, Taylor Sparks, Thomas Strohmer, Christopher Stubbs, Stephen Thomas, Suriyanarayanan Vaikuntanathan, Rene Vidal, Francisco Villaescusa-Navarro, Gregory Voth, Benjamin Wandelt, Rachel Ward, Melanie Weber, Risa Wechsler, Stephen Whitelam, Olaf Wiest, Mike Williams, Zhuoran Yang, Yaroslava G. Yingling, Bin Yu, Shuwen Yue, Ann Zabludoff, Huimin Zhao, Tong Zhang
Abstract: This community paper developed out of the NSF Workshop on the Future of Artificial Intelligence (AI) and the Mathematical and Physics Sciences (MPS), which was held in March 2025 with the goal of understanding how the MPS domains (Astronomy, Chemistry, Materials Research, Mathematical Sciences, and Physics) can best capitalize on, and contribute to, the future of AI. We present here a summary and snapshot of the MPS community's perspective, as of Spring/Summer 2025, in a rapidly developing field. The link between AI and MPS is becoming increasingly inextricable; now is a crucial moment to strengthen the link between AI and Science by pursuing a strategy that proactively and thoughtfully leverages the potential of AI for scientific discovery and optimizes opportunities to impact the development of AI by applying concepts from fundamental science. To achieve this, we propose activities and strategic priorities that: (1) enable AI+MPS research in both directions; (2) build up an interdisciplinary community of AI+MPS researchers; and (3) foster education and workforce development in AI for MPS researchers and students. We conclude with a summary of suggested priorities for funding agencies, educational institutions, and individual researchers to help position the MPS community to be a leader in, and take full advantage of, the transformative potential of AI+MPS.
Authors: Delong Chen, Theo Moutakanni, Willy Chung, Yejin Bang, Ziwei Ji, Allen Bolourchi, Pascale Fung
Abstract: Effective planning requires strong world models, but high-level world models that can understand and reason about actions with semantic and temporal abstraction remain largely underdeveloped. We introduce the Vision Language World Model (VLWM), a foundation model trained for language-based world modeling on natural videos. Given visual observations, the VLWM first infers the overall goal achievements then predicts a trajectory composed of interleaved actions and world state changes. Those targets are extracted by iterative LLM Self-Refine conditioned on compressed future observations represented by Tree of Captions. The VLWM learns both an action policy and a dynamics model, which respectively facilitates reactive system-1 plan decoding and reflective system-2 planning via cost minimization. The cost evaluates the semantic distance between the hypothetical future states given by VLWM roll-outs and the expected goal state, and is measured by a critic model that we trained in a self-supervised manner. The VLWM achieves state-of-the-art Visual Planning for Assistance (VPA) performance on both benchmark evaluations and our proposed PlannerArena human evaluations, where system-2 improves the Elo score by +27% upon system-1. The VLWM models also outperforms strong VLM baselines on RoboVQA and WorldPrediction benchmark.
Authors: Matthew Russo, Tim Kraska
Abstract: With advances in large language models (LLMs), researchers are creating new systems that can perform AI-driven analytics over large unstructured datasets. Recent work has explored executing such analytics queries using semantic operators -- a declarative set of AI-powered data transformations with natural language specifications. However, even when optimized, these operators can be expensive to execute on millions of records and their iterator execution semantics make them ill-suited for interactive data analytics tasks. In another line of work, Deep Research systems have demonstrated an ability to answer natural language question(s) over large datasets. These systems use one or more LLM agent(s) to plan their execution, process the dataset(s), and iteratively refine their answer. However, these systems do not explicitly optimize their query plans which can lead to poor plan execution. In order for AI-driven analytics to excel, we need a runtime which combines the optimized execution of semantic operators with the flexibility and more dynamic execution of Deep Research systems. As a first step towards this vision, we build a prototype which enables Deep Research agents to write and execute optimized semantic operator programs. We evaluate our prototype and demonstrate that it can outperform a handcrafted semantic operator program and open Deep Research systems on two basic queries. Compared to a standard open Deep Research agent, our prototype achieves up to 1.95x better F1-score. Furthermore, even if we give the agent access to semantic operators as tools, our prototype still achieves cost and runtime savings of up to 76.8% and 72.7% thanks to its optimized execution.
Authors: Mingyi Wang, Jingke Wang, Tengju Ye, Junbo Chen, Kaicheng Yu
Abstract: Recent breakthroughs in large language models (LLMs) have not only advanced natural language processing but also inspired their application in domains with structurally similar problems--most notably, autonomous driving motion generation. Both domains involve autoregressive sequence modeling, token-based representations, and context-aware decision making, making the transfer of LLM components a natural and increasingly common practice. However, despite promising early attempts, a systematic understanding of which LLM modules are truly transferable remains lacking. In this paper, we present a comprehensive evaluation of five key LLM modules--tokenizer design, positional embedding, pre-training paradigms, post-training strategies, and test-time computation--within the context of motion generation for autonomous driving. Through extensive experiments on the Waymo Sim Agents benchmark, we demonstrate that, when appropriately adapted, these modules can significantly improve performance for autonomous driving motion generation. In addition, we identify which techniques can be effectively transferred, analyze the potential reasons for the failure of others, and discuss the specific adaptations needed for autonomous driving scenarios. We evaluate our method on the Sim Agents task and achieve competitive results.
Authors: Ananth Hariharan, Vardhan Dongre, Dilek Hakkani-T\"ur, Gokhan Tur
Abstract: Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative verification framework in which a Judge LLM critiques action sequences and a Planner LLM applies the revisions, yielding progressively cleaner and more spatially coherent trajectories. Unlike rule-based approaches, our method relies on natural language prompting, enabling broad generalization across error types including irrelevant actions, contradictions, and missing steps. On a set of manually annotated actions from the TEACh embodied AI dataset, our framework achieves up to 90% recall and 100% precision across four state-of-the-art LLMs (GPT o4-mini, DeepSeek-R1, Gemini 2.5, LLaMA 4 Scout). The refinement loop converges quickly, with 96.5% of sequences requiring at most three iterations, while improving both temporal efficiency and spatial action organization. Crucially, the method preserves human error-recovery patterns rather than collapsing them, supporting future work on robust corrective behavior. By establishing plan verification as a reliable LLM capability for spatial planning and action refinement, we provide a scalable path to higher-quality training data for imitation learning in embodied AI.
Authors: V\'aclav Sobotka, Lucas Kletzander, Nysret Musliu, Hana Rudov\'a
Abstract: Cross-domain selection hyper-heuristics aim to distill decades of research on problem-specific heuristic search algorithms into adaptable general-purpose search strategies. In this respect, existing selection hyper-heuristics primarily focus on an adaptive selection of low-level heuristics (LLHs) from a predefined set. In contrast, we concentrate on the composition of this set and its strategic transformations. We systematically analyze transformations based on three key principles: solution acceptance, LLH repetitions, and perturbation intensity, i.e., the proportion of a solution affected by a perturbative LLH. We demonstrate the raw effects of our transformations on a trivial unbiased random selection mechanism. With an appropriately constructed transformation, this trivial method outperforms all available state-of-the-art hyper-heuristics on three challenging real-world domains and finds 11 new best-known solutions. The same method is competitive with the winner of the CHeSC competition, commonly used as the standard cross-domain benchmark. Moreover, we accompany several recent hyper-heuristics with such strategic transformations. Using this approach, we outperform the current state-of-the-art methods on both the CHeSC benchmark and real-world domains while often simplifying their designs.
Authors: Blai Bonet, Hector Geffner
Abstract: Combinatorial methods for learning general policies that solve large collections of planning problems have been recently developed. One of their strengths, in relation to deep learning approaches, is that the resulting policies can be understood and shown to be correct. A weakness is that the methods do not scale up and learn only from small training instances and feature pools that contain a few hundreds of states and features at most. In this work, we propose a new symbolic method for learning policies based on the generalization of sampled plans that ensures structural termination and hence acyclicity. The proposed learning approach is not based on SAT/ASP, as previous symbolic methods, but on a hitting set algorithm that can effectively handle problems with millions of states, and pools with hundreds of thousands of features. The formal properties of the approach are analyzed, and its scalability is tested on a number of benchmarks.
Authors: Leonidas Bakopoulos, Georgios Chalkiadakis
Abstract: Adaptive exploration methods propose ways to learn complex policies via alternating between exploration and exploitation. An important question for such methods is to determine the appropriate moment to switch between exploration and exploitation and vice versa. This is critical in domains that require the learning of long and complex sequences of actions. In this work, we present a generic adaptive exploration framework that employs uncertainty to address this important issue in a principled manner. Our framework includes previous adaptive exploration approaches as special cases. Moreover, we can incorporate in our framework any uncertainty-measuring mechanism of choice, for instance mechanisms used in intrinsic motivation or epistemic uncertainty-based exploration methods. We experimentally demonstrate that our framework gives rise to adaptive exploration strategies that outperform standard ones across several MuJoCo environments.
Authors: Prachi Bagave, Marcus Westberg, Marijn Janssen, Aaron Yi Ding
Abstract: AI is transforming the healthcare domain and is increasingly helping practitioners to make health-related decisions. Therefore, accountability becomes a crucial concern for critical AI-driven decisions. Although regulatory bodies, such as the EU commission, provide guidelines, they are highlevel and focus on the ''what'' that should be done and less on the ''how'', creating a knowledge gap for actors. Through an extensive analysis, we found that the term accountability is perceived and dealt with in many different ways, depending on the actor's expertise and domain of work. With increasing concerns about AI accountability issues and the ambiguity around this term, this paper bridges the gap between the ''what'' and ''how'' of AI accountability, specifically for AI systems in healthcare. We do this by analysing the concept of accountability, formulating an accountability framework, and providing a three-tier structure for handling various accountability mechanisms. Our accountability framework positions the regulations of healthcare AI systems and the mechanisms adopted by the actors under a consistent accountability regime. Moreover, the three-tier structure guides the actors of the healthcare AI system to categorise the mechanisms based on their conduct. Through our framework, we advocate that decision-making in healthcare AI holds shared dependencies, where accountability should be dealt with jointly and should foster collaborations. We highlight the role of explainability in instigating communication and information sharing between the actors to further facilitate the collaborative process.
Authors: Evgenii Kniazev, Arseny Kravchenko, Igor Rekun, James Broadhead, Nikita Shamgunov, Pranav Sah, Pratik Nichite, Ivan Yamshchikov
Abstract: We present app.build (https://github.com/appdotbuild/agent/), an open-source framework that improves LLM-based application generation through systematic validation and structured environments. Our approach combines multi-layered validation pipelines, stack-specific orchestration, and model-agnostic architecture, implemented across three reference stacks. Through evaluation on 30 generation tasks, we demonstrate that comprehensive validation achieves 73.3% viability rate with 30% reaching perfect quality scores, while open-weights models achieve 80.8% of closed-model performance when provided structured environments. The open-source framework has been adopted by the community, with over 3,000 applications generated to date. This work demonstrates that scaling reliable AI agents requires scaling environments, not just models -- providing empirical insights and complete reference implementations for production-oriented agent systems.
Authors: Yunxin Sun, Abulhair Saparov
Abstract: Reasoning is a core capability in artificial intelligence systems, for which large language models (LLMs) have recently shown remarkable progress. However, most work focuses exclusively on deductive reasoning, which is problematic since other types of reasoning are also essential in solving real-world problems, and they are less explored. This work focuses on evaluating LLMs' inductive and abductive reasoning capabilities. We introduce a programmable and synthetic dataset, InAbHyD (pronounced in-a-bid), where each reasoning example consists of an incomplete world model and a set of observations. The task for the intelligent agent is to produce hypotheses to explain observations under the incomplete world model to solve each reasoning example. We propose a new metric to evaluate the quality of hypotheses based on Occam's Razor. We evaluate and analyze some state-of-the-art LLMs. Our analysis shows that LLMs can perform inductive and abductive reasoning in simple scenarios, but struggle with complex world models and producing high-quality hypotheses, even with popular reasoning-enhancing techniques such as in-context learning and RLVR.
Authors: Peter J. Bentley, Soo Ling Lim, Fuyuki Ishikawa
Abstract: Agentic LLM AI agents are often little more than autonomous chatbots: actors following scripts, often controlled by an unreliable director. This work introduces a bottom-up framework that situates AI agents in their environment, with all behaviors triggered by changes in their environments. It introduces the notion of aspects, similar to the idea of umwelt, where sets of agents perceive their environment differently to each other, enabling clearer control of information. We provide an illustrative implementation and show that compared to a typical architecture, which leaks up to 83% of the time, aspective agentic AI enables zero information leakage. We anticipate that this concept of specialist agents working efficiently in their own information niches can provide improvements to both security and efficiency.
Authors: Yiyang Huang, Zixuan Wang, Zishen Wan, Yapeng Tian, Haobo Xu, Yinhe Han, Yiming Gan
Abstract: The integration of vision-language-action (VLA) models into embodied AI (EAI) robots is rapidly advancing their ability to perform complex, long-horizon tasks in humancentric environments. However, EAI systems introduce critical security risks: a compromised VLA model can directly translate adversarial perturbations on sensory input into unsafe physical actions. Traditional safety definitions and methodologies from the machine learning community are no longer sufficient. EAI systems raise new questions, such as what constitutes safety, how to measure it, and how to design effective attack and defense mechanisms in physically grounded, interactive settings. In this work, we present the first systematic study of adversarial safety attacks on embodied AI systems, grounded in ISO standards for human-robot interactions. We (1) formalize a principled taxonomy of safety violations (critical, dangerous, risky) based on physical constraints such as separation distance, velocity, and collision boundaries; (2) introduce ANNIEBench, a benchmark of nine safety-critical scenarios with 2,400 video-action sequences for evaluating embodied safety; and (3) ANNIE-Attack, a task-aware adversarial framework with an attack leader model that decomposes long-horizon goals into frame-level perturbations. Our evaluation across representative EAI models shows attack success rates exceeding 50% across all safety categories. We further demonstrate sparse and adaptive attack strategies and validate the real-world impact through physical robot experiments. These results expose a previously underexplored but highly consequential attack surface in embodied AI systems, highlighting the urgent need for security-driven defenses in the physical AI era. Code is available at https://github.com/RLCLab/Annie.
Authors: Zhuo Cao, Yunxiao Shi, Min Xu
Abstract: This work introduces SAM-LLM, a novel hybrid architecture that bridges the gap between the contextual reasoning of Large Language Models (LLMs) and the physical precision of kinematic lane change models for autonomous driving. The system is designed for interpretable lane change trajectory prediction by finetuning an LLM to output the core physical parameters of a trajectory model instead of raw coordinates. For lane-keeping scenarios, the model predicts discrete coordinates, but for lane change maneuvers, it generates the parameters for an enhanced Sinusoidal Acceleration Model (SAM), including lateral displacement, maneuver duration, initial lateral velocity, and longitudinal velocity change. This parametric approach yields a complete, continuous, and physically plausible trajectory model that is inherently interpretable and computationally efficient, achieving an 80% reduction in output size compared to coordinate-based methods. The SAM-LLM achieves a state-of-the-art overall intention prediction accuracy of 98.73%, demonstrating performance equivalent to traditional LLM predictors while offering significant advantages in explainability and resource efficiency.
Authors: Zichuan Yang
Abstract: I investigate a stronger form of regularization by deactivating neurons for extended periods, a departure from the temporary changes of methods like Dropout. However, this long-term dynamism introduces a critical challenge: severe training instability when neurons are revived with random weights. To solve this, I propose the Lifecycle (LC) principle, a regularization mechanism centered on a key innovation: state memory. Instead of re-initializing a revived neuron, my method restores its parameters to their last known effective state. This process preserves learned knowledge and avoids destructive optimization shocks. My theoretical analysis reveals that the LC principle smooths the loss landscape, guiding optimization towards flatter minima associated with better generalization. Experiments on image classification benchmarks demonstrate that my method improves generalization and robustness. Crucially, ablation studies confirm that state memory is essential for achieving these gains.
Authors: Mazyar Taghavi, Rahman Farnoosh
Abstract: Protecting endangered wildlife from illegal poaching presents a critical challenge, particularly in vast and partially observable environments where real-time response is essential. This paper introduces a novel Expectation-Maximization (EM) based latent variable modeling approach in the context of Multi-Agent Reinforcement Learning (MARL) for Unmanned Aerial Vehicle (UAV) coordination in wildlife protection. By modeling hidden environmental factors and inter-agent dynamics through latent variables, our method enhances exploration and coordination under uncertainty.We implement and evaluate our EM-MARL framework using a custom simulation involving 10 UAVs tasked with patrolling protected habitats of the endangered Iranian leopard. Extensive experimental results demonstrate superior performance in detection accuracy, adaptability, and policy convergence when compared to standard algorithms such as Proximal Policy Optimization (PPO) and Deep Deterministic Policy Gradient (DDPG). Our findings underscore the potential of combining EM inference with MARL to improve decentralized decisionmaking in complex, high-stakes conservation scenarios. The full implementation, simulation environment, and training scripts are publicly available on GitHub.
Authors: Azanzi Jiomekong, Hande K\"u\c{c}\"uk McGinty, Keith G. Mills, Allard Oelen, Enayat Rajabi, Harry McElroy, Antrea Christou, Anmol Saini, Janice Anta Zebaze, Hannah Kim, Anna M. Jacyszyn, S\"oren Auer
Abstract: Despite the growing availability of tools designed to support scholarly knowledge extraction and organization, many researchers still rely on manual methods, sometimes due to unfamiliarity with existing technologies or limited access to domain-adapted solutions. Meanwhile, the rapid increase in scholarly publications across disciplines has made it increasingly difficult to stay current, further underscoring the need for scalable, AI-enabled approaches to structuring and synthesizing scholarly knowledge. Various research communities have begun addressing this challenge independently, developing tools and frameworks aimed at building reliable, dynamic, and queryable scholarly knowledge bases. However, limited interaction across these communities has hindered the exchange of methods, models, and best practices, slowing progress toward more integrated solutions. This manuscript identifies ways to foster cross-disciplinary dialogue, identify shared challenges, categorize new collaboration and shape future research directions in scholarly knowledge and organization.
Authors: Esha Sadia Nasir, Jiaqi Lv, Mostafa Jahanifer, Shan E Ahmed Raza
Abstract: Automated detection and classification of mitotic figures especially distinguishing atypical from normal remain critical challenges in computational pathology. We present MitoDetect++, a unified deep learning pipeline designed for the MIDOG 2025 challenge, addressing both mitosis detection and atypical mitosis classification. For detection (Track 1), we employ a U-Net-based encoder-decoder architecture with EfficientNetV2-L as the backbone, enhanced with attention modules, and trained via combined segmentation losses. For classification (Track 2), we leverage the Virchow2 vision transformer, fine-tuned efficiently using Low-Rank Adaptation (LoRA) to minimize resource consumption. To improve generalization and mitigate domain shifts, we integrate strong augmentations, focal loss, and group-aware stratified 5-fold cross-validation. At inference, we deploy test-time augmentation (TTA) to boost robustness. Our method achieves a balanced accuracy of 0.892 across validation domains, highlighting its clinical applicability and scalability across tasks.
Authors: Xuan Qi, Dominic Labella, Thomas Sanford, Maxwell Lee
Abstract: We tackle atypical versus normal mitosis classification in the MIDOG 2025 challenge using EfficientViT-L2, a hybrid CNN--ViT architecture optimized for accuracy and efficiency. A unified dataset of 13,938 nuclei from seven cancer types (MIDOG++ and AMi-Br) was used, with atypical mitoses comprising ~15. To assess domain generalization, we applied leave-one-cancer-type-out cross-validation with 5-fold ensembles, using stain-deconvolution for image augmentation. For challenge submissions, we trained an ensemble with the same 5-fold split but on all cancer types. In the preliminary evaluation phase, this model achieved balanced accuracy of 0.859, ROC AUC of 0.942, and raw accuracy of 0.85, demonstrating competitive and well-balanced performance across metrics.
Authors: Mieko Ochi, Bae Yuan
Abstract: Mitotic figures are classified into typical and atypical variants, with atypical counts correlating strongly with tumor aggressiveness. Accurate differentiation is therefore essential for patient prognostication and resource allocation, yet remains challenging even for expert pathologists. Here, we leveraged Pathology Foundation Models (PFMs) pre-trained on large histopathology datasets and applied parameter-efficient fine-tuning via low-rank adaptation. During training, we employ a fisheye transform to emphasize mitoses and Fourier Domain Adaptation using ImageNet target images. Finally, we ensembled multiple PFMs to integrate complementary morphological insights, achieving a high balanced accuracy on the Preliminary Evaluation Phase dataset.
Authors: Hunter Gittlin
Abstract: Class imbalance remains a fundamental challenge in machine learning, with traditional solutions often creating as many problems as they solve. We demonstrate that group-aware threshold calibration--setting different decision thresholds for different demographic groups--provides superior robustness compared to synthetic data generation methods. Through extensive experiments, we show that group-specific thresholds achieve 1.5-4% higher balanced accuracy than SMOTE and CT-GAN augmented models while improving worst-group balanced accuracy. Unlike single-threshold approaches that apply one cutoff across all groups, our group-aware method optimizes the Pareto frontier between balanced accuracy and worst-group balanced accuracy, enabling fine-grained control over group-level performance. Critically, we find that applying group thresholds to synthetically augmented data yields minimal additional benefit, suggesting these approaches are fundamentally redundant. Our results span seven model families including linear, tree-based, instance-based, and boosting methods, confirming that group-aware threshold calibration offers a simpler, more interpretable, and more effective solution to class imbalance.
Authors: Rapha\"el Bourgade, Guillaume Balezo, Thomas Walter
Abstract: Mitotic figures represent a key histoprognostic feature in tumor pathology, providing crucial insights into tumor aggressiveness and proliferation. However, their identification remains challenging, subject to significant inter-observer variability, even among experienced pathologists. To address this issue, the MItosis DOmain Generalization (MIDOG) 2025 challenge marks the third edition of an international competition aiming to develop robust mitosis detection algorithms. In this paper, we present a mitotic figures detection approach based on the YOLOv12 object detection architecture, achieving a $F_1$-score of 0.801 on the preliminary test set of the MIDOG 2025 challenge, without relying on external data.
Authors: Sandhanakrishnan Ravichandran, Shivesh Kumar, Rogerio Corga Da Silva, Miguel Romano, Reinhard Berkels, Michiel van der Heijden, Olivier Fail, Valentine Emmanuel Gnanapragasam
Abstract: Evaluating large language models (LLMs) on their ability to generate high-quality, accurate, situationally aware answers to clinical questions requires going beyond conventional benchmarks to assess how these systems behave in complex, high-stake clincal scenarios. Traditional evaluations are often limited to multiple-choice questions that fail to capture essential competencies such as contextual reasoning, awareness and uncertainty handling etc. To address these limitations, we evaluate our agentic, RAG-based clinical support assistant, DR.INFO, using HealthBench, a rubric-driven benchmark composed of open-ended, expert-annotated health conversations. On the Hard subset of 1,000 challenging examples, DR.INFO achieves a HealthBench score of 0.51, substantially outperforming leading frontier LLMs (GPT-5, o3, Grok 3, GPT-4, Gemini 2.5, etc.) across all behavioral axes (accuracy, completeness, instruction following, etc.). In a separate 100-sample evaluation against similar agentic RAG assistants (OpenEvidence, Pathway.md), it maintains a performance lead with a health-bench score of 0.54. These results highlight DR.INFOs strengths in communication, instruction following, and accuracy, while also revealing areas for improvement in context awareness and completeness of a response. Overall, the findings underscore the utility of behavior-level, rubric-based evaluation for building a reliable and trustworthy AI-enabled clinical support assistant.
Authors: Andrew Broad, Jason Keighley, Lucy Godson, Alex Wright
Abstract: We present a novel approach which extends the existing Fully Convolutional One-Stage Object Detector (FCOS) for mitotic figure detection. Our composite model adds a Feedback Attention Ladder CNN (FAL-CNN) model for classification of normal versus abnormal mitotic figures, feeding into a fusion network that is trained to generate adjustments to bounding boxes predicted by FCOS. Our network aims to reduce the false positive rate of the FCOS object detector, to improve the accuracy of object detection and enhance the generalisability of the network. Our model achieved an F1 score of 0.655 for mitosis detection on the preliminary evaluation dataset.
Authors: Jorn K. Teutloff
Abstract: We present a comparative docking experiment that aligns human-subject interview data with large language model (LLM)-driven synthetic personas to evaluate fidelity, divergence, and blind spots in AI-enabled simulation. Fifteen early-stage startup founders were interviewed about their hopes and concerns regarding AI-powered validation, and the same protocol was replicated with AI-generated founder and investor personas. A structured thematic synthesis revealed four categories of outcomes: (1) Convergent themes - commitment-based demand signals, black-box trust barriers, and efficiency gains were consistently emphasized across both datasets; (2) Partial overlaps - founders worried about outliers being averaged away and the stress of real customer validation, while synthetic personas highlighted irrational blind spots and framed AI as a psychological buffer; (3) Human-only themes - relational and advocacy value from early customer engagement and skepticism toward moonshot markets; and (4) Synthetic-only themes - amplified false positives and trauma blind spots, where AI may overstate adoption potential by missing negative historical experiences. We interpret this comparative framework as evidence that LLM-driven personas constitute a form of hybrid social simulation: more linguistically expressive and adaptable than traditional rule-based agents, yet bounded by the absence of lived history and relational consequence. Rather than replacing empirical studies, we argue they function as a complementary simulation category - capable of extending hypothesis space, accelerating exploratory validation, and clarifying the boundaries of cognitive realism in computational social science.
Authors: Nisanth Kumar Panneerselvam, Guneet Mummaneni, Emilie Roncali
Abstract: Radioembolization is a localized liver cancer treatment that delivers radioactive microspheres (30 micron) to tumors via a catheter inserted in the hepatic arterial tree. The goal is to maximize therapeutic efficacy while minimizing damage to healthy liver tissue. However, optimization is challenging due to complex hepatic artery anatomy, variable blood flow, and uncertainty in microsphere transport. The creation of dynamic, patient-specific digital twins may provide a transformative solution to these challenges. This work outlines a framework for a liver radioembolization digital twin using high-fidelity computational fluid dynamics (CFD) and/or recent physics-informed machine learning approaches. The CFD approach involves microsphere transport calculations in the hepatic arterial tree with individual patient data, which enables personalized treatment planning. Although accurate, traditional CFD is computationally expensive and limits clinical applicability. To accelerate simulations, physics-informed neural networks (PINNs) and their generative extensions play an increasingly important role. PINNs integrate governing equations, such as the Navier-Stokes equations, directly into the neural network training process, enabling mesh-free, data-efficient approximation of blood flow and microsphere transport. Physics-informed generative adversarial networks (PI-GANs), diffusion models (PI-DMs), and transformer-based architectures further enable uncertainty-aware, temporally resolved predictions with reduced computational cost. These AI surrogates not only maintain physical fidelity but also support rapid sampling of diverse flow scenarios, facilitating real-time decision support. Together, CFD and physics-informed AI methods form the foundation of dynamic, patient-specific digital twin to optimize radioembolization planning and ultimately improve clinical outcomes.
Authors: Yanmei Hu, Yihang Wu, Bing Sun, Xue Yue, Biao Cai, Xiangtao Li, Yang Chen
Abstract: Identifying influential nodes in complex networks is a fundamental task in network analysis with wide-ranging applications across domains. While deep learning has advanced node influence detection, existing supervised approaches remain constrained by their reliance on labeled data, limiting their applicability in real-world scenarios where labels are scarce or unavailable. While contrastive learning demonstrates significant potential for performance enhancement, existing approaches predominantly rely on multiple-embedding generation to construct positive/negative sample pairs. To overcome these limitations, we propose ReCC (\textit{r}egular \textit{e}quivalence-based \textit{c}ontrastive \textit{c}lustering), a novel deep unsupervised framework for influential node identification. We first reformalize influential node identification as a label-free deep clustering problem, then develop a contrastive learning mechanism that leverages regular equivalence-based similarity, which captures structural similarities between nodes beyond local neighborhoods, to generate positive and negative samples. This mechanism is integrated into a graph convolutional network to learn node embeddings that are used to differentiate influential from non-influential nodes. ReCC is pre-trained using network reconstruction loss and fine-tuned with a combined contrastive and clustering loss, with both phases being independent of labeled data. Additionally, ReCC enhances node representations by combining structural metrics with regular equivalence-based similarities. Extensive experiments demonstrate that ReCC outperforms state-of-the-art approaches across several benchmarks.
Authors: Jonathan Feldman, Tal Feldman
Abstract: Recent advances in generative biology have enabled the design of novel proteins, creating significant opportunities for drug discovery while also introducing new risks, including the potential development of synthetic bioweapons. Existing biosafety measures primarily rely on inference-time filters such as sequence alignment and protein-protein interaction (PPI) prediction to detect dangerous outputs. In this study, we evaluate the performance of three leading PPI prediction tools: AlphaFold 3, AF3Complex, and SpatialPPIv2. These models were tested on well-characterized viral-host interactions, such as those involving Hepatitis B and SARS-CoV-2. Despite being trained on many of the same viruses, the models fail to detect a substantial number of known interactions. Strikingly, none of the tools successfully identify any of the four experimentally validated SARS-CoV-2 mutants with confirmed binding. These findings suggest that current predictive filters are inadequate for reliably flagging even known biological threats and are even more unlikely to detect novel ones. We argue for a shift toward response-oriented infrastructure, including rapid experimental validation, adaptable biomanufacturing, and regulatory frameworks capable of operating at the speed of AI-driven developments.
Authors: Leire Benito-Del-Valle, Pedro A. Moreno-S\'anchez, Itziar Egusquiza, Itsaso Vitoria, Artzai Pic\'on, Cristina L\'opez-Saratxaga, Adrian Galdran
Abstract: The MIDOG 2025 challenge extends prior work on mitotic figure detection by introducing a new Track 2 on atypical mitosis classification. This task aims to distinguish normal from atypical mitotic figures in histopathology images, a clinically relevant but highly imbalanced and cross-domain problem. We investigated two complementary backbones: (i) ConvNeXt-Small, pretrained on ImageNet, and (ii) a histopathology-specific ViT from Lunit trained via self-supervision. To address the strong prevalence imbalance (9408 normal vs. 1741 atypical), we synthesized additional atypical examples to approximate class balance and compared models trained with real-only vs. real+synthetic data. Using five-fold cross-validation, both backbones reached strong performance (mean AUROC approximately 95 percent), with ConvNeXt achieving slightly higher peaks while Lunit exhibited greater fold-to-fold stability. Synthetic balancing, however, did not lead to consistent improvements. On the organizers' preliminary hidden test set, explicitly designed as an out-of-distribution debug subset, ConvNeXt attained the highest AUROC (95.4 percent), whereas Lunit remained competitive on balanced accuracy. These findings suggest that both ImageNet and domain-pretrained backbones are viable for atypical mitosis classification, with domain-pretraining conferring robustness and ImageNet pretraining reaching higher peaks, while naive synthetic balancing has limited benefit. Full hidden test set results will be reported upon challenge completion.
Authors: Mariia Drozdova, Erica Lastufka, Vitaliy Kinakh, Taras Holotyak, Daniel Schaerer, Slava Voloshynovskiy
Abstract: Vision-Language Models (VLMs), such as recent Qwen and Gemini models, are positioned as general-purpose AI systems capable of reasoning across domains. Yet their capabilities in scientific imaging, especially on unfamiliar and potentially previously unseen data distributions, remain poorly understood. In this work, we assess whether generic VLMs, presumed to lack exposure to astronomical corpora, can perform morphology-based classification of radio galaxies using the MiraBest FR-I/FR-II dataset. We explore prompting strategies using natural language and schematic diagrams, and, to the best of our knowledge, we are the first to introduce visual in-context examples within prompts in astronomy. Additionally, we evaluate lightweight supervised adaptation via LoRA fine-tuning. Our findings reveal three trends: (i) even prompt-based approaches can achieve good performance, suggesting that VLMs encode useful priors for unfamiliar scientific domains; (ii) however, outputs are highly unstable, i.e. varying sharply with superficial prompt changes such as layout, ordering, or decoding temperature, even when semantic content is held constant; and (iii) with just 15M trainable parameters and no astronomy-specific pretraining, fine-tuned Qwen-VL achieves near state-of-the-art performance (3% Error rate), rivaling domain-specific models. These results suggest that the apparent "reasoning" of VLMs often reflects prompt sensitivity rather than genuine inference, raising caution for their use in scientific domains. At the same time, with minimal adaptation, generic VLMs can rival specialized models, offering a promising but fragile tool for scientific discovery.
Authors: Berger Cl\'ementine (IDS, S2A), Stamadiatis Paraskevas (IDS, S2A), Badeau Roland (IDS, S2A), Essid Slim (IDS, S2A)
Abstract: We are interested in audio systems capable of performing a differentiated processing of stationary backgrounds and isolated acoustic events within an acoustic scene, whether for applying specific processing methods to each part or for focusing solely on one while ignoring the other. Such systems have applications in real-world scenarios, including robust adaptive audio rendering systems (e.g., EQ or compression), plosive attenuation in voice mixing, noise suppression or reduction, robust acoustic event classification or even bioacoustics. To this end, we introduce IS${}^3$, a neural network designed for Impulsive--Stationary Sound Separation, that isolates impulsive acoustic events from the stationary background using a deep filtering approach, that can act as a pre-processing stage for the above-mentioned tasks. To ensure optimal training, we propose a sophisticated data generation pipeline that curates and adapts existing datasets for this task. We demonstrate that a learning-based approach, build on a relatively lightweight neural architecture and trained with well-designed and varied data, is successful in this previously unaddressed task, outperforming the Harmonic--Percussive Sound Separation masking method, adapted from music signal processing research, and wavelet filtering on objective separation metrics.
Authors: Minja Axelsson, Jiaee Cheong, Rune Nyrup, Hatice Gunes
Abstract: Recent studies indicate that robotic coaches can play a crucial role in promoting wellbeing. However, the real-world deployment of wellbeing robots raises numerous ethical and socio-technical questions and concerns. To explore these questions, we undertake a community-centered investigation to examine three different communities' perspectives on using robotic wellbeing coaches in real-world environments. We frame our work as an anticipatory ethical investigation, which we undertake to better inform the development of robotic technologies with communities' opinions, with the ultimate goal of aligning robot development with public interest. We conducted workshops with three communities who are under-represented in robotics development: 1) members of the public at a science festival, 2) women computer scientists at a conference, and 3) humanities researchers interested in history and philosophy of science. In the workshops, we collected qualitative data using the Social Robot Co-Design Canvas on Ethics. We analysed the collected qualitative data with Thematic Analysis, informed by notes taken during workshops. Through our analysis, we identify four themes regarding key ethical and socio-technical questions about the real-world use of wellbeing robots. We group participants' insights and discussions around these broad thematic questions, discuss them in light of state-of-the-art literature, and highlight areas for future investigation. Finally, we provide the four questions as a broad framework that roboticists can and should use during robotic development and deployment, in order to reflect on the ethics and socio-technical dimensions of their robotic applications, and to engage in dialogue with communities of robot users. The four questions are: 1) Is the robot safe and how can we know that?, 2) Who is the robot built for and with?, 3) Who owns the robot and the data?, and 4) Why a robot?.
Authors: Jie Xiao, Mengye Lyu, Shaojun Liu
Abstract: MIDOG 2025 Track 1 requires mitosis detection in whole-slide images (WSIs) containing non-tumor, inflamed, and necrotic regions. Due to the complicated and heterogeneous context, as well as possible artifacts, there are often false positives and false negatives, thus degrading the detection F1-score. To address this problem, we propose a two-stage framework. Firstly, an improved YOLO11x, integrated with EMA attention and LSConv, is employed to generate mitosis candidates. We use a low confidence threshold to generate as many proposals as possible, ensuring the detection recall. Then, a ConvNeXt-Tiny classifier is employed to filter out the false positives, ensuring the detection precision. Consequently, the proposed two-stage framework can generate a high detection F1-score. Evaluated on a fused dataset comprising MIDOG++, MITOS_WSI_CCMCT, and MITOS_WSI_CMC, our framework achieves an F1-score of 0.882, which is 0.035 higher than the single-stage YOLO11x baseline. This performance gain is produced by a significant precision improvement, from 0.762 to 0.839, and a comparable recall. The code is available at https://github.com/xxiao0304/MIDOG-2025-Track-1-of-SZTU.
URLs: https://github.com/xxiao0304/MIDOG-2025-Track-1-of-SZTU.
Authors: Yasemin Topuz, M. Taha G\"okcan, Serdar Y{\i}ld{\i}z, Song\"ul Varl{\i}
Abstract: Mitotic figure detection is a crucial task in computational pathology, as mitotic activity serves as a strong prognostic marker for tumor aggressiveness. However, domain variability that arises from differences in scanners, tissue types, and staining protocols poses a major challenge to the robustness of automated detection methods. In this study, we introduce SDF-YOLO (Single Detect Focused YOLO), a lightweight yet domain-robust detection framework designed specifically for small, rare targets such as mitotic figures. The model builds on YOLOv11 with task-specific modifications, including a single detection head aligned with mitotic figure scale, coordinate attention to enhance positional sensitivity, and improved cross-channel feature mixing. Experiments were conducted on three datasets that span human and canine tumors: MIDOG ++, canine cutaneous mast cell tumor (CCMCT), and canine mammary carcinoma (CMC). When submitted to the preliminary test set for the MIDOG2025 challenge, SDF-YOLO achieved an average precision (AP) of 0.799, with a precision of 0.758, a recall of 0.775, an F1 score of 0.766, and an FROC-AUC of 5.793, demonstrating both competitive accuracy and computational efficiency. These results indicate that SDF-YOLO provides a reliable and efficient framework for robust mitotic figure detection across diverse domains.
Authors: Hojjat Torabi Goudarzi, Maziyar Baran Pouyan
Abstract: Single-cell RNA sequencing (scRNA-seq) provides unprecedented insights into cellular heterogeneity, enabling detailed analysis of complex biological systems at single-cell resolution. However, the high dimensionality and technical noise inherent in scRNA-seq data pose significant analytical challenges. While current embedding methods focus primarily on gene expression levels, they often overlook crucial gene-gene interactions that govern cellular identity and function. To address this limitation, we present a novel embedding approach that integrates both gene expression profiles and data-driven gene-gene interactions. Our method first constructs a Cell-Leaf Graph (CLG) using random forest models to capture regulatory relationships between genes, while simultaneously building a K-Nearest Neighbor Graph (KNNG) to represent expression similarities between cells. These graphs are then combined into an Enriched Cell-Leaf Graph (ECLG), which serves as input for a graph neural network to compute cell embeddings. By incorporating both expression levels and gene-gene interactions, our approach provides a more comprehensive representation of cellular states. Extensive evaluation across multiple datasets demonstrates that our method enhances the detection of rare cell populations and improves downstream analyses such as visualization, clustering, and trajectory inference. This integrated approach represents a significant advance in single-cell data analysis, offering a more complete framework for understanding cellular diversity and dynamics.
Authors: Biwen Meng, Xi Long, Jingxin Liu
Abstract: Atypical mitotic figures (AMFs) are clinically relevant indicators of abnormal cell division, yet their reliable detection remains challenging due to morphological ambiguity and scanner variability. In this work, we investigated three variants of adapting the pathology foundation model UNI2-h for the MIDOG2025 Track 2 challenge. Starting from a LoRA-based baseline, we found that visual prompt tuning (VPT) substantially improved generalization, and that further integrating test-time augmentation (TTA) with Vahadane and Macenko stain normalization provided the best robustness. Our final submission achieved a balanced accuracy of 0.8837 and an ROC-AUC of 0.9513 on the preliminary leaderboard, ranking within the top 10 teams. These results demonstrate that prompt-based adaptation combined with stain-normalization TTA offers an effective strategy for atypical mitosis classification under diverse imaging conditions.
Authors: Bin Feng, Jiying Zhang, Xinni Zhang, Zijing Liu, Yu Li
Abstract: Molecular dynamics (MD) simulations are essential tools in computational chemistry and drug discovery, offering crucial insights into dynamic molecular behavior. However, their utility is significantly limited by substantial computational costs, which severely restrict accessible timescales for many biologically relevant processes. Despite the encouraging performance of existing machine learning (ML) methods, they struggle to generate extended biomolecular system trajectories, primarily due to the lack of MD datasets and the large computational demands of modeling long historical trajectories. Here, we introduce BioMD, the first all-atom generative model to simulate long-timescale protein-ligand dynamics using a hierarchical framework of forecasting and interpolation. We demonstrate the effectiveness and versatility of BioMD on the DD-13M (ligand unbinding) and MISATO datasets. For both datasets, BioMD generates highly realistic conformations, showing high physical plausibility and low reconstruction errors. Besides, BioMD successfully generates ligand unbinding paths for 97.1% of the protein-ligand systems within ten attempts, demonstrating its ability to explore critical unbinding pathways. Collectively, these results establish BioMD as a tool for simulating complex biomolecular processes, offering broad applicability for computational chemistry and drug discovery.
Authors: Roland Pihlakas, Sruthi Kuriakose
Abstract: Relatively many past AI safety discussions have centered around the dangers of unbounded utility maximisation by RL agents, illustrated by scenarios like the "paperclip maximiser" or by specification gaming in general. Unbounded maximisation is problematic for many reasons. We wanted to verify whether these RL runaway optimisation problems are still relevant with LLMs as well. Turns out, strangely, this is indeed clearly the case. The problem is not that the LLMs just lose context or become incoherent. The problem is that in various scenarios, LLMs lose context in very specific ways, which systematically resemble runaway optimisers in the following distinct ways: 1) Ignoring homeostatic targets and "defaulting" to unbounded maximisation instead. 2) It is equally concerning that the "default" meant also reverting back to single-objective optimisation. Our findings also suggest that long-running scenarios are important. Systematic failures emerge after periods of initially successful behaviour. In some trials the LLMs were successful until the end. This means, while current LLMs do conceptually grasp biological and economic alignment, they exhibit randomly triggered problematic behavioural tendencies under sustained long-running conditions, particularly involving multiple or competing objectives. Once they flip, they usually do not recover. Even though LLMs look multi-objective and bounded on the surface, the underlying mechanisms seem to be actually still biased towards being single-objective and unbounded.
Authors: Saarang Panchavati, Corey Arnold, William Speier
Abstract: This work explores the potential of foundation models, specifically a Mamba-based selective state space model, for enhancing EEG analysis in neurological disorder diagnosis. EEG, crucial for diagnosing conditions like epilepsy, presents significant challenges due to its noisy, high-dimensional, and nonlinear nature. Traditional machine learning methods have made advances in automating EEG analysis but often fail to capture its complex spatio-temporal dynamics. Recent advances in deep learning, particularly in sequence modeling, offer new avenues for creating more generalized and expressive models capable of handling such complexities. By training a Mamba-based model on a large dataset containing seizure and non-seizure EEG recordings through a self-supervised reconstruction task followed by a seizure detection task, we demonstrate the model's effectiveness, achieving an AUROC of 0.72 on a held-out test set. This approach marks a significant step toward developing large-scale, clinically applicable foundation models for EEG data analysis.
Authors: Michael Bouzinier, Sergey Trifonov
Abstract: This article describes an ontology and methodology for annotating and organizing Euclidean Geometry problems, developed in the early 1990s and implemented as a software tool. While the majority of this work -- including the ontology and solution graph paradigm -- was completed over thirty years ago, we argue that it has renewed relevance in the context of modern artificial intelligence. In particular, we explore the hypothesis that this established framework can facilitate automated solution validation and feedback when paired with contemporary large language models, thereby supporting teachers and self-learners in geometry education. We document the original architecture and its enduring value, and outline pathways for bridging historical educational resources with next-generation AI techniques.
Authors: Arnab Mazumder, Javier E. Santos, Noah Hobbs, Mohamed Mehana, Daniel O'Malley
Abstract: We present the Transparent Earth, a transformer-based architecture for reconstructing subsurface properties from heterogeneous datasets that vary in sparsity, resolution, and modality, where each modality represents a distinct type of observation (e.g., stress angle, mantle temperature, tectonic plate type). The model incorporates positional encodings of observations together with modality encodings, derived from a text embedding model applied to a description of each modality. This design enables the model to scale to an arbitrary number of modalities, making it straightforward to add new ones not considered in the initial design. We currently include eight modalities spanning directional angles, categorical classes, and continuous properties such as temperature and thickness. These capabilities support in-context learning, enabling the model to generate predictions either with no inputs or with an arbitrary number of additional observations from any subset of modalities. On validation data, this reduces errors in predicting stress angle by more than a factor of three. The proposed architecture is scalable and demonstrates improved performance with increased parameters. Together, these advances make the Transparent Earth an initial foundation model for the Earth's subsurface that ultimately aims to predict any subsurface property anywhere on Earth.
Authors: Jusheng Zhang, Yijia Fan, Kaitong Cai, Zimeng Huang, Xiaofei Sun, Jian Wang, Chengpei Tang, Keze Wang
Abstract: This paper introduces DrDiff, a novel framework for long-text generation that overcomes the efficiency-quality trade-off through three core technologies. First, we design a dynamic expert scheduling mechanism that intelligently allocates computational resources during the diffusion process based on text complexity, enabling more efficient handling of text generation tasks of varying difficulty. Second, we introduce a Hierarchical Sparse Attention (HSA) mechanism that adaptively adjusts attention patterns according to a variety of input lengths, reducing computational complexity from O($n^2$) to O($n$) while maintaining model performance. Finally, we propose a soft absorption guidance optimization strategy that combines with DPM-solver++ to reduce diffusion steps, significantly improving generation speed. Comprehensive experiments on various long-text generation benchmarks demonstrate the superiority of our DrDiff over the existing SOTA methods.
Authors: Isaac Ronald Ward, Mark Paral, Kristopher Riordan, Mykel J. Kochenderfer
Abstract: Autonomously controlling quadrotors in large-scale subterranean environments is applicable to many areas such as environmental surveying, mining operations, and search and rescue. Learning-based controllers represent an appealing approach to autonomy, but are known to not generalize well to `out-of-distribution' environments not encountered during training. In this work, we train a normalizing flow-based prior over the environment, which provides a measure of how far out-of-distribution the quadrotor is at any given time. We use this measure as a runtime monitor, allowing us to switch between a learning-based controller and a safe controller when we are sufficiently out-of-distribution. Our methods are benchmarked on a point-to-point navigation task in a simulated 3D cave environment based on real-world point cloud data from the DARPA Subterranean Challenge Final Event Dataset. Our experimental results show that our combined controller simultaneously possesses the liveness of the learning-based controller (completing the task quickly) and the safety of the safety controller (avoiding collision).
Authors: Towhidul Islam, Md Sumon Ali
Abstract: Obesity is a critical global health issue driven by dietary, physiological, and environmental factors, and is strongly associated with chronic diseases such as diabetes, cardiovascular disorders, and cancer. Machine learning has emerged as a promising approach for early obesity risk prediction, yet a comparative evaluation of ensemble techniques -- particularly hybrid majority voting and ensemble stacking -- remains limited. This study aims to compare hybrid majority voting and ensemble stacking methods for obesity risk prediction, identifying which approach delivers higher accuracy and efficiency. The analysis seeks to highlight the complementary strengths of these ensemble techniques in guiding better predictive model selection for healthcare applications. Two datasets were utilized to evaluate three ensemble models: Majority Hard Voting, Weighted Hard Voting, and Stacking (with a Multi-Layer Perceptron as meta-classifier). A pool of nine Machine Learning (ML) algorithms, evaluated across a total of 50 hyperparameter configurations, was analyzed to identify the top three models to serve as base learners for the ensemble methods. Preprocessing steps involved dataset balancing, and outlier detection, and model performance was evaluated using Accuracy and F1-Score. On Dataset-1, weighted hard voting and stacking achieved nearly identical performance (Accuracy: 0.920304, F1: 0.920070), outperforming majority hard voting. On Dataset-2, stacking demonstrated superior results (Accuracy: 0.989837, F1: 0.989825) compared to majority hard voting (Accuracy: 0.981707, F1: 0.981675) and weighted hard voting, which showed the lowest performance. The findings confirm that ensemble stacking provides stronger predictive capability, particularly for complex data distributions, while hybrid majority voting remains a robust alternative.
Authors: Gustavo Bonil, Jo\~ao Gondim, Marina dos Santos, Simone Hashiguti, Helena Maia, Nadia Silva, Helio Pedrini, Sandra Avila
Abstract: This study investigates how large language models, in particular LLaMA 3.2-3B, construct narratives about Black and white women in short stories generated in Portuguese. From 2100 texts, we applied computational methods to group semantically similar stories, allowing a selection for qualitative analysis. Three main discursive representations emerge: social overcoming, ancestral mythification and subjective self-realization. The analysis uncovers how grammatically coherent, seemingly neutral texts materialize a crystallized, colonially structured framing of the female body, reinforcing historical inequalities. The study proposes an integrated approach, that combines machine learning techniques with qualitative, manual discourse analysis.
Authors: Payel Santra, Madhusudan Ghosh, Debasis Ganguly, Partha Basuchowdhuri, Sudip Kumar Naskar
Abstract: Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). However, effectively combining evidence from these heterogeneous sources is challenging as the respective similarity scores are not inter-comparable. Additionally, aggregating beliefs from the outputs of multiple rankers can improve the effectiveness of RAG. Our proposed method first aggregates the top-documents from a number of IR models using a standard rank fusion technique for each source (labeled and unlabeled). Next, we standardize the retrieval score distributions within each source by applying z-score transformation before merging the top-retrieved documents from the two sources. We evaluate our approach on the fact verification task, demonstrating that it consistently improves over the best-performing individual ranker or source and also shows better out-of-domain generalization.
Authors: Sophia Sun, Rose Yu
Abstract: Conformal prediction has been explored as a general and efficient way to provide uncertainty quantification for time series. However, current methods struggle to handle time series data with change points - sudden shifts in the underlying data-generating process. In this paper, we propose a novel Conformal Prediction for Time-series with Change points (CPTC) algorithm, addressing this gap by integrating a model to predict the underlying state with online conformal prediction to model uncertainties in non-stationary time series. We prove CPTC's validity and improved adaptivity in the time series setting under minimum assumptions, and demonstrate CPTC's practical effectiveness on 6 synthetic and real-world datasets, showing improved validity and adaptivity compared to state-of-the-art baselines.
Authors: Diana A. Wolfe, Alice Choe, Fergus Kidd
Abstract: Despite extensive investment in artificial intelligence, 95% of enterprises report no measurable profit impact from AI deployments (MIT, 2025). We argue that this gap reflects paradigmatic lock-in that channels AI into incremental optimization rather than structural transformation. Using a cross-case analysis, we propose a 2x2 framework that reconceptualizes AI strategy along two independent dimensions: the degree of transformation achieved (incremental to transformational) and the treatment of human contribution (reduced to amplified). The framework surfaces four patterns now dominant in practice: individual augmentation, process automation, workforce substitution, and a less deployed frontier of collaborative intelligence. Evidence shows that the first three reinforce legacy work models and yield localized gains without durable value capture. Realizing collaborative intelligence requires three mechanisms: complementarity (pairing distinct human and machine strengths), co-evolution (mutual adaptation through interaction), and boundary-setting (human determination of ethical and strategic parameters). Complementarity and boundary-setting are observable in regulated and high-stakes domains; co-evolution is largely absent, which helps explain limited system-level impact. A case study analysis illustrates that advancing toward collaborative intelligence requires material restructuring of roles, governance, and data architecture rather than additional tools. The framework reframes AI transformation as an organizational design challenge: moving from optimizing the division of labor between humans and machines to architecting their convergence, with implications for operating models, workforce development, and the future of work.
Authors: Vikas Kashtriya, Pardeep Singh
Abstract: Class imbalance remains a critical challenge in machine learning (ML), particularly in the medical domain, where underrepresented minority classes lead to biased models and reduced predictive performance. This study introduces Quantum-Inspired SMOTE (QI-SMOTE), a novel data augmentation technique that enhances the performance of ML classifiers, including Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), k-Nearest Neighbors (KNN), Gradient Boosting (GB), and Neural Networks, by leveraging quantum principles such as quantum evolution and layered entanglement. Unlike conventional oversampling methods, QI-SMOTE generates synthetic instances that preserve complex data structures, improving model generalization and classification accuracy. We validate QI-SMOTE on the MIMIC-III and MIMIC-IV datasets, using mortality detection as a benchmark task due to their clinical significance and inherent class imbalance. We compare our method against traditional oversampling techniques, including Borderline-SMOTE, ADASYN, SMOTE-ENN, SMOTE-TOMEK, and SVM-SMOTE, using key performance metrics such as Accuracy, F1-score, G-Mean, and AUC-ROC. The results demonstrate that QI-SMOTE significantly improves the effectiveness of ensemble methods (RF, GB, ADA), kernel-based models (SVM), and deep learning approaches by producing more informative and balanced training data. By integrating quantum-inspired transformations into the ML pipeline, QI-SMOTE not only mitigates class imbalance but also enhances the robustness and reliability of predictive models in medical diagnostics and decision-making. This study highlights the potential of quantum-inspired resampling techniques in advancing state-of-the-art ML methodologies.
Authors: Kesen Wang, Daulet Toibazar, Pedro J. Moreno
Abstract: We present an end-to-end, self-evolving adversarial workflow for long-context Question-Answer (QA) Generation in Arabic. By orchestrating multiple specialized LVLMs: a question generator, an evaluator, and a swarm of answer generators, our system iteratively refines its own performance without any human intervention. Starting from raw, multi-page Arabic documents across diverse domains, the question generator produces fine-grained, context-aware queries to be tackled by the answer generator swarm, and the evaluator assesses and feeds back quality metrics. This closed-loop cycle enables continuous learning: low-confidence outputs trigger automated re-generation and model updates, progressively enhancing question difficulty and relevance. Moreover, we set the quality metrics as a tunable hyperparameter, enabling question generation at controllable and customizable difficulty levels. We release AraLongBench, a large-scale Arabic benchmark of single- and multi-page challenges spanning hundreds of pages, and demonstrate that our self-evolving workflow substantially outperform static pipelines, markedly boosting the long-context comprehension capabilities of leading Arabic Large Vision Language Models (LVLMs). Lastly, we also meticulously architect a fully automated agentic workflow for long-context Arabic document collection.
Authors: Akshay Kekuda, Murali Mohana Krishna Dandu, Rimita Lahiri, Shiqin Cai, Sinduja Subramaniam, Evren Korpeoglu, Kannan Achan
Abstract: Modern e-commerce platforms strive to enhance customer experience by providing timely and contextually relevant recommendations. However, recommending general merchandise to customers focused on grocery shopping -- such as pairing milk with a milk frother -- remains a critical yet under-explored challenge. This paper introduces a cross-pollination (XP) framework, a novel approach that bridges grocery and general merchandise cross-category recommendations by leveraging multi-source product associations and real-time cart context. Our solution employs a two-stage framework: (1) A candidate generation mechanism that uses co-purchase market basket analysis and LLM-based approach to identify novel item-item associations; and (2) a transformer-based ranker that leverages the real-time sequential cart context and optimizes for engagement signals such as add-to-carts. Offline analysis and online A/B tests show an increase of 36\% add-to-cart rate with LLM-based retrieval, and 27\% NDCG\@4 lift using cart context-based ranker. Our work contributes practical techniques for cross-category recommendations and broader insights for e-commerce systems.
Authors: Sepanta Zeighami, Shreya Shankar, Aditya Parameswaran
Abstract: Large Language Models (LLMs) are being increasingly used as a building block in data systems to process large text datasets. To do so, LLM model providers offer multiple LLMs with different sizes, spanning various cost-quality trade-offs when processing text at scale. Top-of-the-line LLMs (e.g., GPT-4o, Claude Sonnet) operate with high accuracy but are prohibitively expensive when processing many records. To avoid high costs, more affordable but lower quality LLMs (e.g., GPT-4o-mini, Claude Haiku) can be used to process records, but we need to ensure that the overall accuracy does not deviate substantially from that of the top-of-the-line LLMs. The model cascade framework provides a blueprint to manage this trade-off, by using the confidence of LLMs in their output (e.g., log-probabilities) to decide on which records to use the affordable LLM. However, existing solutions following this framework provide only marginal cost savings and weak theoretical guarantees because of poor estimation of the quality of the affordable LLM's outputs. We present BARGAIN, a method that judiciously uses affordable LLMs in data processing to significantly reduce cost while providing strong theoretical guarantees on the solution quality. BARGAIN employs a novel adaptive sampling strategy and statistical estimation procedure that uses data and task characteristics and builds on recent statistical tools to make accurate estimations with tight theoretical guarantees. Variants of BARGAIN can support guarantees on accuracy, precision, or recall of the output. Experimental results across 8 real-world datasets show that BARGAIN reduces cost, on average, by up to 86% more than state-of-the-art, while providing stronger theoretical guarantees on accuracy of output, with similar gains when guaranteeing a desired level of precision or recall.
Authors: Sandra C. Matz, C. Blaine Horton, Sofie Goethals
Abstract: Large language models (LLMs) increasingly act on people's behalf: they write emails, buy groceries, and book restaurants. While the outsourcing of human decision-making to AI can be both efficient and effective, it raises a fundamental question: how does delegating identity-defining choices to AI reshape who people become? We study the impact of agentic LLMs on two identity-relevant outcomes: interpersonal distinctiveness - how unique a person's choices are relative to others - and intrapersonal diversity - the breadth of a single person's choices over time. Using real choices drawn from social-media behavior of 1,000 U.S. users (110,000 choices in total), we compare a generic and personalized agent to a human baseline. Both agents shift people's choices toward more popular options, reducing the distinctiveness of their behaviors and preferences. While the use of personalized agents tempers this homogenization (compared to the generic AI), it also more strongly compresses the diversity of people's preference portfolios by narrowing what they explore across topics and psychological affinities. Understanding how AI agents might flatten human experience, and how using generic versus personalized agents involves distinctiveness-diversity trade-offs, is critical for designing systems that augment rather than constrain human agency, and for safeguarding diversity in thought, taste, and expression.
Authors: Midhat Urooj, Ayan Banerjee, Farhat Shaikh, Kuntal Thakur, Sandeep Gupta
Abstract: Domain generalization remains a critical challenge in medical imaging, where models trained on single sources often fail under real-world distribution shifts. We propose KG-DG, a neuro-symbolic framework for diabetic retinopathy (DR) classification that integrates vision transformers with expert-guided symbolic reasoning to enable robust generalization across unseen domains. Our approach leverages clinical lesion ontologies through structured, rule-based features and retinal vessel segmentation, fusing them with deep visual representations via a confidence-weighted integration strategy. The framework addresses both single-domain generalization (SDG) and multi-domain generalization (MDG) by minimizing the KL divergence between domain embeddings, thereby enforcing alignment of high-level clinical semantics. Extensive experiments across four public datasets (APTOS, EyePACS, Messidor-1, Messidor-2) demonstrate significant improvements: up to a 5.2% accuracy gain in cross-domain settings and a 6% improvement over baseline ViT models. Notably, our symbolic-only model achieves a 63.67% average accuracy in MDG, while the complete neuro-symbolic integration achieves the highest accuracy compared to existing published baselines and benchmarks in challenging SDG scenarios. Ablation studies reveal that lesion-based features (84.65% accuracy) substantially outperform purely neural approaches, confirming that symbolic components act as effective regularizers beyond merely enhancing interpretability. Our findings establish neuro-symbolic integration as a promising paradigm for building clinically robust, and domain-invariant medical AI systems.
Authors: Nefeli Manoudaki, Mert Toka, Iason Paterakis, Diarmid Flatley
Abstract: Simulacra Naturae is a data-driven media installation that explores collective care through the entanglement of biological computation, material ecologies, and generative systems. The work translates pre-recorded neural activity from brain organoids, lab-grown three-dimensional clusters of neurons, into a multi-sensory environment composed of generative visuals, spatial audio, living plants, and fabricated clay artifacts. These biosignals, streamed through a real-time system, modulate emergent agent behaviors inspired by natural systems such as termite colonies and slime molds. Rather than using biosignals as direct control inputs, Simulacra Naturae treats organoid activity as a co-creative force, allowing neural rhythms to guide the growth, form, and atmosphere of a generative ecosystem. The installation features computationally fabricated clay prints embedded with solenoids, adding physical sound resonances to the generative surround composition. The spatial environment, filled with live tropical plants and a floor-level projection layer featuring real-time generative AI visuals, invites participants into a sensory field shaped by nonhuman cognition. By grounding abstract data in living materials and embodied experience, Simulacra Naturae reimagines visualization as a practice of care, one that decentralizes human agency and opens new spaces for ethics, empathy, and ecological attunement within hybrid computational systems.
Authors: Erik M. Lintunen
Abstract: In self-supervised reinforcement learning (RL), one of the key challenges is learning a diverse set of skills to prepare agents for unknown future tasks. Despite impressive advances, scalability and evaluation remain prevalent issues. Regarding scalability, the search for meaningful skills can be obscured by high-dimensional feature spaces, where relevant features may vary across downstream task domains. For evaluating skill diversity, defining what constitutes "diversity" typically requires a hard commitment to a specific notion of what it means for skills to be diverse, potentially leading to inconsistencies in how skill diversity is understood, making results across different approaches hard to compare, and leaving many forms of diversity unexplored. To address these issues, we adopt a measure of sample diversity that translates ideas from ecology to machine learning -- the Vendi Score -- allowing the user to specify and evaluate any desired form of diversity. We demonstrate how this metric facilitates skill evaluation and introduce VendiRL, a unified framework for learning diversely diverse sets of skills. Given distinct similarity functions, VendiRL motivates distinct forms of diversity, which could support skill-diversity pretraining in new and richly interactive environments where optimising for various forms of diversity may be desirable.
Authors: Kaustuv Mukherji, Jaikrishna Manojkumar Patil, Dyuman Aditya, Paulo Shakarian, Devendra Parkar, Lahari Pokala, Clark Dorman, Gerardo I. Simari
Abstract: We introduce Lattice Annotated Temporal (LAT) Logic, an extension of Generalized Annotated Logic Programs (GAPs) that incorporates temporal reasoning and supports open-world semantics through the use of a lower lattice structure. This logic combines an efficient deduction process with temporal logic programming to support non-Markovian relationships and open-world reasoning capabilities. The open-world aspect, a by-product of the use of the lower-lattice annotation structure, allows for efficient grounding through a Skolemization process, even in domains with infinite or highly diverse constants. We provide a suite of theoretical results that bound the computational complexity of the grounding process, in addition to showing that many of the results on GAPs (using an upper lattice) still hold with the lower lattice and temporal extensions (though different proof techniques are required). Our open-source implementation, PyReason, features modular design, machine-level optimizations, and direct integration with reinforcement learning environments. Empirical evaluations across multi-agent simulations and knowledge graph tasks demonstrate up to three orders of magnitude speedup and up to five orders of magnitude memory reduction while maintaining or improving task performance. Additionally, we evaluate LAT Logic's value in reinforcement learning environments as a non-Markovian simulator, achieving up to three orders of magnitude faster simulation with improved agent performance, including a 26% increase in win rate due to capturing richer temporal dependencies. These results highlight LAT Logic's potential as a unified, extensible framework for open-world temporal reasoning in dynamic and uncertain environments. Our implementation is available at: pyreason.syracuse.edu.
Authors: Yujin Wang, Tianyi Wang, Quanfeng Liu, Wenxian Fan, Junfeng Jiao, Christian Claudel, Yunbing Yan, Bingzhao Gao, Jianqiang Wang, Hong Chen
Abstract: Accurate short-horizon trajectory prediction is pivotal for safe and reliable autonomous driving, yet existing vision-language models (VLMs) often fail to effectively ground their reasoning in scene dynamics and domain knowledge. To address this challenge, this paper introduces KEPT, a knowledge-enhanced VLM framework that predicts ego trajectories directly from consecutive front-view driving frames. KEPT couples a temporal frequency-spatial fusion (TFSF) video encoder, trained via self-supervised learning with hard-negative mining, with a scalable k-means + HNSW retrieval stack that supplies scene-aligned exemplars. Retrieved priors are embedded into chain-of-thought (CoT) prompts with explicit planning constraints, while a triple-stage fine-tuning schedule incrementally aligns the language head to metric spatial cues, physically feasible motion, and temporally conditioned front-view planning. Evaluated on nuScenes dataset, KEPT achieves state-of-the-art performance across open-loop protocols: under NoAvg, it achieves 0.70m average L2 with a 0.21\% collision rate; under TemAvg with lightweight ego status, it attains 0.31m average L2 and a 0.07\% collision rate. Ablation studies show that all three fine-tuning stages contribute complementary benefits, and that using Top-2 retrieved exemplars yields the best accuracy-safety trade-off. The k-means-clustered HNSW index delivers sub-millisecond retrieval latency, supporting practical deployment. These results indicate that retrieval-augmented, CoT-guided VLMs offer a promising, data-efficient pathway toward interpretable and trustworthy autonomous driving.
Authors: Chen Zeng, Tiehang Xu, Qiao Wang
Abstract: Conventional neural networks frequently face challenges in spectral analysis of signals. To address this challenge, Fourier neural networks (FNNs) and similar approaches integrate components of Fourier series into the structure of neural networks. Nonetheless, a significant hurdle is often overlooked: the superposition of periodic signals does not necessarily result in a periodic signal. For example, when forecasting almost periodic functions composed of signals with incommensurate frequencies, traditional models such as Autoregressive Integrated Moving Average (ARIMA) frequently outperform most neural networks including large language models (LLMs). To tackle this goal, we propose Autoregressive-Weight-Enhanced AR-KAN, a hybrid model that combines the benefits of both methods. Using the Universal Myopic Mapping Theorem, we apply a Kolmogorov-Arnold Network (KAN) for the static nonlinear part and include memory through a pre-trained AR component, which can be explained to retain the most useful information while eliminating redundancy. Experimental data indicates that AR-KAN delivers superior results on $72\%$ of real-world datasets.
Authors: Hritik Arasu, Faisal R Jahangiri
Abstract: Sleep staging models often degrade when deployed on patients with unseen physiology or recording conditions. We propose a streaming, source-free test-time adaptation (TTA) recipe that combines entropy minimization (Tent) with Batch-Norm statistic refresh and two safety rails: an entropy gate to pause adaptation on uncertain windows and an EMA-based reset to reel back drift. On Sleep-EDF Expanded, using single-lead EEG (Fpz-Cz, 100 Hz, 30s epochs; R&K to AASM mapping), we show consistent gains over a frozen baseline at seconds-level latency and minimal memory, reporting per-stage metrics and Cohen's k. The method is model-agnostic, requires no source data or patient calibration, and is practical for on-device or bedside use.
Authors: Alexis Ivan Lopez Escamilla, Gilberto Ochoa, Sharib Al
Abstract: We present a lesion-aware image captioning framework for ulcerative colitis (UC). The model integrates ResNet embeddings, Grad-CAM heatmaps, and CBAM-enhanced attention with a T5 decoder. Clinical metadata (MES score 0-3, vascular pattern, bleeding, erythema, friability, ulceration) is injected as natural-language prompts to guide caption generation. The system produces structured, interpretable descriptions aligned with clinical practice and provides MES classification and lesion tags. Compared with baselines, our approach improves caption quality and MES classification accuracy, supporting reliable endoscopic reporting.
Authors: Moontaha Nishat Chowdhury, Andr\'e Bauer, Minxuan Zhou
Abstract: In today's data-driven world, recommendation systems personalize user experiences across industries but rely on sensitive data, raising privacy concerns. Fully homomorphic encryption (FHE) can secure these systems, but a significant challenge in applying FHE to recommendation systems is efficiently handling the inherently large and sparse user-item rating matrices. FHE operations are computationally intensive, and naively processing various sparse matrices in recommendation systems would be prohibitively expensive. Additionally, the communication overhead between parties remains a critical concern in encrypted domains. We propose a novel approach combining Compressed Sparse Row (CSR) representation with FHE-based matrix factorization that efficiently handles matrix sparsity in the encrypted domain while minimizing communication costs. Our experimental results demonstrate high recommendation accuracy with encrypted data while achieving the lowest communication costs, effectively preserving user privacy.
Authors: Sohee Kim, Soohyun Ryu, Joonhyung Park, Eunho Yang
Abstract: Large Vision-Language Models (LVLMs) generate contextually relevant responses by jointly interpreting visual and textual inputs. However, our finding reveals they often mistakenly perceive text inputs lacking visual evidence as being part of the image, leading to erroneous responses. In light of this finding, we probe whether LVLMs possess an internal capability to determine if textual concepts are grounded in the image, and discover a specific subset of Feed-Forward Network (FFN) neurons, termed Visual Absence-aware (VA) neurons, that consistently signal the visual absence through a distinctive activation pattern. Leveraging these patterns, we develop a detection module that systematically classifies whether an input token is visually grounded. Guided by its prediction, we propose a method to refine the outputs by reinterpreting question prompts or replacing the detected absent tokens during generation. Extensive experiments show that our method effectively mitigates the models' tendency to falsely presume the visual presence of text input and its generality across various LVLMs.
Authors: Bilge Taskin, Wenxiong Xie, Teddy Lazebnik
Abstract: Symbolic regression (SR) has emerged as a powerful tool for automated scientific discovery, enabling the derivation of governing equations from experimental data. A growing body of work illustrates the promise of integrating domain knowledge into the SR to improve the discovered equation's generality and usefulness. Physics-informed SR (PiSR) addresses this by incorporating domain knowledge, but current methods often require specialized formulations and manual feature engineering, limiting their adaptability only to domain experts. In this study, we leverage pre-trained Large Language Models (LLMs) to facilitate knowledge integration in PiSR. By harnessing the contextual understanding of LLMs trained on vast scientific literature, we aim to automate the incorporation of domain knowledge, reducing the need for manual intervention and making the process more accessible to a broader range of scientific problems. Namely, the LLM is integrated into the SR's loss function, adding a term of the LLM's evaluation of the SR's produced equation. We extensively evaluate our method using three SR algorithms (DEAP, gplearn, and PySR) and three pre-trained LLMs (Falcon, Mistral, and LLama 2) across three physical dynamics (dropping ball, simple harmonic motion, and electromagnetic wave). The results demonstrate that LLM integration consistently improves the reconstruction of physical dynamics from data, enhancing the robustness of SR models to noise and complexity. We further explore the impact of prompt engineering, finding that more informative prompts significantly improve performance.
Authors: Pengyang Yu, Haoquan Wang, Gerard Marks, Tahar Kechadi, Laurence T. Yang, Sahraoui Dhelim, Nyothiri Aung
Abstract: Accurate skin-lesion segmentation remains a key technical challenge for computer-aided diagnosis of skin cancer. Convolutional neural networks, while effective, are constrained by limited receptive fields and thus struggle to model long-range dependencies. Vision Transformers capture global context, yet their quadratic complexity and large parameter budgets hinder use on the small-sample medical datasets common in dermatology. We introduce the MedLiteNet, a lightweight CNN Transformer hybrid tailored for dermoscopic segmentation that achieves high precision through hierarchical feature extraction and multi-scale context aggregation. The encoder stacks depth-wise Mobile Inverted Bottleneck blocks to curb computation, inserts a bottleneck-level cross-scale token-mixing unit to exchange information between resolutions, and embeds a boundary-aware self-attention module to sharpen lesion contours.
Authors: Haijun Zhang, Jinxiang Wang, Zhenhua Yu, Yanyong Zhang, Xuejie Ji, Kaining Mao, Jun Zhang, Yaqing Zhang, Ting Wu, Fei Jie, Xiemin Huang, Zhifang Cai, Junhua Cheng, Shuwei Wang, Wei Li, Xiaoming Bao, Hua Xu, Shixiong Zhao, Jun Li, Hongwei Sun, Ziyang Zhang, Yi Xiong, Chunsheng Li
Abstract: Large language models (LLMs) have made a profound impact across various fields due to their advanced capabilities. However, training these models at unprecedented scales requires extensive AI accelerator clusters and sophisticated parallelism strategies, which pose significant challenges in maintaining system reliability over prolonged training periods. A major concern is the substantial loss of training time caused by inevitable hardware and software failures. To address these challenges, we present FlashRecovery, a fast and low-cost failure recovery system comprising three core modules: (1) Active and real-time failure detection. This module performs continuous training state monitoring, enabling immediate identification of hardware and software failures within seconds, thus ensuring rapid incident response; (2) Scale-independent task restart. By employing different recovery strategies for normal and faulty nodes, combined with an optimized communication group reconstruction protocol, our approach ensures that the recovery time remains nearly constant, regardless of cluster scale; (3) Checkpoint-free recovery within one step. Our novel recovery mechanism enables single-step restoration, completely eliminating dependence on traditional checkpointing methods and their associated overhead. Collectively, these innovations enable FlashRecovery to achieve optimal Recovery Time Objective (RTO) and Recovery Point Objective (RPO), substantially improving the reliability and efficiency of long-duration LLM training. Experimental results demonstrate that FlashRecovery system can achieve training restoration on training cluster with 4, 800 devices in 150 seconds. We also verify that the time required for failure recovery is nearly consistent for different scales of training tasks.
Authors: Xinzhe Zheng, Zhen-Qun Yang, Haoran Xie, S. Joe Qin, Arlene Chen, Fangzhen Lin
Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of Natural Language Processing (NLP) tasks, but require substantial memory and computational resources. Binary quantization, which compresses model weights from 16-bit Brain Float to 1-bit representations in {-1, 1}, offers significant reductions in storage and inference costs. However, such aggressive quantization often leads to notable performance degradation compared to more conservative 4-bit quantization methods. In this research, we propose a novel optimization objective tailored for binary quantization, along with three algorithms designed to realize it effectively. Our method enhances blocked quantization by dynamically identifying optimal unstructured sub-matrices through adaptive grouping strategies. Experimental results demonstrate that our approach achieves an average bit length of just 1.007 bits, while maintaining high model quality. Specifically, our quantized LLaMA 3.2 3B model attains a perplexity of 8.23, remarkably close to the original 7.81, and surpasses previous SOTA BiLLM with a perplexity of only 123.90. Furthermore, our method is competitive with SOTA 4-bit approaches such as GPTQ in both performance and efficiency. The compression process is highly efficient, requiring only 14 seconds to quantize the full LLaMA 3.2 3B weights on a single CPU core, with the entire process completing in under 100 minutes and exhibiting embarrassingly parallel properties. Code - https://github.com/johnnyzheng0636/WGM_bi_quan
Authors: Xingyue Huang, Rishabh, Gregor Franke, Ziyi Yang, Jiamu Bai, Weijie Bai, Jinhe Bi, Zifeng Ding, Yiqun Duan, Chengyu Fan, Wendong Fan, Xin Gao, Ruohao Guo, Yuan He, Zhuangzhuang He, Xianglong Hu, Neil Johnson, Bowen Li, Fangru Lin, Siyu Lin, Tong Liu, Yunpu Ma, Hao Shen, Hao Sun, Beibei Wang, Fangyijie Wang, Hao Wang, Haoran Wang, Yang Wang, Yifeng Wang, Zhaowei Wang, Ziyang Wang, Yifan Wu, Zikai Xiao, Chengxing Xie, Fan Yang, Junxiao Yang, Qianshuo Ye, Ziyu Ye, Guangtao Zeng, Yuwen Ebony Zhang, Zeyu Zhang, Zihao Zhu, Bernard Ghanem, Philip Torr, Guohao Li
Abstract: Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RLVR), particularly in domains like mathematics and programming, where ground-truth correctness can be automatically evaluated. However, extending this success to other reasoning-intensive domains remains challenging due to the scarcity of high-quality, verifiable datasets and the high cost of human supervision. In this work, we introduce the Loong Project: an open-source framework for scalable synthetic data generation and verification across a diverse range of reasoning-intensive domains. The framework consists of two key components: (1) LoongBench, a curated seed dataset containing 8,729 human-vetted examples across 12 domains (e.g., Advanced Mathematics, Chemistry, Logic), each paired with executable code and rich metadata; and (2) LoongEnv, a modular synthetic data generation environment that supports multiple prompting strategies to produce new question-answer-code triples. Together, these components form an agent-environment loop that enables reinforcement learning, where an LLM-based agent is rewarded for generating Chain-of-Thought (CoT) solutions that align with code-executed answers. Empirically, we benchmark LoongBench on a broad suite of both open-source and proprietary LLMs to evaluate domain coverage and reveal performance bottlenecks. In addition, we conduct a comprehensive analysis of synthetic data generated by LoongEnv, examining correctness, difficulty, and diversity. Code and documentation are available at https://github.com/camel-ai/loong.
Authors: Huaicheng Zhang, Ruoxin Wang, Chenlian Zhou, Jiguang Shi, Yue Ge, Zhoutong Li, Sheng Chang, Hao Wang, Jin He, Qijun Huang
Abstract: As one of the most effective methods for cardiovascular disease (CVD) diagnosis, multi-lead Electrocardiogram (ECG) signals present a characteristic multi-sensor information fusion challenge that has been continuously researched in deep learning domains. Despite the numerous algorithms proposed with different DL architectures, maintaining a balance among performance, computational complexity, and multi-source ECG feature fusion remains challenging. Recently, state space models (SSMs), particularly Mamba, have demonstrated remarkable effectiveness across various fields. Their inherent design for high-efficiency computation and linear complexity makes them particularly suitable for low-dimensional data like ECGs. This work proposes S2M2ECG, an SSM architecture featuring three-level fusion mechanisms: (1) Spatio-temporal bi-directional SSMs with segment tokenization for low-level signal fusion, (2) Intra-lead temporal information fusion with bi-directional scanning to enhance recognition accuracy in both forward and backward directions, (3) Cross-lead feature interaction modules for spatial information fusion. To fully leverage the ECG-specific multi-lead mechanisms inherent in ECG signals, a multi-branch design and lead fusion modules are incorporated, enabling individual analysis of each lead while ensuring seamless integration with others. Experimental results reveal that S2M2ECG achieves superior performance in the rhythmic, morphological, and clinical scenarios. Moreover, its lightweight architecture ensures it has nearly the fewest parameters among existing models, making it highly suitable for efficient inference and convenient deployment. Collectively, S2M2ECG offers a promising alternative that strikes an excellent balance among performance, computational complexity, and ECG-specific characteristics, paving the way for high-performance, lightweight computations in CVD diagnosis.
Authors: Fatih Pehlivan, Ar\c{c}in \"Ulk\"u Erg\"uzen, Sahand Moslemi Yengejeh, Mayasah Lami, Anil Koyuncu
Abstract: Traditional static analysis methods struggle to detect semantic design flaws, such as violations of the SOLID principles, which require a strong understanding of object-oriented design patterns and principles. Existing solutions typically focus on individual SOLID principles or specific programming languages, leaving a gap in the ability to detect violations across all five principles in multi-language codebases. This paper presents a new approach: a methodology that leverages tailored prompt engineering to assess LLMs on their ability to detect SOLID violations across multiple languages. We present a benchmark of four leading LLMs-CodeLlama, DeepSeekCoder, QwenCoder, and GPT-4o Mini-on their ability to detect violations of all five SOLID principles. For this evaluation, we construct a new benchmark dataset of 240 manually validated code examples. Using this dataset, we test four distinct prompt strategies inspired by established zero-shot, few-shot, and chain-of-thought techniques to systematically measure their impact on detection accuracy. Our emerging results reveal a stark hierarchy among models, with GPT-4o Mini decisively outperforming others, yet even struggles with challenging principles like DIP. Crucially, we show that prompt strategy has a dramatic impact, but no single strategy is universally best; for instance, a deliberative ENSEMBLE prompt excels at OCP detection while a hint-based EXAMPLE prompt is superior for DIP violations. Across all experiments, detection accuracy is heavily influenced by language characteristics and degrades sharply with increasing code complexity. These initial findings demonstrate that effective, AI-driven design analysis requires not a single best model, but a tailored approach that matches the right model and prompt to the specific design context, highlighting the potential of LLMs to support maintainability through AI-assisted code analysis.
Authors: Jialu Li, Chen Wu, Meiqi Hu
Abstract: Time series change detection is a critical task for exploring ecosystem dynamics using time series remote sensing images, because it can simultaneously indicate where and when change occur. While deep learning has shown excellent performance in this domain, it continues to approach change area detection and change moment identification as distinct tasks. Given that change area can be inferred from change moment, we propose a time series change detection network, named CAIM-Net (Change Area Inference from Moment Network), to ensure consistency between change area and change moment results. CAIM-Net infers change area from change moment based on the intrinsic relationship between time series analysis and spatial change detection. The CAIM-Net comprises three key steps: Difference Extraction and Enhancement, Coarse Change Moment Extraction, and Fine Change Moment Extraction and Change Area Inference. In the Difference Extraction and Enhancement, a lightweight encoder with batch dimension stacking is designed to rapidly extract difference features. Subsequently, boundary enhancement convolution is applied to amplify these difference features. In the Coarse Change Moment Extraction, the enhanced difference features from the first step are used to spatiotemporal correlation analysis, and then two distinct methods are employed to determine coarse change moments. In the Fine Change Moment Extraction and Change Area Inference, a multiscale temporal Class Activation Mapping (CAM) module first increases the weight of the change-occurring moment from coarse change moments. Then the weighted change moment is used to infer change area based on the fact that pixels with the change moment must have undergone a change.
Authors: Hankang Gu, Yuli Zhang, Chengming Wang, Ruiyuan Jiang, Ziheng Qiao, Pengfei Fan, Dongyao Jia
Abstract: Deep reinforcement learning (DRL) has become a popular approach in traffic signal control (TSC) due to its ability to learn adaptive policies from complex traffic environments. Within DRL-based TSC methods, two primary control paradigms are ``choose phase" and ``switch" strategies. Although the agent in the choose phase paradigm selects the next active phase adaptively, this paradigm may result in unexpected phase sequences for drivers, disrupting their anticipation and potentially compromising safety at intersections. Meanwhile, the switch paradigm allows the agent to decide whether to switch to the next predefined phase or extend the current phase. While this structure maintains a more predictable order, it can lead to unfair and inefficient phase allocations, as certain movements may be extended disproportionately while others are neglected. In this paper, we propose a DRL model, named Deep Hierarchical Cycle Planner (DHCP), to allocate the traffic signal cycle duration hierarchically. A high-level agent first determines the split of the total cycle time between the North-South (NS) and East-West (EW) directions based on the overall traffic state. Then, a low-level agent further divides the allocated duration within each major direction between straight and left-turn movements, enabling more flexible durations for the two movements. We test our model on both real and synthetic road networks, along with multiple sets of real and synthetic traffic flows. Empirical results show our model achieves the best performance over all datasets against baselines.
Authors: Yue Li, Xin Yi, Dongsheng Shi, Yongyi Cui, Gerard de Melo, Xiaoling Wang, Linlin Wang
Abstract: The intellectual property (IP) protection of Large Language Models (LLMs) is increasingly critical. Injecting specialized fingerprints into LLMs through instruction tuning is a common IP protection technique. However, this may significantly degrade model performance, requires substantial computational resources, and exhibits poor persistence under model modifications. We argue that knowledge editing offers a lightweight alternative that is more suitable for fingerprint injection. Accordingly, we apply knowledge editing to fingerprint injection for the first time and demonstrate its strong capability. Despite using scrambled text as fingerprints to prevent them from being overwritten during fine-tuning, degradation still occurs under large-scale fine-tuning. To address this, we propose Fingerprint Subspace-aware Fine-Tuning (FSFT), which reduces fingerprint degradation by constraining the update of the fingerprint subspace. The performance of FSFT exceeds fine-tuning by 10% even in the worst-case scenario. Additionally, we observe that the fingerprint-injected models struggle to distinguish between fingerprints and similar texts due to the high similarity of their features. This finding underscores the urgent need for more robust and fine-grained fingerprinting injection methods for LLMs.
Authors: Chenxia Tang, Jianchun Liu, Hongli Xu, Liusheng Huang
Abstract: Large language models (LLMs) inference relies heavily on KV-caches to accelerate autoregressive decoding, but the resulting memory footprint grows rapidly with sequence length, posing significant efficiency challenges. Current KV-cache compression methods suffer from a Procrustes' bed problem: they force diverse workloads into fixed compression ratios, leading to suboptimal resource allocation and inference performance. To this end, we present GVote, an adaptive KV-cache compression scheme that eliminates manual budget specification while achieving superior accuracy-efficiency trade-offs. GVote operates on the principle that the important keys are the aggregation of keys required by future queries. The method predicts future query attention demands by Monte-Carlo style sampling potential queries and aggregating selected keys to determine the optimal cache budget without manual specification. Experimental evaluation demonstrates GVote's effectiveness across multiple benchmarks, including GSM8K, RULER and Longbench. Compared to baselines, GVote exhibits 2$\times$ memory reduction while the accuracy maintains higher or comparable.
Authors: Li Yi, Qian Yang
Abstract: Liquid scintillation triple-to-doubly coincident ratio (TDCR) spectroscopy is widely adopted as a standard method for radionuclide quantification because of its inherent advantages such as high precision, self-calibrating capability, and independence from radioactive reference sources. However, multiradionuclide analysis via TDCR faces the challenges of limited automation and reliance on mixture-specific standards, which may not be easily available. Here, we present an Artificial Intelligence (AI) framework that combines numerical spectral simulation and deep learning for standard-free automated analysis. $\beta$ spectra for model training were generated using Geant4 simulations coupled with statistically modeled detector response sampling. A tailored neural network architecture, trained on this dataset covering various nuclei mix ratio and quenching scenarios, enables autonomous resolution of individual radionuclide activities and detecting efficiency through end-to-end learning paradigms. The model delivers consistent high accuracy across tasks: activity proportions (mean absolute error = 0.009), detection efficiencies (mean absolute error = 0.002), and spectral reconstruction (Structural Similarity Index = 0.9998), validating its physical plausibility for quenched $\beta$ spectroscopy. This AI-driven methodology exhibits significant potential for automated safety-compliant multiradionuclide analysis with robust generalization, real-time processing capabilities, and engineering feasibility, particularly in scenarios where reference materials are unavailable or rapid field analysis is required.
Authors: Nadezhda Dobreva, Emmanuel Blazquez, Jai Grover, Dario Izzo, Yuzhen Qin, Dominik Dold
Abstract: We present a decentralized model for autonomous reconfiguration of homogeneous pivoting cube modular robots in two dimensions. Each cube in the ensemble is controlled by a neural network that only gains information from other cubes in its local neighborhood, trained using reinforcement learning. Furthermore, using geometric deep learning, we include the grid symmetries of the cube ensemble in the neural network architecture. We find that even the most localized versions succeed in reconfiguring to the target shape, although reconfiguration happens faster the more information about the whole ensemble is available to individual cubes. Near-optimal reconfiguration is achieved with only nearest neighbor interactions by using multiple information passing between cubes, allowing them to accumulate more global information about the ensemble. Compared to standard neural network architectures, using geometric deep learning approaches provided only minor benefits. Overall, we successfully demonstrate mostly local control of a modular self-assembling system, which is transferable to other space-relevant systems with different action spaces, such as sliding cube modular robots and CubeSat swarms.
Authors: Rafael Seidi Oyamada, Jari Peeperkorn, Jochen De Weerdt, Johannes De Smedt
Abstract: In recent years, Large Language Models (LLMs) have emerged as a prominent area of interest across various research domains, including Process Mining (PM). Current applications in PM have predominantly centered on prompt engineering strategies or the transformation of event logs into narrative-style datasets, thereby exploiting the semantic capabilities of LLMs to address diverse tasks. In contrast, this study investigates the direct adaptation of pretrained LLMs to process data without natural language reformulation, motivated by the fact that these models excel in generating sequences of tokens, similar to the objective in PM. More specifically, we focus on parameter-efficient fine-tuning techniques to mitigate the computational overhead typically associated with such models. Our experimental setup focuses on Predictive Process Monitoring (PPM), and considers both single- and multi-task predictions. The results demonstrate a potential improvement in predictive performance over state-of-the-art recurrent neural network (RNN) approaches and recent narrative-style-based solutions, particularly in the multi-task setting. Additionally, our fine-tuned models exhibit faster convergence and require significantly less hyperparameter optimization.
Authors: Helge Spieker, J{\o}rn Eirik Betten, Arnaud Gotlieb, Nadjib Lazaar, Nassim Belmecheri
Abstract: Explainable AI (XAI) is essential for validating and trusting models in safety-critical applications like autonomous driving. However, the reliability of XAI is challenged by the Rashomon effect, where multiple, equally accurate models can offer divergent explanations for the same prediction. This paper provides the first empirical quantification of this effect for the task of action prediction in real-world driving scenes. Using Qualitative Explainable Graphs (QXGs) as a symbolic scene representation, we train Rashomon sets of two distinct model classes: interpretable, pair-based gradient boosting models and complex, graph-based Graph Neural Networks (GNNs). Using feature attribution methods, we measure the agreement of explanations both within and between these classes. Our results reveal significant explanation disagreement. Our findings suggest that explanation ambiguity is an inherent property of the problem, not just a modeling artifact.
Authors: Alma M. Liezenga, Stefan Wijnja, Puck de Haan, Niels W. T. Brink, Jip J. van Stijn, Yori Kamphuis, Klamer Schutte
Abstract: Poisoning attacks pose an increasing threat to the security and robustness of Artificial Intelligence systems in the military domain. The widespread use of open-source datasets and pretrained models exacerbates this risk. Despite the severity of this threat, there is limited research on the application and detection of poisoning attacks on object detection systems. This is especially problematic in the military domain, where attacks can have grave consequences. In this work, we both investigate the effect of poisoning attacks on military object detectors in practice, and the best approach to detect these attacks. To support this research, we create a small, custom dataset featuring military vehicles: MilCivVeh. We explore the vulnerability of military object detectors for poisoning attacks by implementing a modified version of the BadDet attack: a patch-based poisoning attack. We then assess its impact, finding that while a positive attack success rate is achievable, it requires a substantial portion of the data to be poisoned -- raising questions about its practical applicability. To address the detection challenge, we test both specialized poisoning detection methods and anomaly detection methods from the visual industrial inspection domain. Since our research shows that both classes of methods are lacking, we introduce our own patch detection method: AutoDetect, a simple, fast, and lightweight autoencoder-based method. Our method shows promising results in separating clean from poisoned samples using the reconstruction error of image slices, outperforming existing methods, while being less time- and memory-intensive. We urge that the availability of large, representative datasets in the military domain is a prerequisite to further evaluate risks of poisoning attacks and opportunities patch detection.
Authors: Zeqiang Zhang, Fabian Wurzberger, Gerrit Schmid, Sebastian Gottwald, Daniel A. Braun
Abstract: Reinforcement learning faces significant challenges when applied to tasks characterized by sparse reward structures. Although imitation learning, within the domain of supervised learning, offers faster convergence, it relies heavily on human-generated demonstrations. Recently, Goal-Conditioned Supervised Learning (GCSL) has emerged as a potential solution by enabling self-imitation learning for autonomous systems. By strategically relabelling goals, agents can derive policy insights from their own experiences. Despite the successes of this framework, it presents two notable limitations: (1) Learning exclusively from self-generated experiences can exacerbate the agents' inherent biases; (2) The relabelling strategy allows agents to focus solely on successful outcomes, precluding them from learning from their mistakes. To address these issues, we propose a novel model that integrates contrastive learning principles into the GCSL framework to learn from both success and failure. Through empirical evaluations, we demonstrate that our algorithm overcomes limitations imposed by agents' initial biases and thereby enables more exploratory behavior. This facilitates the identification and adoption of effective policies, leading to superior performance across a variety of challenging environments.
Authors: Jing Zhang, Siying Tao, Jiao Li, Tianhe Wang, Junchen Wu, Ruqian Hao, Xiaohui Du, Ruirong Tan, Rui Li
Abstract: Organoids replicate organ structure and function, playing a crucial role in fields such as tumor treatment and drug screening. Their shape and size can indicate their developmental status, but traditional fluorescence labeling methods risk compromising their structure. Therefore, this paper proposes an automated, non-destructive approach to organoid segmentation and tracking. We introduced the LGBP-OrgaNet, a deep learning-based system proficient in accurately segmenting, tracking, and quantifying organoids. The model leverages complementary information extracted from CNN and Transformer modules and introduces the innovative feature fusion module, Learnable Gaussian Band Pass Fusion, to merge data from two branches. Additionally, in the decoder, the model proposes a Bidirectional Cross Fusion Block to fuse multi-scale features, and finally completes the decoding through progressive concatenation and upsampling. SROrga demonstrates satisfactory segmentation accuracy and robustness on organoids segmentation datasets, providing a potent tool for organoid research.
Authors: Harald Vilhelm Skat-R{\o}rdam, Sneha Das, Kathrine Sofie Rasmussen, Nicole Nadine L{\o}nfeldt, Line Clemmensen
Abstract: Accurate evaluation of event detection in time series is essential for applications such as stress monitoring with wearable devices, where ground truth is typically annotated as single-point events, even though the underlying phenomena are gradual and temporally diffused. Standard metrics like F1 and point-adjusted F1 (F1$_{pa}$) often misrepresent model performance in such real-world, imbalanced datasets. We introduce a window-based F1 metric (F1$_w$) that incorporates temporal tolerance, enabling a more robust assessment of event detection when exact alignment is unrealistic. Empirical analysis in three physiological datasets, two in-the-wild (ADARP, Wrist Angel) and one experimental (ROAD), indicates that F1$_w$ reveals meaningful model performance patterns invisible to conventional metrics, while its window size can be adapted to domain knowledge to avoid overestimation. We show that the choice of evaluation metric strongly influences the interpretation of model performance: using predictions from TimesFM, only our temporally tolerant metrics reveal statistically significant improvements over random and null baselines in the two in-the-wild use cases. This work addresses key gaps in time series evaluation and provides practical guidance for healthcare applications where requirements for temporal precision vary by context.
Authors: Yiming Yao, Fei Liu, Liang Zhao, Xi Lin, Qingfu Zhang
Abstract: Expensive multi-objective optimization is a prevalent and crucial concern in many real-world scenarios, where sample-efficiency is vital due to the limited evaluations to recover the true Pareto front for decision making. Existing works either involve rebuilding Gaussian process surrogates from scratch for each objective in each new problem encountered, or rely on extensive past domain experiments for pre-training deep learning models, making them hard to generalize and impractical to cope with various emerging applications in the real world. To address this issue, we propose a new paradigm named FoMEMO (Foundation Models for Expensive Multi-objective Optimization), which enables the establishment of a foundation model conditioned on any domain trajectory and user preference, and facilitates fast in-context optimization based on the predicted preference-wise aggregation posteriors. Rather than accessing extensive domain experiments in the real world, we demonstrate that pre-training the foundation model with a diverse set of hundreds of millions of synthetic data can lead to superior adaptability to unknown problems, without necessitating any subsequent model training or updates in the optimization process. We evaluate our method across a variety of synthetic benchmarks and real-word applications, and demonstrate its superior generality and competitive performance compared to existing methods.
Authors: Daniel Raggi, Gem Stapleton, Mateja Jamnik, Aaron Stockdill, Grecia Garcia Garcia, Peter C-H. Cheng
Abstract: Representation choice is of fundamental importance to our ability to communicate and reason effectively. A major unsolved problem, addressed in this paper, is how to devise \textit{representational-system (RS) agnostic} techniques that drive representation transformation and choice. We present a novel calculus, called \textit{structure transfer}, that enables representation transformation across diverse RSs. Specifically, given a \textit{source} representation drawn from a source RS, the rules of structure transfer allow us to generate a \textit{target} representation for a target RS. The generality of structure transfer comes in part from its ability to ensure that the source representation and the generated target representation satisfy \textit{any} specified relation (such as semantic equivalence). This is done by exploiting \textit{schemas}, which encode knowledge about RSs. Specifically, schemas can express \textit{preservation of information} across relations between any pair of RSs, and this knowledge is used by structure transfer to derive a structure for the target representation which ensures that the desired relation holds. We formalise this using Representational Systems Theory~\cite{raggi2022rst}, building on the key concept of a \textit{construction space}. The abstract nature of construction spaces grants them the generality to model RSs of diverse kinds, including formal languages, geometric figures and diagrams, as well as informal notations. Consequently, structure transfer is a system-agnostic calculus that can be used to identify alternative representations in a wide range of practical settings.
Authors: Minjung Park, Gyuyeon Na, Soyoun Kim, Sunyoung Moon, HyeonJeong Cha, Sangmi Chai
Abstract: Abnormal cryptocurrency transactions - such as mixing services, fraudulent transfers, and pump-and-dump operations -- pose escalating risks to financial integrity but remain notoriously difficult to detect due to class imbalance, temporal volatility, and complex network dependencies. Existing approaches are predominantly model-centric and post hoc, flagging anomalies only after they occur and thus offering limited preventive value. This paper introduces HyPV-LEAD (Hyperbolic Peak-Valley Lead-time Enabled Anomaly Detection), a data-driven early-warning framework that explicitly incorporates lead time into anomaly detection. Unlike prior methods, HyPV-LEAD integrates three innovations: (1) window-horizon modeling to guarantee actionable lead-time alerts, (2) Peak-Valley (PV) sampling to mitigate class imbalance while preserving temporal continuity, and (3) hyperbolic embedding to capture the hierarchical and scale-free properties of blockchain transaction networks. Empirical evaluation on large-scale Bitcoin transaction data demonstrates that HyPV-LEAD consistently outperforms state-of-the-art baselines, achieving a PR-AUC of 0.9624 with significant gains in precision and recall. Ablation studies further confirm that each component - PV sampling, hyperbolic embedding, and structural-temporal modeling - provides complementary benefits, with the full framework delivering the highest performance. By shifting anomaly detection from reactive classification to proactive early-warning, HyPV-LEAD establishes a robust foundation for real-time risk management, anti-money laundering (AML) compliance, and financial security in dynamic blockchain environments.
Authors: David Cortes, Carlos Juiz, Belen Bermejo
Abstract: Training large-scale deep learning models has become a key challenge for the scientific community and industry. While the massive use of GPUs can significantly speed up training times, this approach has a negative impact on efficiency. In this article, we present a detailed analysis of the times reported by MLPerf Training v4.1 on four workloads: BERT, Llama2 LoRA, RetinaNet, and Stable Diffusion, showing that there are configurations that optimise the relationship between performance, GPU usage, and efficiency. The results point to a break-even point that allows training times to be reduced while maximising efficiency.
Authors: Napsu Karmitsa, Antti Airola, Tapio Pahikkala, Tinja Pitk\"am\"aki
Abstract: The increasing availability of personal data has enabled significant advances in fields such as machine learning, healthcare, and cybersecurity. However, this data abundance also raises serious privacy concerns, especially in light of powerful re-identification attacks and growing legal and ethical demands for responsible data use. Differential privacy (DP) has emerged as a principled, mathematically grounded framework for mitigating these risks. This review provides a comprehensive survey of DP, covering its theoretical foundations, practical mechanisms, and real-world applications. It explores key algorithmic tools and domain-specific challenges - particularly in privacy-preserving machine learning and synthetic data generation. The report also highlights usability issues and the need for improved communication and transparency in DP systems. Overall, the goal is to support informed adoption of DP by researchers and practitioners navigating the evolving landscape of data privacy.
Authors: Arnau Quera-Bofarull, Nicholas Bishop, Joel Dyer, Daniel Jarne Ornia, Anisoara Calinescu, Doyne Farmer, Michael Wooldridge
Abstract: Agent-based models (ABMs) simulate complex systems by capturing the bottom-up interactions of individual agents comprising the system. Many complex systems of interest, such as epidemics or financial markets, involve thousands or even millions of agents. Consequently, ABMs often become computationally demanding and rely on the calibration of numerous free parameters, which has significantly hindered their widespread adoption. In this paper, we demonstrate that automatic differentiation (AD) techniques can effectively alleviate these computational burdens. By applying AD to ABMs, the gradients of the simulator become readily available, greatly facilitating essential tasks such as calibration and sensitivity analysis. Specifically, we show how AD enables variational inference (VI) techniques for efficient parameter calibration. Our experiments demonstrate substantial performance improvements and computational savings using VI on three prominent ABMs: Axtell's model of firms; Sugarscape; and the SIR epidemiological model. Our approach thus significantly enhances the practicality and scalability of ABMs for studying complex systems.
Authors: Xizhe Zhang, Jiayang Zhu
Abstract: Astrocytes are critical glial cells whose altered morphology and density are hallmarks of many neurological disorders. However, their intricate branching and stain dependent variability make automated detection of histological images a highly challenging task. To address these challenges, we propose a hybrid CNN Transformer detector that combines local feature extraction with global contextual reasoning. A heatmap guided query mechanism generates spatially grounded anchors for small and faint astrocytes, while a lightweight Transformer module improves discrimination in dense clusters. Evaluated on ALDH1L1 and GFAP stained astrocyte datasets, the model consistently outperformed Faster R-CNN, YOLOv11 and DETR, achieving higher sensitivity with fewer false positives, as confirmed by FROC analysis. These results highlight the potential of hybrid CNN Transformer architectures for robust astrocyte detection and provide a foundation for advanced computational pathology tools.
Authors: Fleur Hendriks, Ond\v{r}ej Roko\v{s}, Martin Do\v{s}k\'a\v{r}, Marc G. D. Geers, Vlado Menkovski
Abstract: Bifurcation phenomena in nonlinear dynamical systems often lead to multiple coexisting stable solutions, particularly in the presence of symmetry breaking. Deterministic machine learning models struggle to capture this multiplicity, averaging over solutions and failing to represent lower-symmetry outcomes. In this work, we propose a generative framework based on flow matching to model the full probability distribution over bifurcation outcomes. Our method enables direct sampling of multiple valid solutions while preserving system symmetries through equivariant modeling. We introduce a symmetric matching strategy that aligns predicted and target outputs under group actions, allowing accurate learning in equivariant settings. We validate our approach on a range of systems, from toy models to complex physical problems such as buckling beams and the Allen-Cahn equation. Our results demonstrate that flow matching significantly outperforms non-probabilistic and variational methods in capturing multimodal distributions and symmetry-breaking bifurcations, offering a principled and scalable solution for modeling multistability in high-dimensional systems.
Authors: Ilana Sebag, Jean-Yves Franceschi, Alain Rakotomamonjy, Alexandre Allauzen, Jamal Atif
Abstract: Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privacy (DP) to protect sensitive data, their sensitivity to membership inference attacks (MIAs), a key threat to data confidentiality, remains poorly understood. In this work, we present the first unified theoretical and empirical analysis of the privacy risks faced by differentially private generative models. We begin by showing, through a stability-based analysis, that GANs exhibit fundamentally lower sensitivity to data perturbations than diffusion models, suggesting a structural advantage in resisting MIAs. We then validate this insight with a comprehensive empirical study using a standardized MIA pipeline to evaluate privacy leakage across datasets and privacy budgets. Our results consistently reveal a marked privacy robustness gap in favor of GANs, even in strong DP regimes, highlighting that model type alone can critically shape privacy leakage.
Authors: Natalia Flechas Manrique, Alberto Mart\'inez, Elena L\'opez-Mart\'inez, Luc Andrea, Rom\'an Orus, Aitor Manteca, Aitziber L. Cortajarena, Lloren\c{c} Espinosa-Portal\'es
Abstract: Epitopes are short antigenic peptide sequences which are recognized by antibodies or immune cell receptors. These are central to the development of immunotherapies, vaccines, and diagnostics. However, the rational design of synthetic epitope libraries is challenging due to the large combinatorial sequence space, $20^n$ combinations for linear epitopes of n amino acids, making screening and testing unfeasible, even with high throughput experimental techniques. In this study, we present a large language model, epiGPTope, pre-trained on protein data and specifically fine-tuned on linear epitopes, which for the first time can directly generate novel epitope-like sequences, which are found to possess statistical properties analogous to the ones of known epitopes. This generative approach can be used to prepare libraries of epitope candidate sequences. We further train statistical classifiers to predict whether an epitope sequence is of bacterial or viral origin, thus narrowing the candidate library and increasing the likelihood of identifying specific epitopes. We propose that such combination of generative and predictive models can be of assistance in epitope discovery. The approach uses only primary amino acid sequences of linear epitopes, bypassing the need for a geometric framework or hand-crafted features of the sequences. By developing a method to create biologically feasible sequences, we anticipate faster and more cost-effective generation and screening of synthetic epitopes, with relevant applications in the development of new biotechnologies.
Authors: Oguzhan Baser, Kaan Kale, Po-han Li, Sandeep Chinchali
Abstract: Resource allocation is crucial for the performance optimization of cloud-assisted multi-agent intelligence. Traditional methods often overlook agents' diverse computational capabilities and complex operating environments, leading to inefficient and unfair resource distribution. To address this, we open-sourced Fair-Synergy, an algorithmic framework that utilizes the concave relationship between the agents' accuracy and the system resources to ensure fair resource allocation across fleet intelligence. We extend traditional allocation approaches to encompass a multidimensional machine learning utility landscape defined by model parameters, training data volume, and task complexity. We evaluate Fair-Synergy with advanced vision and language models such as BERT, VGG16, MobileNet, and ResNets on datasets including MNIST, CIFAR-10, CIFAR-100, BDD, and GLUE. We demonstrate that Fair-Synergy outperforms standard benchmarks by up to 25% in multi-agent inference and 11% in multi-agent learning settings. Also, we explore how the level of fairness affects the least advantaged, most advantaged, and average agents, providing insights for equitable fleet intelligence.
Authors: Akash Malhotra, Nac\'era Seghouani
Abstract: We introduce the Neural Field Turing Machine (NFTM), a differentiable architecture that unifies symbolic computation, physical simulation, and perceptual inference within continuous spatial fields. NFTM combines a neural controller, continuous memory field, and movable read/write heads that perform local updates. At each timestep, the controller reads local patches, computes updates via learned rules, and writes them back while updating head positions. This design achieves linear O(N) scaling through fixed-radius neighborhoods while maintaining Turing completeness under bounded error. We demonstrate three example instantiations of NFTM: cellular automata simulation (Rule 110), physics-informed PDE solvers (2D heat equation), and iterative image refinement (CIFAR-10 inpainting). These instantiations learn local update rules that compose into global dynamics, exhibit stable long-horizon rollouts, and generalize beyond training horizons. NFTM provides a unified computational substrate bridging discrete algorithms and continuous field dynamics within a single differentiable framework.
Authors: Guoxin Wang, Qingyuan Wang, Binhua Huang, Shaowu Chen, Deepu John
Abstract: Vision Transformers (ViTs) achieve strong performance in image classification but incur high computational costs from processing all image tokens. To reduce inference costs in large ViTs without compromising accuracy, we propose TinyDrop, a training-free token dropping framework guided by a lightweight vision model. The guidance model estimates the importance of tokens while performing inference, thereby selectively discarding low-importance tokens if large vit models need to perform attention calculations. The framework operates plug-and-play, requires no architectural modifications, and is compatible with diverse ViT architectures. Evaluations on standard image classification benchmarks demonstrate that our framework reduces FLOPs by up to 80% for ViTs with minimal accuracy degradation, highlighting its generalization capability and practical utility for efficient ViT-based classification.
Authors: Chenlu Ye, Zhou Yu, Ziji Zhang, Hao Chen, Narayanan Sadagopan, Jing Huang, Tong Zhang, Anurag Beniwal
Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged to be a predominant paradigm for mathematical reasoning tasks, offering stable improvements in reasoning ability. However, Outcome Reward Models (ORMs) in RLVR are too coarse-grained to distinguish flawed reasoning within correct answers or valid reasoning within incorrect answers. This lack of granularity introduces noisy and misleading gradients significantly and hinders further progress in reasoning process quality. While Process Reward Models (PRMs) offer fine-grained guidance for intermediate steps, they frequently suffer from inaccuracies and are susceptible to reward hacking. To resolve this dilemma, we introduce PRocess cOnsistency Filter (PROF), an effective data process curation method that harmonizes noisy, fine-grained process rewards with accurate, coarse-grained outcome rewards. Rather than naively blending PRM and ORM in the objective function (arXiv:archive/2506.18896), PROF leverages their complementary strengths through consistency-driven sample selection. Our approach retains correct responses with higher averaged process values and incorrect responses with lower averaged process values, while maintaining positive/negative training sample balance. Extensive experiments demonstrate that our method not only consistently improves the final accuracy over $4\%$ compared to the blending approaches, but also strengthens the quality of intermediate reasoning steps. Codes and training recipes are available at https://github.com/Chenluye99/PROF.
Authors: Hoan My Tran, Damien Lolive, Aghilas Sini, Arnaud Delhay, Pierre-Fran\c{c}ois Marteau, David Guennec
Abstract: Recent advancements in generative AI, particularly in speech synthesis, have enabled the generation of highly natural-sounding synthetic speech that closely mimics human voices. While these innovations hold promise for applications like assistive technologies, they also pose significant risks, including misuse for fraudulent activities, identity theft, and security threats. Current research on spoofing detection countermeasures remains limited by generalization to unseen deepfake attacks and languages. To address this, we propose a gating mechanism extracting relevant feature from the speech foundation XLS-R model as a front-end feature extractor. For downstream back-end classifier, we employ Multi-kernel gated Convolution (MultiConv) to capture both local and global speech artifacts. Additionally, we introduce Centered Kernel Alignment (CKA) as a similarity metric to enforce diversity in learned features across different MultiConv layers. By integrating CKA with our gating mechanism, we hypothesize that each component helps improving the learning of distinct synthetic speech patterns. Experimental results demonstrate that our approach achieves state-of-the-art performance on in-domain benchmarks while generalizing robustly to out-of-domain datasets, including multilingual speech samples. This underscores its potential as a versatile solution for detecting evolving speech deepfake threats.
Authors: Soukeina Elhassen, Lama Al Khuzayem, Areej Alhothali, Ohoud Alzamzami, Nahed Alowaidi
Abstract: Sign language (SL) is an essential communication form for hearing-impaired and deaf people, enabling engagement within the broader society. Despite its significance, limited public awareness of SL often leads to inequitable access to educational and professional opportunities, thereby contributing to social exclusion, particularly in Saudi Arabia, where over 84,000 individuals depend on Saudi Sign Language (SSL) as their primary form of communication. Although certain technological approaches have helped to improve communication for individuals with hearing impairments, there continues to be an urgent requirement for more precise and dependable translation techniques, especially for Arabic sign language variants like SSL. Most state-of-the-art solutions have primarily focused on non-Arabic sign languages, resulting in a considerable absence of resources dedicated to Arabic sign language, specifically SSL. The complexity of the Arabic language and the prevalence of isolated sign language datasets that concentrate on individual words instead of continuous speech contribute to this issue. To address this gap, our research represents an important step in developing SSL resources. To address this, we introduce the first continuous Saudi Sign Language dataset called KAU-CSSL, focusing on complete sentences to facilitate further research and enable sophisticated recognition systems for SSL recognition and translation. Additionally, we propose a transformer-based model, utilizing a pretrained ResNet-18 for spatial feature extraction and a Transformer Encoder with Bidirectional LSTM for temporal dependencies, achieving 99.02\% accuracy at signer dependent mode and 77.71\% accuracy at signer independent mode. This development leads the way to not only improving communication tools for the SSL community but also making a substantial contribution to the wider field of sign language.
Authors: Yubo Gao, Renbo Tu, Gennady Pekhimenko, Nandita Vijaykumar
Abstract: Differentially-Private SGD (DP-SGD) is a powerful technique to protect user privacy when using sensitive data to train neural networks. During training, converting model weights and activations into low-precision formats, i.e., quantization, can drastically reduce training times, energy consumption, and cost, and is thus a widely used technique. In this work, we demonstrate that quantization causes significantly higher accuracy degradation in DP-SGD compared to regular SGD. We observe that this is caused by noise injection in DP-SGD, which amplifies quantization variance, leading to disproportionately large accuracy degradation. To address this challenge, we present QPQuant, a dynamic quantization framework that adaptively selects a changing subset of layers to quantize at each epoch. Our method combines two key ideas that effectively reduce quantization variance: (i) probabilistic sampling of the layers that rotates which layers are quantized every epoch, and (ii) loss-aware layer prioritization, which uses a differentially private loss sensitivity estimator to identify layers that can be quantized with minimal impact on model quality. This estimator consumes a negligible fraction of the overall privacy budget, preserving DP guarantees. Empirical evaluations on ResNet18, ResNet50, and DenseNet121 across a range of datasets demonstrate that DPQuant consistently outperforms static quantization baselines, achieving near Pareto-optimal accuracy-compute trade-offs and up to 2.21x theoretical throughput improvements on low-precision hardware, with less than 2% drop in validation accuracy.
Authors: Duy A. Nguyen, Abhi Kamboj, Minh N. Do
Abstract: Addressing missing modalities and limited labeled data is crucial for advancing robust multimodal learning. We propose Robult, a scalable framework designed to mitigate these challenges by preserving modality-specific information and leveraging redundancy through a novel information-theoretic approach. Robult optimizes two core objectives: (1) a soft Positive-Unlabeled (PU) contrastive loss that maximizes task-relevant feature alignment while effectively utilizing limited labeled data in semi-supervised settings, and (2) a latent reconstruction loss that ensures unique modality-specific information is retained. These strategies, embedded within a modular design, enhance performance across various downstream tasks and ensure resilience to incomplete modalities during inference. Experimental results across diverse datasets validate that Robult achieves superior performance over existing approaches in both semi-supervised learning and missing modality contexts. Furthermore, its lightweight design promotes scalability and seamless integration with existing architectures, making it suitable for real-world multimodal applications.
Authors: Jigang Fan, Zhenghong Zhou, Ruofan Jin, Le Cong, Mengdi Wang, Zaixi Zhang
Abstract: Proteins play crucial roles in almost all biological processes. The advancement of deep learning has greatly accelerated the development of protein foundation models, leading to significant successes in protein understanding and design. However, the lack of systematic red-teaming for these models has raised serious concerns about their potential misuse, such as generating proteins with biological safety risks. This paper introduces SafeProtein, the first red-teaming framework designed for protein foundation models to the best of our knowledge. SafeProtein combines multimodal prompt engineering and heuristic beam search to systematically design red-teaming methods and conduct tests on protein foundation models. We also curated SafeProtein-Bench, which includes a manually constructed red-teaming benchmark dataset and a comprehensive evaluation protocol. SafeProtein achieved continuous jailbreaks on state-of-the-art protein foundation models (up to 70% attack success rate for ESM3), revealing potential biological safety risks in current protein foundation models and providing insights for the development of robust security protection technologies for frontier models. The codes will be made publicly available at https://github.com/jigang-fan/SafeProtein.
Authors: Han Shen
Abstract: For RL algorithms, appropriate entropy control is crucial to their effectiveness. To control the policy entropy, a commonly used method is entropy regularization, which is adopted in various popular RL algorithms including PPO, SAC and A3C. Although entropy regularization proves effective in robotic and games RL conventionally, studies found that it gives weak to no gains in LLM-RL training. In this work, we study the issues of entropy bonus in LLM-RL setting. Specifically, we first argue that the conventional entropy regularization suffers from the LLM's extremely large response space and the sparsity of the optimal outputs. As a remedy, we propose AEnt, an entropy control method that utilizes a new clamped entropy bonus with an automatically adjusted coefficient. The clamped entropy is evaluated with the re-normalized policy defined on certain smaller token space, which encourages exploration within a more compact response set. In addition, the algorithm automatically adjusts entropy coefficient according to the clamped entropy value, effectively controlling the entropy-induced bias while leveraging the entropy's benefits. AEnt is tested in math-reasoning tasks under different base models and datasets, and it is observed that AEnt outperforms the baselines consistently across multiple benchmarks.
Authors: Itai Zilberstein, Alberto Candela, Steve Chien
Abstract: Advancements in onboard computing mean remote sensing agents can employ state-of-the-art computer vision and machine learning at the edge. These capabilities can be leveraged to unlock new rare, transient, and pinpoint measurements of dynamic science phenomena. In this paper, we present an automated workflow that synthesizes the detection of these dynamic events in look-ahead satellite imagery with autonomous trajectory planning for a follow-up high-resolution sensor to obtain pinpoint measurements. We apply this workflow to the use case of observing volcanic plumes. We analyze classification approaches including traditional machine learning algorithms and convolutional neural networks. We present several trajectory planning algorithms that track the morphological features of a plume and integrate these algorithms with the classifiers. We show through simulation an order of magnitude increase in the utility return of the high-resolution instrument compared to baselines while maintaining efficient runtimes.
Authors: Honglu Zhou, Xiangyu Peng, Shrikant Kendre, Michael S. Ryoo, Silvio Savarese, Caiming Xiong, Juan Carlos Niebles
Abstract: Next-generation AI companions must go beyond general video understanding to resolve spatial and temporal references in dynamic, real-world environments. Existing Video Large Language Models (Video LLMs), while capable of coarse-level comprehension, struggle with fine-grained, spatiotemporal reasoning, especially when user queries rely on time-based event references for temporal anchoring, or gestural cues for spatial anchoring to clarify object references and positions. To bridge this critical gap, we introduce Strefer, a synthetic instruction data generation framework designed to equip Video LLMs with spatiotemporal referring and reasoning capabilities. Strefer produces diverse instruction-tuning data using a data engine that pseudo-annotates temporally dense, fine-grained video metadata, capturing rich spatial and temporal information in a structured manner, including subjects, objects, their locations as masklets, and their action descriptions and timelines. Our approach enhances the ability of Video LLMs to interpret spatial and temporal references, fostering more versatile, space-time-aware reasoning essential for real-world AI companions. Without using proprietary models, costly human annotation, or the need to annotate large volumes of new videos, experimental evaluations show that models trained with data produced by Strefer outperform baselines on tasks requiring spatial and temporal disambiguation. Additionally, these models exhibit enhanced space-time-aware reasoning, establishing a new foundation for perceptually grounded, instruction-tuned Video LLMs.
Authors: Gwen Legate, Irina Rish, Eugene Belilovsky
Abstract: Federated learning enables collaborative model training across numerous edge devices without requiring participants to share data; however, memory and communication constraints on these edge devices may preclude their participation in training. We consider a setting in which a subset of edge devices are below a critical memory or communication threshold required to conduct model updates. Under typical federated optimization algorithms, these devices are excluded from training which renders their data inaccessible and increases system induced bias. We are inspired by MeZO, a zeroth-order method used for memory-efficient fine-tuning. The increased variance inherent to zeroth-order gradient approximations has relegated previous zeroth-order optimizers exclusively to the domain of fine tuning; a limitation we seek to correct. We devise a federated, memory-efficient zeroth-order optimizer, ZOWarmUp that permits zeroth-order training from a random initialization. ZOWarmUp leverages differing client capabilities and careful variance reduction techniques to facilitate participation of under-represented, low-resource clients in model training. Like other federated zeroth-order methods, ZOWarmUp eliminates the need for edge devices to transmit their full gradients to the server and instead relies on only a small set of random seeds, rendering the up-link communication cost negligible. We present experiments using various datasets and model architectures to show that ZOWarmUp is a robust algorithm that can can be applied under a wide variety of circumstances. For systems with a high proportion of edge devices that would otherwise be excluded from training, this algorithm provides access to a greater volume and diversity of data, thus improving training outcomes.
Authors: Xingxuan Zhang, Gang Ren, Han Yu, Hao Yuan, Hui Wang, Jiansheng Li, Jiayun Wu, Lang Mo, Li Mao, Mingchao Hao, Ningbo Dai, Renzhe Xu, Shuyang Li, Tianyang Zhang, Yue He, Yuanrui Wang, Yunjia Zhang, Zijing Xu, Dongzhe Li, Fang Gao, Hao Zou, Jiandong Liu, Jiashuo Liu, Jiawei Xu, Kaijie Cheng, Kehan Li, Linjun Zhou, Qing Li, Shaohua Fan, Xiaoyu Lin, Xinyan Han, Xuanyue Li, Yan Lu, Yuan Xue, Yuanyuan Jiang, Zimu Wang, Zhenlei Wang, Peng Cui
Abstract: We argue that progress toward general intelligence requires complementary foundation models grounded in language, the physical world, and structured data. This report presents LimiX, the first installment of our large structured-data models (LDMs). LimiX treats structured data as a joint distribution over variables and missingness, thus capable of addressing a wide range of tabular tasks through query-based conditional prediction via a single model. LimiX is pretrained using masked joint-distribution modeling with an episodic, context-conditional objective, where the model predicts for query subsets conditioned on dataset-specific contexts, supporting rapid, training-free adaptation at inference. We evaluate LimiX across 10 large structured-data benchmarks with broad regimes of sample size, feature dimensionality, class number, categorical-to-numerical feature ratio, missingness, and sample-to-feature ratios. With a single model and a unified interface, LimiX consistently surpasses strong baselines including gradient-boosting trees, deep tabular networks, recent tabular foundation models, and automated ensembles, as shown in Figure 1 and Figure 2. The superiority holds across a wide range of tasks, such as classification, regression, missing value imputation, and data generation, often by substantial margins, while avoiding task-specific architectures or bespoke training per task. All LimiX models are publicly accessible under Apache 2.0.
Authors: Yanlin Zhang, Sungyong Chung, Nachuan Li, Dana Monzer, Hani S. Mahmassani, Samer H. Hamdar, Alireza Talebpour
Abstract: The Waymo Open Motion Dataset (WOMD) has become a popular resource for data-driven modeling of autonomous vehicles (AVs) behavior. However, its validity for behavioral analysis remains uncertain due to proprietary post-processing, the absence of error quantification, and the segmentation of trajectories into 20-second clips. This study examines whether WOMD accurately captures the dynamics and interactions observed in real-world AV operations. Leveraging an independently collected naturalistic dataset from Level 4 AV operations in Phoenix, Arizona (PHX), we perform comparative analyses across three representative urban driving scenarios: discharging at signalized intersections, car-following, and lane-changing behaviors. For the discharging analysis, headways are manually extracted from aerial video to ensure negligible measurement error. For the car-following and lane-changing cases, we apply the Simulation-Extrapolation (SIMEX) method to account for empirically estimated error in the PHX data and use Dynamic Time Warping (DTW) distances to quantify behavioral differences. Results across all scenarios consistently show that behavior in PHX falls outside the behavioral envelope of WOMD. Notably, WOMD underrepresents short headways and abrupt decelerations. These findings suggest that behavioral models calibrated solely on WOMD may systematically underestimate the variability, risk, and complexity of naturalistic driving. Caution is therefore warranted when using WOMD for behavior modeling without proper validation against independently collected data.
Authors: Kaizhi Zheng, Kaiwen Zhou, Jing Gu, Yue Fan, Jialu Wang, Zonglin Di, Xuehai He, Xin Eric Wang
Abstract: Building a conversational embodied agent to execute real-life tasks has been a long-standing yet quite challenging research goal, as it requires effective human-agent communication, multi-modal understanding, long-range sequential decision making, etc. Traditional symbolic methods have scaling and generalization issues, while end-to-end deep learning models suffer from data scarcity and high task complexity, and are often hard to explain. To benefit from both worlds, we propose JARVIS, a neuro-symbolic commonsense reasoning framework for modular, generalizable, and interpretable conversational embodied agents. First, it acquires symbolic representations by prompting large language models (LLMs) for language understanding and sub-goal planning, and by constructing semantic maps from visual observations. Then the symbolic module reasons for sub-goal planning and action generation based on task- and action-level common sense. Extensive experiments on the TEACh dataset validate the efficacy and efficiency of our JARVIS framework, which achieves state-of-the-art (SOTA) results on all three dialog-based embodied tasks, including Execution from Dialog History (EDH), Trajectory from Dialog (TfD), and Two-Agent Task Completion (TATC) (e.g., our method boosts the unseen Success Rate on EDH from 6.1\% to 15.8\%). Moreover, we systematically analyze the essential factors that affect the task performance and also demonstrate the superiority of our method in few-shot settings. Our JARVIS model ranks first in the Alexa Prize SimBot Public Benchmark Challenge.
Authors: Vanshika Vats, Marzia Binta Nizam, Minghao Liu, Ziyuan Wang, Richard Ho, Mohnish Sai Prasad, Vincent Titterton, Sai Venkat Malreddy, Riya Aggarwal, Yanwen Xu, Lei Ding, Jay Mehta, Nathan Grinnell, Li Liu, Sijia Zhong, Devanathan Nallur Gandamani, Xinyi Tang, Rohan Ghosalkar, Celeste Shen, Rachel Shen, Nafisa Hussain, Kesav Ravichandran, James Davis
Abstract: As the capabilities of artificial intelligence (AI) continue to expand rapidly, Human-AI (HAI) Collaboration, combining human intellect and AI systems, has become pivotal for advancing problem-solving and decision-making processes. The advent of Large Foundation Models (LFMs) has greatly expanded its potential, offering unprecedented capabilities by leveraging vast amounts of data to understand and predict complex patterns. At the same time, realizing this potential responsibly requires addressing persistent challenges related to safety, fairness, and control. This paper reviews the crucial integration of LFMs with HAI, highlighting both opportunities and risks. We structure our analysis around four areas: human-guided model development, collaborative design principles, ethical and governance frameworks, and applications in high-stakes domains. Our review shows that successful HAI systems are not the automatic result of stronger models but the product of careful, human-centered design. By identifying key open challenges, this survey aims to give insight into current and future research that turns the raw power of LFMs into partnerships that are reliable, trustworthy, and beneficial to society.
Authors: Stylianos Loukas Vasileiou, William Yeoh, Alessandro Previti, Tran Cao Son
Abstract: Explanation generation frameworks aim to make AI systems' decisions transparent and understandable to human users. However, generating explanations in uncertain environments characterized by incomplete information and probabilistic models remains a significant challenge. In this paper, we propose a novel framework for generating probabilistic monolithic explanations and model reconciling explanations. Monolithic explanations provide self-contained reasons for an explanandum without considering the agent receiving the explanation, while model reconciling explanations account for the knowledge of the agent receiving the explanation. For monolithic explanations, our approach integrates uncertainty by utilizing probabilistic logic to increase the probability of the explanandum. For model reconciling explanations, we propose a framework that extends the logic-based variant of the model reconciliation problem to account for probabilistic human models, where the goal is to find explanations that increase the probability of the explanandum while minimizing conflicts between the explanation and the probabilistic human model. We introduce explanatory gain and explanatory power as quantitative metrics to assess the quality of these explanations. Further, we present algorithms that exploit the duality between minimal correction sets and minimal unsatisfiable sets to efficiently compute both types of explanations in probabilistic contexts. Extensive experimental evaluations on various benchmarks demonstrate the effectiveness and scalability of our approach in generating explanations under uncertainty.
Authors: Itzel Olivos-Castillo, Paul Schrater, Xaq Pitkow
Abstract: A key challenge in advancing artificial intelligence is achieving the right balance between utility maximization and resource use by both external movement and internal computation. While this trade-off has been studied in fully observable settings, our understanding of resource efficiency in partially observable environments remains limited. Motivated by this challenge, we develop a version of the POMDP framework where the information gained through inference is treated as a resource that must be optimized alongside task performance and motion effort. By solving this problem in environments described by linear-Gaussian dynamics, we uncover fundamental principles of resource efficiency. Our study reveals a phase transition in the inference, switching from a Bayes-optimal approach to one that strategically leaves some uncertainty unresolved. This frugal behavior gives rise to a structured family of equally effective strategies, facilitating adaptation to later objectives and constraints overlooked during the original optimization. We illustrate the applicability of our framework and the generality of the principles we derived using two nonlinear tasks. Overall, this work provides a foundation for a new type of rational computation that both brains and machines could use for effective but resource-efficient control under uncertainty.
Authors: Siyuan Lu, Jiaqi Shao, Bing Luo, Tao Lin
Abstract: Large Language Model (LLM) based multi-agent systems (MAS) have shown promise in tackling complex tasks, but often rely on predefined roles and centralized coordination, limiting their adaptability to evolving challenges. This paper introduces MorphAgent, a novel Autonomous, Self-Organizing, and Self-Adaptive Multi-Agent System for decentralized agent collaboration that enables agents to dynamically evolve their roles and capabilities. Our approach employs self-evolving agent profiles, optimized through three key metrics, guiding agents in refining their individual expertise while maintaining complementary team dynamics. MorphAgent implements a two-phase process: a Profile Update phase for profile optimization, followed by a Task Execution phase where agents continuously adapt their roles based on task feedback. Our experimental results show that MorphAgent outperforms existing frameworks in terms of task performance and adaptability to changing requirements, paving the way for more robust and versatile multi-agent collaborative systems.
Authors: Hanqi Duan, Yao Cheng, Jianxiang Yu, Yao Liu, Xiang Li
Abstract: Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, GNNs lack the inherent semantic understanding capability of rich textual node attributes, limiting their effectiveness in applications. On the other hand, we empirically observe that for existing GNN models, no one can consistently outperforms others across diverse datasets. In this paper, we study whether LLMs can act as an ensembler for multi-GNNs and propose the LensGNN model. The model first aligns multiple GNNs, mapping the representations of different GNNs into the same space. Then, through LoRA fine-tuning, it aligns the space between the GNN and the LLM, injecting graph tokens and textual information into LLMs. This allows LensGNN to ensemble multiple GNNs and take advantage of the strengths of LLM, leading to a deeper understanding of both textual semantic information and graph structural information. The experimental results show that LensGNN outperforms existing models. This research advances text-attributed graph ensemble learning by providing a robust and superior solution for integrating semantic and structural information. We provide our code and data here: https://github.com/AquariusAQ/LensGNN.
Authors: Daniel C. Castro, Aurelia Bustos, Shruthi Bannur, Stephanie L. Hyland, Kenza Bouzid, Maria Teodora Wetscherek, Maria Dolores S\'anchez-Valverde, Lara Jaques-P\'erez, Lourdes P\'erez-Rodr\'iguez, Kenji Takeda, Jos\'e Mar\'ia Salinas, Javier Alvarez-Valle, Joaqu\'in Galant Herrero, Antonio Pertusa
Abstract: Radiology report generation (RRG) aims to create free-text radiology reports from clinical imaging. Grounded radiology report generation (GRRG) extends RRG by including the localisation of individual findings on the image. Currently, there are no manually annotated chest X-ray (CXR) datasets to train GRRG models. In this work, we present a dataset called PadChest-GR (Grounded-Reporting) derived from PadChest aimed at training GRRG models for CXR images. We curate a public bi-lingual dataset of 4,555 CXR studies with grounded reports (3,099 abnormal and 1,456 normal), each containing complete lists of sentences describing individual present (positive) and absent (negative) findings in English and Spanish. In total, PadChest-GR contains 7,037 positive and 3,422 negative finding sentences. Every positive finding sentence is associated with up to two independent sets of bounding boxes labelled by different readers and has categorical labels for finding type, locations, and progression. To the best of our knowledge, PadChest-GR is the first manually curated dataset designed to train GRRG models for understanding and interpreting radiological images and generated text. By including detailed localization and comprehensive annotations of all clinically relevant findings, it provides a valuable resource for developing and evaluating GRRG models from CXR images. PadChest-GR can be downloaded under request from https://bimcv.cipf.es/bimcv-projects/padchest-gr/
Authors: Chengshuai Zhao, Riccardo De Maria, Tharindu Kumarage, Kumar Satvik Chaudhary, Garima Agrawal, Yiwen Li, Jongchan Park, Yuli Deng, Ying-Chih Chen, Huan Liu
Abstract: Advancements in large language models (LLMs) have enabled the development of intelligent educational tools that support inquiry-based learning across technical domains. In cybersecurity education, where accuracy and safety are paramount, systems must go beyond surface-level relevance to provide information that is both trustworthy and domain-appropriate. To address this challenge, we introduce CyberBOT, a question-answering chatbot that leverages a retrieval-augmented generation (RAG) pipeline to incorporate contextual information from course-specific materials and validate responses using a domain-specific cybersecurity ontology. The ontology serves as a structured reasoning layer that constrains and verifies LLM-generated answers, reducing the risk of misleading or unsafe guidance. CyberBOT has been deployed in a large graduate-level course at Arizona State University (ASU), where more than one hundred students actively engage with the system through a dedicated web-based platform. Computational evaluations in lab environments highlight the potential capacity of CyberBOT, and a forthcoming field study will evaluate its pedagogical impact. By integrating structured domain reasoning with modern generative capabilities, CyberBOT illustrates a promising direction for developing reliable and curriculum-aligned AI applications in specialized educational contexts.
Authors: Elliott Thornley
Abstract: Many fear that future artificial agents will resist shutdown. I present an idea - the POST-Agents Proposal - for ensuring that doesn't happen. I propose that we train agents to satisfy Preferences Only Between Same-Length Trajectories (POST). I then prove that POST - together with other conditions - implies Neutrality+: the agent maximizes expected utility, ignoring the probability distribution over trajectory-lengths. I argue that Neutrality+ keeps agents shutdownable and allows them to be useful.
Authors: Zhiyuan Wang, Bokui Chen, Yinya Huang, Qingxing Cao, Ming He, Jianping Fan, Xiaodan Liang
Abstract: Operations research (OR) is widely deployed to solve critical decision-making problems with complex objectives and constraints, impacting manufacturing, logistics, finance, and healthcare outcomes. While Large Language Models (LLMs) have shown promising results in various domains, their practical application in industry-relevant operations research (OR) problems presents significant challenges and opportunities. Preliminary industrial applications of LLMs for operations research face two critical deployment challenges: 1) Self-correction focuses on code syntax rather than mathematical accuracy, causing costly errors; 2) Complex expert selection creates unpredictable workflows that reduce transparency and increase maintenance costs, making them impractical for time-sensitive business applications. To address these business limitations, we introduce ORMind, a cognitive-inspired framework that enhances optimization through counterfactual reasoning. Our approach emulates human cognition, implementing an end-to-end workflow that systematically transforms requirements into mathematical models and executable solver code. It is currently being tested internally in Lenovo's AI Assistant, with plans to enhance optimization capabilities for both business and consumer customers. Experiments demonstrate that ORMind outperforms existing methods, achieving a 9.5\% improvement on the NL4Opt dataset and a 14.6\% improvement on the ComplexOR dataset.
Authors: Christopher Subia-Waud (Rayonlabs Team)
Abstract: Current AutoML platforms leave substantial performance untapped. Testing 180 fine-tuning tasks across models from 70M to 70B parameters, we found that HuggingFace AutoTrain, TogetherAI, Databricks, and Google Cloud consistently produce suboptimal configurations. Gradients, built on the Bittensor network, attacks this problem through competition. Independent miners race to find optimal hyperparameters, earning rewards proportional to their models' performance. This tournament drives exploration of configuration spaces that single-strategy methods never examine. In our experiments, Gradients achieved a 100\% win rate against TogetherAI, Databricks, and Google Cloud, and beat HuggingFace AutoTrain in 82.8\% of experiments. Mean improvements reached 42.1\% against commercial platforms. Retrieval-augmented generation tasks saw 30-40\% gains; diffusion models improved 23.4\% on person-specific generation. When miners compete for rewards, they develop optimization strategies that centralized approaches overlook. These findings demonstrate that decentralized systems with economic incentives can systematically outperform traditional AutoML, suggesting market dynamics may be key to achieving superior fine-tuning results. Code is available at https://github.com/rayonlabs/G.O.D.
Authors: Yuxuan Huang, Yihang Chen, Haozheng Zhang, Kang Li, Huichi Zhou, Meng Fang, Linyi Yang, Xiaoguang Li, Lifeng Shang, Songcen Xu, Jianye Hao, Kun Shao, Jun Wang
Abstract: The rapid progress of Large Language Models (LLMs) has given rise to a new category of autonomous AI systems, referred to as Deep Research (DR) agents. These agents are designed to tackle complex, multi-turn informational research tasks by leveraging a combination of dynamic reasoning, adaptive long-horizon planning, multi-hop information retrieval, iterative tool use, and the generation of structured analytical reports. In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute Deep Research agents. We begin by reviewing information acquisition strategies, contrasting API-based retrieval methods with browser-based exploration. We then examine modular tool-use frameworks, including code execution, multimodal input processing, and the integration of Model Context Protocols (MCPs) to support extensibility and ecosystem development. To systematize existing approaches, we propose a taxonomy that differentiates between static and dynamic workflows, and we classify agent architectures based on planning strategies and agent composition, including single-agent and multi-agent configurations. We also provide a critical evaluation of current benchmarks, highlighting key limitations such as restricted access to external knowledge, sequential execution inefficiencies, and misalignment between evaluation metrics and the practical objectives of DR agents. Finally, we outline open challenges and promising directions for future research. A curated and continuously updated repository of DR agent research is available at: {https://github.com/ai-agents-2030/awesome-deep-research-agent}.
URLs: https://github.com/ai-agents-2030/awesome-deep-research-agent
Authors: Zhiyuan Wang, Bokui Chen
Abstract: Continual learning (CL) empowers pre-trained vision-language models to adapt effectively to novel or previously underrepresented data distributions without comprehensive retraining, enhancing their adaptability and efficiency. While vision-language models like CLIP show great promise, they struggle to maintain performance across domains in incremental learning scenarios. Existing prompt learning methods face two main limitations: 1) they primarily focus on class-incremental learning scenarios, lacking specific strategies for multi-domain task incremental learning; 2) most current approaches employ single-modal prompts, neglecting the potential benefits of cross-modal information exchange. To address these challenges, we propose the \ChordPrompt framework, which facilitates a harmonious interplay between visual and textual prompts. \ChordPrompt introduces cross-modal prompts to leverage interactions between visual and textual information. Our approach also employs domain-adaptive text prompts to select appropriate prompts for continual adaptation across multiple domains. Comprehensive experiments on multi-domain incremental learning benchmarks demonstrate that \ChordPrompt outperforms state-of-the-art methods in zero-shot generalization and downstream task performance.
Authors: Ilias Chatzistefanidis, Navid Nikaein
Abstract: Large Language Model (LLM)-based autonomous agents are expected to play a vital role in the evolution of 6G networks, by empowering real-time decision-making related to management and service provisioning to end-users. This shift facilitates the transition from a specialized intelligence approach, where artificial intelligence (AI) algorithms handle isolated tasks, to artificial general intelligence (AGI)-driven networks, where agents possess broader reasoning capabilities and can manage diverse network functions. In this paper, we introduce a novel agentic paradigm that combines LLMs with real-time optimization algorithms towards Trustworthy AI, defined as symbiotic agents. Optimizers at the LLM's input-level provide bounded uncertainty steering for numerically precise tasks, whereas output-level optimizers supervised by the LLM enable adaptive real-time control. We design and implement two novel agent types including: (i) Radio Access Network optimizers, and (ii) multi-agent negotiators for Service-Level Agreements (SLAs). We further propose an end-to-end architecture for AGI networks and evaluate it on a 5G testbed capturing channel fluctuations from moving vehicles. Results show that symbiotic agents reduce decision errors fivefold compared to standalone LLM-based agents, while smaller language models (SLM) achieve similar accuracy with a 99.9% reduction in GPU resource overhead and in near-real-time loops of 82 ms. A multi-agent demonstration for collaborative RAN on the real-world testbed highlights significant flexibility in service-level agreement and resource allocation, reducing RAN over-utilization by approximately 44%. Drawing on our findings and open-source implementations, we introduce the symbiotic paradigm as the foundation for next-generation, AGI-driven networks-systems designed to remain adaptable, efficient, and trustworthy even as LLMs advance.
Authors: Forrest Hare Alec Sculley, Cameron Stockton
Abstract: We argue that ontology-structured knowledge graphs can play a crucial role in generating predictions about future events. By leveraging the semantic framework provided by Basic Formal Ontology (BFO) and Common Core Ontologies (CCO), we demonstrate how data such as the movements of a fishing vessel can be organized in and retrieved from a knowledge graph. These query results are then used to create Markov chain models, allowing us to predict future states based on the vessel's history. To fully support this process, we introduce the term `spatiotemporal instant' to complete the necessary structural semantics. Additionally, we critique the prevailing ontological model of probability, according to which probabilities are about the future. We propose an alternative view, where at least some probabilities are treated as being about actual process profiles, which better captures the dynamics of real-world phenomena. Finally, we demonstrate how our Markov chain-based probability calculations can be seamlessly integrated back into the knowledge graph, enabling further analysis and decision-making.
Authors: Ping Yu, Jack Lanchantin, Tianlu Wang, Weizhe Yuan, Olga Golovneva, Ilia Kulikov, Sainbayar Sukhbaatar, Jason Weston, Jing Xu
Abstract: We propose CoT-Self-Instruct, a synthetic data generation method that instructs LLMs to first reason and plan via Chain-of-Thought (CoT) based on given seed tasks, and then generate a new synthetic example of similar quality and complexity. This is followed by a filtering step to select high-quality data using automatic metrics, which are then used for LLM training. In verifiable reasoning, our synthetic data significantly outperforms existing training datasets, such as s1k and OpenMathReasoning, when evaluated on MATH500, AMC23, AIME24, and GPQA-Diamond. For non-verifiable instruction-following tasks, our method surpasses the performance of both human and standard Self-Instruct training data on the AlpacaEval 2.0 and Arena-Hard benchmarks.
Authors: Mubaris Nadeem, Johannes Zenkert, Lisa Bender, Christian Weber, Madjid Fathi
Abstract: Over the years, the need for rescue operations throughout the world has increased rapidly. Demographic changes and the resulting risk of injury or health disorders form the basis for emergency calls. In such scenarios, first responders are in a rush to reach the patient in need, provide first aid, and save lives. In these situations, they must be able to provide personalized and optimized healthcare in the shortest possible time and estimate the patients condition with the help of freshly recorded vital data in an emergency situation. However, in such a timedependent situation, first responders and medical experts cannot fully grasp their knowledge and need assistance and recommendation for further medical treatments. To achieve this, on the spot calculated, evaluated, and processed knowledge must be made available to improve treatments by first responders. The Knowledge Graph presented in this article as a central knowledge representation provides first responders with an innovative knowledge management that enables intelligent treatment recommendations with an artificial intelligence-based pre-recognition of the situation.
Authors: Xiancheng Gao, Yufeng Shi, Wengang Zhou, Houqiang Li
Abstract: Offline reinforcement learning refers to the process of learning policies from fixed datasets, without requiring additional environment interaction. However, it often relies on well-defined reward functions, which are difficult and expensive to design. Human feedback is an appealing alternative, but its two common forms, expert demonstrations and preferences, have complementary limitations. Demonstrations provide stepwise supervision, but they are costly to collect and often reflect limited expert behavior modes. In contrast, preferences are easier to collect, but it is unclear which parts of a behavior contribute most to a trajectory segment, leaving credit assignment unresolved. In this paper, we introduce a Search-Based Preference Weighting (SPW) scheme to unify these two feedback sources. For each transition in a preference labeled trajectory, SPW searches for the most similar state-action pairs from expert demonstrations and directly derives stepwise importance weights based on their similarity scores. These weights are then used to guide standard preference learning, enabling more accurate credit assignment that traditional approaches struggle to achieve. We demonstrate that SPW enables effective joint learning from preferences and demonstrations, outperforming prior methods that leverage both feedback types on challenging robot manipulation tasks.
Authors: Xinran Zhao, Boyuan Zheng, Chenglei Si, Haofei Yu, Ken Liu, Runlong Zhou, Ruochen Li, Tong Chen, Xiang Li, Yiming Zhang, Tongshuang Wu
Abstract: This paper revisits Ramon Llull's Ars combinatoria - a medieval framework for generating knowledge through symbolic recombination - as a conceptual foundation for building a modern Llull's thinking machine for research ideation. Our approach defines three compositional axes: Theme (e.g., efficiency, adaptivity), Domain (e.g., question answering, machine translation), and Method (e.g., adversarial training, linear attention). These elements represent high-level abstractions common in scientific work - motivations, problem settings, and technical approaches - and serve as building blocks for LLM-driven exploration. We mine elements from human experts or conference papers and show that prompting LLMs with curated combinations produces research ideas that are diverse, relevant, and grounded in current literature. This modern thinking machine offers a lightweight, interpretable tool for augmenting scientific creativity and suggests a path toward collaborative ideation between humans and AI.
Authors: Tony Lee, Haoqin Tu, Chi Heem Wong, Zijun Wang, Siwei Yang, Yifan Mai, Yuyin Zhou, Cihang Xie, Percy Liang
Abstract: Evaluations of audio-language models (ALMs) -- multimodal models that take interleaved audio and text as input and output text -- are hindered by the lack of standardized benchmarks; most benchmarks measure only one or two capabilities and omit evaluative aspects such as fairness or safety. Furthermore, comparison across models is difficult as separate evaluations test a limited number of models and use different prompting methods and inference parameters. To address these shortfalls, we introduce AHELM, a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE, which evaluates the ALMs on avoiding stereotypes, and CoRe-Bench, which measures reasoning over conversational audio through inferential multi-turn question answering -- to holistically measure the performance of ALMs across 10 aspects we have identified as important to the development and usage of ALMs: audio perception, knowledge, reasoning, emotion detection, bias, fairness, multilinguality, robustness, toxicity, and safety. We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models. We test 14 open-weight and closed-API ALMs from 3 developers and 3 additional simple baseline systems each consisting of an automatic speech recognizer and a language model. Our results show that while Gemini 2.5 Pro ranks top in 5 out of 10 aspects, it exhibits group unfairness ($p=0.01$) on ASR tasks whereas most of the other models do not. We also find that the baseline systems perform reasonably well on AHELM, with one ranking 6th overall despite having only speech-to-text capabilities. For transparency, all raw prompts, model generations, and outputs are available on our website at https://crfm.stanford.edu/helm/audio/v1.0.0. AHELM is intended to be a living benchmark and new datasets and models will be added over time.
Authors: Ziqi Wang, Boqin Yuan
Abstract: We present L-MARS (Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search), a system that reduces hallucination and uncertainty in legal question answering through coordinated multi-agent reasoning and retrieval. Unlike single-pass retrieval-augmented generation (RAG), L-MARS decomposes queries into subproblems, issues targeted searches across heterogeneous sources (Serper web, local RAG, CourtListener case law), and employs a Judge Agent to verify sufficiency, jurisdiction, and temporal validity before answer synthesis. This iterative reasoning-search-verification loop maintains coherence, filters noisy evidence, and grounds answers in authoritative law. We evaluated L-MARS on LegalSearchQA, a new benchmark of 200 up-to-date multiple choice legal questions in 2025. Results show that L-MARS substantially improves factual accuracy, reduces uncertainty, and achieves higher preference scores from both human experts and LLM-based judges. Our work demonstrates that multi-agent reasoning with agentic search offers a scalable and reproducible blueprint for deploying LLMs in high-stakes domains requiring precise legal retrieval and deliberation.
Authors: Zonghai Yao, Talha Chafekar, Junda Wang, Shuo Han, Feiyun Ouyang, Junhui Qian, Lingxi Li, Hong Yu
Abstract: Real-world adoption of closed-loop insulin delivery systems (CLIDS) in type 1 diabetes remains low, driven not by technical failure, but by diverse behavioral, psychosocial, and social barriers. We introduce ChatCLIDS, the first benchmark to rigorously evaluate LLM-driven persuasive dialogue for health behavior change. Our framework features a library of expert-validated virtual patients, each with clinically grounded, heterogeneous profiles and realistic adoption barriers, and simulates multi-turn interactions with nurse agents equipped with a diverse set of evidence-based persuasive strategies. ChatCLIDS uniquely supports longitudinal counseling and adversarial social influence scenarios, enabling robust, multi-dimensional evaluation. Our findings reveal that while larger and more reflective LLMs adapt strategies over time, all models struggle to overcome resistance, especially under realistic social pressure. These results highlight critical limitations of current LLMs for behavior change, and offer a high-fidelity, scalable testbed for advancing trustworthy persuasive AI in healthcare and beyond.
Authors: Jay Vaghasiya, Omkar Ghugarkar, Vishvesh Bhat, Vipul Dholaria, Julian McAuley
Abstract: We introduce CoreThink, a state-of-the-art Reasoning Layer built upon a novel reasoning method called General Symbolics. This approach diverges from reasoning paradigms such as test-time scaling, Supervised Fine-Tuning (SFT), and Reinforcement Learning with Verifiable Rewards (RLVR). CoreThink General Symbolic Reasoner (GSR) is specifically structured around three key use cases: tool-calling, code generation, and planning, demonstrating exemplary performance across a total of seven benchmarks in their respective areas. Notably, we are achieving SOTA scores of 66.66% on Livecodebench v6, 89% on Instruction-Following Evals, and 24.4% on ARC-AGI-2. We also present an agentic coding IDE, developed using the principles of General Symbolics, which achieves a state-of-the-art accuracy of 62.3% on SWE-Bench Lite. We are able to achieve these improvements without any fine-tuning or training costs. Our Reasoning Layer is designed to provide a pure performance uplift, ensuring that a model's accuracy on reasoning tasks is never negatively impacted. We argue that incumbent methods will eventually lead to diminishing returns in LLM performance, necessitating the development of new reasoning techniques. This technical report details our approach at a high level and the availability of the CoreThink models for reasoning-intensive use cases.
Authors: Yusheng Zheng, Yanpeng Hu, Wei Zhang, Andi Quinn
Abstract: Operating system schedulers suffer from a fundamental semantic gap, where kernel policies fail to understand application-specific needs, leading to suboptimal performance. We introduce SchedCP, the first framework that enables fully autonomous Large Language Model (LLM) agents to safely and efficiently optimize Linux schedulers without human involvement. Our core insight is that the challenge is not merely to apply a better LLM, but to architect a decoupled control plane that separates the AI's role of semantic reasoning ("what to optimize") from the system's role of execution ("how to observe and act"). Implemented as Model Context Protocol(MCP) server, SchedCP provides a stable interface with three key services: a Workload Analysis Engine, an evolving Scheduler Policy Repository, and an Execution Verifier that validates all AI-generated code and configure before deployment with static and dynamic analysis. We demonstrate this architecture's power with sched-agent, a multi-agent system that autonomously analyzes workloads, synthesizes custom eBPF scheduling policies, and deploys them via the sched\_ext infrastructure. Our evaluation shows that SchedCP achieves up to an 1.79x performance improvement, and a 13x cost reduction compared to naive agentic approaches, all while maintaining high success rate. By bridging the semantic gap, SchedCP democratizes expert-level system optimization and represents a step towards creating truly self-optimizing, application-aware operating systems. The code is open-sourced in https://github.com/eunomia-bpf/schedcp
Authors: Zhiyuan Wang, Xiaoyang Qu, Jing Xiao, Bokui Chen, Jianzong Wang
Abstract: Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive Prompt Decision Transformer (P2DT). This method enhances a transformer-based model by dynamically appending decision tokens during new task training, thus fostering task-specific policies. Our approach mitigates forgetting in continual and offline reinforcement learning scenarios. Moreover, P2DT leverages trajectories collected via traditional reinforcement learning from all tasks and generates new task-specific tokens during training, thereby retaining knowledge from previous studies. Preliminary results demonstrate that our model effectively alleviates catastrophic forgetting and scales well with increasing task environments.
Authors: Sean P. Walton, Ben J. Evans, Alma A. M. Rahat, James Stovold, Jakub Vincalek
Abstract: As AI systems increasingly shape decision making in creative design contexts, understanding how humans engage with these tools has become a critical challenge for interactive intelligent systems research. This paper contributes a challenge to rethink how to evaluate human--AI collaborative systems, advocating for a more nuanced and multidimensional approach. Findings from one of the largest field studies to date (n = 808) of a human--AI co-creative system, The Genetic Car Designer, complemented by a controlled lab study (n = 12) are presented. The system is based on an interactive evolutionary algorithm where participants were tasked with designing a simple two dimensional representation of a car. Participants were exposed to galleries of design suggestions generated by an intelligent system, MAP--Elites, and a random control. Results indicate that exposure to galleries generated by MAP--Elites significantly enhanced both cognitive and behavioural engagement, leading to higher-quality design outcomes. Crucially for the wider community, the analysis reveals that conventional evaluation methods, which often focus on solely behavioural and design quality metrics, fail to capture the full spectrum of user engagement. By considering the human--AI design process as a changing emotional, behavioural and cognitive state of the designer, we propose evaluating human--AI systems holistically and considering intelligent systems as a core part of the user experience -- not simply a back end tool.
Authors: Ayoub Si-ahmed, Mohammed Ali Al-Garadi, Narhimene Boustia
Abstract: The Internet of Medical Things transcends traditional medical boundaries, enabling a transition from reactive treatment to proactive prevention. This innovative method revolutionizes healthcare by facilitating early disease detection and tailored care, particularly in chronic disease management, where IoMT automates treatments based on real-time health data collection. Nonetheless, its benefits are countered by significant security challenges that endanger the lives of its users due to the sensitivity and value of the processed data, thereby attracting malicious interests. Moreover, the utilization of wireless communication for data transmission exposes medical data to interception and tampering by cybercriminals. Additionally, anomalies may arise due to human error, network interference, or hardware malfunctions. In this context, anomaly detection based on Machine Learning (ML) is an interesting solution, but it comes up against obstacles in terms of explicability and privacy protection. To address these challenges, a new framework for Intrusion Detection Systems is introduced, leveraging Artificial Neural Networks for intrusion detection while utilizing Federated Learning for privacy preservation. Additionally, eXplainable Artificial Intelligence methods are incorporated to enhance model explanation and interpretation. The efficacy of the proposed framework is evaluated and compared with centralized approaches using multiple datasets containing network and medical data, simulating various attack types impacting the confidentiality, integrity, and availability of medical and physiological data. The results offer compelling evidence that the FL method performs comparably to the centralized method, demonstrating high performance. Additionally, it affords the dual advantage of safeguarding privacy and providing model explanation while adhering to ethical principles.
Authors: Anran Hu, Junzi Zhang
Abstract: Reinforcement learning for multi-agent games has attracted lots of attention recently. However, given the challenge of solving Nash equilibria for large population games, existing works with guaranteed polynomial complexities either focus on variants of zero-sum and potential games, or aim at solving (coarse) correlated equilibria, or require access to simulators, or rely on certain assumptions that are hard to verify. This work proposes MF-OML (Mean-Field Occupation-Measure Learning), an online mean-field reinforcement learning algorithm for computing approximate Nash equilibria of large population sequential symmetric games. MF-OML is the first fully polynomial multi-agent reinforcement learning algorithm for provably solving Nash equilibria (up to mean-field approximation gaps that vanish as the number of players $N$ goes to infinity) beyond variants of zero-sum and potential games. When evaluated by the cumulative deviation from Nash equilibria, the algorithm is shown to achieve a high probability regret bound of $\tilde{O}(M^{3/4}+N^{-1/2}M)$ for games with the strong Lasry-Lions monotonicity condition, and a regret bound of $\tilde{O}(M^{11/12}+N^{- 1/6}M)$ for games with only the Lasry-Lions monotonicity condition, where $M$ is the total number of episodes and $N$ is the number of agents of the game. As a byproduct, we also obtain the first tractable globally convergent computational algorithm for computing approximate Nash equilibria of monotone mean-field games.
Authors: Qianchao Zhu, Jiangfei Duan, Chang Chen, Siran Liu, Guanyu Feng, Xin Lv, Xiao Chuanfu, Dahua Lin, Chao Yang
Abstract: Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity require additional pretraining or finetuning, and often sacrifice model accuracy. In this paper, we first provide both theoretical and empirical foundations for near-lossless sparse attention. We find dynamically capturing head-specific sparse patterns at runtime with low overhead is crucial. To address this, we propose SampleAttention, an adaptive structured and near-lossless sparse attention. Leveraging observed significant sparse patterns, SampleAttention attends to a fixed percentage of adjacent tokens to capture local window patterns, and employs a two-stage query-guided key-value filtering approach, which adaptively select a minimum set of key-values with low overhead, to capture column stripe patterns. Comprehensive evaluations show that SampleAttention can seamlessly replace vanilla attention in off-the-shelf LLMs with nearly no accuracy loss, and reduces TTFT by up to $2.42\times$ compared with FlashAttention.
Authors: Johnny Li, Saksham Consul, Eda Zhou, James Wong, Naila Farooqui, Yuxin Ye, Nithyashree Manohar, Zhuxiaona Wei, Tian Wu, Ben Echols, Sharon Zhou, Gregory Diamos
Abstract: Despite their powerful chat, coding, and reasoning abilities, Large Language Models (LLMs) frequently hallucinate. Conventional wisdom suggests that hallucinations are a consequence of a balance between creativity and factuality, which can be mitigated, but not eliminated, by grounding the LLM in external knowledge sources. Through extensive systematic experiments, we show that these traditional approaches fail to explain why LLMs hallucinate in practice. Specifically, we show that LLMs augmented with a massive Mixture of Memory Experts (MoME) can easily memorize large datasets of random numbers. We corroborate these experimental findings with a theoretical construction showing that simple neural networks trained to predict the next token hallucinate when the training loss is above a threshold as it usually does in practice when training on internet scale data. We interpret our findings by comparing against traditional retrieval methods for mitigating hallucinations. We use our findings to design a first generation model for removing hallucinations -- Lamini-1 -- that stores facts in a massive mixture of millions of memory experts that are retrieved dynamically.
Authors: Ruoyu Qin, Zheming Li, Weiran He, Mingxing Zhang, Yongwei Wu, Weimin Zheng, Xinran Xu
Abstract: Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates the prefill and decoding clusters. It also leverages the underutilized CPU, DRAM, and SSD resources of the GPU cluster to implement a disaggregated cache of KVCache. The core of Mooncake is its KVCache-centric scheduler, which balances maximizing overall effective throughput while meeting latency-related Service Level Objectives (SLOs). Unlike traditional studies that assume all requests will be processed, Mooncake faces challenges due to highly overloaded scenarios. To mitigate these, we developed a prediction-based early rejection policy. Experiments show that Mooncake excels in long-context scenarios. Compared to the baseline method, Mooncake can achieve up to a 525% increase in throughput in certain simulated scenarios while adhering to SLOs. Under real workloads, Mooncake's innovative architecture enables Kimi to handle 75% more requests.
Authors: Arief Purnama Muharram, Ayu Purwarianti
Abstract: Automated fact-checking is a key strategy to overcome the spread of COVID-19 misinformation on the internet. These systems typically leverage deep learning approaches through Natural Language Inference (NLI) to verify the truthfulness of information based on supporting evidence. However, one challenge that arises in deep learning is performance stagnation due to a lack of knowledge during training. This study proposes using a Knowledge Graph (KG) as external knowledge to enhance NLI performance for automated COVID-19 fact-checking in the Indonesian language. The proposed model architecture comprises three modules: a fact module, an NLI module, and a classifier module. The fact module processes information from the KG, while the NLI module handles semantic relationships between the given premise and hypothesis. The representation vectors from both modules are concatenated and fed into the classifier module to produce the final result. The model was trained using the generated Indonesian COVID-19 fact-checking dataset and the COVID-19 KG Bahasa Indonesia. Our study demonstrates that incorporating KGs can significantly improve NLI performance in fact-checking, achieving the best accuracy of 0.8616. This suggests that KGs are a valuable component for enhancing NLI performance in automated fact-checking.
Authors: Antonin Sulc, Thorsten Hellert, Raimund Kammering, Hayden Hoschouer, Jason St. John
Abstract: As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized to control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show three examples, where we demonstrate the viability of such architecture.
Authors: Lukas Muttenthaler, Klaus Greff, Frieda Born, Bernhard Spitzer, Simon Kornblith, Michael C. Mozer, Klaus-Robert M\"uller, Thomas Unterthiner, Andrew K. Lampinen
Abstract: Deep neural networks have achieved success across a wide range of applications, including as models of human behavior and neural representations in vision tasks. However, neural network training and human learning differ in fundamental ways, and neural networks often fail to generalize as robustly as humans do raising questions regarding the similarity of their underlying representations. What is missing for modern learning systems to exhibit more human-aligned behavior? We highlight a key misalignment between vision models and humans: whereas human conceptual knowledge is hierarchically organized from fine- to coarse-scale distinctions, model representations do not accurately capture all these levels of abstraction. To address this misalignment, we first train a teacher model to imitate human judgments, then transfer human-aligned structure from its representations to refine the representations of pretrained state-of-the-art vision foundation models via finetuning. These human-aligned models more accurately approximate human behavior and uncertainty across a wide range of similarity tasks, including a new dataset of human judgments spanning multiple levels of semantic abstractions. They also perform better on a diverse set of machine learning tasks, increasing generalization and out-of-distribution robustness. Thus, infusing neural networks with additional human knowledge yields a best-of-both-worlds representation that is both more consistent with human cognitive judgments and more practically useful, thus paving the way toward more robust, interpretable, and human-aligned artificial intelligence systems.
Authors: Shiben Liu, Huijie Fan, Qiang Wang, Weihong Ren, Yandong Tang, Yang Cong
Abstract: Lifelong person re-identification (LReID) exhibits a contradictory relationship between intra-domain discrimination and inter-domain gaps when learning from continuous data. Intra-domain discrimination focuses on individual nuances (i.e., clothing type, accessories, etc.), while inter-domain gaps emphasize domain consistency. Achieving a trade-off between maximizing intra-domain discrimination and minimizing inter-domain gaps is a crucial challenge for improving LReID performance. Most existing methods strive to reduce inter-domain gaps through knowledge distillation to maintain domain consistency. However, they often ignore intra-domain discrimination. To address this challenge, we propose a novel domain consistency representation learning (DCR) model that explores global and attribute-wise representations as a bridge to balance intra-domain discrimination and inter-domain gaps. At the intra-domain level, we explore the complementary relationship between global and attribute-wise representations to improve discrimination among similar identities. Excessive learning intra-domain discrimination can lead to catastrophic forgetting. We further develop an attribute-oriented anti-forgetting (AF) strategy that explores attribute-wise representations to enhance inter-domain consistency, and propose a knowledge consolidation (KC) strategy to facilitate knowledge transfer. Extensive experiments show that our DCR achieves superior performance compared to state-of-the-art LReID methods. Our code is available at https://github.com/LiuShiBen/DCR.
Authors: Jiahao Qiu, Yifu Lu, Yifan Zeng, Jiacheng Guo, Jiayi Geng, Chenhao Zhu, Xinzhe Juan, Ling Yang, Huazheng Wang, Kaixuan Huang, Yue Wu, Mengdi Wang
Abstract: Inference-time alignment enhances the performance of large language models without requiring additional training or fine-tuning but presents challenges due to balancing computational efficiency with high-quality output. Best-of-N (BoN) sampling, as a simple yet powerful approach, generates multiple responses and selects the best one, achieving improved performance but with a high computational cost. We propose TreeBoN, a novel framework that integrates a speculative tree-search strategy into Best-of-N (BoN) Sampling. TreeBoN maintains a set of parent nodes, iteratively branching and pruning low-quality responses, thereby reducing computational overhead while maintaining high output quality. Our approach also leverages token-level rewards from Direct Preference Optimization (DPO) to guide tree expansion and prune low-quality paths. We evaluate TreeBoN using AlpacaFarm, HH-RLHF, UltraFeedback, GSM8K, and TutorEval datasets, demonstrating consistent improvements. Specifically, TreeBoN achieves the highest win rate of 65% on TutorEval and around 60% win rates across other different datasets, outperforming standard BoN with the same computational cost and showcasing its scalability and alignment efficacy.
Authors: Yunkai Dang, Mengxi Gao, Yibo Yan, Xin Zou, Yanggan Gu, Jungang Li, Jingyu Wang, Peijie Jiang, Aiwei Liu, Jia Liu, Xuming Hu
Abstract: Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding. However, existing studies have concentrated mainly on visual-textual misalignment, leaving largely unexplored the MLLMs' ability to preserve an originally correct answer when confronted with misleading information. We reveal a response uncertainty phenomenon: across nine standard datasets, twelve state-of-the-art open-source MLLMs overturn a previously correct answer in 65% of cases after receiving a single deceptive cue. To systematically quantify this vulnerability, we propose a two-stage evaluation pipeline: (1) elicit each model's original response on unperturbed inputs; (2) inject explicit (false-answer hints) and implicit (contextual contradictions) misleading instructions, and compute the misleading rate - the fraction of correct-to-incorrect flips. Leveraging the most susceptible examples, we curate the Multimodal Uncertainty Benchmark (MUB), a collection of image-question pairs stratified into low, medium, and high difficulty based on how many of twelve state-of-the-art MLLMs they mislead. Extensive evaluation on twelve open-source and five closed-source models reveals a high uncertainty: average misleading rates exceed 86%, with explicit cues over 67.19% and implicit cues over 80.67%. To reduce the misleading rate, we then fine-tune all open-source MLLMs on a compact 2000-sample mixed-instruction dataset, reducing misleading rates to 6.97% (explicit) and 32.77% (implicit), boosting consistency by nearly 29.37% on highly deceptive inputs, and slightly improving accuracy on standard benchmarks. Our code is available at https://github.com/Yunkaidang/uncertainty
Authors: Haeyong Kang, Chang D. Yoo
Abstract: Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), which provides suboptimal fine-tuning solutions, we propose a novel fully fine-tuned continual learning (CL) method referred to as Soft-TransFormers (Soft-TF). Soft-TF sequentially learns and selects an optimal soft-network for each task. During sequential training in CL, a well-initialized Soft-TF mask optimizes the weights of sparse layers to obtain task-adaptive soft (real-valued) networks, while keeping the well-pre-trained layer parameters frozen. In inference, the identified task-adaptive network of Soft-TF masks the parameters of the pre-trained network, mapping to an optimal solution for each task and minimizing Catastrophic Forgetting (CF) - the soft-masking preserves the knowledge of the pre-trained network. Extensive experiments on the Vision Transformer (ViT) and the Language Transformer (Bert) demonstrate the effectiveness of Soft-TF, achieving state-of-the-art performance across Vision and Language Class Incremental Learning (CIL) scenarios.
Authors: Ruoqi Wang, Haitao Wang, Qiong Luo
Abstract: Galaxy morphology analysis involves studying galaxies based on their shapes and structures. For such studies, fundamental tasks include identifying and classifying galaxies in astronomical images, as well as retrieving visually or structurally similar galaxies through similarity search. Existing methods either directly train domain-specific foundation models on large, annotated datasets or fine-tune vision foundation models on a smaller set of images. The former is effective but costly, while the latter is more resource-efficient but often yields lower accuracy. To address these challenges, we introduce GalaxAlign, a multimodal approach inspired by how citizen scientists identify galaxies in astronomical images by following textual descriptions and matching schematic symbols. Specifically, GalaxAlign employs a tri-modal alignment framework to align three types of data during fine-tuning: (1) schematic symbols representing galaxy shapes and structures, (2) textual labels for these symbols, and (3) galaxy images. By incorporating multimodal instructions, GalaxAlign eliminates the need for expensive pretraining and enhances the effectiveness of fine-tuning. Experiments on galaxy classification and similarity search demonstrate that our method effectively fine-tunes general pre-trained models for astronomical tasks by incorporating domain-specific multi-modal knowledge. Code is available at https://github.com/RapidsAtHKUST/GalaxAlign.
Authors: Carlos G\"uemes-Palau, Miquel Ferriol-Galm\'es, Jordi Paillisse-Vilanova, Albert L\'opez-Bresc\'o, Pere Barlet-Ros, Albert Cabellos-Aparicio
Abstract: Network simulation is pivotal in network modeling, assisting with tasks ranging from capacity planning to performance estimation. Traditional approaches such as Discrete Event Simulation (DES) face limitations in terms of computational cost and accuracy. This paper introduces RouteNet-Gauss, a novel integration of a testbed network with a Machine Learning (ML) model to address these challenges. By using the testbed as a hardware accelerator, RouteNet-Gauss generates training datasets rapidly and simulates network scenarios with high fidelity to real-world conditions. Experimental results show that RouteNet-Gauss significantly reduces prediction errors by up to 95% and achieves a 488x speedup in inference time compared to state-of-the-art DES-based methods. RouteNet-Gauss's modular architecture is dynamically constructed based on the specific characteristics of the network scenario, such as topology and routing. This enables it to understand and generalize to different network configurations beyond those seen during training, including networks up to 10x larger. Additionally, it supports Temporal Aggregated Performance Estimation (TAPE), providing configurable temporal granularity and maintaining high accuracy in flow performance metrics. This approach shows promise in improving both simulation efficiency and accuracy, offering a valuable tool for network operators.
Authors: Qiang Liu, Xinlong Chen, Yue Ding, Bowen Song, Weiqiang Wang, Shu Wu, Liang Wang
Abstract: Hallucination has emerged as a significant barrier to the effective application of Large Language Models (LLMs). In this work, we introduce a novel Attention-Guided SElf-Reflection (AGSER) approach for zero-shot hallucination detection in LLMs. The AGSER method utilizes attention contributions to categorize the input query into attentive and non-attentive queries. Each query is then processed separately through the LLMs, allowing us to compute consistency scores between the generated responses and the original answer. The difference between the two consistency scores serves as a hallucination estimator. In addition to its efficacy in detecting hallucinations, AGSER notably reduces computational overhead, requiring only three passes through the LLM and utilizing two sets of tokens. We have conducted extensive experiments with four widely-used LLMs across three different hallucination benchmarks, demonstrating that our approach significantly outperforms existing methods in zero-shot hallucination detection.
Authors: Manousos Linardakis, Iraklis Varlamis, Georgios Th. Papadopoulos
Abstract: Hand gesture recognition has become an important research area, driven by the growing demand for human-computer interaction in fields such as sign language recognition, virtual and augmented reality, and robotics. Despite the rapid growth of the field, there are few surveys that comprehensively cover recent research developments, available solutions, and benchmark datasets. This survey addresses this gap by examining the latest advancements in hand gesture and 3D hand pose recognition from various types of camera input data including RGB images, depth images, and videos from monocular or multiview cameras, examining the differing methodological requirements of each approach. Furthermore, an overview of widely used datasets is provided, detailing their main characteristics and application domains. Finally, open challenges such as achieving robust recognition in real-world environments, handling occlusions, ensuring generalization across diverse users, and addressing computational efficiency for real-time applications are highlighted to guide future research directions. By synthesizing the objectives, methodologies, and applications of recent studies, this survey offers valuable insights into current trends, challenges, and opportunities for future research in human hand gesture recognition.
Authors: Srinitish Srinivasan, Omkumar CU
Abstract: Graph representation learning has emerged as a cornerstone for tasks like node classification and link prediction, yet prevailing self-supervised learning (SSL) methods face challenges such as computational inefficiency, reliance on contrastive objectives, and representation collapse. Existing approaches often depend on feature reconstruction, negative sampling, or complex decoders, which introduce training overhead and hinder generalization. Further, current techniques which address such limitations fail to account for the contribution of node embeddings to a certain prediction in the absence of labeled nodes. To address these limitations, we propose a novel joint embedding predictive framework for graph SSL that eliminates contrastive objectives and negative sampling while preserving semantic and structural information. Additionally, we introduce a semantic-aware objective term that incorporates pseudo-labels derived from Gaussian Mixture Models (GMMs), enhancing node discriminability by evaluating latent feature contributions. Extensive experiments demonstrate that our framework outperforms state-of-the-art graph SSL methods across benchmarks, achieving superior performance without contrastive loss or complex decoders. Key innovations include (1) a non-contrastive, view-invariant joint embedding predictive architecture, (2) Leveraging single context and multiple targets relationship between subgraphs, and (3) GMM-based pseudo-label scoring to capture semantic contributions. This work advances graph SSL by offering a computationally efficient, collapse-resistant paradigm that bridges spatial and semantic graph features for downstream tasks. The code for our paper can be found at https://github.com/Deceptrax123/JPEB-GSSL
Authors: Royson Lee, Minyoung Kim, Fady Rezk, Rui Li, Stylianos I. Venieris, Timothy Hospedales
Abstract: Federated learning (FL) has enabled the training of multilingual large language models (LLMs) on diverse and decentralized multilingual data, especially on low-resource languages. To improve client-specific performance, personalization via the use of parameter-efficient fine-tuning (PEFT) modules such as LoRA is common. This involves a personalization strategy (PS), such as the design of the PEFT adapter structures (e.g., in which layers to add LoRAs and what ranks) and choice of hyperparameters (e.g., learning rates) for fine-tuning. Instead of manual PS configuration, we propose FedP$^2$EFT, a federated learning-to-personalize method for multilingual LLMs in cross-device FL settings. Unlike most existing PEFT structure selection methods, which are prone to overfitting low-data regimes, FedP$^2$EFT collaboratively learns the optimal personalized PEFT structure for each client via Bayesian sparse rank selection. Evaluations on both simulated and real-world multilingual FL benchmarks demonstrate that FedP$^2$EFT largely outperforms existing personalized fine-tuning methods, while complementing other existing FL methods. Code is available at https://github.com/SamsungLabs/fedp2eft.
Authors: Wentao Wang, Guangyuan Jiang, Tal Linzen, Brenden M. Lake
Abstract: Humans can quickly learn a new word from a few illustrative examples, and then systematically and flexibly use it in novel contexts. Yet the abilities of current language models for few-shot word learning, and methods for improving these abilities, are underexplored. In this study, we introduce a novel method, Meta-training for IN-context learNing Of Words (Minnow). This method trains language models to generate new examples of a word's usage given a few in-context examples, using a special placeholder token to represent the new word. This training is repeated on many new words to develop a general word-learning ability. We find that training models from scratch with Minnow on human-scale child-directed language enables strong few-shot word learning, comparable to a large language model (LLM) pre-trained on orders of magnitude more data. Furthermore, through discriminative and generative evaluations, we demonstrate that finetuning pre-trained LLMs with Minnow improves their ability to discriminate between new words, identify syntactic categories of new words, and generate reasonable new usages and definitions for new words, based on one or a few in-context examples. These findings highlight the data efficiency of Minnow and its potential to improve language model performance in word learning tasks.
Authors: Abhilash Neog, Arka Daw, Sepideh Fatemi Khorasgani, Medha Sawhney, Aanish Pradhan, Mary E. Lofton, Bennett J. McAfee, Adrienne Breef-Pilz, Heather L. Wander, Dexter W Howard, Cayelan C. Carey, Paul Hanson, Anuj Karpatne
Abstract: Modeling Irregularly-sampled and Multivariate Time Series (IMTS) is crucial across a variety of applications where different sets of variates may be missing at different time-steps due to sensor malfunctions or high data acquisition costs. Existing approaches for IMTS either consider a two-stage impute-then-model framework or involve specialized architectures specific to a particular model and task. We perform a series of experiments to derive novel insights about the performance of IMTS methods on a variety of semi-synthetic and real-world datasets for both classification and forecasting. We also introduce Missing Feature-aware Time Series Modeling (MissTSM) or MissTSM, a novel model-agnostic and imputation-free approach for IMTS modeling. We show that MissTSM shows competitive performance compared to other IMTS approaches, especially when the amount of missing values is large and the data lacks simplistic periodic structures - conditions common to real-world IMTS applications.
Authors: Gaye Colakoglu, G\"urkan Solmaz, Jonathan F\"urst
Abstract: This paper defines and explores the design space for information extraction (IE) from layout-rich documents using large language models (LLMs). The three core challenges of layout-aware IE with LLMs are 1) data structuring, 2) model engagement, and 3) output refinement. Our study investigates the sub-problems and methods within these core challenges, such as input representation, chunking, prompting, selection of LLMs, and multimodal models. It examines the effect of different design choices through LayIE-LLM, a new, open-source, layout-aware IE test suite, benchmarking against traditional, fine-tuned IE models. The results on two IE datasets show that LLMs require adjustment of the IE pipeline to achieve competitive performance: the optimized configuration found with LayIE-LLM achieves 13.3--37.5 F1 points more than a general-practice baseline configuration using the same LLM. To find a well-working configuration, we develop a one-factor-at-a-time (OFAT) method that achieves near-optimal results. Our method is only 0.8--1.8 points lower than the best full factorial exploration with a fraction (2.8%) of the required computation. Overall, we demonstrate that, if well-configured, general-purpose LLMs match the performance of specialized models, providing a cost-effective, finetuning-free alternative. Our test-suite is available at https://github.com/gayecolakoglu/LayIE-LLM.
Authors: Yifei He, Yang Liu, Chen Liang, Hany Hassan Awadalla
Abstract: Mixture-of-Experts (MoE) models have become a key approach for scaling large language models efficiently by activating only a subset of experts during training and inference. Typically, the number of activated experts presents a trade-off: fewer experts reduce computational costs, while more experts improve performance. Recent studies reveal that not all activated experts contribute equally to model performance, with some providing minimal utility, particularly when finetuning pretrained MoE models for specialized downstream tasks. The co-existence of significant and redundant parameters in experts provides us an opportunity to reduce the number of activated experts while maintaining model performance. In this work, we propose the concept of compressed experts, lightweight modules that serve as compact representations of full experts. Our approach preserves the most important experts while replacing other auxiliary activated experts with compressed experts. The reduction of active parameters significantly lowers inference costs while achieving comparable performance. Extensive experiments on models including Phi-MoE and OLMoE demonstrate that compressed experts recover over 90% of full expert performance across various tasks while reducing more than 30% active parameters and saving 20% in inference costs. This approach enables efficient deployment of MoE models in resource-constrained settings and facilitates scaling to larger models with manageable overhead. Our code is available at https://github.com/yifei-he/Compressed-Experts.
Authors: Raphael Trumpp, Ansgar Sch\"afftlein, Mirco Theile, Marco Caccamo
Abstract: As image-based deep reinforcement learning tackles more challenging tasks, increasing model size has become an important factor in improving performance. Recent studies achieved this by focusing on the parameter efficiency of scaled networks, typically using Impala-CNN, a 15-layer ResNet-inspired network, as the image encoder. However, while Impala-CNN evidently outperforms older CNN architectures, potential advancements in network design for deep reinforcement learning-specific image encoders remain largely unexplored. We find that replacing the flattening of output feature maps in Impala-CNN with global average pooling leads to a notable performance improvement. This approach outperforms larger and more complex models in the Procgen Benchmark, particularly in terms of generalization. We call our proposed encoder model Impoola-CNN. A decrease in the network's translation sensitivity may be central to this improvement, as we observe the most significant gains in games without agent-centered observations. Our results demonstrate that network scaling is not just about increasing model size - efficient network design is also an essential factor. We make our code available at https://github.com/raphajaner/impoola.
Authors: Rohit Kundu, Shan Jia, Vishal Mohanty, Athula Balachandran, Amit K. Roy-Chowdhury
Abstract: Detecting DeepFakes has become a crucial research area as the widespread use of AI image generators enables the effortless creation of face-manipulated and fully synthetic content, while existing methods are often limited to binary classification (real vs. fake) and lack interpretability. To address these challenges, we propose TruthLens, a novel, unified, and highly generalizable framework that goes beyond traditional binary classification, providing detailed, textual reasoning for its predictions. Distinct from conventional methods, TruthLens performs MLLM grounding. TruthLens uses a task-driven representation integration strategy that unites global semantic context from a multimodal large language model (MLLM) with region-specific forensic cues through explicit cross-modal adaptation of a vision-only model. This enables nuanced, region-grounded reasoning for both face-manipulated and fully synthetic content, and supports fine-grained queries such as "Does the eyes/nose/mouth look real or fake?"- capabilities beyond pretrained MLLMs alone. Extensive experiments across diverse datasets demonstrate that TruthLens sets a new benchmark in both forensic interpretability and detection accuracy, generalizing to seen and unseen manipulations alike. By unifying high-level scene understanding with fine-grained region grounding, TruthLens delivers transparent DeepFake forensics, bridging a critical gap in the literature.
Authors: Giovanni Cioffi, Leonard Bauersfeld, Davide Scaramuzza
Abstract: Visual-inertial odometry (VIO) is widely used for state estimation in autonomous micro aerial vehicles using onboard sensors. Current methods improve VIO by incorporating a model of the translational vehicle dynamics, yet their performance degrades when faced with low-accuracy vehicle models or continuous external disturbances, like wind. Additionally, incorporating rotational dynamics in these models is computationally intractable when they are deployed in online applications, e.g., in a closed-loop control system. We present HDVIO2.0, which models full 6-DoF, translational and rotational, vehicle dynamics and tightly incorporates them into a VIO with minimal impact on the runtime. HDVIO2.0 builds upon the previous work, HDVIO, and addresses these challenges through a hybrid dynamics model combining a point-mass vehicle model with a learning-based component, with access to control commands and IMU history, to capture complex aerodynamic effects. The key idea behind modeling the rotational dynamics is to represent them with continuous-time functions. HDVIO2.0 leverages the divergence between the actual motion and the predicted motion from the hybrid dynamics model to estimate external forces as well as the robot state. Our system surpasses the performance of state-of-the-art methods in experiments using public and new drone dynamics datasets, as well as real-world flights in winds up to 25 km/h. Unlike existing approaches, we also show that accurate vehicle dynamics predictions are achievable without precise knowledge of the full vehicle state.
Authors: Yundi Zhang, Paul Hager, Che Liu, Suprosanna Shit, Chen Chen, Daniel Rueckert, Jiazhen Pan
Abstract: Cardiac magnetic resonance imaging is the gold standard for non-invasive cardiac assessment, offering rich spatio-temporal views of the cardiac anatomy and physiology. Patient-level health factors, such as demographics, metabolic, and lifestyle, are known to substantially influence cardiovascular health and disease risk, yet remain uncaptured by CMR alone. To holistically understand cardiac health and to enable the best possible interpretation of an individual's disease risk, CMR and patient-level factors must be jointly exploited within an integrated framework. Recent multi-modal approaches have begun to bridge this gap, yet they often rely on limited spatio-temporal data and focus on isolated clinical tasks, thereby hindering the development of a comprehensive representation for cardiac health evaluation. To overcome these limitations, we introduce ViTa, a step toward foundation models that delivers a comprehensive representation of the heart and a precise interpretation of individual disease risk. Leveraging data from 42,000 UK Biobank participants, ViTa integrates 3D+T cine stacks from short-axis and long-axis views, enabling a complete capture of the cardiac cycle. These imaging data are then fused with detailed tabular patient-level factors, enabling context-aware insights. This multi-modal paradigm supports a wide spectrum of downstream tasks, including cardiac phenotype and physiological feature prediction, segmentation, and classification of cardiac and metabolic diseases within a single unified framework. By learning a shared latent representation that bridges rich imaging features and patient context, ViTa moves beyond traditional, task-specific models toward a universal, patient-specific understanding of cardiac health, highlighting its potential to advance clinical utility and scalability in cardiac analysis.
Authors: Braeden Sherritt, Isar Nejadgholi, Efstratios Aivaliotis, Khaled Mslmani, Marzieh Amini
Abstract: 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.
Authors: Syed Mohammad Kashif, Peng Liang, Amjed Tahir
Abstract: AI code generation tools have gained significant popularity among developers, who use them to assist in software development due to their capability to generate code. Existing studies mainly explored the quality, e.g., correctness and security, of AI-generated code, while in real-world software development, the prerequisite is to distinguish AI-generated code from human-written code, which emphasizes the need to explicitly declare AI-generated code by developers. To this end, this study intends to understand the ways developers use to self-declare AI-generated code and explore the reasons why developers choose to self-declare or not. We conducted a mixed-methods study consisting of two phases. In the first phase, we mined GitHub repositories and collected 613 instances of AI-generated code snippets. In the second phase, we conducted a follow-up practitioners' survey, which received 111 valid responses. Our research revealed the practices followed by developers to self-declare AI-generated code. Most practitioners (76.6%) always or sometimes self-declare AI-generated code. In contrast, other practitioners (23.4%) noted that they never self-declare AI-generated code. The reasons for self-declaring AI-generated code include the need to track and monitor the code for future review and debugging, and ethical considerations. The reasons for not self-declaring AI-generated code include extensive modifications to AI-generated code and the developers' perception that self-declaration is an unnecessary activity. We finally provided guidelines for practitioners to self-declare AI-generated code, addressing ethical and code quality concerns.
Authors: Debarati Das, Khanh Chi Le, Ritik Sachin Parkar, Karin De Langis, Brendan Madson, Chad M. Berryman, Robin M. Willis, Daniel H. Moses, Brett McDonnell, Daniel Schwarcz, Dongyeop Kang
Abstract: Legal practitioners, particularly those early in their careers, face complex, high-stakes tasks that require adaptive, context-sensitive reasoning. While AI holds promise in supporting legal work, current datasets and models are narrowly focused on isolated subtasks and fail to capture the end-to-end decision-making required in real-world practice. To address this gap, we introduce LawFlow, a dataset of complete end-to-end legal workflows collected from trained law students, grounded in real-world business entity formation scenarios. Unlike prior datasets focused on input-output pairs or linear chains of thought, LawFlow captures dynamic, modular, and iterative reasoning processes that reflect the ambiguity, revision, and client-adaptive strategies of legal practice. Using LawFlow, we compare human and LLM-generated workflows, revealing systematic differences in structure, reasoning flexibility, and plan execution. Human workflows tend to be modular and adaptive, while LLM workflows are more sequential, exhaustive, and less sensitive to downstream implications. Our findings also suggest that legal professionals prefer AI to carry out supportive roles, such as brainstorming, identifying blind spots, and surfacing alternatives, rather than executing complex workflows end-to-end. Our results highlight both the current limitations of LLMs in supporting complex legal workflows and opportunities for developing more collaborative, reasoning-aware legal AI systems. All data and code are available on our project page (https://minnesotanlp.github.io/LawFlow-website/).
Authors: Muhammad Tayyab Khan, Zane Yong, Lequn Chen, Jun Ming Tan, Wenhe Feng, Seung Ki Moon
Abstract: Accurate extraction of key information from 2D engineering drawings is crucial for high-precision manufacturing. Manual extraction is slow and labor-intensive, while traditional Optical Character Recognition (OCR) techniques often struggle with complex layouts and overlapping symbols, resulting in unstructured outputs. To address these challenges, this paper proposes a novel hybrid deep learning framework for structured information extraction by integrating an Oriented Bounding Box (OBB) detection model with a transformer-based document parsing model (Donut). An in-house annotated dataset is used to train YOLOv11 for detecting nine key categories: Geometric Dimensioning and Tolerancing (GD&T), General Tolerances, Measures, Materials, Notes, Radii, Surface Roughness, Threads, and Title Blocks. Detected OBBs are cropped into images and labeled to fine-tune Donut for structured JSON output. Fine-tuning strategies include a single model trained across all categories and category-specific models. Results show that the single model consistently outperforms category-specific ones across all evaluation metrics, achieving higher precision (94.77% for GD&T), recall (100% for most categories), and F1 score (97.3%), while reducing hallucinations (5.23%). The proposed framework improves accuracy, reduces manual effort, and supports scalable deployment in precision-driven industries.
Authors: Lang Feng, Zhenghai Xue, Tingcong Liu, Bo An
Abstract: Recent advances in group-based reinforcement learning (RL) have driven frontier large language models (LLMs) in single-turn tasks like mathematical reasoning. However, their scalability to long-horizon LLM agent training remains limited. Unlike static tasks, agent-environment interactions unfold over many steps and often yield sparse or delayed rewards, making credit assignment across individual steps significantly more challenging. In this work, we propose Group-in-Group Policy Optimization (GiGPO), a novel RL algorithm that achieves fine-grained credit assignment for LLM agents while preserving the appealing properties of group-based RL: critic-free, low memory, and stable convergence. GiGPO introduces a two-level structure for estimating relative advantage: (i) At the episode-level, GiGPO computes macro relative advantages based on groups of complete trajectories; (ii) At the step-level, GiGPO introduces an anchor state grouping mechanism that retroactively constructs step-level groups by identifying repeated environment states across trajectories. Actions stemming from the same state are grouped together, enabling micro relative advantage estimation. This hierarchical structure effectively captures both global trajectory quality and local step effectiveness without relying on auxiliary models or additional rollouts. We evaluate GiGPO on two challenging agent benchmarks, ALFWorld and WebShop, using Qwen2.5-1.5B-Instruct and Qwen2.5-7B-Instruct. Crucially, GiGPO delivers fine-grained per-step credit signals and achieves performance gains of > 12\% on ALFWorld and > 9\% on WebShop over the GRPO baseline: all while maintaining the same GPU memory overhead, identical LLM rollout, and incurring little to no additional time cost.
Authors: Juntian Zhu, Miguel de Carvalho, Zhouwang Yang, Fengxiang He
Abstract: An AI agent might surprisingly find she has reached an unknown state which she has never been aware of -- an unknown unknown. We mathematically ground this scenario in reinforcement learning: an agent, after taking an action calculated from value functions $Q$ and $V$ defined on the {\it {aware domain}}, reaches a state out of the domain. To enable the agent to handle this scenario, we propose an {\it episodic Markov decision {process} with growing awareness} (EMDP-GA) model, taking a new {\it noninformative value expansion} (NIVE) approach to expand value functions to newly aware areas: when an agent arrives at an unknown unknown, value functions $Q$ and $V$ whereon are initialised by noninformative beliefs -- the averaged values on the aware domain. This design is out of respect for the complete absence of knowledge in the newly discovered state. The upper confidence bound momentum Q-learning is then adapted to the growing awareness for training the EMDP-GA model. We prove that (1) the regret of our approach is asymptotically consistent with the state of the art (SOTA) without exposure to unknown unknowns in an extremely uncertain environment, and (2) our computational complexity and space complexity are comparable with the SOTA -- these collectively suggest that though an unknown unknown is surprising, it will be asymptotically properly discovered with decent speed and an affordable cost.
Authors: Wei Liu, Siya Qi, Xinyu Wang, Chen Qian, Yali Du, Yulan He
Abstract: Recent advances such as DeepSeek R1-Zero highlight the effectiveness of incentive training, a reinforcement learning paradigm that computes rewards solely based on the final answer part of a language model's output, thereby encouraging the generation of intermediate reasoning steps. However, these methods fundamentally rely on external verifiers, which limits their applicability to domains like mathematics and coding where such verifiers are readily available. Although reward models can serve as verifiers, they require high-quality annotated data and are costly to train. In this work, we propose NOVER, NO-VERifier Reinforcement Learning, a general reinforcement learning framework that requires only standard supervised fine-tuning data with no need for an external verifier. NOVER enables incentive training across a wide range of text-to-text tasks and outperforms the model of the same size distilled from large reasoning models such as DeepSeek R1 671B by 7.7 percent. Moreover, the flexibility of NOVER enables new possibilities for optimizing large language models, such as inverse incentive training.
Authors: Kristin Qi, Jiali Cheng, Youxiang Zhu, Hadi Amiri, Xiaohui Liang
Abstract: Detecting Mild Cognitive Impairment from picture descriptions is critical yet challenging, especially in multilingual and multiple picture settings. Prior work has primarily focused on English speakers describing a single picture (e.g., the 'Cookie Theft'). The TAUKDIAL-2024 challenge expands this scope by introducing multilingual speakers and multiple pictures, which presents new challenges in analyzing picture-dependent content. To address these challenges, we propose a framework with three components: (1) enhancing discriminative representation learning via supervised contrastive learning, (2) involving image modality rather than relying solely on speech and text modalities, and (3) applying a Product of Experts (PoE) strategy to mitigate spurious correlations and overfitting. Our framework improves MCI detection performance, achieving a +7.1% increase in Unweighted Average Recall (UAR) (from 68.1% to 75.2%) and a +2.9% increase in F1 score (from 80.6% to 83.5%) compared to the text unimodal baseline. Notably, the contrastive learning component yields greater gains for the text modality compared to speech. These results highlight our framework's effectiveness in multilingual and multi-picture MCI detection.
Authors: Kristin Qi, Youxiang Zhu, Caroline Summerour, John A. Batsis, Xiaohui Liang
Abstract: Early detection of cognitive decline is crucial for enabling interventions that can slow neurodegenerative disease progression. Traditional diagnostic approaches rely on labor-intensive clinical assessments, which are impractical for frequent monitoring. Our pilot study investigates voice assistant systems (VAS) as non-invasive tools for detecting cognitive decline through longitudinal analysis of speech patterns in voice commands. Over an 18-month period, we collected voice commands from 35 older adults, with 15 participants providing daily at-home VAS interactions. To address the challenges of analyzing these short, unstructured and noisy commands, we propose Cog-TiPRO, a framework that combines (1) LLM-driven iterative prompt refinement for linguistic feature extraction, (2) HuBERT-based acoustic feature extraction, and (3) transformer-based temporal modeling. Using iTransformer, our approach achieves 73.80% accuracy and 72.67% F1-score in detecting MCI, outperforming its baseline by 27.13%. Through our LLM approach, we identify linguistic features that uniquely characterize everyday command usage patterns in individuals experiencing cognitive decline.
Authors: Dong Liu, Yanxuan Yu, Jiayi Zhang, Yifan Li, Ben Lengerich, Ying Nian Wu
Abstract: Diffusion Transformers (DiT) are powerful generative models but remain computationally intensive due to their iterative structure and deep transformer stacks. To alleviate this inefficiency, we propose FastCache, a hidden-state-level caching and compression framework that accelerates DiT inference by exploiting redundancy within the model's internal representations. FastCache introduces a dual strategy: (1) a spatial-aware token selection mechanism that adaptively filters redundant tokens based on hidden state saliency, and (2) a transformer-level cache that reuses latent activations across timesteps when changes are statistically insignificant. These modules work jointly to reduce unnecessary computation while preserving generation fidelity through learnable linear approximation. Theoretical analysis shows that FastCache maintains bounded approximation error under a hypothesis-testing-based decision rule. Empirical evaluations across multiple DiT variants demonstrate substantial reductions in latency and memory usage, with best generation output quality compared to other cache methods, as measured by FID and t-FID. Code implementation of FastCache is available on GitHub at https://github.com/NoakLiu/FastCache-xDiT.
Authors: Manuel Costa, Boris K\"opf, Aashish Kolluri, Andrew Paverd, Mark Russinovich, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Santiago Zanella-B\'eguelin
Abstract: As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees for AI agents. We present a formal model to reason about the security and expressiveness of agent planners. Using this model, we characterize the class of properties enforceable by dynamic taint-tracking and construct a taxonomy of tasks to evaluate security and utility trade-offs of planner designs. Informed by this exploration, we present Fides, a planner that tracks confidentiality and integrity labels, deterministically enforces security policies, and introduces novel primitives for selectively hiding information. Its evaluation in AgentDojo demonstrates that this approach enables us to complete a broad range of tasks with security guarantees. A tutorial to walk readers through the the concepts introduced in the paper can be found at https://github.com/microsoft/fides
Authors: Alexander Marusov, Aleksandr Yugay, Alexey Zaytsev
Abstract: Self-supervised learning (SSL) has emerged as a powerful approach to learning representations, particularly in the field of computer vision. However, its application to dependent data, such as temporal and spatio-temporal domains, remains underexplored. Besides, traditional contrastive SSL methods often assume \emph{semantic independence between samples}, which does not hold for dependent data exhibiting complex correlations. We propose a novel theoretical framework for contrastive SSL tailored to \emph{continuous dependent data}, which allows the nearest samples to be semantically close to each other. In particular, we propose two possible \textit{ground truth similarity measures} between objects -- \emph{hard} and \emph{soft} closeness. Under it, we derive an analytical form for the \textit{estimated similarity matrix} that accommodates both types of closeness between samples, thereby introducing dependency-aware loss functions. We validate our approach, \emph{Dependent TS2Vec}, on temporal and spatio-temporal downstream problems. Given the dependency patterns presented in the data, our approach surpasses modern ones for dependent data, highlighting the effectiveness of our theoretically grounded loss functions for SSL in capturing spatio-temporal dependencies. Specifically, we outperform TS2Vec on the standard UEA and UCR benchmarks, with accuracy improvements of $4.17$\% and $2.08$\%, respectively. Furthermore, on the drought classification task, which involves complex spatio-temporal patterns, our method achieves a $7$\% higher ROC-AUC score.
Authors: Reza Fayyazi, Michael Zuzak, Shanchieh Jay Yang
Abstract: Large Language Models (LLMs) are increasingly used for cybersecurity threat analysis, but their deployment in security-sensitive environments raises trust and safety concerns. With over 21,000 vulnerabilities disclosed in 2025, manual analysis is infeasible, making scalable and verifiable AI support critical. When querying LLMs, dealing with emerging vulnerabilities is challenging as they have a training cut-off date. While Retrieval-Augmented Generation (RAG) can inject up-to-date context to alleviate the cut-off date limitation, it remains unclear how much LLMs rely on retrieved evidence versus the model's internal knowledge, and whether the retrieved information is meaningful or even correct. This uncertainty could mislead security analysts, mis-prioritize patches, and increase security risks. Therefore, this work proposes LLM Embedding-based Attribution (LEA) to analyze the generated responses for vulnerability exploitation analysis. More specifically, LEA quantifies the relative contribution of internal knowledge vs. retrieved content in the generated responses. We evaluate LEA on 500 critical vulnerabilities disclosed between 2016 and 2025, across three RAG settings -- valid, generic, and incorrect -- using three state-of-the-art LLMs. Our results demonstrate LEA's ability to detect clear distinctions between non-retrieval, generic-retrieval, and valid-retrieval scenarios with over 95% accuracy on larger models. Finally, we demonstrate the limitations posed by incorrect retrieval of vulnerability information and raise a cautionary note to the cybersecurity community regarding the blind reliance on LLMs and RAG for vulnerability analysis. LEA offers security analysts with a metric to audit RAG-enhanced workflows, improving the transparent and trustworthy deployment of AI in cybersecurity threat analysis.
Authors: Zhiyuan Su, Sunhao Dai, Xiao Zhang
Abstract: Clustering of Bandits (CB) methods enhance sequential decision-making by grouping bandits into clusters based on similarity and incorporating cluster-level contextual information, demonstrating effectiveness and adaptability in applications like personalized streaming recommendations. However, when extending CB algorithms to their neural version (commonly referred to as Clustering of Neural Bandits, or CNB), they suffer from loss of plasticity, where neural network parameters become rigid and less adaptable over time, limiting their ability to adapt to non-stationary environments (e.g., dynamic user preferences in recommendation). To address this challenge, we propose Selective Reinitialization (SeRe), a novel bandit learning framework that dynamically preserves the adaptability of CNB algorithms in evolving environments. SeRe leverages a contribution utility metric to identify and selectively reset underutilized units, mitigating loss of plasticity while maintaining stable knowledge retention. Furthermore, when combining SeRe with CNB algorithms, the adaptive change detection mechanism adjusts the reinitialization frequency according to the degree of non-stationarity, ensuring effective adaptation without unnecessary resets. Theoretically, we prove that SeRe enables sublinear cumulative regret in piecewise-stationary environments, outperforming traditional CNB approaches in long-term performances. Extensive experiments on six real-world recommendation datasets demonstrate that SeRe-enhanced CNB algorithms can effectively mitigate the loss of plasticity with lower regrets, improving adaptability and robustness in dynamic settings.
Authors: Rohit Mohan, Julia Hindel, Florian Drews, Claudius Gl\"aser, Daniele Cattaneo, Abhinav Valada
Abstract: Autonomous vehicles that navigate in open-world environments may encounter previously unseen object classes. However, most existing LiDAR panoptic segmentation models rely on closed-set assumptions, failing to detect unknown object instances. In this work, we propose ULOPS, an uncertainty-guided open-set panoptic segmentation framework that leverages Dirichlet-based evidential learning to model predictive uncertainty. Our architecture incorporates separate decoders for semantic segmentation with uncertainty estimation, embedding with prototype association, and instance center prediction. During inference, we leverage uncertainty estimates to identify and segment unknown instances. To strengthen the model's ability to differentiate between known and unknown objects, we introduce three uncertainty-driven loss functions. Uniform Evidence Loss to encourage high uncertainty in unknown regions. Adaptive Uncertainty Separation Loss ensures a consistent difference in uncertainty estimates between known and unknown objects at a global scale. Contrastive Uncertainty Loss refines this separation at the fine-grained level. To evaluate open-set performance, we extend benchmark settings on KITTI-360 and introduce a new open-set evaluation for nuScenes. Extensive experiments demonstrate that ULOPS consistently outperforms existing open-set LiDAR panoptic segmentation methods.
Authors: Yunhao Liu, Suyang Xi, Shiqi Liu, Hong Ding, Chicheng Jin, Chong Zhong, Junjun He, Catherine C. Liu, Yiqing Shen
Abstract: Medical image analysis increasingly relies on the integration of multiple imaging modalities to capture complementary anatomical and functional information, enabling more accurate diagnosis and treatment planning. Achieving aligned feature representations across these diverse modalities is therefore important for effective multimodal analysis. While contrastive language-image pre-training (CLIP) and its variant have enabled image-text alignments, they require explicitly paired data between arbitrary two modalities, which is difficult to acquire in medical contexts. To address the gap, we present Multimodal Medical Image Binding with Text (M\textsuperscript{3}Bind), a novel pre-training framework that enables seamless alignment of multiple medical imaging modalities through a shared text representation space without requiring explicit paired data between any two medical image modalities. Specifically, based on the insight that different images can naturally bind with text, M\textsuperscript{3}Bind first fine-tunes pre-trained CLIP-like image-text models to align their modality-specific text embedding space while preserving their original image-text alignments. Subsequently, we distill these modality-specific text encoders into a unified model, creating a shared text embedding space. Experiments on X-ray, CT, retina, ECG, and pathological images on multiple downstream tasks demonstrate that M\textsuperscript{3}Bind achieves state-of-the-art performance in zero-shot, few-shot classification and cross-modal retrieval tasks compared to its CLIP-like counterparts. These results validate M\textsuperscript{3}Bind's effectiveness in achieving cross-image-modal alignment for medical analysis.
Authors: Gabor Petnehazi, Bernadett Aradi
Abstract: The explosive growth of complex datasets across various modalities necessitates advanced analytical tools that not only group data effectively but also provide human-understandable insights into the discovered structures. We introduce HERCULES (Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization), a novel algorithm and Python package designed for hierarchical k-means clustering of diverse data types, including text, images, and numeric data (processed one modality per run). HERCULES constructs a cluster hierarchy by recursively applying k-means clustering, starting from individual data points at level 0. A key innovation is its deep integration of Large Language Models (LLMs) to generate semantically rich titles and descriptions for clusters at each level of the hierarchy, significantly enhancing interpretability. The algorithm supports two main representation modes: `direct' mode, which clusters based on original data embeddings or scaled numeric features, and `description' mode, which clusters based on embeddings derived from LLM-generated summaries. Users can provide a `topic\_seed' to guide LLM-generated summaries towards specific themes. An interactive visualization tool facilitates thorough analysis and understanding of the clustering results. We demonstrate HERCULES's capabilities and discuss its potential for extracting meaningful, hierarchical knowledge from complex datasets.
Authors: Siyi Zhou, Yiquan Zhou, Yi He, Xun Zhou, Jinchao Wang, Wei Deng, Jingchen Shu
Abstract: Existing autoregressive large-scale text-to-speech (TTS) models have advantages in speech naturalness, but their token-by-token generation mechanism makes it difficult to precisely control the duration of synthesized speech. This becomes a significant limitation in applications requiring strict audio-visual synchronization, such as video dubbing. This paper introduces IndexTTS2, which proposes a novel, general, and autoregressive model-friendly method for speech duration control. The method supports two generation modes: one explicitly specifies the number of generated tokens to precisely control speech duration; the other freely generates speech in an autoregressive manner without specifying the number of tokens, while faithfully reproducing the prosodic features of the input prompt. Furthermore, IndexTTS2 achieves disentanglement between emotional expression and speaker identity, enabling independent control over timbre and emotion. In the zero-shot setting, the model can accurately reconstruct the target timbre (from the timbre prompt) while perfectly reproducing the specified emotional tone (from the style prompt). To enhance speech clarity in highly emotional expressions, we incorporate GPT latent representations and design a novel three-stage training paradigm to improve the stability of the generated speech. Additionally, to lower the barrier for emotional control, we designed a soft instruction mechanism based on text descriptions by fine-tuning Qwen3, effectively guiding the generation of speech with the desired emotional orientation. Finally, experimental results on multiple datasets show that IndexTTS2 outperforms state-of-the-art zero-shot TTS models in terms of word error rate, speaker similarity, and emotional fidelity. Audio samples are available at: https://index-tts.github.io/index-tts2.github.io/
Authors: Hamza Rasaee, Taha Koleilat, Hassan Rivaz
Abstract: Accurate and generalizable object segmentation in ultrasound imaging remains a significant challenge due to anatomical variability, diverse imaging protocols, and limited annotated data. In this study, we propose a prompt-driven vision-language model (VLM) that integrates Grounding DINO with SAM2 to enable object segmentation across multiple ultrasound organs. A total of 18 public ultrasound datasets, encompassing the breast, thyroid, liver, prostate, kidney, and paraspinal muscle, were utilized. These datasets were divided into 15 for fine-tuning and validation of Grounding DINO using Low Rank Adaptation (LoRA) to the ultrasound domain, and 3 were held out entirely for testing to evaluate performance in unseen distributions. Comprehensive experiments demonstrate that our approach outperforms state-of-the-art segmentation methods, including UniverSeg, MedSAM, MedCLIP-SAM, BiomedParse, and SAMUS on most seen datasets while maintaining strong performance on unseen datasets without additional fine-tuning. These results underscore the promise of VLMs in scalable and robust ultrasound image analysis, reducing dependence on large, organ-specific annotated datasets. We will publish our code on code.sonography.ai after acceptance.
Authors: Huaqiu Li, Yong Wang, Tongwen Huang, Hailang Huang, Haoqian Wang, Xiangxiang Chu
Abstract: Unified image restoration is a significantly challenging task in low-level vision. Existing methods either make tailored designs for specific tasks, limiting their generalizability across various types of degradation, or rely on training with paired datasets, thereby suffering from closed-set constraints. To address these issues, we propose a novel, dataset-free, and unified approach through recurrent posterior sampling utilizing a pretrained latent diffusion model. Our method incorporates the multimodal understanding model to provide sematic priors for the generative model under a task-blind condition. Furthermore, it utilizes a lightweight module to align the degraded input with the generated preference of the diffusion model, and employs recurrent refinement for posterior sampling. Extensive experiments demonstrate that our method outperforms state-of-the-art methods, validating its effectiveness and robustness. Our code and data are available at https://github.com/AMAP-ML/LD-RPS.
Authors: Yiming Li, Shuo Shao, Yu He, Junfeng Guo, Tianwei Zhang, Zhan Qin, Pin-Yu Chen, Michael Backes, Philip Torr, Dacheng Tao, Kui Ren
Abstract: The (generative) artificial intelligence (AI) era has profoundly reshaped the meaning and value of data. No longer confined to static content, data now permeates every stage of the AI lifecycle from the training samples that shape model parameters to the prompts and outputs that drive real-world model deployment. This shift renders traditional notions of data protection insufficient, while the boundaries of what needs safeguarding remain poorly defined. Failing to safeguard data in AI systems can inflict societal and individual, underscoring the urgent need to clearly delineate the scope of and rigorously enforce data protection. In this perspective, we propose a four-level taxonomy, including non-usability, privacy preservation, traceability, and deletability, that captures the diverse protection needs arising in modern (generative) AI models and systems. Our framework offers a structured understanding of the trade-offs between data utility and control, spanning the entire AI pipeline, including training datasets, model weights, system prompts, and AI-generated content. We analyze representative technical approaches at each level and reveal regulatory blind spots that leave critical assets exposed. By offering a structured lens to align future AI technologies and governance with trustworthy data practices, we underscore the urgency of rethinking data protection for modern AI techniques and provide timely guidance for developers, researchers, and regulators alike.
Authors: Tanvi Bajpai, Chandra Chekuri, Pooja Kulkarni
Abstract: We consider the problem of covering multiple submodular constraints. Given a finite ground set $N$, a cost function $c: N \rightarrow \mathbb{R}_+$, $r$ monotone submodular functions $f_1,f_2,\ldots,f_r$ over $N$ and requirements $b_1,b_2,\ldots,b_r$ the goal is to find a minimum cost subset $S \subseteq N$ such that $f_i(S) \ge b_i$ for $1 \le i \le r$. When $r=1$ this is the well-known Submodular Set Cover problem. Previous work \cite{chekuri2022covering} considered the setting when $r$ is large and developed bi-criteria approximation algorithms, and approximation algorithms for the important special case when each $f_i$ is a weighted coverage function. These are fairly general models and capture several concrete and interesting problems as special cases. The approximation ratios for these problem are at least $\Omega(\log r)$ which is unavoidable when $r$ is part of the input. In this paper, motivated by some recent applications, we consider the problem when $r$ is a \emph{fixed constant} and obtain two main results. For covering multiple submodular constraints we obtain a randomized bi-criteria approximation algorithm that for any given integer $\alpha \ge 1$ outputs a set $S$ such that $f_i(S) \ge$ $(1-1/e^\alpha -\epsilon)b_i$ for each $i \in [r]$ and $\mathbb{E}[c(S)] \le (1+\epsilon)\alpha \cdot \sf{OPT}$. Second, when the $f_i$ are weighted coverage functions from a deletion-closed set system we obtain a $(1+\epsilon)$ $(\frac{e}{e-1})$ $(1+\beta)$-approximation where $\beta$ is the approximation ratio for the underlying set cover instances via the natural LP. These results show that one can obtain nearly as good an approximation for any fixed $r$ as what one would achieve for $r=1$. We mention some applications that follow easily from these general results and anticipate more in the future.
Authors: Jeremy Styborski, Mingzhi Lyu, Jiayou Lu, Nupur Kapur, Adams Kong
Abstract: Poisoning attacks pose significant challenges to the robustness of diffusion models (DMs). In this paper, we systematically analyze when and where poisoning attacks textual inversion (TI), a widely used personalization technique for DMs. We first introduce Semantic Sensitivity Maps, a novel method for visualizing the influence of poisoning on text embeddings. Second, we identify and experimentally verify that DMs exhibit non-uniform learning behavior across timesteps, focusing on lower-noise samples. Poisoning attacks inherit this bias and inject adversarial signals predominantly at lower timesteps. Lastly, we observe that adversarial signals distract learning away from relevant concept regions within training data, corrupting the TI process. Based on these insights, we propose Safe-Zone Training (SZT), a novel defense mechanism comprised of 3 key components: (1) JPEG compression to weaken high-frequency poison signals, (2) restriction to high timesteps during TI training to avoid adversarial signals at lower timesteps, and (3) loss masking to constrain learning to relevant regions. Extensive experiments across multiple poisoning methods demonstrate that SZT greatly enhances the robustness of TI against all poisoning attacks, improving generative quality beyond prior published defenses. Code: www.github.com/JStyborski/Diff_Lab Data: www.github.com/JStyborski/NC10
Authors: Vinil Polepalli
Abstract: The invasive spotted lanternfly (SLF) poses a significant threat to agriculture and ecosystems, causing widespread damage. Current control methods, such as egg scraping, pesticides, and quarantines, prove labor-intensive, environmentally hazardous, and inadequate for long-term SLF suppression. This research introduces LanternNet, a novel autonomous robotic Hub-and-Spoke system designed for scalable detection and suppression of SLF populations. A central, tree-mimicking hub utilizes a YOLOv8 computer vision model for precise SLF identification. Three specialized robotic spokes perform targeted tasks: pest neutralization, environmental monitoring, and navigation/mapping. Field deployment across multiple infested sites over 5 weeks demonstrated LanternNet's efficacy. Quantitative analysis revealed significant reductions (p < 0.01, paired t-tests) in SLF populations and corresponding improvements in tree health indicators across the majority of test sites. Compared to conventional methods, LanternNet offers substantial cost advantages and improved scalability. Furthermore, the system's adaptability for enhanced autonomy and targeting of other invasive species presents significant potential for broader ecological impact. LanternNet demonstrates the transformative potential of integrating robotics and AI for advanced invasive species management and improved environmental outcomes.
Authors: Mingcong Lei, Honghao Cai, Binbin Que, Zezhou Cui, Liangchen Tan, Junkun Hong, Gehan Hu, Shuangyu Zhu, Yimou Wu, Shaohan Jiang, Ge Wang, Zhen Li, Shuguang Cui, Yiming Zhao, Yatong Han
Abstract: We present RoboMemory, a brain-inspired multi-memory framework for lifelong learning in physical embodied systems, addressing critical challenges in real-world environments: continuous learning, multi-module memory latency, task correlation capture, and infinite-loop mitigation in closed-loop planning. Grounded in cognitive neuroscience, it integrates four core modules: the Information Preprocessor (thalamus-like), the Lifelong Embodied Memory System (hippocampus-like), the Closed-Loop Planning Module (prefrontal lobe-like), and the Low-Level Executer (cerebellum-like) to enable long-term planning and cumulative learning. The Lifelong Embodied Memory System, central to the framework, alleviates inference speed issues in complex memory frameworks via parallelized updates/retrieval across Spatial, Temporal, Episodic, and Semantic submodules. It incorporates a dynamic Knowledge Graph (KG) and consistent architectural design to enhance memory consistency and scalability. Evaluations on EmbodiedBench show RoboMemory outperforms the open-source baseline (Qwen2.5-VL-72B-Ins) by 25% in average success rate and surpasses the closed-source State-of-the-Art (SOTA) (Claude3.5-Sonnet) by 5%, establishing new SOTA. Ablation studies validate key components (critic, spatial memory, long-term memory), while real-world deployment confirms its lifelong learning capability with significantly improved success rates across repeated tasks. RoboMemory alleviates high latency challenges with scalability, serving as a foundational reference for integrating multi-modal memory systems in physical robots.
Authors: Claudiu Leoveanu-Condrei
Abstract: Generative models, particularly Large Language Models (LLMs), produce fluent outputs yet lack verifiable guarantees. We adapt Design by Contract (DbC) and type-theoretic principles to introduce a contract layer that mediates every LLM call. Contracts stipulate semantic and type requirements on inputs and outputs, coupled with probabilistic remediation to steer generation toward compliance. The layer exposes the dual view of LLMs as semantic parsers and probabilistic black-box components. Contract satisfaction is probabilistic and semantic validation is operationally defined through programmer-specified conditions on well-typed data structures. More broadly, this work postulates that any two agents satisfying the same contracts are \emph{functionally equivalent} with respect to those contracts.
Authors: Liujian Tang, Shaokang Dong, Yijia Huang, Minqi Xiang, Hongtao Ruan, Bin Wang, Shuo Li, Zhiheng Xi, Zhihui Cao, Hailiang Pang, Heng Kong, He Yang, Mingxu Chai, Zhilin Gao, Xingyu Liu, Yingnan Fu, Jiaming Liu, Xuanjing Huang, Yu-Gang Jiang, Tao Gui, Qi Zhang, Kang Wang, Yunke Zhang, Yuran Wang
Abstract: This paper presents MagicGUI, a foundational mobile GUI agent designed to address critical challenges in perception, grounding, and reasoning within real-world mobile GUI environments. The framework is underpinned by following six key components: (1) a comprehensive and accurate dataset, constructed via the scalable GUI Data Pipeline, which aggregates the largest and most diverse GUI-centric multimodal data to date from open-source repositories, automated crawling, and targeted manual annotation; (2) enhanced perception and grounding capabilities, facilitating fine-grained multimodal alignment for UI element referencing, grounding, and screen comprehension; (3) a comprehensive and unified action space, encompassing both fundamental UI operations and complex interactive intents to support human-agent interactions; (4) planning-oriented reasoning mechanisms that enable the model to decompose complex user instructions into sequential actions with explicit intermediate meta-paln reasoning; (5) an iterative two-stage training procedure, combining large-scale continue pre-training on 7.8M samples with reinforcement fine-tuning utilizing a spatially enhanced composite reward and dual filtering strategy; and (6) competitive performance on both the proprietary Magic-RICH benchmark and over a dozen public benchmarks, achieving superior performance across GUI perception and agent tasks, while demonstrating robust generalization and real-world deployment potential in practical mobile GUI scenarios, as detailed in Figure 1.
Authors: Xiang Li, Shanshan Wang, Chenglong Xiao
Abstract: Extensive experiments and prior studies show that no single maximum clique algorithm consistently performs best across all instances, highlighting the importance of selecting suitable algorithms based on instance features. Through an extensive analysis of relevant studies, it is found that there is a lack of research work concerning algorithm selection oriented toward the Maximum Clique Problem (MCP). In this work, we propose a learning-based framework that integrates both traditional machine learning and graph neural networks to address this gap. We construct a labeled dataset by running four exact MCP algorithms on a diverse collection of graph instances, accompanied by structural and global statistical features extracted from each graph. We first evaluate four conventional classifiers: Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and K-Nearest Neighbors (KNN), across multiple dataset variants. Experimental results show that RF consistently shows strong performance across metrics and dataset variants, making it a reliable baseline. In addition, feature importance analysis indicates that connectivity and topological structure are strong predictors of algorithm performance. Building on these findings, we develop a dual-channel model named GAT-MLP, which combines a Graph Attention Network (GAT) for local structural encoding with a Multilayer Perceptron (MLP) for global feature modeling. The GAT-MLP model shows strong and consistent performance across all metrics. Our results highlight the effectiveness of dual-channel architectures and the promise of graph neural networks in combinatorial algorithm selection.
Authors: Maozhen Zhang, Mengnan Zhao, Bo Wang
Abstract: Prompt-based tuning has emerged as a lightweight alternative to full fine-tuning in large vision-language models, enabling efficient adaptation via learned contextual prompts. This paradigm has recently been extended to federated learning settings (e.g., PromptFL), where clients collaboratively train prompts under data privacy constraints. However, the security implications of prompt-based aggregation in federated multimodal learning remain largely unexplored, leaving a critical attack surface unaddressed. In this paper, we introduce \textbf{BadPromptFL}, the first backdoor attack targeting prompt-based federated learning in multimodal contrastive models. In BadPromptFL, compromised clients jointly optimize local backdoor triggers and prompt embeddings, injecting poisoned prompts into the global aggregation process. These prompts are then propagated to benign clients, enabling universal backdoor activation at inference without modifying model parameters. Leveraging the contextual learning behavior of CLIP-style architectures, BadPromptFL achieves high attack success rates (e.g., \(>90\%\)) with minimal visibility and limited client participation. Extensive experiments across multiple datasets and aggregation protocols validate the effectiveness, stealth, and generalizability of our attack, raising critical concerns about the robustness of prompt-based federated learning in real-world deployments.
Authors: Tegan McCaslin, Jide Alaga, Samira Nedungadi, Seth Donoughe, Tom Reed, Rishi Bommasani, Chris Painter, Luca Righetti
Abstract: Evaluations of dangerous AI capabilities are important for managing catastrophic risks. Public transparency into these evaluations - including what they test, how they are conducted, and how their results inform decisions - is crucial for building trust in AI development. We propose STREAM (A Standard for Transparently Reporting Evaluations in AI Model Reports), a standard to improve how model reports disclose evaluation results, initially focusing on chemical and biological (ChemBio) benchmarks. Developed in consultation with 23 experts across government, civil society, academia, and frontier AI companies, this standard is designed to (1) be a practical resource to help AI developers present evaluation results more clearly, and (2) help third parties identify whether model reports provide sufficient detail to assess the rigor of the ChemBio evaluations. We concretely demonstrate our proposed best practices with "gold standard" examples, and also provide a three-page reporting template to enable AI developers to implement our recommendations more easily.
Authors: Tomer Wolfson, Harsh Trivedi, Mor Geva, Yoav Goldberg, Dan Roth, Tushar Khot, Ashish Sabharwal, Reut Tsarfaty
Abstract: Automated agents, powered by Large language models (LLMs), are emerging as the go-to tool for querying information. However, evaluation benchmarks for LLM agents rarely feature natural questions that are both information-seeking and genuinely time-consuming for humans. To address this gap we introduce MoNaCo, a benchmark of 1,315 natural and time-consuming questions that require dozens, and at times hundreds, of intermediate steps to solve -- far more than any existing QA benchmark. To build MoNaCo, we developed a decomposed annotation pipeline to elicit and manually answer real-world time-consuming questions at scale. Frontier LLMs evaluated on MoNaCo achieve at most 61.2% F1, hampered by low recall and hallucinations. Our results underscore the limitations of LLM-powered agents in handling the complexity and sheer breadth of real-world information-seeking tasks -- with MoNaCo providing an effective resource for tracking such progress. The MoNaCo benchmark, codebase, prompts and models predictions are all publicly available at: https://tomerwolgithub.github.io/monaco
Authors: Arshia Akhavan, Alireza Hosseinpour, Abbas Heydarnoori, Mehdi Keshani
Abstract: Issue-to-commit link recovery plays an important role in software traceability and improves project management. However, it remains a challenging task. A study on GitHub shows that only 42.2% of the issues are correctly linked to their commits. This highlights the potential for further development and research in this area. Existing studies have employed various AI/ML-based approaches, and with the recent development of large language models, researchers have leveraged LLMs to tackle this problem. These approaches suffer from two main issues. First, LLMs are constrained by limited context windows and cannot ingest all of the available data sources, such as long commit histories, extensive issue comments, and large code repositories. Second, most methods operate on individual issue-commit pairs; that is, given a single issue-commit pair, they determine whether the commit resolves the issue. This quickly becomes impractical in real-world repositories containing tens of thousands of commits. To address these limitations, we present LinkAnchor, the first autonomous LLM-based agent designed for issue-to-commit link recovery. The lazy-access architecture of LinkAnchor enables the underlying LLM to access the rich context of software, spanning commits, issue comments, and code files, without exceeding the token limit by dynamically retrieving only the most relevant contextual data. Additionally, LinkAnchor is able to automatically pinpoint the target commit rather than exhaustively scoring every possible candidate. Our evaluations show that LinkAnchor outperforms state-of-the-art issue-to-commit link recovery approaches by 60-262% in Hit@1 score across all our case study projects. We also publicly release LinkAnchor as a ready-to-use tool, along with our replication package. LinkAnchor is designed and tested for GitHub and Jira, and is easily extendable to other platforms.
Authors: Gohar Irfan Chaudhry, Esha Choukse, Haoran Qiu, \'I\~nigo Goiri, Rodrigo Fonseca, Adam Belay, Ricardo Bianchini
Abstract: Agentic workflows commonly coordinate multiple models and tools with complex control logic. They are quickly becoming the dominant paradigm for AI applications. However, serving them remains inefficient with today's frameworks. The key problem is that they expose workflows as opaque sequences of model and tool calls that tightly couple agent logic with model and hardware choices. Often, these workflow components are fragmented across different entities, preventing systems from reasoning about trade-offs across accuracy, latency, energy, and cost. This leads to resource waste and degraded service-level objectives (SLOs). We present Murakkab, a resource-efficient serving system for agentic workflows. Murakkab introduces a declarative abstraction that decouples workflow specification from execution configuration. A profile-guided optimizer and adaptive runtime jointly manage the full stack: orchestrating workflow components, mapping them to models and hardware, and dynamically reconfiguring execution to satisfy user-defined SLOs. By exposing the internal structure of agentic workflows, Murakkab enables cross-layer optimization that existing frameworks and cloud schedulers cannot achieve. Our evaluation on diverse workflows shows that Murakkab reduces GPU usage by up to 2.8$\times$, energy consumption by 3.7$\times$, and cost by 4.3$\times$ while maintaining SLOs.
Authors: Vojtech Mrazek, Konstantinos Balaskas, Paula Carolina Lozano Duarte, Zdenek Vasicek, Mehdi B. Tahoori, Georgios Zervakis
Abstract: Printed electronics offer a promising alternative for applications beyond silicon-based systems, requiring properties like flexibility, stretchability, conformality, and ultra-low fabrication costs. Despite the large feature sizes in printed electronics, printed neural networks have attracted attention for meeting target application requirements, though realizing complex circuits remains challenging. This work bridges the gap between classification accuracy and area efficiency in printed neural networks, covering the entire processing-near-sensor system design and co-optimization from the analog-to-digital interface-a major area and power bottleneck-to the digital classifier. We propose an automated framework for designing printed Ternary Neural Networks with arbitrary input precision, utilizing multi-objective optimization and holistic approximation. Our circuits outperform existing approximate printed neural networks by 17x in area and 59x in power on average, being the first to enable printed-battery-powered operation with under 5% accuracy loss while accounting for analog-to-digital interfacing costs.
Authors: Luca Ambrogioni
Abstract: Generative diffusion models have emerged as a powerful class of models in machine learning, yet a unified theoretical understanding of their operation is still developing. This perspective paper provides an integrated perspective on generative diffusion by connecting their dynamic, information-theoretic, and thermodynamic properties under a unified mathematical framework. We demonstrate that the rate of conditional entropy production during generation (i.e. the generative bandwidth) is directly governed by the expected divergence of the score function's vector field. This divergence, in turn, is linked to the branching of trajectories and generative bifurcations, which we characterize as symmetry-breaking phase transitions in the energy landscape. This synthesis offers a powerful insight: the process of generation is fundamentally driven by the controlled, noise-induced breaking of (approximate) symmetries, where peaks in information transfer correspond to critical transitions between possible outcomes. The score function acts as a dynamic non-linear filter that regulates the bandwidth of the noise by suppressing fluctuations that are incompatible with the data.
Authors: Hyejun Jeong, Mohammadreza Teymoorianfard, Abhinav Kumar, Amir Houmansadr, Eugene Bagdasarian
Abstract: We show that Web and Research Agents (WRAs) -- language model-based systems that investigate complex topics on the Internet -- are vulnerable to inference attacks by passive network adversaries such as ISPs. These agents could be deployed locally by organizations and individuals for privacy, legal, or financial purposes. Unlike sporadic web browsing by humans, WRAs visit $70{-}140$ domains with distinguishable timing correlations, enabling unique fingerprinting attacks. Specifically, we demonstrate a novel prompt and user trait leakage attack against WRAs that only leverages their network-level metadata (i.e., visited IP addresses and their timings). We start by building a new dataset of WRA traces based on user search queries and queries generated by synthetic personas. We define a behavioral metric (called OBELS) to comprehensively assess similarity between original and inferred prompts, showing that our attack recovers over 73% of the functional and domain knowledge of user prompts. Extending to a multi-session setting, we recover up to 19 of 32 latent traits with high accuracy. Our attack remains effective under partial observability and noisy conditions. Finally, we discuss mitigation strategies that constrain domain diversity or obfuscate traces, showing negligible utility impact while reducing attack effectiveness by an average of 29%.
Authors: Jie Zhu, Chihao Shen, Ziyang Li, Jiahao Yu, Yizheng Chen, Kexin Pei
Abstract: Directed fuzzing aims to find program inputs that lead to specified target program states. It has broad applications, such as debugging system crashes, confirming reported bugs, and generating exploits for potential vulnerabilities. This task is inherently challenging because target states are often deeply nested in the program, while the search space manifested by numerous possible program inputs is prohibitively large. Existing approaches rely on branch distances or manually-specified constraints to guide the search; however, the branches alone are often insufficient to precisely characterize progress toward reaching the target states, while the manually specified constraints are often tailored for specific bug types and thus difficult to generalize to diverse target states and programs. We present Locus, a novel framework to improve the efficiency of directed fuzzing. Our key insight is to synthesize predicates to capture fuzzing progress as semantically meaningful intermediate states, serving as milestones towards reaching the target states. When used to instrument the program under fuzzing, they can reject executions unlikely to reach the target states, while providing additional coverage guidance. To automate this task and generalize to diverse programs, Locus features an agentic framework with program analysis tools to synthesize and iteratively refine the candidate predicates, while ensuring the predicates strictly relax the target states to prevent false rejections via symbolic execution. Our evaluation shows that Locus substantially improves the efficiency of eight state-of-the-art fuzzers in discovering real-world vulnerabilities, achieving an average speedup of 41.6x. So far, Locus has found eight previously unpatched bugs, with one already acknowledged with a draft patch.
Authors: Justin Jung
Abstract: Generating realistic sparse multi-category 3D voxel structures is difficult due to the cubic memory scaling of voxel structures and moreover the significant class imbalance caused by sparsity. We introduce Scaffold Diffusion, a generative model designed for sparse multi-category 3D voxel structures. By treating voxels as tokens, Scaffold Diffusion uses a discrete diffusion language model to generate 3D voxel structures. We show that discrete diffusion language models can be extended beyond inherently sequential domains such as text to generate spatially coherent 3D structures. We evaluate on Minecraft house structures from the 3D-Craft dataset and demonstrate that, unlike prior baselines and an auto-regressive formulation, Scaffold Diffusion produces realistic and coherent structures even when trained on data with over 98% sparsity. We provide an interactive viewer where readers can visualize generated samples and the generation process: https://scaffold.deepexploration.org/
Authors: Akshay K. Jagadish, Mirko Thalmann, Julian Coda-Forno, Marcel Binz, Eric Schulz
Abstract: Human cognition is profoundly shaped by the environments in which it unfolds. Yet, it remains an open question whether learning and decision making can be explained as a principled adaptation to the statistical structure of real-world tasks. We introduce ecologically rational analysis, a computational framework that unifies the normative foundations of rational analysis with ecological grounding. Leveraging large language models to generate ecologically valid cognitive tasks at scale, and using meta-learning to derive rational models optimized for these environments, we develop a new class of learning algorithms: Ecologically Rational Meta-learned Inference (ERMI). ERMI internalizes the statistical regularities of naturalistic problem spaces and adapts flexibly to novel situations, without requiring hand-crafted heuristics or explicit parameter updates. We show that ERMI captures human behavior across 15 experiments spanning function learning, category learning, and decision making, outperforming several established cognitive models in trial-by-trial prediction. Our results suggest that much of human cognition may reflect adaptive alignment to the ecological structure of the problems we encounter in everyday life.
Authors: Jared Perlo, Alexander Robey, Fazl Barez, Luciano Floridi, Jakob M\"okander
Abstract: The field of embodied AI (EAI) is rapidly advancing. Unlike virtual AI, EAI systems can exist in, learn from, reason about, and act in the physical world. With recent advances in AI models and hardware, EAI systems are becoming increasingly capable across wider operational domains. While EAI systems can offer many benefits, they also pose significant risks, including physical harm from malicious use, mass surveillance, as well as economic and societal disruption. These risks require urgent attention from policymakers, as existing policies governing industrial robots and autonomous vehicles are insufficient to address the full range of concerns EAI systems present. To help address this issue, this paper makes three contributions. First, we provide a taxonomy of the physical, informational, economic, and social risks EAI systems pose. Second, we analyze policies in the US, EU, and UK to assess how existing frameworks address these risks and to identify critical gaps. We conclude by offering policy recommendations for the safe and beneficial deployment of EAI systems, such as mandatory testing and certification schemes, clarified liability frameworks, and strategies to manage EAI's potentially transformative economic and societal impacts.
Authors: Changin Choi, Wonseok Lee, Jungmin Ko, Wonjong Rhee
Abstract: While Multimodal Large Language Models (MLLMs) have significantly advanced multimodal understanding, their performance remains limited on knowledge-intensive visual questions that require external knowledge beyond the image. Retrieval-Augmented Generation (RAG) has become a promising solution for providing models with external knowledge, its conventional single-pass framework often fails to gather sufficient knowledge. To overcome this limitation, we propose MI-RAG, a Multimodal Iterative RAG framework that leverages reasoning to enhance retrieval and update reasoning over newly retrieved knowledge across modalities. At each iteration, MI-RAG leverages an accumulated reasoning record to dynamically formulate a multi-query. These queries then drive a joint search across heterogeneous knowledge bases containing both visually-grounded and textual knowledge. The newly acquired knowledge is synthesized into the reasoning record, progressively refining understanding across iterations. Experiments on challenging benchmarks, including Encyclopedic VQA, InfoSeek, and OK-VQA, show that MI-RAG significantly improves both retrieval recall and answer accuracy, establishing a scalable approach for compositional reasoning in knowledge-intensive VQA.
Authors: Yutong Gao, Maoyuan Shao, Xinyang Huang, Chuang Zhu, Lijuan Sun, Yu Weng, Xuan Liu, Guoshun Nan
Abstract: CLIP's success has demonstrated that prompt tuning can achieve robust cross-modal semantic alignment for tasks ranging from open-domain recognition to fine-grained classification. However, redundant or weakly relevant feature components introduce noise and incur unnecessary computational costs. In this work, we propose Spotlighter, a lightweight token-selection framework that simultaneously enhances accuracy and efficiency in prompt tuning. Spotlighter evaluates each visual token's activation from both sample-wise and semantic-wise perspectives and retains only the top-scoring tokens for downstream prediction. A class-specific semantic memory bank of learned prototypes refines this selection, ensuring semantic representativeness and compensating for discarded features. To further prioritize informative signals, we introduce a two-level ranking mechanism that dynamically weights token--prototype interactions. Across 11 few-shot benchmarks, Spotlighter outperforms CLIP by up to 11.19\% in harmonic mean accuracy and achieves up to 0.8K additional FPS, with only 21 extra parameters. These results establish Spotlighter as an effective and scalable baseline for prompt tuning. Code for our method will be available at https://github.com/greatest-gourmet/Spotlighter.
Authors: Yi-Ning Weng, Hsuan-Wei Lee
Abstract: Cooperation emergence in multi-agent systems represents a fundamental statistical physics problem where microscopic learning rules drive macroscopic collective behavior transitions. We propose a Q-learning-based variant of adaptive rewiring that builds on mechanisms studied in the literature. This method combines temporal difference learning with network restructuring so that agents can optimize strategies and social connections based on interaction histories. Through neighbor-specific Q-learning, agents develop sophisticated partnership management strategies that enable cooperator cluster formation, creating spatial separation between cooperative and defective regions. Using power-law networks that reflect real-world heterogeneous connectivity patterns, we evaluate emergent behaviors under varying rewiring constraint levels, revealing distinct cooperation patterns across parameter space rather than sharp thermodynamic transitions. Our systematic analysis identifies three behavioral regimes: a permissive regime (low constraints) enabling rapid cooperative cluster formation, an intermediate regime with sensitive dependence on dilemma strength, and a patient regime (high constraints) where strategic accumulation gradually optimizes network structure. Simulation results show that while moderate constraints create transition-like zones that suppress cooperation, fully adaptive rewiring enhances cooperation levels through systematic exploration of favorable network configurations. Quantitative analysis reveals that increased rewiring frequency drives large-scale cluster formation with power-law size distributions. Our results establish a new paradigm for understanding intelligence-driven cooperation pattern formation in complex adaptive systems, revealing how machine learning serves as an alternative driving force for spontaneous organization in multi-agent networks.
Authors: Chao Deng, Xiaosen Li, Xiao Qin
Abstract: The nnUNet segmentation framework adeptly adjusts most hyperparameters in training scripts automatically, but it overlooks the tuning of internal hyperparameters within the segmentation network itself, which constrains the model's ability to generalize. Addressing this limitation, this study presents a novel Self-Adaptive Convolution Module that dynamically adjusts the size of the convolution kernels depending on the unique fingerprints of different datasets. This adjustment enables the MSA2-Net, when equipped with this module, to proficiently capture both global and local features within the feature maps. Self-Adaptive Convolution Module is strategically integrated into two key components of the MSA2-Net: the Multi-Scale Convolution Bridge and the Multi-Scale Amalgamation Decoder. In the MSConvBridge, the module enhances the ability to refine outputs from various stages of the CSWin Transformer during the skip connections, effectively eliminating redundant data that could potentially impair the decoder's performance. Simultaneously, the MSADecoder, utilizing the module, excels in capturing detailed information of organs varying in size during the decoding phase. This capability ensures that the decoder's output closely reproduces the intricate details within the feature maps, thus yielding highly accurate segmentation images. MSA2-Net, bolstered by this advanced architecture, has demonstrated exceptional performance, achieving Dice coefficient scores of 86.49\%, 92.56\%, 93.37\%, and 92.98\% on the Synapse, ACDC, Kvasir, and Skin Lesion Segmentation (ISIC2017) datasets, respectively. This underscores MSA2-Net's robustness and precision in medical image segmentation tasks across various datasets.
Authors: Akis Nousias, Stavros Nousias
Abstract: Currently, prominent Transformer architectures applied on graphs and meshes for shape analysis tasks employ traditional attention layers that heavily utilize spectral features requiring costly eigenvalue decomposition-based methods. To encode the mesh structure, these methods derive positional embeddings, that heavily rely on eigenvalue decomposition based operations, e.g. on the Laplacian matrix, or on heat-kernel signatures, which are then concatenated to the input features. This paper proposes a novel approach inspired by the explicit construction of the Hodge Laplacian operator in Discrete Exterior Calculus as a product of discrete Hodge operators and exterior derivatives, i.e. $(L := \star_0^{-1} d_0^T \star_1 d_0)$. We adjust the Transformer architecture in a novel deep learning layer that utilizes the multi-head attention mechanism to approximate Hodge matrices $\star_0$, $\star_1$ and $\star_2$ and learn families of discrete operators $L$ that act on mesh vertices, edges and faces. Our approach results in a computationally-efficient architecture that achieves comparable performance in mesh segmentation and classification tasks, through a direct learning framework, while eliminating the need for costly eigenvalue decomposition operations or complex preprocessing operations.
Authors: Shubham Laxmikant Deshmukh, Matthew Wilchek, Feras A. Batarseh
Abstract: Ongoing advancements in computer vision, particularly in pattern recognition and scene classification, have enabled new applications in environmental monitoring. Deep learning now offers non-contact methods for assessing water quality and detecting contamination, both critical for disaster response and public health protection. This work introduces HydroVision, a deep learning-based scene classification framework that estimates optically active water quality parameters including Chlorophyll-Alpha, Chlorophylls, Colored Dissolved Organic Matter (CDOM), Phycocyanins, Suspended Sediments, and Turbidity from standard Red-Green-Blue (RGB) images of surface water. HydroVision supports early detection of contamination trends and strengthens monitoring by regulatory agencies during external environmental stressors, industrial activities, and force majeure events. The model is trained on more than 500,000 seasonally varied images collected from the United States Geological Survey Hydrologic Imagery Visualization and Information System between 2022 and 2024. This approach leverages widely available RGB imagery as a scalable, cost-effective alternative to traditional multispectral and hyperspectral remote sensing. Four state-of-the-art convolutional neural networks (VGG-16, ResNet50, MobileNetV2, DenseNet121) and a Vision Transformer are evaluated through transfer learning to identify the best-performing architecture. DenseNet121 achieves the highest validation performance, with an R2 score of 0.89 in predicting CDOM, demonstrating the framework's promise for real-world water quality monitoring across diverse conditions. While the current model is optimized for well-lit imagery, future work will focus on improving robustness under low-light and obstructed scenarios to expand its operational utility.
Authors: Kyeongman Park, Nakyeong Yang, Kyomin Jung
Abstract: Large Language Models (LLMs) often generate repetitive and monotonous outputs, especially in tasks like story generation, due to limited creative diversity when given the same input prompt. To address this challenge, we propose a novel decoding strategy, Avoidance Decoding, that modifies token logits by penalizing similarity to previously generated outputs, thereby encouraging more diverse multi-branch stories. This penalty adaptively balances two similarity measures: (1) Concept-level Similarity Penalty, which is prioritized in early stages to diversify initial story concepts, and (2) Narrative-level Similarity Penalty, which is increasingly emphasized later to ensure natural yet diverse plot development. Notably, our method achieves up to 2.6 times higher output diversity and reduces repetition by an average of 30% compared to strong baselines, while effectively mitigating text degeneration. Furthermore, we reveal that our method activates a broader range of neurons, demonstrating that it leverages the model's intrinsic creativity.
Authors: Junxi Wu, Jinpeng Wang, Zheng Liu, Bin Chen, Dongjian Hu, Hao Wu, Shu-Tao Xia
Abstract: The rapid advancement of large language models has intensified public concerns about the potential misuse. Therefore, it is important to build trustworthy AI-generated text detection systems. Existing methods neglect stylistic modeling and mostly rely on static thresholds, which greatly limits the detection performance. In this paper, we propose the Mixture of Stylistic Experts (MoSEs) framework that enables stylistics-aware uncertainty quantification through conditional threshold estimation. MoSEs contain three core components, namely, the Stylistics Reference Repository (SRR), the Stylistics-Aware Router (SAR), and the Conditional Threshold Estimator (CTE). For input text, SRR can activate the appropriate reference data in SRR and provide them to CTE. Subsequently, CTE jointly models the linguistic statistical properties and semantic features to dynamically determine the optimal threshold. With a discrimination score, MoSEs yields prediction labels with the corresponding confidence level. Our framework achieves an average improvement 11.34% in detection performance compared to baselines. More inspiringly, MoSEs shows a more evident improvement 39.15% in the low-resource case. Our code is available at https://github.com/creator-xi/MoSEs.