Authors: Amir Hadifar, Christopher Ochs, Arjan Van Ewijk
Abstract: Competitor analysis is essential in modern business due to the influence of industry rivals on strategic planning. It involves assessing multiple aspects and balancing trade-offs to make informed decisions. Recent Large Language Models (LLMs) have demonstrated impressive capabilities to reason about such trade-offs but grapple with inherent limitations such as a lack of knowledge about contemporary or future realities and an incomplete understanding of a market's competitive landscape. In this paper, we address this gap by incorporating business aspects into LLMs to enhance their understanding of a competitive market. Through quantitative and qualitative experiments, we illustrate how integrating such aspects consistently improves model performance, thereby enhancing analytical efficacy in competitor analysis.
Authors: Tu Ao, Yanhua Yu, Yuling Wang, Yang Deng, Zirui Guo, Liang Pang, Pinghui Wang, Tat-Seng Chua, Xiao Zhang, Zhen Cai
Abstract: Large Language Models (LLMs) have impressive capabilities in text understanding and zero-shot reasoning. However, delays in knowledge updates may cause them to reason incorrectly or produce harmful results. Knowledge Graphs (KGs) provide rich and reliable contextual information for the reasoning process of LLMs by structurally organizing and connecting a wide range of entities and relations. Existing KG-based LLM reasoning methods only inject KGs' knowledge into prompts in a textual form, ignoring its structural information. Moreover, they mostly rely on close-source models or open-source models with large parameters, which poses challenges to high resource consumption. To address this, we propose a novel Lightweight and efficient Prompt learning-ReasOning Framework for KGQA (LightPROF), which leverages the full potential of LLMs to tackle complex reasoning tasks in a parameter-efficient manner. Specifically, LightPROF follows a "Retrieve-Embed-Reason process", first accurately, and stably retrieving the corresponding reasoning graph from the KG through retrieval module. Next, through a Transformer-based Knowledge Adapter, it finely extracts and integrates factual and structural information from the KG, then maps this information to the LLM's token embedding space, creating an LLM-friendly prompt to be used by the LLM for the final reasoning. Additionally, LightPROF only requires training Knowledge Adapter and can be compatible with any open-source LLM. Extensive experiments on two public KGQA benchmarks demonstrate that LightPROF achieves superior performance with small-scale LLMs. Furthermore, LightPROF shows significant advantages in terms of input token count and reasoning time.
Authors: Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, Pengfei Liu
Abstract: Large Language Models (LLMs) equipped with web search capabilities have demonstrated impressive potential for deep research tasks. However, current approaches predominantly rely on either manually engineered prompts (prompt engineering-based) with brittle performance or reinforcement learning within controlled Retrieval-Augmented Generation (RAG) environments (RAG-based) that fail to capture the complexities of real-world interaction. In this paper, we introduce DeepResearcher, the first comprehensive framework for end-to-end training of LLM-based deep research agents through scaling reinforcement learning (RL) in real-world environments with authentic web search interactions. Unlike RAG-based approaches that assume all necessary information exists within a fixed corpus, our method trains agents to navigate the noisy, unstructured, and dynamic nature of the open web. We implement a specialized multi-agent architecture where browsing agents extract relevant information from various webpage structures and overcoming significant technical challenges. Extensive experiments on open-domain research tasks demonstrate that DeepResearcher achieves substantial improvements of up to 28.9 points over prompt engineering-based baselines and up to 7.2 points over RAG-based RL agents. Our qualitative analysis reveals emergent cognitive behaviors from end-to-end RL training, including the ability to formulate plans, cross-validate information from multiple sources, engage in self-reflection to redirect research, and maintain honesty when unable to find definitive answers. Our results highlight that end-to-end training in real-world web environments is not merely an implementation detail but a fundamental requirement for developing robust research capabilities aligned with real-world applications. We release DeepResearcher at https://github.com/GAIR-NLP/DeepResearcher.
Authors: Linfeng Zhao, Willie McClinton, Aidan Curtis, Nishanth Kumar, Tom Silver, Leslie Pack Kaelbling, Lawson L. S. Wong
Abstract: Generalizable robotic mobile manipulation in open-world environments poses significant challenges due to long horizons, complex goals, and partial observability. A promising approach to address these challenges involves planning with a library of parameterized skills, where a task planner sequences these skills to achieve goals specified in structured languages, such as logical expressions over symbolic facts. While vision-language models (VLMs) can be used to ground these expressions, they often assume full observability, leading to suboptimal behavior when the agent lacks sufficient information to evaluate facts with certainty. This paper introduces a novel framework that leverages VLMs as a perception module to estimate uncertainty and facilitate symbolic grounding. Our approach constructs a symbolic belief representation and uses a belief-space planner to generate uncertainty-aware plans that incorporate strategic information gathering. This enables the agent to effectively reason about partial observability and property uncertainty. We demonstrate our system on a range of challenging real-world tasks that require reasoning in partially observable environments. Simulated evaluations show that our approach outperforms both vanilla VLM-based end-to-end planning or VLM-based state estimation baselines by planning for and executing strategic information gathering. This work highlights the potential of VLMs to construct belief-space symbolic scene representations, enabling downstream tasks such as uncertainty-aware planning.
Authors: Tristan Cazenave, Benjamin Negrevergne, Florian Sikora
Abstract: Graph Coloring is probably one of the most studied and famous problem in graph algorithms. Exact methods fail to solve instances with more than few hundred vertices, therefore, a large number of heuristics have been proposed. Nested Monte Carlo Search (NMCS) and Nested Rollout Policy Adaptation (NRPA) are Monte Carlo search algorithms for single player games. Surprisingly, few work has been dedicated to evaluating Monte Carlo search algorithms to combinatorial graph problems. In this paper we expose how to efficiently apply Monte Carlo search to Graph Coloring and compare this approach to existing ones.
Authors: Lars Krupp, Daniel Gei{\ss}ler, Peter Hevesi, Marco Hirsch, Paul Lukowicz, Jakob Karolus
Abstract: Integrated into websites, LLM-powered chatbots offer alternative means of navigation and information retrieval, leading to a shift in how users access information on the web. Yet, predominantly closed-sourced solutions limit proliferation among web hosts and suffer from a lack of transparency with regard to implementation details and energy efficiency. In this work, we propose our openly available agent Talk2X leveraging an adapted retrieval-augmented generation approach (RAG) combined with an automatically generated vector database, benefiting energy efficiency. Talk2X's architecture is generalizable to arbitrary websites offering developers a ready to use tool for integration. Using a mixed-methods approach, we evaluated Talk2X's usability by tasking users to acquire specific assets from an open science repository. Talk2X significantly improved task completion time, correctness, and user experience supporting users in quickly pinpointing specific information as compared to standard user-website interaction. Our findings contribute technical advancements to an ongoing paradigm shift of how we access information on the web.
Authors: Xianyuan Liu, Jiayang Zhang, Shuo Zhou, Thijs L. van der Plas, Avish Vijayaraghavan, Anastasiia Grishina, Mengdie Zhuang, Daniel Schofield, Christopher Tomlinson, Yuhan Wang, Ruizhe Li, Louisa van Zeeland, Sina Tabakhi, Cyndie Demeocq, Xiang Li, Arunav Das, Orlando Timmerman, Thomas Baldwin-McDonald, Jinge Wu, Peizhen Bai, Zahraa Al Sahili, Omnia Alwazzan, Thao N. Do, Mohammod N. I. Suvon, Angeline Wang, Lucia Cipolina-Kun, Luigi A. Moretti, Lucas Farndale, Nitisha Jain, Natalia Efremova, Yan Ge, Marta Varela, Hak-Keung Lam, Oya Celiktutan, Ben R. Evans, Alejandro Coca-Castro, Honghan Wu, Zahraa S. Abdallah, Chen Chen, Valentin Danchev, Nataliya Tkachenko, Lei Lu, Tingting Zhu, Gregory G. Slabaugh, Roger K. Moore, William K. Cheung, Peter H. Charlton, Haiping Lu
Abstract: Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering. However, most multimodal AI advances focus on models for vision and language data, while their deployability remains a key challenge. We advocate a deployment-centric workflow that incorporates deployment constraints early to reduce the likelihood of undeployable solutions, complementing data-centric and model-centric approaches. We also emphasise deeper integration across multiple levels of multimodality and multidisciplinary collaboration to significantly broaden the research scope beyond vision and language. To facilitate this approach, we identify common multimodal-AI-specific challenges shared across disciplines and examine three real-world use cases: pandemic response, self-driving car design, and climate change adaptation, drawing expertise from healthcare, social science, engineering, science, sustainability, and finance. By fostering multidisciplinary dialogue and open research practices, our community can accelerate deployment-centric development for broad societal impact.
Authors: Xinyi Wang, Shawn Tan, Mingyu Jin, William Yang Wang, Rameswar Panda, Yikang Shen
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks requiring complex reasoning. However, the effects of scaling on their reasoning abilities remain insufficiently understood. In this paper, we introduce a synthetic multihop reasoning environment designed to closely replicate the structure and distribution of real-world large-scale knowledge graphs. Our reasoning task involves completing missing edges in the graph, which requires advanced multi-hop reasoning and mimics real-world reasoning scenarios. To evaluate this, we pretrain language models (LMs) from scratch solely on triples from the incomplete graph and assess their ability to infer the missing edges. Interestingly, we observe that overparameterization can impair reasoning performance due to excessive memorization. We investigate different factors that affect this U-shaped loss curve, including graph structure, model size, and training steps. To predict the optimal model size for a specific knowledge graph, we find an empirical scaling that linearly maps the knowledge graph search entropy to the optimal model size. This work provides new insights into the relationship between scaling and reasoning in LLMs, shedding light on possible ways to optimize their performance for reasoning tasks.
Authors: Richard J. Tong, Marina Cort\^es, Jeanine A. DeFalco, Mark Underwood, Janusz Zalewski
Abstract: Generative Artificial Intelligence (AI) is enabling unprecedented automation in content creation and decision support, but it also raises novel risks. This paper presents a first-principles risk assessment framework underlying the IEEE P3396 Recommended Practice for AI Risk, Safety, Trustworthiness, and Responsibility. We distinguish between process risks (risks arising from how AI systems are built or operated) and outcome risks (risks manifest in the AI system's outputs and their real-world effects), arguing that generative AI governance should prioritize outcome risks. Central to our approach is an information-centric ontology that classifies AI-generated outputs into four fundamental categories: (1) Perception-level information, (2) Knowledge-level information, (3) Decision/Action plan information, and (4) Control tokens (access or resource directives). This classification allows systematic identification of harms and more precise attribution of responsibility to stakeholders (developers, deployers, users, regulators) based on the nature of the information produced. We illustrate how each information type entails distinct outcome risks (e.g. deception, misinformation, unsafe recommendations, security breaches) and requires tailored risk metrics and mitigations. By grounding the framework in the essence of information, human agency, and cognition, we align risk evaluation with how AI outputs influence human understanding and action. The result is a principled approach to AI risk that supports clear accountability and targeted safeguards, in contrast to broad application-based risk categorizations. We include example tables mapping information types to risks and responsibilities. This work aims to inform the IEEE P3396 Recommended Practice and broader AI governance with a rigorous, first-principles foundation for assessing generative AI risks while enabling responsible innovation.
Authors: Mario Lino, Tobias Pfaff, Nils Thuerey
Abstract: Physical systems with complex unsteady dynamics, such as fluid flows, are often poorly represented by a single mean solution. For many practical applications, it is crucial to access the full distribution of possible states, from which relevant statistics (e.g., RMS and two-point correlations) can be derived. Here, we propose a graph-based latent diffusion (or alternatively, flow-matching) model that enables direct sampling of states from their equilibrium distribution, given a mesh discretization of the system and its physical parameters. This allows for the efficient computation of flow statistics without running long and expensive numerical simulations. The graph-based structure enables operations on unstructured meshes, which is critical for representing complex geometries with spatially localized high gradients, while latent-space diffusion modeling with a multi-scale GNN allows for efficient learning and inference of entire distributions of solutions. A key finding is that the proposed networks can accurately learn full distributions even when trained on incomplete data from relatively short simulations. We apply this method to a range of fluid dynamics tasks, such as predicting pressure distributions on 3D wing models in turbulent flow, demonstrating both accuracy and computational efficiency in challenging scenarios. The ability to directly sample accurate solutions, and capturing their diversity from short ground-truth simulations, is highly promising for complex scientific modeling tasks.
Authors: Lu Cheng, Qixiu Zhang, Beibei Xu, Zhiwei Huang, Cirun Zhang, Yanan Lyu, Fan Zhang
Abstract: The transition to intelligent, low-carbon power systems necessitates advanced optimization strategies for managing renewable energy integration, energy storage, and carbon emissions. Generative Large Models (GLMs) provide a data-driven approach to enhancing forecasting, scheduling, and market operations by processing multi-source data and capturing complex system dynamics. This paper explores the role of GLMs in optimizing load-side management, energy storage utilization, and electricity carbon, with a focus on Smart Wide-area Hybrid Energy Systems with Storage and Carbon (SGLSC). By leveraging spatiotemporal modeling and reinforcement learning, GLMs enable dynamic energy scheduling, improve grid stability, enhance carbon trading strategies, and strengthen resilience against extreme weather events. The proposed framework highlights the transformative potential of GLMs in achieving efficient, adaptive, and low-carbon power system operations.
Authors: Karthik Shivashankar
Abstract: The prospect of 4D video in Extended Reality (XR) platform is huge and exciting, it opens a whole new way of human computer interaction and the way we perceive the reality and consume multimedia. In this thesis, we have shown that feasibility of rendering 4D video in Microsoft mixed reality platform. This enables us to port any 3D performance capture from CVSSP into XR product like the HoloLens device with relative ease. However, if the 3D model is too complex and is made up of millions of vertices, the data bandwidth required to port the model is a severe limitation with the current hardware and communication system. Therefore, in this project we have also developed a compact representation of both shape and appearance of the 4d video sequence using deep learning models to effectively learn the compact representation of 4D video sequence and reconstruct it without affecting the shape and appearance of the video sequence.
Authors: Hongliu Cao, Ilias Driouich, Robin Singh, Eoin Thomas
Abstract: Large Language Models (LLMs) have demonstrated impressive performance across diverse domains, yet they still encounter challenges such as insufficient domain-specific knowledge, biases, and hallucinations. This underscores the need for robust evaluation methodologies to accurately assess LLM-based applications. Traditional evaluation methods, which rely on word overlap or text embeddings, are inadequate for capturing the nuanced semantic information necessary to evaluate dynamic, open-ended text generation. Recent research has explored leveraging LLMs to mimic human reasoning and decision-making processes for evaluation purposes known as LLM-as-a-judge framework. However, these existing frameworks have two significant limitations. First, they lack the flexibility to adapt to different text styles, including various answer and ground truth styles, thereby reducing their generalization performance. Second, the evaluation scores produced by these frameworks are often skewed and hard to interpret, showing a low correlation with human judgment. To address these challenges, we propose a novel dynamic multi-agent system that automatically designs personalized LLM judges for various natural language generation applications. This system iteratively refines evaluation prompts and balances the trade-off between the adaptive requirements of downstream tasks and the alignment with human perception. Our experimental results show that the proposed multi-agent LLM Judge framework not only enhances evaluation accuracy compared to existing methods but also produces evaluation scores that better align with human perception.
Authors: Frank P. -W. Lo, Jianing Qiu, Zeyu Wang, Haibao Yu, Yeming Chen, Gao Zhang, Benny Lo
Abstract: Resume screening is a critical yet time-intensive process in talent acquisition, requiring recruiters to analyze vast volume of job applications while remaining objective, accurate, and fair. With the advancements in Large Language Models (LLMs), their reasoning capabilities and extensive knowledge bases demonstrate new opportunities to streamline and automate recruitment workflows. In this work, we propose a multi-agent framework for resume screening using LLMs to systematically process and evaluate resumes. The framework consists of four core agents, including a resume extractor, an evaluator, a summarizer, and a score formatter. To enhance the contextual relevance of candidate assessments, we integrate Retrieval-Augmented Generation (RAG) within the resume evaluator, allowing incorporation of external knowledge sources, such as industry-specific expertise, professional certifications, university rankings, and company-specific hiring criteria. This dynamic adaptation enables personalized recruitment, bridging the gap between AI automation and talent acquisition. We assess the effectiveness of our approach by comparing AI-generated scores with ratings provided by HR professionals on a dataset of anonymized online resumes. The findings highlight the potential of multi-agent RAG-LLM systems in automating resume screening, enabling more efficient and scalable hiring workflows.
Authors: Enshuo Hsu, Martin Ugbala, Krishna Kumar Kookal, Zouaidi Kawtar, Nicholas L. Rider, Muhammad F. Walji, Kirk Roberts
Abstract: Generative information extraction using large language models, particularly through few-shot learning, has become a popular method. Recent studies indicate that providing a detailed, human-readable guideline-similar to the annotation guidelines traditionally used for training human annotators can significantly improve performance. However, constructing these guidelines is both labor- and knowledge-intensive. Additionally, the definitions are often tailored to meet specific needs, making them highly task-specific and often non-reusable. Handling these subtle differences requires considerable effort and attention to detail. In this study, we propose a self-improving method that harvests the knowledge summarization and text generation capacity of LLMs to synthesize annotation guidelines while requiring virtually no human input. Our zero-shot experiments on the clinical named entity recognition benchmarks, 2012 i2b2 EVENT, 2012 i2b2 TIMEX, 2014 i2b2, and 2018 n2c2 showed 25.86%, 4.36%, 0.20%, and 7.75% improvements in strict F1 scores from the no-guideline baseline. The LLM-synthesized guidelines showed equivalent or better performance compared to human-written guidelines by 1.15% to 4.14% in most tasks. In conclusion, this study proposes a novel LLM self-improving method that requires minimal knowledge and human input and is applicable to multiple biomedical domains.
Authors: Ingmar Bakermans, Daniel De Pascale, Gon\c{c}alo Marcelino, Giuseppe Cascavilla, Zeno Geradts
Abstract: Darknet markets (DNMs) facilitate the trade of illegal goods on a global scale. Gathering data on DNMs is critical to ensuring law enforcement agencies can effectively combat crime. Manually extracting data from DNMs is an error-prone and time-consuming task. Aiming to automate this process we develop a framework for extracting data from DNMs and evaluate the application of three state-of-the-art Named Entity Recognition (NER) models, ELMo-BiLSTM \citep{ShahEtAl2022}, UniversalNER \citep{ZhouEtAl2024}, and GLiNER \citep{ZaratianaEtAl2023}, at the task of extracting complex entities from DNM product listing pages. We propose a new annotated dataset, which we use to train, fine-tune, and evaluate the models. Our findings show that state-of-the-art NER models perform well in information extraction from DNMs, achieving 91% Precision, 96% Recall, and an F1 score of 94%. In addition, fine-tuning enhances model performance, with UniversalNER achieving the best performance.
Authors: Junchi Zhou, Haozhou Wang, Yoichiro Kato, Tejasri Nampally, P. Rajalakshmi, M. Balram, Keisuke Katsura, Hao Lu, Yue Mu, Wanneng Yang, Yangmingrui Gao, Feng Xiao, Hongtao Chen, Yuhao Chen, Wenjuan Li, Jingwen Wang, Fenghua Yu, Jian Zhou, Wensheng Wang, Xiaochun Hu, Yuanzhu Yang, Yanfeng Ding, Wei Guo, Shouyang Liu
Abstract: Developing computer vision-based rice phenotyping techniques is crucial for precision field management and accelerating breeding, thereby continuously advancing rice production. Among phenotyping tasks, distinguishing image components is a key prerequisite for characterizing plant growth and development at the organ scale, enabling deeper insights into eco-physiological processes. However, due to the fine structure of rice organs and complex illumination within the canopy, this task remains highly challenging, underscoring the need for a high-quality training dataset. Such datasets are scarce, both due to a lack of large, representative collections of rice field images and the time-intensive nature of annotation. To address this gap, we established the first comprehensive multi-class rice semantic segmentation dataset, RiceSEG. We gathered nearly 50,000 high-resolution, ground-based images from five major rice-growing countries (China, Japan, India, the Philippines, and Tanzania), encompassing over 6,000 genotypes across all growth stages. From these original images, 3,078 representative samples were selected and annotated with six classes (background, green vegetation, senescent vegetation, panicle, weeds, and duckweed) to form the RiceSEG dataset. Notably, the sub-dataset from China spans all major genotypes and rice-growing environments from the northeast to the south. Both state-of-the-art convolutional neural networks and transformer-based semantic segmentation models were used as baselines. While these models perform reasonably well in segmenting background and green vegetation, they face difficulties during the reproductive stage, when canopy structures are more complex and multiple classes are involved. These findings highlight the importance of our dataset for developing specialized segmentation models for rice and other crops.
Authors: Takanori Ugai
Abstract: Knowledge graph embedding (KGE) is a technique that enhances knowledge graphs by addressing incompleteness and improving knowledge retrieval. A limitation of the existing KGE models is their underutilization of ontologies, specifically the relationships between properties. This study proposes a KGE model, TransU, designed for knowledge graphs with well-defined ontologies that incorporate relationships between properties. The model treats properties as a subset of entities, enabling a unified representation. We present experimental results using a standard dataset and a practical dataset.
Authors: Khanh-Tung Tran, Barry O'Sullivan, Hoang D. Nguyen
Abstract: Recent advances in test-time compute scaling have enabled Large Language Models (LLMs) to tackle deep reasoning tasks by generating a chain-of-thought (CoT) that includes trial and error, backtracking, and intermediate reasoning steps before producing the final answer. However, these techniques have been applied predominantly to popular languages, such as English, leaving reasoning in low-resource languages underexplored and misaligned. In this work, we investigate the multilingual mechanism by which LLMs internally operate in a latent space biased toward their inherently dominant language. To leverage this phenomenon for low-resource languages, we train models to generate the CoT in English while outputting the final response in the target language, given input in the low-resource language. Our experiments demonstrate that this approach, named English-Pivoted CoT Training, outperforms other baselines, including training to generate both the CoT and the final response solely in the target language, with up to 28.33% improvement. Further analysis provides novel insights into the relationships between reasoning and multilinguality of LLMs, prompting for better approaches in developing multilingual large reasoning models
Authors: Kurmanbek Kaiyrbekov, Nicholas J Dobbins, Sean D Mooney
Abstract: Objective: Traditional phone-based surveys are among the most accessible and widely used methods to collect biomedical and healthcare data, however, they are often costly, labor intensive, and difficult to scale effectively. To overcome these limitations, we propose an end-to-end survey collection framework driven by conversational Large Language Models (LLMs). Materials and Methods: Our framework consists of a researcher responsible for designing the survey and recruiting participants, a conversational phone agent powered by an LLM that calls participants and administers the survey, a second LLM (GPT-4o) that analyzes the conversation transcripts generated during the surveys, and a database for storing and organizing the results. To test our framework, we recruited 8 participants consisting of 5 native and 3 non-native english speakers and administered 40 surveys. We evaluated the correctness of LLM-generated conversation transcripts, accuracy of survey responses inferred by GPT-4o and overall participant experience. Results: Survey responses were successfully extracted by GPT-4o from conversation transcripts with an average accuracy of 98% despite transcripts exhibiting an average per-line word error rate of 7.7%. While participants noted occasional errors made by the conversational LLM agent, they reported that the agent effectively conveyed the purpose of the survey, demonstrated good comprehension, and maintained an engaging interaction. Conclusions: Our study highlights the potential of LLM agents in conducting and analyzing phone surveys for healthcare applications. By reducing the workload on human interviewers and offering a scalable solution, this approach paves the way for real-world, end-to-end AI-powered phone survey collection systems.
Authors: Ahsan Bilal, Beiyu Lin, Mehdi Zaeifi
Abstract: Large language models (LLMs) have been widely used for various tasks and applications. However, LLMs and fine-tuning are limited to the pre-trained data. For example, ChatGPT's world knowledge until 2021 can be outdated or inaccurate. To enhance the capabilities of LLMs, Retrieval-Augmented Generation (RAG), is proposed to augment LLMs with additional, new, latest details and information to LLMs. While RAG offers the correct information, it may not best present it, especially to different population groups with personalizations. Reinforcement Learning from Human Feedback (RLHF) adapts to user needs by aligning model responses with human preference through feedback loops. In real-life applications, such as mental health problems, a dynamic and feedback-based model would continuously adapt to new information and offer personalized assistance due to complex factors fluctuating in a daily environment. Thus, we propose an Online Reinforcement Learning-based Retrieval-Augmented Generation (OnRL-RAG) system to detect and personalize the responding systems to mental health problems, such as stress, anxiety, and depression. We use an open-source dataset collected from 2028 College Students with 28 survey questions for each student to demonstrate the performance of our proposed system with the existing systems. Our system achieves superior performance compared to standard RAG and simple LLM via GPT-4o, GPT-4o-mini, Gemini-1.5, and GPT-3.5. This work would open up the possibilities of real-life applications of LLMs for personalized services in the everyday environment. The results will also help researchers in the fields of sociology, psychology, and neuroscience to align their theories more closely with the actual human daily environment.
Authors: Farida Al Haddad, Yuxin Wang, Malcolm Mielle
Abstract: Artificial intelligence has the potential to impact safety and efficiency in safety-critical domains such as construction, manufacturing, and healthcare. For example, using sensor data from wearable devices, such as inertial measurement units (IMUs), human gestures can be detected while maintaining privacy, thereby ensuring that safety protocols are followed. However, strict safety requirements in these domains have limited the adoption of AI, since accurate calibration of predicted probabilities and robustness against out-of-distribution (OOD) data is necessary. This paper proposes UAC (Uncertainty-Aware Calibration), a novel two-step method to address these challenges in IMU-based gesture recognition. First, we present an uncertainty-aware gesture network architecture that predicts both gesture probabilities and their associated uncertainties from IMU data. This uncertainty is then used to calibrate the probabilities of each potential gesture. Second, an entropy-weighted expectation of predictions over multiple IMU data windows is used to improve accuracy while maintaining correct calibration. Our method is evaluated using three publicly available IMU datasets for gesture detection and is compared to three state-of-the-art calibration methods for neural networks: temperature scaling, entropy maximization, and Laplace approximation. UAC outperforms existing methods, achieving improved accuracy and calibration in both OOD and in-distribution scenarios. Moreover, we find that, unlike our method, none of the state-of-the-art methods significantly improve the calibration of IMU-based gesture recognition models. In conclusion, our work highlights the advantages of uncertainty-aware calibration of neural networks, demonstrating improvements in both calibration and accuracy for gesture detection using IMU data.
Authors: Giuseppe Russo, Kristina Gligori\'c, Vincent Moreau, Robert West
Abstract: Reducing meat consumption is crucial for achieving global environmental and nutritional targets. Meat-Free Day (MFD) is a widely adopted strategy to address this challenge by encouraging plant-based diets through the removal of animal-based meals. We assessed the environmental, behavioral, and nutritional impacts of MFD by implementing 67 MFDs over 18 months (once a week on a randomly chosen day) across 12 cafeterias on a large university campus, analyzing over 400,000 food purchases. MFD reduced on-campus food-related greenhouse gas (GHG) emissions on treated days by 52.9% and contributed to improved fiber (+26.9%) and cholesterol (-4.5%) consumption without altering caloric intake. These nutritional benefits were, however, accompanied by a 27.6% decrease in protein intake and a 34.2% increase in sugar consumption. Moreover, the increase in plant-based meals did not carry over to subsequent days, as evidenced by a 3.5% rebound in animal-based meal consumption on days immediately following treated days. MFD also led to a 16.8% drop in on-campus meal sales on treated days.Monte Carlo simulations suggest that if 8.7% of diners were to eat burgers off-campus on treated days, MFD's GHG savings would be fully negated. As our analysis identifies on-campus customer retention as the main challenge to MFD effectiveness, we recommend combining MFD with customer retention interventions to ensure environmental and nutritional benefits.
Authors: Bo Yuan, Yulin Chen, Yin Zhang, Wei Jiang
Abstract: Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solutions identify noisy labels and adopt active learning to query human experts on them for denoising. In the era of large language models (LLMs), although we can reduce the human effort to improve these methods, their performances are still subject to accurately separating the clean and noisy samples from noisy data. In this paper, we propose an innovative collaborative learning framework NoiseAL based on active learning to combine LLMs and small models (SMs) for learning from noisy labels. During collaborative training, we first adopt two SMs to form a co-prediction network and propose a dynamic-enhanced threshold strategy to divide the noisy data into different subsets, then select the clean and noisy samples from these subsets to feed the active annotator LLMs to rectify noisy samples. Finally, we employ different optimization objectives to conquer subsets with different degrees of label noises. Extensive experiments on synthetic and real-world noise datasets further demonstrate the superiority of our framework over state-of-the-art baselines.
Authors: Liangjie Huang, Dawei Li, Huan Liu, Lu Cheng
Abstract: Large Language Models (LLMs) have demonstrated remarkable self-improvement capabilities, whereby models iteratively revise their outputs through self-generated feedback. While this reflective mechanism has shown promise in enhancing task performance, recent studies suggest that it may also introduce undesirable biases-most notably, self-bias, or the tendency of LLMs to favor their own prior outputs. In this work, we extend this line of inquiry by investigating the impact on confidence estimation. We evaluate three representative self-improvement paradigms-basic prompting, Chain-of-Thought (CoT) prompting, and tuning-based methods and find that iterative self-improvement can lead to systematic overconfidence, as evidenced by a steadily increasing Expected Calibration Error (ECE) and lower accuracy with high confidence. We then further explore the integration of confidence calibration techniques with self-improvement. Specifically, we compare three strategies: (1) applying calibration after multiple rounds of self-improvement, (2) calibrating before self-improvement, and (3) applying calibration iteratively at each self-improvement step. Our results show that iterative calibration is most effective in reducing ECE, yielding improved calibration. Our work pioneers the study of self-improving LLMs from a calibration perspective, offering valuable insights into balancing model performance and reliability.
Authors: Hongzhe Du, Weikai Li, Min Cai, Karim Saraipour, Zimin Zhang, Himabindu Lakkaraju, Yizhou Sun, Shichang Zhang
Abstract: Post-training is essential for the success of large language models (LLMs), transforming pre-trained base models into more useful and aligned post-trained models. While plenty of works have studied post-training algorithms and evaluated post-training models by their outputs, it remains understudied how post-training reshapes LLMs internally. In this paper, we compare base and post-trained LLMs mechanistically from four perspectives to better understand post-training effects. Our findings across model families and datasets reveal that: (1) Post-training does not change the factual knowledge storage locations, and it adapts knowledge representations from the base model while developing new knowledge representations; (2) Both truthfulness and refusal can be represented by linear vectors in the hidden representation space. The truthfulness direction is highly similar between the base and post-trained model, and it is effectively transferable for interventions; (3) The refusal direction is different between the base and post-trained models, and it shows limited forward transferability; (4) Differences in confidence between the base and post-trained models cannot be attributed to entropy neurons. Our study provides insights into the fundamental mechanisms preserved and altered during post-training, facilitates downstream tasks like model steering, and could potentially benefit future research in interpretability and LLM post-training.
Authors: Zhihan Zhang, Yixin Cao, Lizi Liao
Abstract: Chart-to-code generation, the process of converting chart images into executable plotting scripts, provides a lossless representation of chart information, requiring models to accurately capture and summarize all visual and structural elements. However, this remains a significant challenge for multimodal large language models (MLLMs), which are not inherently well-aligned with code generation tasks. To bridge this gap, we introduce Chart2Code, a novel iterative dual preference learning framework designed to enhance MLLMs' chart-to-code generation capabilities through structured code variant generation and fine-grained dual reward signals. We validate Chart2Code across three MLLMs and find that iterative preference learning consistently improves out-of-distribution chart-to-code generation quality. Throughout this process, our dual scoring method, which evaluates both the textual code structure and its visual representation, leads to greater performance improvements, even with a reduced preference dataset size. Further analysis explores the key components of our framework and highlights the interplay between chart-to-code generation and broader chart reasoning, paving the way for future advancements in chart comprehension.
Authors: Zaid M. Altukhi, Sojen Pradhan
Abstract: Explainable AI (XAI) seeks to transform black-box algorithmic processes into transparent ones, enhancing trust in AI applications across various sectors such as education. This review aims to examine the various definitions of XAI within the literature and explore the challenges of XAI in education. Our goal is to shed light on how XAI can contribute to enhancing the educational field. This systematic review, utilising the PRISMA method for rigorous and transparent research, identified 19 relevant studies. Our findings reveal 15 definitions and 62 challenges. These challenges are categorised using thematic analysis into seven groups: explainability, ethical, technical, human-computer interaction (HCI), trustworthiness, policy and guideline, and others, thereby deepening our understanding of the implications of XAI in education. Our analysis highlights the absence of standardised definitions for XAI, leading to confusion, especially because definitions concerning ethics, trustworthiness, technicalities, and explainability tend to overlap and vary.
Authors: Mohammad Reza Ghasemi Madani, Aryo Pradipta Gema, Gabriele Sarti, Yu Zhao, Pasquale Minervini, Andrea Passerini
Abstract: Feature attribution (FA) methods are common post-hoc approaches that explain how Large Language Models (LLMs) make predictions. Accordingly, generating faithful attributions that reflect the actual inner behavior of the model is crucial. In this paper, we introduce Noiser, a perturbation-based FA method that imposes bounded noise on each input embedding and measures the robustness of the model against partially noised input to obtain the input attributions. Additionally, we propose an answerability metric that employs an instructed judge model to assess the extent to which highly scored tokens suffice to recover the predicted output. Through a comprehensive evaluation across six LLMs and three tasks, we demonstrate that Noiser consistently outperforms existing gradient-based, attention-based, and perturbation-based FA methods in terms of both faithfulness and answerability, making it a robust and effective approach for explaining language model predictions.
Authors: Rohit Agarwal, Aryan Dessai, Arif Ahmed Sekh, Krishna Agarwal, Alexander Horsch, Dilip K. Prasad
Abstract: The field of varying feature space in online learning settings, also known as haphazard inputs, is very prominent nowadays due to its applicability in various fields. However, the current solutions to haphazard inputs are model-dependent and cannot benefit from the existing advanced deep-learning methods, which necessitate inputs of fixed dimensions. Therefore, we propose to transform the varying feature space in an online learning setting to a fixed-dimension image representation on the fly. This simple yet novel approach is model-agnostic, allowing any vision-based models to be applicable for haphazard inputs, as demonstrated using ResNet and ViT. The image representation handles the inconsistent input data seamlessly, making our proposed approach scalable and robust. We show the efficacy of our method on four publicly available datasets. The code is available at https://github.com/Rohit102497/HaphazardInputsAsImages.
URLs: https://github.com/Rohit102497/HaphazardInputsAsImages.
Authors: Thanathip Suenghataiphorn, Narisara Tribuddharat, Pojsakorn Danpanichkul, Narathorn Kulthamrongsri
Abstract: Background: Large language models (LLMs) are rapidly being integrated into healthcare, promising to enhance various clinical tasks. However, concerns exist regarding their potential for bias, which could compromise patient care and exacerbate health inequities. This systematic review investigates the prevalence, sources, manifestations, and clinical implications of bias in LLMs. Methods: We conducted a systematic search of PubMed, OVID, and EMBASE from database inception through 2025, for studies evaluating bias in LLMs applied to clinical tasks. We extracted data on LLM type, bias source, bias manifestation, affected attributes, clinical task, evaluation methods, and outcomes. Risk of bias was assessed using a modified ROBINS-I tool. Results: Thirty-eight studies met inclusion criteria, revealing pervasive bias across various LLMs and clinical applications. Both data-related bias (from biased training data) and model-related bias (from model training) were significant contributors. Biases manifested as: allocative harm (e.g., differential treatment recommendations); representational harm (e.g., stereotypical associations, biased image generation); and performance disparities (e.g., variable output quality). These biases affected multiple attributes, most frequently race/ethnicity and gender, but also age, disability, and language. Conclusions: Bias in clinical LLMs is a pervasive and systemic issue, with a potential to lead to misdiagnosis and inappropriate treatment, particularly for marginalized patient populations. Rigorous evaluation of the model is crucial. Furthermore, the development and implementation of effective mitigation strategies, coupled with continuous monitoring in real-world clinical settings, are essential to ensure the safe, equitable, and trustworthy deployment of LLMs in healthcare.
Authors: Julian Minder, Clement Dumas, Caden Juang, Bilal Chugtai, Neel Nanda
Abstract: Model diffing is the study of how fine-tuning changes a model's representations and internal algorithms. Many behaviours of interest are introduced during fine-tuning, and model diffing offers a promising lens to interpret such behaviors. Crosscoders are a recent model diffing method that learns a shared dictionary of interpretable concepts represented as latent directions in both the base and fine-tuned models, allowing us to track how concepts shift or emerge during fine-tuning. Notably, prior work has observed concepts with no direction in the base model, and it was hypothesized that these model-specific latents were concepts introduced during fine-tuning. However, we identify two issues which stem from the crosscoders L1 training loss that can misattribute concepts as unique to the fine-tuned model, when they really exist in both models. We develop Latent Scaling to flag these issues by more accurately measuring each latent's presence across models. In experiments comparing Gemma 2 2B base and chat models, we observe that the standard crosscoder suffers heavily from these issues. Building on these insights, we train a crosscoder with BatchTopK loss and show that it substantially mitigates these issues, finding more genuinely chat-specific and highly interpretable concepts. We recommend practitioners adopt similar techniques. Using the BatchTopK crosscoder, we successfully identify a set of genuinely chat-specific latents that are both interpretable and causally effective, representing concepts such as $\textit{false information}$ and $\textit{personal question}$, along with multiple refusal-related latents that show nuanced preferences for different refusal triggers. Overall, our work advances best practices for the crosscoder-based methodology for model diffing and demonstrates that it can provide concrete insights into how chat tuning modifies language model behavior.
Authors: Nikhil Shivakumar Nayak
Abstract: Graph Neural Networks (GNNs) have emerged as the de facto standard for modeling graph data, with attention mechanisms and transformers significantly enhancing their performance on graph-based tasks. Despite these advancements, the performance of GNNs on heterogeneous graphs often remains complex, with networks generally underperforming compared to their homogeneous counterparts. This work benchmarks various GNN architectures to identify the most effective methods for heterogeneous graphs, with a particular focus on node classification and link prediction. Our findings reveal that graph attention networks excel in these tasks. As a main contribution, we explore enhancements to these attention networks by integrating positional encodings for node embeddings. This involves utilizing the full Laplacian spectrum to accurately capture both the relative and absolute positions of each node within the graph, further enhancing performance on downstream tasks such as node classification and link prediction.
Authors: Xianwei Zhuang, Yuxin Xie, Yufan Deng, Dongchao Yang, Liming Liang, Jinghan Ru, Yuguo Yin, Yuexian Zou
Abstract: In this work, we present VARGPT-v1.1, an advanced unified visual autoregressive model that builds upon our previous framework VARGPT. The model preserves the dual paradigm of next-token prediction for visual understanding and next-scale generation for image synthesis. Specifically, VARGPT-v1.1 integrates: (1) a novel training strategy combining iterative visual instruction tuning with reinforcement learning through Direct Preference Optimization (DPO), (2) an expanded training corpus containing 8.3M visual-generative instruction pairs, (3) an upgraded language model backbone using Qwen2, (4) enhanced image generation resolution, and (5) emergent image editing capabilities without architectural modifications. These advancements enable VARGPT-v1.1 to achieve state-of-the-art performance in multimodal understanding and text-to-image instruction-following tasks, demonstrating significant improvements in both comprehension and generation metrics. Notably, through visual instruction tuning, the model acquires image editing functionality while maintaining architectural consistency with its predecessor, revealing the potential for unified visual understanding, generation, and editing. Our findings suggest that well-designed unified visual autoregressive models can effectively adopt flexible training strategies from large language models (LLMs), exhibiting promising scalability. The codebase and model weights are publicly available at https://github.com/VARGPT-family/VARGPT-v1.1.
Authors: Rafal Wlodarski, Leonardo da Silva Sousa, Allison Connell Pensky
Abstract: In software engineering (SE), the ability to review code and critique designs is essential for professional practice. However, these skills are rarely emphasized in formal education, and peer feedback quality and engagement can vary significantly among students. This paper introduces Socratique, a gamified peer-assessment platform integrated with Generative AI (GenAI) assistance, designed to develop students' peer-review skills in a functional programming course. By incorporating game elements, Socratique aims to motivate students to provide more feedback, while the GenAI assistant offers real-time support in crafting high quality, constructive comments. To evaluate the impact of this approach, we conducted a randomized controlled experiment with master's students comparing a treatment group with a gamified, GenAI-driven setup against a control group with minimal gamification. Results show that students in the treatment group provided significantly more voluntary feedback, with higher scores on clarity, relevance, and specificity - all key aspects of effective code and design reviews. This study provides evidence for the effectiveness of combining gamification and AI to improve peer review processes, with implications for fostering review-related competencies in software engineering curricula.
Authors: Zhipeng Yin, Zichong Wang, Weifeng Xu, Jun Zhuang, Pallab Mozumder, Antoinette Smith, Wenbin Zhang
Abstract: Digital forensics plays a pivotal role in modern investigative processes, utilizing specialized methods to systematically collect, analyze, and interpret digital evidence for judicial proceedings. However, traditional digital forensic techniques are primarily based on manual labor-intensive processes, which become increasingly insufficient with the rapid growth and complexity of digital data. To this end, Large Language Models (LLMs) have emerged as powerful tools capable of automating and enhancing various digital forensic tasks, significantly transforming the field. Despite the strides made, general practitioners and forensic experts often lack a comprehensive understanding of the capabilities, principles, and limitations of LLM, which limits the full potential of LLM in forensic applications. To fill this gap, this paper aims to provide an accessible and systematic overview of how LLM has revolutionized the digital forensics approach. Specifically, it takes a look at the basic concepts of digital forensics, as well as the evolution of LLM, and emphasizes the superior capabilities of LLM. To connect theory and practice, relevant examples and real-world scenarios are discussed. We also critically analyze the current limitations of applying LLMs to digital forensics, including issues related to illusion, interpretability, bias, and ethical considerations. In addition, this paper outlines the prospects for future research, highlighting the need for effective use of LLMs for transparency, accountability, and robust standardization in the forensic process.
Authors: Abhishek Sharma, Dan Goldwasser
Abstract: LLMs' remarkable ability to tackle a wide range of language tasks opened new opportunities for collaborative human-AI problem solving. LLMs can amplify human capabilities by applying their intuitions and reasoning strategies at scale. We explore whether human guides can be simulated, by generalizing from human demonstrations of guiding an AI system to solve complex language problems. We introduce CoLa, a novel self-guided learning paradigm for training automated $\textit{guides}$ and evaluate it on two QA datasets, a puzzle-solving task, and a constrained text generation task. Our empirical results show that CoLa consistently outperforms competitive approaches across all domains. Moreover, a small-sized trained guide outperforms a strong model like GPT-4 when acting as a guide. We compare the strategies employed by humans and automated guides by conducting a human study on a QA dataset. We show that automated guides outperform humans by adapting their strategies to reasoners' capabilities and conduct qualitative analyses highlighting distinct differences in guiding strategies.
Authors: Llu\'is Pastor-P\'erez, Javier Alonso-Garcia, Lukas Mauch
Abstract: Order-Preserving (OP) GFlowNets have demonstrated remarkable success in tackling complex multi-objective (MOO) black-box optimization problems using stochastic optimization techniques. Specifically, they can be trained online to efficiently sample diverse candidates near the Pareto front. A key advantage of OP GFlowNets is their ability to impose a local order on training samples based on Pareto dominance, eliminating the need for scalarization - a common requirement in other approaches like Preference-Conditional GFlowNets. However, we identify an important limitation of OP GFlowNets: imposing a local order on training samples can lead to conflicting optimization objectives. To address this issue, we introduce Global-Order GFlowNets, which transform the local order into a global one, thereby resolving these conflicts. Our experimental evaluations on various benchmarks demonstrate the efficacy and promise of our proposed method.
Authors: Prasanta Dutta, Anirban Mukhopadhyay
Abstract: Compact Genetic Algorithms (cGAs) are condensed variants of classical Genetic Algorithms (GAs) that use a probability vector representation of the population instead of the complete population. cGAs have been shown to significantly reduce the number of function evaluations required while producing outcomes similar to those of classical GAs. However, cGAs have a tendency to repeatedly generate the same chromosomes as they approach convergence, resulting in unnecessary evaluations of identical chromosomes. This article introduces the concept of caching in cGAs as a means of avoiding redundant evaluations of the same chromosomes. Our proposed approach operates equivalently to cGAs, but enhances the algorithm's time efficiency by reducing the number of function evaluations. We also present a data structure for efficient cache maintenance to ensure low overhead. The proposed caching approach has an asymptotically constant time complexity on average. The proposed method further generalizes the caching mechanism with higher selection pressure for elitism-based cGAs. We conduct a rigorous analysis based on experiments on benchmark optimization problems using two well-known cache replacement strategies. The results demonstrate that caching significantly reduces the number of function evaluations required while maintaining the same level of performance accuracy.
Authors: Nooshin Bahador
Abstract: This study investigates the localization of knowledge representation in fine-tuned GPT-2 models using Causal Layer Attribution via Activation Patching (CLAP), a method that identifies critical neural layers responsible for correct answer generation. The model was fine-tuned on 9,958 PubMed abstracts (epilepsy: 20,595 mentions, EEG: 11,674 mentions, seizure: 13,921 mentions) using two configurations with validation loss monitoring for early stopping. CLAP involved (1) caching clean (correct answer) and corrupted (incorrect answer) activations, (2) computing logit difference to quantify model preference, and (3) patching corrupted activations with clean ones to assess recovery. Results revealed three findings: First, patching the first feedforward layer recovered 56% of correct preference, demonstrating that associative knowledge is distributed across multiple layers. Second, patching the final output layer completely restored accuracy (100% recovery), indicating that definitional knowledge is localised. The stronger clean logit difference for definitional questions further supports this localized representation. Third, minimal recovery from convolutional layer patching (13.6%) suggests low-level features contribute marginally to high-level reasoning. Statistical analysis confirmed significant layer-specific effects (p<0.01). These findings demonstrate that factual knowledge is more localized and associative knowledge depends on distributed representations. We also showed that editing efficacy depends on task type. Our findings not only reconcile conflicting observations about localization in model editing but also emphasize on using task-adaptive techniques for reliable, interpretable updates.
Authors: Sheridan Feucht, Eric Todd, Byron Wallace, David Bau
Abstract: Prior work on in-context copying has shown the existence of induction heads, which attend to and promote individual tokens during copying. In this work we introduce a new type of induction head: concept-level induction heads, which copy entire lexical units instead of individual tokens. Concept induction heads learn to attend to the ends of multi-token words throughout training, working in parallel with token-level induction heads to copy meaningful text. We show that these heads are responsible for semantic tasks like word-level translation, whereas token induction heads are vital for tasks that can only be done verbatim, like copying nonsense tokens. These two "routes" operate independently: in fact, we show that ablation of token induction heads causes models to paraphrase where they would otherwise copy verbatim. In light of these findings, we argue that although token induction heads are vital for specific tasks, concept induction heads may be more broadly relevant for in-context learning.
Authors: Jannis Bl\"uml, Cedric Derstroff, Bjarne Gregori, Elisabeth Dillies, Quentin Delfosse, Kristian Kersting
Abstract: Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant background details. To address this issue, object-centric agents have recently emerged. However, they require different representations tailored to the task specifications. Contrary to deep agents, no single object-centric architecture can be applied to any environment. Inspired by principles of cognitive science and Occam's Razor, we introduce Object-Centric Attention via Masking (OCCAM), which selectively preserves task-relevant entities while filtering out irrelevant visual information. Specifically, OCCAM takes advantage of the object-centric inductive bias. Empirical evaluations on Atari benchmarks demonstrate that OCCAM significantly improves robustness to novel perturbations and reduces sample complexity while showing similar or improved performance compared to conventional pixel-based RL. These results suggest that structured abstraction can enhance generalization without requiring explicit symbolic representations or domain-specific object extraction pipelines.
Authors: Hanping Zhang, Yuhong Guo
Abstract: Safe Reinforcement Learning (Safe RL) aims to train an RL agent to maximize its performance in real-world environments while adhering to safety constraints, as exceeding safety violation limits can result in severe consequences. In this paper, we propose a novel safe RL approach called Safety Modulated Policy Optimization (SMPO), which enables safe policy function learning within the standard policy optimization framework through safety modulated rewards. In particular, we consider safety violation costs as feedback from the RL environments that are parallel to the standard awards, and introduce a Q-cost function as safety critic to estimate expected future cumulative costs. Then we propose to modulate the rewards using a cost-aware weighting function, which is carefully designed to ensure the safety limits based on the estimation of the safety critic, while maximizing the expected rewards. The policy function and the safety critic are simultaneously learned through gradient descent during online interactions with the environment. We conduct experiments using multiple RL environments and the experimental results demonstrate that our method outperforms several classic and state-of-the-art comparison methods in terms of overall safe RL performance.
Authors: Chengyang He, Wenlong Zhang, Violet Xinying Chen, Yue Ning, Ping Wang
Abstract: Accurate medical symptom coding from unstructured clinical text, such as vaccine safety reports, is a critical task with applications in pharmacovigilance and safety monitoring. Symptom coding, as tailored in this study, involves identifying and linking nuanced symptom mentions to standardized vocabularies like MedDRA, differentiating it from broader medical coding tasks. Traditional approaches to this task, which treat symptom extraction and linking as independent workflows, often fail to handle the variability and complexity of clinical narratives, especially for rare cases. Recent advancements in Large Language Models (LLMs) offer new opportunities but face challenges in achieving consistent performance. To address these issues, we propose Task as Context (TACO) Prompting, a novel framework that unifies extraction and linking tasks by embedding task-specific context into LLM prompts. Our study also introduces SYMPCODER, a human-annotated dataset derived from Vaccine Adverse Event Reporting System (VAERS) reports, and a two-stage evaluation framework to comprehensively assess both symptom linking and mention fidelity. Our comprehensive evaluation of multiple LLMs, including Llama2-chat, Jackalope-7b, GPT-3.5 Turbo, GPT-4 Turbo, and GPT-4o, demonstrates TACO's effectiveness in improving flexibility and accuracy for tailored tasks like symptom coding, paving the way for more specific coding tasks and advancing clinical text processing methodologies.
Authors: Hyun-Ho Choi, Kangsoo Kim, Ki-Ho Lee, Kisong Lee
Abstract: Accurate and real-time three-dimensional (3D) pose estimation is challenging in resource-constrained and dynamic environments owing to its high computational complexity. To address this issue, this study proposes a novel cooperative inference method for real-time 3D human pose estimation in mobile edge computing (MEC) networks. In the proposed method, multiple end devices equipped with lightweight inference models employ dual confidence thresholds to filter ambiguous images. Only the filtered images are offloaded to an edge server with a more powerful inference model for re-evaluation, thereby improving the estimation accuracy under computational and communication constraints. We numerically analyze the performance of the proposed inference method in terms of the inference accuracy and end-to-end delay and formulate a joint optimization problem to derive the optimal confidence thresholds and transmission time for each device, with the objective of minimizing the mean per-joint position error (MPJPE) while satisfying the required end-to-end delay constraint. To solve this problem, we demonstrate that minimizing the MPJPE is equivalent to maximizing the sum of the inference accuracies for all devices, decompose the problem into manageable subproblems, and present a low-complexity optimization algorithm to obtain a near-optimal solution. The experimental results show that a trade-off exists between the MPJPE and end-to-end delay depending on the confidence thresholds. Furthermore, the results confirm that the proposed cooperative inference method achieves a significant reduction in the MPJPE through the optimal selection of confidence thresholds and transmission times, while consistently satisfying the end-to-end delay requirement in various MEC environments.
Authors: Hao Yan, Yuhong Guo
Abstract: Domain generalization aims at developing suitable learning algorithms in source training domains such that the model learned can generalize well on a different unseen testing domain. We present a novel two-stage approach called Context-Aware Self-Adaptation (CASA) for domain generalization. CASA simulates an approximate meta-generalization scenario and incorporates a self-adaptation module to adjust pre-trained meta source models to the meta-target domains while maintaining their predictive capability on the meta-source domains. The core concept of self-adaptation involves leveraging contextual information, such as the mean of mini-batch features, as domain knowledge to automatically adapt a model trained in the first stage to new contexts in the second stage. Lastly, we utilize an ensemble of multiple meta-source models to perform inference on the testing domain. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on standard benchmarks.
Authors: Huiyong Li, Boxuan Ma
Abstract: Large Language Model (LLM) tools have demonstrated their potential to deliver high-quality assistance by providing instant, personalized feedback that is crucial for effective programming education. However, many of these tools operate independently from institutional Learning Management Systems, which creates a significant disconnect. This isolation limits the ability to leverage learning materials and exercise context for generating tailored, context-aware feedback. Furthermore, previous research on self-regulated learning and LLM support mainly focused on knowledge acquisition, not the development of important self-regulation skills. To address these challenges, we developed CodeRunner Agent, an LLM-based programming assistant that integrates the CodeRunner, a student-submitted code executing and automated grading plugin in Moodle. CodeRunner Agent empowers educators to customize AI-generated feedback by incorporating detailed context from lecture materials, programming questions, student answers, and execution results. Additionally, it enhances students' self-regulated learning by providing strategy-based AI responses. This integrated, context-aware, and skill-focused approach offers promising avenues for data-driven improvements in programming education.
Authors: Amir Ali Farzin, Yuen-Man Pun, Philipp Braun, Iman Shames
Abstract: This paper studies properties of fixed points of generalised Extra-gradient (GEG) algorithms applied to min-max problems. We discuss connections between saddle points of the objective function of the min-max problem and GEG fixed points. We show that, under appropriate step-size selections, the set of saddle points (Nash equilibria) is a subset of stable fixed points of GEG. Convergence properties of the GEG algorithm are obtained through a stability analysis of a discrete-time dynamical system. The results and benefits when compared to existing methods are illustrated through numerical examples.
Authors: Ziyu Liu, Lintao Tang, Zeliang Sun, Zhengliang Liu, Yanjun Lyu, Wei Ruan, Yangshuang Xu, Liang Shan, Jiyoon Shin, Xiaohe Chen, Dajiang Zhu, Tianming Liu, Rongjie Liu, Chao Huang
Abstract: Large language models (LLMs) have emerged as powerful tools for medical information retrieval, yet their accuracy and depth remain limited in specialized domains such as Alzheimer's disease (AD), a growing global health challenge. To address this gap, we introduce AD-GPT, a domain-specific generative pre-trained transformer designed to enhance the retrieval and analysis of AD-related genetic and neurobiological information. AD-GPT integrates diverse biomedical data sources, including potential AD-associated genes, molecular genetic information, and key gene variants linked to brain regions. We develop a stacked LLM architecture combining Llama3 and BERT, optimized for four critical tasks in AD research: (1) genetic information retrieval, (2) gene-brain region relationship assessment, (3) gene-AD relationship analysis, and (4) brain region-AD relationship mapping. Comparative evaluations against state-of-the-art LLMs demonstrate AD-GPT's superior precision and reliability across these tasks, underscoring its potential as a robust and specialized AI tool for advancing AD research and biomarker discovery.
Authors: Jakub Kacper Szelag, Ji-Jian Chin, Lauren Ansell, Sook-Chin Yip
Abstract: Federated Learning (FL) has recently emerged as a promising paradigm for privacy-preserving, distributed machine learning. However, FL systems face significant security threats, particularly from adaptive adversaries capable of modifying their attack strategies to evade detection. One such threat is the presence of Reconnecting Malicious Clients (RMCs), which exploit FLs open connectivity by reconnecting to the system with modified attack strategies. To address this vulnerability, we propose integration of Identity-Based Identification (IBI) as a security measure within FL environments. By leveraging IBI, we enable FL systems to authenticate clients based on cryptographic identity schemes, effectively preventing previously disconnected malicious clients from re-entering the system. Our approach is implemented using the TNC-IBI (Tan-Ng-Chin) scheme over elliptic curves to ensure computational efficiency, particularly in resource-constrained environments like Internet of Things (IoT). Experimental results demonstrate that integrating IBI with secure aggregation algorithms, such as Krum and Trimmed Mean, significantly improves FL robustness by mitigating the impact of RMCs. We further discuss the broader implications of IBI in FL security, highlighting research directions for adaptive adversary detection, reputation-based mechanisms, and the applicability of identity-based cryptographic frameworks in decentralized FL architectures. Our findings advocate for a holistic approach to FL security, emphasizing the necessity of proactive defence strategies against evolving adaptive adversarial threats.
Authors: Saumendu Roy, Saikat Mondal, Banani Roy, Chanchal Roy
Abstract: The lack of interpretability is a major barrier that limits the practical usage of AI models. Several eXplainable AI (XAI) techniques (e.g., SHAP, LIME) have been employed to interpret these models' performance. However, users often face challenges when leveraging these techniques in real-world scenarios and thus submit questions in technical Q&A forums like Stack Overflow (SO) to resolve these challenges. We conducted an exploratory study to expose these challenges, their severity, and features that can make XAI techniques more accessible and easier to use. Our contributions to this study are fourfold. First, we manually analyzed 663 SO questions that discussed challenges related to XAI techniques. Our careful investigation produced a catalog of seven challenges (e.g., disagreement issues). We then analyzed their prevalence and found that model integration and disagreement issues emerged as the most prevalent challenges. Second, we attempt to estimate the severity of each XAI challenge by determining the correlation between challenge types and answer metadata (e.g., the presence of accepted answers). Our analysis suggests that model integration issues is the most severe challenge. Third, we attempt to perceive the severity of these challenges based on practitioners' ability to use XAI techniques effectively in their work. Practitioners' responses suggest that disagreement issues most severely affect the use of XAI techniques. Fourth, we seek agreement from practitioners on improvements or features that could make XAI techniques more accessible and user-friendly. The majority of them suggest consistency in explanations and simplified integration. Our study findings might (a) help to enhance the accessibility and usability of XAI and (b) act as the initial benchmark that can inspire future research.
Authors: Md Zahidul Islam, Md Shahidul Islam, Biswajit Chandra das, Syed Ali Reza, Proshanta Kumar Bhowmik, Kanchon Kumar Bishnu, Md Shafiqur Rahman, Redoyan Chowdhury, Laxmi Pant
Abstract: The dramatic adoption of Bitcoin and other cryptocurrencies in the USA has revolutionized the financial landscape and provided unprecedented investment and transaction efficiency opportunities. The prime objective of this research project is to develop machine learning algorithms capable of effectively identifying and tracking suspicious activity in Bitcoin wallet transactions. With high-tech analysis, the study aims to create a model with a feature for identifying trends and outliers that can expose illicit activity. The current study specifically focuses on Bitcoin transaction information in America, with a strong emphasis placed on the importance of knowing about the immediate environment in and through which such transactions pass through. The dataset is composed of in-depth Bitcoin wallet transactional information, including important factors such as transaction values, timestamps, network flows, and addresses for wallets. All entries in the dataset expose information about financial transactions between wallets, including received and sent transactions, and such information is significant for analysis and trends that can represent suspicious activity. This study deployed three accredited algorithms, most notably, Logistic Regression, Random Forest, and Support Vector Machines. In retrospect, Random Forest emerged as the best model with the highest F1 Score, showcasing its ability to handle non-linear relationships in the data. Insights revealed significant patterns in wallet activity, such as the correlation between unredeemed transactions and final balances. The application of machine algorithms in tracking cryptocurrencies is a tool for creating transparent and secure U.S. markets.
Authors: Zhiqun Zuo, Ding Zhu, Mohammad Mahdi Khalili
Abstract: This paper presents a post-processing algorithm for training fair neural network regression models that satisfy statistical parity, utilizing an explainable singular value decomposition (SVD) of the weight matrix. We propose a linear transformation of the weight matrix, whereby the singular values derived from the SVD of the transformed matrix directly correspond to the differences in the first and second moments of the output distributions across two groups. Consequently, we can convert the fairness constraints into constraints on the singular values. We analytically solve the problem of finding the optimal weights under these constraints. Experimental validation on various datasets demonstrates that our method achieves a similar or superior fairness-accuracy trade-off compared to the baselines without using the sensitive attribute at the inference time.
Authors: Xuanyu Liu, Huiyun Yao, Jinggui Gao, Zhongyi Guo, Xue Zhang, Yulin Dong
Abstract: Background:Convolutional Neural Networks(CNN) and Vision Transformers(ViT) are the main techniques used in Medical image segmentation. However, CNN is limited to local contextual information, and ViT's quadratic complexity results in significant computational costs. At the same time, equipping the model to distinguish lesion boundaries with varying degrees of severity is also a challenge encountered in skin lesion segmentation. Purpose:This research aims to optimize the balance between computational costs and long-range dependency modelling and achieve excellent generalization across lesions with different degrees of severity. Methods:we propose a lightweight U-shape network that utilizes Vision Fastformer with Fusion Mechanism (VFFM-UNet). We inherit the advantages of Fastformer's additive attention mechanism, combining element-wise product and matrix product for comprehensive feature extraction and channel reduction to save computational costs. In order to accurately identify the lesion boundaries with varying degrees of severity, we designed Fusion Mechanism including Multi-Granularity Fusion and Channel Fusion, which can process the feature maps in the granularity and channel levels to obtain different contextual information. Results:Comprehensive experiments on the ISIC2017, ISIC2018 and PH2 datasets demonstrate that VFFM-UNet outperforms existing state-of-the-art models regarding parameter numbers, computational complexity and segmentation performance. In short, compared to MISSFormer, our model achieves superior segmentation performance while reducing parameter and computation costs by 101x and 15x, respectively. Conclusions:Both quantitative and qualitative analyses show that VFFM-UNet sets a new benchmark by reaching an ideal balance between parameter numbers, computational complexity, and segmentation performance compared to existing state-of-the-art models.
Authors: Ziteng Wei, Qiang He, Bing Li, Feifei Chen, Yun Yang
Abstract: Vision Transformers (ViTs) excel in computer vision tasks but lack flexibility for edge devices' diverse needs. A vital issue is that ViTs pre-trained to cover a broad range of tasks are \textit{over-qualified} for edge devices that usually demand only part of a ViT's knowledge for specific tasks. Their task-specific accuracy on these edge devices is suboptimal. We discovered that small ViTs that focus on device-specific tasks can improve model accuracy and in the meantime, accelerate model inference. This paper presents NuWa, an approach that derives small ViTs from the base ViT for edge devices with specific task requirements. NuWa can transfer task-specific knowledge extracted from the base ViT into small ViTs that fully leverage constrained resources on edge devices to maximize model accuracy with inference latency assurance. Experiments with three base ViTs on three public datasets demonstrate that compared with state-of-the-art solutions, NuWa improves model accuracy by up to $\text{11.83}\%$ and accelerates model inference by 1.29$\times$ - 2.79$\times$. Code for reproduction is available at https://anonymous.4open.science/r/Task_Specific-3A5E.
Authors: Sinjini Mitra, Anuj Srivastava, Avipsa Roy, Pavan Turaga
Abstract: Human mobility analysis at urban-scale requires models to represent the complex nature of human movements, which in turn are affected by accessibility to nearby points of interest, underlying socioeconomic factors of a place, and local transport choices for people living in a geographic region. In this work, we represent human mobility and the associated flow of movements as a grapyh. Graph-based approaches for mobility analysis are still in their early stages of adoption and are actively being researched. The challenges of graph-based mobility analysis are multifaceted - the lack of sufficiently high-quality data to represent flows at high spatial and teporal resolution whereas, limited computational resources to translate large voluments of mobility data into a network structure, and scaling issues inherent in graph models etc. The current study develops a methodology by embedding graphs into a continuous space, which alleviates issues related to fast graph matching, graph time-series modeling, and visualization of mobility dynamics. Through experiments, we demonstrate how mobility data collected from taxicab trajectories could be transformed into network structures and patterns of mobility flow changes, and can be used for downstream tasks reporting approx 40% decrease in error on average in matched graphs vs unmatched ones.
Authors: Haozhan Tang, Tianyi Zhang, Oliver Kroemer, Matthew Johnson-Roberson, Weiming Zhi
Abstract: Robots operating in unstructured environments often require accurate and consistent object-level representations. This typically requires segmenting individual objects from the robot's surroundings. While recent large models such as Segment Anything (SAM) offer strong performance in 2D image segmentation. These advances do not translate directly to performance in the physical 3D world, where they often over-segment objects and fail to produce consistent mask correspondences across views. In this paper, we present GraphSeg, a framework for generating consistent 3D object segmentations from a sparse set of 2D images of the environment without any depth information. GraphSeg adds edges to graphs and constructs dual correspondence graphs: one from 2D pixel-level similarities and one from inferred 3D structure. We formulate segmentation as a problem of edge addition, then subsequent graph contraction, which merges multiple 2D masks into unified object-level segmentations. We can then leverage \emph{3D foundation models} to produce segmented 3D representations. GraphSeg achieves robust segmentation with significantly fewer images and greater accuracy than prior methods. We demonstrate state-of-the-art performance on tabletop scenes and show that GraphSeg enables improved performance on downstream robotic manipulation tasks. Code available at https://github.com/tomtang502/graphseg.git.
Authors: Junkai Zhang, Bin Li, Shoujun Zhou, Yue Du
Abstract: Medical Visual Question Answering (Med-VQA) answers clinical questions using medical images, aiding diagnosis. Designing the MedVQA system holds profound importance in assisting clinical diagnosis and enhancing diagnostic accuracy. Building upon this foundation, Hierarchical Medical VQA extends Medical VQA by organizing medical questions into a hierarchical structure and making level-specific predictions to handle fine-grained distinctions. Recently, many studies have proposed hierarchical MedVQA tasks and established datasets, However, several issues still remain: (1) imperfect hierarchical modeling leads to poor differentiation between question levels causing semantic fragmentation across hierarchies. (2) Excessive reliance on implicit learning in Transformer-based cross-modal self-attention fusion methods, which obscures crucial local semantic correlations in medical scenarios. To address these issues, this study proposes a HiCA-VQA method, including two modules: Hierarchical Prompting for fine-grained medical questions and Hierarchical Answer Decoders. The hierarchical prompting module pre-aligns hierarchical text prompts with image features to guide the model in focusing on specific image regions according to question types, while the hierarchical decoder performs separate predictions for questions at different levels to improve accuracy across granularities. The framework also incorporates a cross-attention fusion module where images serve as queries and text as key-value pairs. Experiments on the Rad-Restruct benchmark demonstrate that the HiCA-VQA framework better outperforms existing state-of-the-art methods in answering hierarchical fine-grained questions. This study provides an effective pathway for hierarchical visual question answering systems, advancing medical image understanding.
Authors: Abdul Mannan Mohammed, Azhar Ali Mohammad, Jason A. Ortiz, Carsten Neumann, Grace Bochenek, Dirk Reiners, Carolina Cruz-Neira
Abstract: Recent developments in Artificial Intelligence (AI) and Machine Learning (ML) are creating new opportunities for Human-Autonomy Teaming (HAT) in tasks, missions, and continuous coordinated activities. A major challenge is enabling humans to maintain awareness and control over autonomous assets, while also building trust and supporting shared contextual understanding. To address this, we present a real-time Human Digital Twin (HDT) architecture that integrates Large Language Models (LLMs) for knowledge reporting, answering, and recommendation, embodied in a visual interface. The system applies a metacognitive approach to enable personalized, context-aware responses aligned with the human teammate's expectations. The HDT acts as a visually and behaviorally realistic team member, integrated throughout the mission lifecycle, from training to deployment to after-action review. Our architecture includes speech recognition, context processing, AI-driven dialogue, emotion modeling, lip-syncing, and multimodal feedback. We describe the system design, performance metrics, and future development directions for more adaptive and realistic HAT systems.
Authors: Kexin Tian, Jingrui Mao, Yunlong Zhang, Jiwan Jiang, Yang Zhou, Zhengzhong Tu
Abstract: Recent advancements in Vision-Language Models (VLMs) have demonstrated strong potential for autonomous driving tasks. However, their spatial understanding and reasoning-key capabilities for autonomous driving-still exhibit significant limitations. Notably, none of the existing benchmarks systematically evaluate VLMs' spatial reasoning capabilities in driving scenarios. To fill this gap, we propose NuScenes-SpatialQA, the first large-scale ground-truth-based Question-Answer (QA) benchmark specifically designed to evaluate the spatial understanding and reasoning capabilities of VLMs in autonomous driving. Built upon the NuScenes dataset, the benchmark is constructed through an automated 3D scene graph generation pipeline and a QA generation pipeline. The benchmark systematically evaluates VLMs' performance in both spatial understanding and reasoning across multiple dimensions. Using this benchmark, we conduct extensive experiments on diverse VLMs, including both general and spatial-enhanced models, providing the first comprehensive evaluation of their spatial capabilities in autonomous driving. Surprisingly, the experimental results show that the spatial-enhanced VLM outperforms in qualitative QA but does not demonstrate competitiveness in quantitative QA. In general, VLMs still face considerable challenges in spatial understanding and reasoning.
Authors: Zeyang Zheng, Arman Hosseini, Dong Chen, Omid Shoghli, Arsalan Heydarian
Abstract: The increasing adoption of electric scooters (e-scooters) in urban areas has coincided with a rise in traffic accidents and injuries, largely due to their small wheels, lack of suspension, and sensitivity to uneven surfaces. While deep learning-based object detection has been widely used to improve automobile safety, its application for e-scooter obstacle detection remains unexplored. This study introduces a novel ground obstacle detection system for e-scooters, integrating an RGB camera, and a depth camera to enhance real-time road hazard detection. Additionally, the Inertial Measurement Unit (IMU) measures linear vertical acceleration to identify surface vibrations, guiding the selection of six obstacle categories: tree branches, manhole covers, potholes, pine cones, non-directional cracks, and truncated domes. All sensors, including the RGB camera, depth camera, and IMU, are integrated within the Intel RealSense Camera D435i. A deep learning model powered by YOLO detects road hazards and utilizes depth data to estimate obstacle proximity. Evaluated on the seven hours of naturalistic riding dataset, the system achieves a high mean average precision (mAP) of 0.827 and demonstrates excellent real-time performance. This approach provides an effective solution to enhance e-scooter safety through advanced computer vision and data fusion. The dataset is accessible at https://zenodo.org/records/14583718, and the project code is hosted on https://github.com/Zeyang-Zheng/Real-Time-Roadway-Obstacle-Detection-for-Electric-Scooters.
URLs: https://zenodo.org/records/14583718,, https://github.com/Zeyang-Zheng/Real-Time-Roadway-Obstacle-Detection-for-Electric-Scooters.
Authors: Jaymari Chua, Chen Wang, Lina Yao
Abstract: Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee constraint satisfaction outside their training distribution due to their reliance on implicit, post-hoc preferences. Inspired by a paradigm shift to first curate data before tuning, we introduce a new framework for safe language alignment that learns natural language constraints from positive and negative demonstrations as a primary step. From inferring both a task-specific reward function and latent constraint functions, our approach fosters adaptation to novel safety requirements and robust generalization under domain shifts and adversarial inputs. We formalize the framework within a Constrained Markov Decision Process (CMDP) and validate it via a text-based navigation environment, demonstrating safe adaptation to changing danger zones. Our experiments show fewer violations upon domain shift when following a safe navigation path, and we achieve zero violations by applying learned constraints to a distilled BERT model as a fine-tuning technique. This work offers a promising path toward building safety-critical and more generalizable LLMs for practical NLP settings.
Authors: Jiaxin Guo, Wenzhen Dong, Tianyu Huang, Hao Ding, Ziyi Wang, Haomin Kuang, Qi Dou, Yun-Hui Liu
Abstract: Reconstructing 3D scenes from monocular surgical videos can enhance surgeon's perception and therefore plays a vital role in various computer-assisted surgery tasks. However, achieving scale-consistent reconstruction remains an open challenge due to inherent issues in endoscopic videos, such as dynamic deformations and textureless surfaces. Despite recent advances, current methods either rely on calibration or instrument priors to estimate scale, or employ SfM-like multi-stage pipelines, leading to error accumulation and requiring offline optimization. In this paper, we present Endo3R, a unified 3D foundation model for online scale-consistent reconstruction from monocular surgical video, without any priors or extra optimization. Our model unifies the tasks by predicting globally aligned pointmaps, scale-consistent video depths, and camera parameters without any offline optimization. The core contribution of our method is expanding the capability of the recent pairwise reconstruction model to long-term incremental dynamic reconstruction by an uncertainty-aware dual memory mechanism. The mechanism maintains history tokens of both short-term dynamics and long-term spatial consistency. Notably, to tackle the highly dynamic nature of surgical scenes, we measure the uncertainty of tokens via Sampson distance and filter out tokens with high uncertainty. Regarding the scarcity of endoscopic datasets with ground-truth depth and camera poses, we further devise a self-supervised mechanism with a novel dynamics-aware flow loss. Abundant experiments on SCARED and Hamlyn datasets demonstrate our superior performance in zero-shot surgical video depth prediction and camera pose estimation with online efficiency. Project page: https://wrld.github.io/Endo3R/.
Authors: Yanming Wan, Jiaxing Wu, Marwa Abdulhai, Lior Shani, Natasha Jaques
Abstract: Effective conversational agents must be able to personalize their behavior to suit a user's preferences, personality, and attributes, whether they are assisting with writing tasks or operating in domains like education or healthcare. Current training methods like Reinforcement Learning from Human Feedback (RLHF) prioritize helpfulness and safety but fall short in fostering truly empathetic, adaptive, and personalized interactions. Traditional approaches to personalization often rely on extensive user history, limiting their effectiveness for new or context-limited users. To overcome these limitations, we propose to incorporate an intrinsic motivation to improve the conversational agents's model of the user as an additional reward alongside multi-turn RLHF. This reward mechanism encourages the agent to actively elicit user traits by optimizing conversations to increase the accuracy of its user model. Consequently, the policy agent can deliver more personalized interactions through obtaining more information about the user. We applied our method both education and fitness settings, where LLMs teach concepts or recommend personalized strategies based on users' hidden learning style or lifestyle attributes. Using LLM-simulated users, our approach outperformed a multi-turn RLHF baseline in revealing information about the users' preferences, and adapting to them.
Authors: Zelun Tony Zhang, Leon Reicherts
Abstract: How can we use generative AI to design tools that augment rather than replace human cognition? In this position paper, we review our own research on AI-assisted decision-making for lessons to learn. We observe that in both AI-assisted decision-making and generative AI, a popular approach is to suggest AI-generated end-to-end solutions to users, which users can then accept, reject, or edit. Alternatively, AI tools could offer more incremental support to help users solve tasks themselves, which we call process-oriented support. We describe findings on the challenges of end-to-end solutions, and how process-oriented support can address them. We also discuss the applicability of these findings to generative AI based on a recent study in which we compared both approaches to assist users in a complex decision-making task with LLMs.
Authors: Yiding Feng, Wei Tang
Abstract: We introduce and study the persuasive calibration problem, where a principal aims to provide trustworthy predictions about underlying events to a downstream agent to make desired decisions. We adopt the standard calibration framework that regulates predictions to be unbiased conditional on their own value, and thus, they can reliably be interpreted at the face value by the agent. Allowing a small calibration error budget, we aim to answer the following question: what is and how to compute the optimal predictor under this calibration error budget, especially when there exists incentive misalignment between the principal and the agent? We focus on standard Lt-norm Expected Calibration Error (ECE) metric. We develop a general framework by viewing predictors as post-processed versions of perfectly calibrated predictors. Using this framework, we first characterize the structure of the optimal predictor. Specifically, when the principal's utility is event-independent and for L1-norm ECE, we show: (1) the optimal predictor is over-(resp. under-) confident for high (resp. low) true expected outcomes, while remaining perfectly calibrated in the middle; (2) the miscalibrated predictions exhibit a collinearity structure with the principal's utility function. On the algorithmic side, we provide a FPTAS for computing approximately optimal predictor for general principal utility and general Lt-norm ECE. Moreover, for the L1- and L-Infinity-norm ECE, we provide polynomial-time algorithms that compute the exact optimal predictor.
Authors: Junjie Yang, Ke Lin, Xing Yu
Abstract: Chain of Thought (CoT) reasoning enhances language models' performance but often leads to inefficient "overthinking" on simple problems. We identify that existing approaches directly penalizing reasoning length fail to account for varying problem complexity. Our approach constructs rewards through length and quality comparisons, guided by theoretical assumptions that jointly enhance solution correctness with conciseness. Moreover, we further demonstrate our method to fuzzy tasks where ground truth is unavailable. Experiments across multiple reasoning benchmarks demonstrate that our method maintains accuracy while generating significantly more concise explanations, effectively teaching models to "think when needed."
Authors: Ibne Farabi Shihab, Anuj Sharma
Abstract: Traffic crash detection in long-form surveillance videos is critical for emergency response and infrastructure planning but remains difficult due to the brief and rare nature of crash events. We introduce HybridMamba, a novel architecture that combines visual transformers with state-space temporal modeling to achieve accurate crash time localization. Our method uses multi-level token compression and hierarchical temporal processing to remain computationally efficient without sacrificing temporal resolution. Evaluated on a large-scale dataset from the Iowa Department of Transportation, HybridMamba achieves a mean absolute error of 1.50 seconds, with 65.2 percent of predictions within one second of the ground truth. It outperforms recent video-language models such as TimeChat and VideoLLaMA2 by up to 2.8 seconds, while using significantly fewer parameters. Our results demonstrate strong generalization across videos ranging from 2 to 40 minutes in diverse conditions. HybridMamba offers a robust and efficient solution for fine-grained temporal localization in traffic surveillance. The code will be released upon publication.
Authors: Akis Nousias, Efklidis Katsaros, Evangelos Syrmos, Panagiotis Radoglou-Grammatikis, Thomas Lagkas, Vasileios Argyriou, Ioannis Moscholios, Evangelos Markakis, Sotirios Goudos, Panagiotis Sarigiannidis
Abstract: Malware detection is increasingly challenged by evolving techniques like obfuscation and polymorphism, limiting the effectiveness of traditional methods. Meanwhile, the widespread adoption of software containers has introduced new security challenges, including the growing threat of malicious software injection, where a container, once compromised, can serve as entry point for further cyberattacks. In this work, we address these security issues by introducing a method to identify compromised containers through machine learning analysis of their file systems. We cast the entire software containers into large RGB images via their tarball representations, and propose to use established Convolutional Neural Network architectures on a streaming, patch-based manner. To support our experiments, we release the COSOCO dataset--the first of its kind--containing 3364 large-scale RGB images of benign and compromised software containers at https://huggingface.co/datasets/k3ylabs/cosoco-image-dataset. Our method detects more malware and achieves higher F1 and Recall scores than all individual and ensembles of VirusTotal engines, demonstrating its effectiveness and setting a new standard for identifying malware-compromised software containers.
URLs: https://huggingface.co/datasets/k3ylabs/cosoco-image-dataset.
Authors: Marius Graumann (German Aerospace Center), Jan Marius St\"urmer (German Aerospace Center), Tobias Koch (German Aerospace Center)
Abstract: Nowadays, a lot of old floor plans exist in printed form or are stored as scanned raster images. Slight rotations or shifts may occur during scanning. Bringing floor plans of this form into a machine readable form to enable further use, still poses a problem. Therefore, we propose an end-to-end pipeline that pre-processes the image and leverages a novel approach to create a region adjacency graph (RAG) from the pre-processed image and predict its nodes. By incorporating normalization steps into the RAG feature extraction, we significantly improved the rotation invariance of the RAG feature calculation. Moreover, applying our method leads to an improved F1 score and IoU on rotated data. Furthermore, we proposed a wall splitting algorithm for partitioning walls into segments associated with the corresponding rooms.
Authors: Kennedy E. Ehimwenma, Hongyu Zhou, Junfeng Wang, Ze Zheng
Abstract: Double-black (DB) nodes have no place in red-black (RB) trees. So when DB nodes are formed, they are immediately removed. The removal of DB nodes that cause rotation and recoloring of other connected nodes poses greater challenges in the teaching and learning of RB trees. To ease this difficulty, this paper extends our previous work on the symbolic arithmetic algebraic (SA) method for removing DB nodes. The SA operations that are given as, Red + Black = Black; Black - Black = Red; Black + Black = DB; and DB - Black = Black removes DB nodes and rebalances black heights in RB trees. By extension, this paper projects three SA mathematical equations, namely, general symbolic arithmetic rule; partial symbolic arithmetic rule1; and partial symbolic arithmetic rule2. The removal of a DB node ultimately affects black heights in RB trees. To balance black heights using the SA equations, all the RB tree cases, namely, LR, RL, LL, and RR, were considered in this work; and the position of the nodes connected directly or indirectly to the DB node was also tested. In this study, to balance a RB tree, the issues considered w.r.t. the different cases of the RB tree were i) whether a DB node has an inner, outer, or both inner and outer black nephews; or ii) whether a DB node has an inner, outer or both inner and outer red nephews. The nephews r and x in this work are the children of the sibling s to a DB, and further up the tree, the parent p of a DB is their grandparent g. Thus, r and x have indirect relationships to a DB at the point of formation of the DB node. The novelty of the SA equations is in their effectiveness in the removal of DB that involves rotation of nodes as well as the recoloring of nodes along any simple path so as to balance black heights in a tree.
Authors: Enguerrand Prebet, Samuel Teuber, Andr\'e Platzer
Abstract: This article presents a formal model and formal safety proofs for the ABZ'25 case study in differential dynamic logic (dL). The case study considers an autonomous car driving on a highway avoiding collisions with neighbouring cars. Using KeYmaera X's dL implementation, we prove absence of collision on an infinite time horizon which ensures that safety is preserved independently of trip length. The safety guarantees hold for time-varying reaction time and brake force. Our dL model considers the single lane scenario with cars ahead or behind. We demonstrate that dL with its tools is a rigorous foundation for runtime monitoring, shielding, and neural network verification. Doing so sheds light on inconsistencies between the provided specification and simulation environment highway-env of the ABZ'25 study. We attempt to fix these inconsistencies and uncover numerous counterexamples which also indicate issues in the provided reinforcement learning environment.
Authors: Maik Larooij, Petter T\"ornberg
Abstract: Recent advancements in AI have reinvigorated Agent-Based Models (ABMs), as the integration of Large Language Models (LLMs) has led to the emergence of ``generative ABMs'' as a novel approach to simulating social systems. While ABMs offer means to bridge micro-level interactions with macro-level patterns, they have long faced criticisms from social scientists, pointing to e.g., lack of realism, computational complexity, and challenges of calibrating and validating against empirical data. This paper reviews the generative ABM literature to assess how this new approach adequately addresses these long-standing criticisms. Our findings show that studies show limited awareness of historical debates. Validation remains poorly addressed, with many studies relying solely on subjective assessments of model `believability', and even the most rigorous validation failing to adequately evidence operational validity. We argue that there are reasons to believe that LLMs will exacerbate rather than resolve the long-standing challenges of ABMs. The black-box nature of LLMs moreover limit their usefulness for disentangling complex emergent causal mechanisms. While generative ABMs are still in a stage of early experimentation, these findings question of whether and how the field can transition to the type of rigorous modeling needed to contribute to social scientific theory.
Authors: Guido Barducci, Ivan Rossi, Francesco Codic\`e, Cesare Rollo, Valeria Repetto, Corrado Pancotti, Virginia Iannibelli, Tiziana Sanavia, Piero Fariselli
Abstract: Understanding how residue variations affect protein stability is crucial for designing functional proteins and deciphering the molecular mechanisms underlying disease-related mutations. Recent advances in protein language models (PLMs) have revolutionized computational protein analysis, enabling, among other things, more accurate predictions of mutational effects. In this work, we introduce JanusDDG, a deep learning framework that leverages PLM-derived embeddings and a bidirectional cross-attention transformer architecture to predict $\Delta \Delta G$ of single and multiple-residue mutations while simultaneously being constrained to respect fundamental thermodynamic properties, such as antisymmetry and transitivity. Unlike conventional self-attention, JanusDDG computes queries (Q) and values (V) as the difference between wild-type and mutant embeddings, while keys (K) alternate between the two. This cross-interleaved attention mechanism enables the model to capture mutation-induced perturbations while preserving essential contextual information. Experimental results show that JanusDDG achieves state-of-the-art performance in predicting $\Delta \Delta G$ from sequence alone, matching or exceeding the accuracy of structure-based methods for both single and multiple mutations.
Authors: Kilian Sprenkamp, Nils Messerschmidt, Amir Sartipi, Igor Tchappi, Xiaohui Wu, Liudmila Zavolokina, Gilbert Fridgen
Abstract: E-participation platforms can be an important asset for governments in increasing trust and fostering democratic societies. By engaging non-governmental and private institutions, domain experts, and even the general public, policymakers can make informed and inclusive decisions. Drawing on the Media Richness Theory and applying the Design Science Research method, we explore how a chatbot can be designed to improve the effectiveness of the policy-making process of existing citizen involvement platforms. Leveraging the Have Your Say platform, which solicits feedback on European Commission initiatives and regulations, a Large Language Model based chatbot, called AskThePublic is created, providing policymakers, journalists, researchers, and interested citizens with a convenient channel to explore and engage with public input. By conducting 11 semistructured interviews, the results show that the participants value the interactive and structured responses as well as enhanced language capabilities, thus increasing their likelihood of engaging with AskThePublic over the existing platform. An outlook for future iterations is provided and discussed with regard to the perspectives of the different stakeholders.
Authors: Bingqian Wang, Quan Fang, Jiachen Sun, Xiaoxiao Ma
Abstract: Formulating statements that support diverse or controversial stances on specific topics is vital for platforms that enable user expression, reshape political discourse, and drive social critique and information dissemination. With the rise of Large Language Models (LLMs), controllable text generation towards specific stances has become a promising research area with applications in shaping public opinion and commercial marketing. However, current datasets often focus solely on pure texts, lacking multimodal content and effective context, particularly in the context of stance detection. In this paper, we formally define and study the new problem of stance-driven controllable content generation for tweets with text and images, where given a multimodal post (text and image/video), a model generates a stance-controlled response. To this end, we create the Multimodal Stance Generation Dataset (StanceGen2024), the first resource explicitly designed for multimodal stance-controllable text generation in political discourse. It includes posts and user comments from the 2024 U.S. presidential election, featuring text, images, videos, and stance annotations to explore how multimodal political content shapes stance expression. Furthermore, we propose a Stance-Driven Multimodal Generation (SDMG) framework that integrates weighted fusion of multimodal features and stance guidance to improve semantic consistency and stance control. We release the dataset and code (https://anonymous.4open.science/r/StanceGen-BE9D) for public use and further research.
Authors: Afshin Khadangi, Amir Sartipi, Igor Tchappi, Ramin Bahmani
Abstract: Large language models (LLMs) often produce inaccurate or misleading content-hallucinations. To address this challenge, we introduce Noise-Augmented Fine-Tuning (NoiseFiT), a novel framework that leverages adaptive noise injection based on the signal-to-noise ratio (SNR) to enhance model robustness. In particular, NoiseFiT selectively perturbs layers identified as either high-SNR (more robust) or low-SNR (potentially under-regularized) using a dynamically scaled Gaussian noise. We further propose a hybrid loss that combines standard cross-entropy, soft cross-entropy, and consistency regularization to ensure stable and accurate outputs under noisy training conditions. Our theoretical analysis shows that adaptive noise injection is both unbiased and variance-preserving, providing strong guarantees for convergence in expectation. Empirical results on multiple test and benchmark datasets demonstrate that NoiseFiT significantly reduces hallucination rates, often improving or matching baseline performance in key tasks. These findings highlight the promise of noise-driven strategies for achieving robust, trustworthy language modeling without incurring prohibitive computational overhead. Given the comprehensive and detailed nature of our experiments, we have publicly released the fine-tuning logs, benchmark evaluation artifacts, and source code online at W&B, Hugging Face, and GitHub, respectively, to foster further research, accessibility and reproducibility.
Authors: Shuang Wu
Abstract: Policy optimization algorithms are crucial in many fields but challenging to grasp and implement, often due to complex calculations related to Markov decision processes and varying use of discount and average reward setups. This paper presents a unified framework that applies generalized ergodicity theory and perturbation analysis to clarify and enhance the application of these algorithms. Generalized ergodicity theory sheds light on the steady-state behavior of stochastic processes, aiding understanding of both discounted and average rewards. Perturbation analysis provides in-depth insights into the fundamental principles of policy optimization algorithms. We use this framework to identify common implementation errors and demonstrate the correct approaches. Through a case study on Linear Quadratic Regulator problems, we illustrate how slight variations in algorithm design affect implementation outcomes. We aim to make policy optimization algorithms more accessible and reduce their misuse in practice.
Authors: Francesca Ronchini, Ho-Hsiang Wu, Wei-Cheng Lin, Fabio Antonacci
Abstract: This paper investigates the design of effective prompt strategies for generating realistic datasets using Text-To-Audio (TTA) models. We also analyze different techniques for efficiently combining these datasets to enhance their utility in sound classification tasks. By evaluating two sound classification datasets with two TTA models, we apply a range of prompt strategies. Our findings reveal that task-specific prompt strategies significantly outperform basic prompt approaches in data generation. Furthermore, merging datasets generated using different TTA models proves to enhance classification performance more effectively than merely increasing the training dataset size. Overall, our results underscore the advantages of these methods as effective data augmentation techniques using synthetic data.
Authors: Guide Yang, Chao Hou, Weilong Peng, Xiang Fang, Yongwei Nie, Peican Zhu, Keke Tang
Abstract: Deep neural networks (DNNs) often exhibit overconfidence when encountering out-of-distribution (OOD) samples, posing significant challenges for deployment. Since DNNs are trained on in-distribution (ID) datasets, the information flow of ID samples through DNNs inevitably differs from that of OOD samples. In this paper, we propose an Entropy-based Out-Of-distribution Detection (EOOD) framework. EOOD first identifies specific block where the information flow differences between ID and OOD samples are more pronounced, using both ID and pseudo-OOD samples. It then calculates the conditional entropy on the selected block as the OOD confidence score. Comprehensive experiments conducted across various ID and OOD settings demonstrate the effectiveness of EOOD in OOD detection and its superiority over state-of-the-art methods.
Authors: Kentaro Nomura, Tatsuya Aoki, Tadahiro Taniguchi, Takato Horii
Abstract: We propose a fully decentralized multi-agent world model that enables both symbol emergence for communication and coordinated behavior through temporal extension of collective predictive coding. Unlike previous research that focuses on either communication or coordination separately, our approach achieves both simultaneously. Our method integrates world models with communication channels, enabling agents to predict environmental dynamics, estimate states from partial observations, and share critical information through bidirectional message exchange with contrastive learning for message alignment. Using a two-agent trajectory drawing task, we demonstrate that our communication-based approach outperforms non-communicative models when agents have divergent perceptual capabilities, achieving the second-best coordination after centralized models. Importantly, our distributed approach with constraints preventing direct access to other agents' internal states facilitates the emergence of more meaningful symbol systems that accurately reflect environmental states. These findings demonstrate the effectiveness of decentralized communication for supporting coordination while developing shared representations of the environment.
Authors: Erik Johannes Husom, Arda Goknil, Merve Astekin, Lwin Khin Shar, Andre K{\aa}sen, Sagar Sen, Benedikt Andreas Mithassel, Ahmet Soylu
Abstract: Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a key technique to enable efficient LLM inference by reducing model size and computational overhead. In this study, we conduct a comprehensive analysis of 28 quantized LLMs from the Ollama library, which applies by default Post-Training Quantization (PTQ) and weight-only quantization techniques, deployed on an edge device (Raspberry Pi 4 with 4GB RAM). We evaluate energy efficiency, inference performance, and output accuracy across multiple quantization levels and task types. Models are benchmarked on five standardized datasets (CommonsenseQA, BIG-Bench Hard, TruthfulQA, GSM8K, and HumanEval), and we employ a high-resolution, hardware-based energy measurement tool to capture real-world power consumption. Our findings reveal the trade-offs between energy efficiency, inference speed, and accuracy in different quantization settings, highlighting configurations that optimize LLM deployment for resource-constrained environments. By integrating hardware-level energy profiling with LLM benchmarking, this study provides actionable insights for sustainable AI, bridging a critical gap in existing research on energy-aware LLM deployment.
Authors: Sanghwan Bae, Jiwoo Hong, Min Young Lee, Hanbyul Kim, JeongYeon Nam, Donghyun Kwak
Abstract: Reasoning-Oriented Reinforcement Learning (RORL) enhances the reasoning ability of Large Language Models (LLMs). However, due to the sparsity of rewards in RORL, effective training is highly dependent on the selection of problems of appropriate difficulty. Although curriculum learning attempts to address this by adjusting difficulty, it often relies on static schedules, and even recent online filtering methods lack theoretical grounding and a systematic understanding of their effectiveness. In this work, we theoretically and empirically show that curating the batch with the problems that the training model achieves intermediate accuracy on the fly can maximize the effectiveness of RORL training, namely balanced online difficulty filtering. We first derive that the lower bound of the KL divergence between the initial and the optimal policy can be expressed with the variance of the sampled accuracy. Building on those insights, we show that balanced filtering can maximize the lower bound, leading to better performance. Experimental results across five challenging math reasoning benchmarks show that balanced online filtering yields an additional 10% in AIME and 4% improvements in average over plain GRPO. Moreover, further analysis shows the gains in sample efficiency and training time efficiency, exceeding the maximum reward of plain GRPO within 60% training time and the volume of the training set.
Authors: Gianluca Maselli, Vieri Giuliano Santucci
Abstract: Dealing with environments with sparse rewards has always been crucial for systems developed to operate in autonomous open-ended learning settings. Intrinsic Motivations could be an effective way to help Deep Reinforcement Learning algorithms learn in such scenarios. In fact, intrinsic reward signals, such as novelty or curiosity, are generally adopted to improve exploration when extrinsic rewards are delayed or absent. Building on previous works, we tackle the problem of learning policies in the presence of sparse rewards by proposing a two-level architecture that alternates an ''intrinsically driven'' phase of exploration and autonomous sub-goal generation, to a phase of sparse reward, goal-directed policy learning. The idea is to build several small networks, each one specialized on a particular sub-path, and use them as starting points for future exploration without the need to further explore from scratch previously learnt paths. Two versions of the system have been trained and tested in the Gym SuperMarioBros environment without considering any additional extrinsic reward. The results show the validity of our approach and the importance of autonomously segment the environment to generate an efficient path towards the final goal.
Authors: Adam Moss
Abstract: We present the AI Cosmologist, an agentic system designed to automate cosmological/astronomical data analysis and machine learning research workflows. This implements a complete pipeline from idea generation to experimental evaluation and research dissemination, mimicking the scientific process typically performed by human researchers. The system employs specialized agents for planning, coding, execution, analysis, and synthesis that work together to develop novel approaches. Unlike traditional auto machine-learning systems, the AI Cosmologist generates diverse implementation strategies, writes complete code, handles execution errors, analyzes results, and synthesizes new approaches based on experimental outcomes. We demonstrate the AI Cosmologist capabilities across several machine learning tasks, showing how it can successfully explore solution spaces, iterate based on experimental results, and combine successful elements from different approaches. Our results indicate that agentic systems can automate portions of the research process, potentially accelerating scientific discovery. The code and experimental data used in this paper are available on GitHub at https://github.com/adammoss/aicosmologist. Example papers included in the appendix demonstrate the system's capability to autonomously produce complete scientific publications, starting from only the dataset and task description
Authors: William Fleshman, Benjamin Van Durme
Abstract: Training large, general-purpose language models poses significant challenges. The growing availability of specialized expert models, fine-tuned from pretrained models for specific tasks or domains, offers a promising alternative. Leveraging the potential of these existing expert models in real-world applications requires effective methods to select or merge the models best suited for a given task. This paper introduces SPECTR, an approach for dynamically composing expert models at each time step during inference. Notably, our method requires no additional training and enables flexible, token- and layer-wise model combinations. Our experimental results demonstrate that SPECTR improves routing accuracy over alternative training-free methods, increasing task performance across expert domains.
Authors: Zisheng Yao, Yuhe Zhang, Zhe Hu, Robert Kl\"ofkorn, Tobias Ritschel, Pablo Villanueva-Perez
Abstract: The unprecedented X-ray flux density provided by modern X-ray sources offers new spatiotemporal possibilities for X-ray imaging of fast dynamic processes. Approaches to exploit such possibilities often result in either i) a limited number of projections or spatial information due to limited scanning speed, as in time-resolved tomography, or ii) a limited number of time points, as in stroboscopic imaging, making the reconstruction problem ill-posed and unlikely to be solved by classical reconstruction approaches. 4D reconstruction from such data requires sample priors, which can be included via deep learning (DL). State-of-the-art 4D reconstruction methods for X-ray imaging combine the power of AI and the physics of X-ray propagation to tackle the challenge of sparse views. However, most approaches do not constrain the physics of the studied process, i.e., a full physical model. Here we present 4D physics-informed optimized neural implicit X-ray imaging (4D-PIONIX), a novel physics-informed 4D X-ray image reconstruction method combining the full physical model and a state-of-the-art DL-based reconstruction method for 4D X-ray imaging from sparse views. We demonstrate and evaluate the potential of our approach by retrieving 4D information from ultra-sparse spatiotemporal acquisitions of simulated binary droplet collisions, a relevant fluid dynamic process. We envision that this work will open new spatiotemporal possibilities for various 4D X-ray imaging modalities, such as time-resolved X-ray tomography and more novel sparse acquisition approaches like X-ray multi-projection imaging, which will pave the way for investigations of various rapid 4D dynamics, such as fluid dynamics and composite testing.
Authors: Shubham Kumar Nigam, Balaramamahanthi Deepak Patnaik, Ajay Varghese Thomas, Noel Shallum, Kripabandhu Ghosh, Arnab Bhattacharya
Abstract: Automating legal document drafting can significantly enhance efficiency, reduce manual effort, and streamline legal workflows. While prior research has explored tasks such as judgment prediction and case summarization, the structured generation of private legal documents in the Indian legal domain remains largely unaddressed. To bridge this gap, we introduce VidhikDastaavej, a novel, anonymized dataset of private legal documents, and develop NyayaShilp, a fine-tuned legal document generation model specifically adapted to Indian legal texts. We propose a Model-Agnostic Wrapper (MAW), a two-step framework that first generates structured section titles and then iteratively produces content while leveraging retrieval-based mechanisms to ensure coherence and factual accuracy. We benchmark multiple open-source LLMs, including instruction-tuned and domain-adapted versions, alongside proprietary models for comparison. Our findings indicate that while direct fine-tuning on small datasets does not always yield improvements, our structured wrapper significantly enhances coherence, factual adherence, and overall document quality while mitigating hallucinations. To ensure real-world applicability, we developed a Human-in-the-Loop (HITL) Document Generation System, an interactive user interface that enables users to specify document types, refine section details, and generate structured legal drafts. This tool allows legal professionals and researchers to generate, validate, and refine AI-generated legal documents efficiently. Extensive evaluations, including expert assessments, confirm that our framework achieves high reliability in structured legal drafting. This research establishes a scalable and adaptable foundation for AI-assisted legal drafting in India, offering an effective approach to structured legal document generation.
Authors: Zihao He, Shengchuan Zhang, Runze Hu, Yunhang Shen, Yan Zhang
Abstract: Super-resolution (SR) techniques are critical for enhancing image quality, particularly in scenarios where high-resolution imagery is essential yet limited by hardware constraints. Existing diffusion models for SR have relied predominantly on Gaussian models for noise generation, which often fall short when dealing with the complex and variable texture inherent in natural scenes. To address these deficiencies, we introduce the Bayesian Uncertainty Guided Diffusion Probabilistic Model (BUFF). BUFF distinguishes itself by incorporating a Bayesian network to generate high-resolution uncertainty masks. These masks guide the diffusion process, allowing for the adjustment of noise intensity in a manner that is both context-aware and adaptive. This novel approach not only enhances the fidelity of super-resolved images to their original high-resolution counterparts but also significantly mitigates artifacts and blurring in areas characterized by complex textures and fine details. The model demonstrates exceptional robustness against complex noise patterns and showcases superior adaptability in handling textures and edges within images. Empirical evidence, supported by visual results, illustrates the model's robustness, especially in challenging scenarios, and its effectiveness in addressing common SR issues such as blurring. Experimental evaluations conducted on the DIV2K dataset reveal that BUFF achieves a notable improvement, with a +0.61 increase compared to baseline in SSIM on BSD100, surpassing traditional diffusion approaches by an average additional +0.20dB PSNR gain. These findings underscore the potential of Bayesian methods in enhancing diffusion processes for SR, paving the way for future advancements in the field.
Authors: Alexander Windmann, Henrik Steude, Daniel Boschmann, Oliver Niggemann
Abstract: Cyber-Physical Systems (CPS) in domains such as manufacturing and energy distribution generate complex time series data crucial for Prognostics and Health Management (PHM). While Deep Learning (DL) methods have demonstrated strong forecasting capabilities, their adoption in industrial CPS remains limited due insufficient robustness. Existing robustness evaluations primarily focus on formal verification or adversarial perturbations, inadequately representing the complexities encountered in real-world CPS scenarios. To address this, we introduce a practical robustness definition grounded in distributional robustness, explicitly tailored to industrial CPS, and propose a systematic framework for robustness evaluation. Our framework simulates realistic disturbances, such as sensor drift, noise and irregular sampling, enabling thorough robustness analyses of forecasting models on real-world CPS datasets. The robustness definition provides a standardized score to quantify and compare model performance across diverse datasets, assisting in informed model selection and architecture design. Through extensive empirical studies evaluating prominent DL architectures (including recurrent, convolutional, attention-based, modular, and structured state-space models) we demonstrate the applicability and effectiveness of our approach. We publicly release our robustness benchmark to encourage further research and reproducibility.
Authors: Md Abu Obaida Zishan, H M Shihab, Sabik Sadman Islam, Maliha Alam Riya, Gazi Mashrur Rahman, Jannatun Noor
Abstract: The electrocardiogram (ECG) monitoring device is an expensive albeit essential device for the treatment and diagnosis of cardiovascular diseases (CVD). The cost of this device typically ranges from $2000 to $10000. Several studies have implemented ECG monitoring systems in micro-controller units (MCU) to reduce industrial development costs by up to 20 times. However, to match industry-grade systems and display heartbeats effectively, it is essential to develop an efficient algorithm for detecting arrhythmia (irregular heartbeat). Hence in this study, a dense neural network is developed to detect arrhythmia on the Arduino Nano. The Nano consists of the ATMega328 microcontroller with a 16MHz clock, 2KB of SRAM, and 32KB of program memory. Additionally, the AD8232 SparkFun Single-Lead Heart Rate Monitor is used as the ECG sensor. The implemented neural network model consists of two layers (excluding the input) with 10 and four neurons respectively with sigmoid activation function. However, four approaches are explored to choose the appropriate activation functions. The model has a size of 1.267 KB, achieves an F1 score (macro-average) of 78.3\% for classifying four types of arrhythmia, an accuracy rate of 96.38%, and requires 0.001314 MOps of floating-point operations (FLOPs).
Authors: Khai Le-Duc, Tuyen Tran, Bach Phan Tat, Nguyen Kim Hai Bui, Quan Dang, Hung-Phong Tran, Thanh-Thuy Nguyen, Ly Nguyen, Tuan-Minh Phan, Thi Thu Phuong Tran, Chris Ngo, Nguyen X. Khanh, Thanh Nguyen-Tang
Abstract: Multilingual speech translation (ST) in the medical domain enhances patient care by enabling efficient communication across language barriers, alleviating specialized workforce shortages, and facilitating improved diagnosis and treatment, particularly during pandemics. In this work, we present the first systematic study on medical ST, to our best knowledge, by releasing MultiMed-ST, a large-scale ST dataset for the medical domain, spanning all translation directions in five languages: Vietnamese, English, German, French, Traditional Chinese and Simplified Chinese, together with the models. With 290,000 samples, our dataset is the largest medical machine translation (MT) dataset and the largest many-to-many multilingual ST among all domains. Secondly, we present the most extensive analysis study in ST research to date, including: empirical baselines, bilingual-multilingual comparative study, end-to-end vs. cascaded comparative study, task-specific vs. multi-task sequence-to-sequence (seq2seq) comparative study, code-switch analysis, and quantitative-qualitative error analysis. All code, data, and models are available online: https://github.com/leduckhai/MultiMed-ST.
Authors: Shuofei Qiao, Zhisong Qiu, Baochang Ren, Xiaobin Wang, Xiangyuan Ru, Ningyu Zhang, Xiang Chen, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen
Abstract: Large Language Models (LLMs) have achieved considerable performance across various agentic planning tasks. However, traditional agent planning approaches adopt a "flood irrigation" methodology that indiscriminately injects gold trajectories, external feedback, and domain knowledge into agent models. This practice overlooks the fundamental human cognitive principle of situational self-awareness during decision-making-the ability to dynamically assess situational demands and strategically employ resources during decision-making. We propose agentic knowledgeable self-awareness to address this gap, a novel paradigm enabling LLM-based agents to autonomously regulate knowledge utilization. Specifically, we propose KnowSelf, a data-centric approach that applies agents with knowledgeable self-awareness like humans. Concretely, we devise a heuristic situation judgement criterion to mark special tokens on the agent's self-explored trajectories for collecting training data. Through a two-stage training process, the agent model can switch between different situations by generating specific special tokens, achieving optimal planning effects with minimal costs. Our experiments demonstrate that KnowSelf can outperform various strong baselines on different tasks and models with minimal use of external knowledge. Code is available at https://github.com/zjunlp/KnowSelf.
Authors: Runnan Fang, Xiaobin Wang, Yuan Liang, Shuofei Qiao, Jialong Wu, Zekun Xi, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen
Abstract: In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate unconventional action spaces. To empower agents to autonomously explore environments, optimize workflows, and enhance their understanding of actions, we propose SynWorld, a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search (MCTS) exploration to effectively refine their action knowledge in the current environment. Our experiments demonstrate that SynWorld is an effective and general approach to learning action knowledge in new environments. Code is available at https://github.com/zjunlp/SynWorld.
Authors: Jad Abou-Chakra, Lingfeng Sun, Krishan Rana, Brandon May, Karl Schmeckpeper, Maria Vittoria Minniti, Laura Herlant
Abstract: Recent advancements in behavior cloning have enabled robots to perform complex manipulation tasks. However, accurately assessing training performance remains challenging, particularly for real-world applications, as behavior cloning losses often correlate poorly with actual task success. Consequently, researchers resort to success rate metrics derived from costly and time-consuming real-world evaluations, making the identification of optimal policies and detection of overfitting or underfitting impractical. To address these issues, we propose real-is-sim, a novel behavior cloning framework that incorporates a dynamic digital twin (based on Embodied Gaussians) throughout the entire policy development pipeline: data collection, training, and deployment. By continuously aligning the simulated world with the physical world, demonstrations can be collected in the real world with states extracted from the simulator. The simulator enables flexible state representations by rendering image inputs from any viewpoint or extracting low-level state information from objects embodied within the scene. During training, policies can be directly evaluated within the simulator in an offline and highly parallelizable manner. Finally, during deployment, policies are run within the simulator where the real robot directly tracks the simulated robot's joints, effectively decoupling policy execution from real hardware and mitigating traditional domain-transfer challenges. We validate real-is-sim on the PushT manipulation task, demonstrating strong correlation between success rates obtained in the simulator and real-world evaluations. Videos of our system can be found at https://realissim.rai-inst.com.
Authors: Peter Baile Chen, Tomer Wolfson, Michael Cafarella, Dan Roth
Abstract: Existing information retrieval systems excel in cases where the language of target documents closely matches that of the user query. However, real-world retrieval systems are often required to implicitly reason whether a document is relevant. For example, when retrieving technical texts or tables, their relevance to the user query may be implied through a particular jargon or structure, rather than explicitly expressed in their content. Large language models (LLMs) hold great potential in identifying such implied relevance by leveraging their reasoning skills. Nevertheless, current LLM-augmented retrieval is hindered by high latency and computation cost, as the LLM typically computes the query-document relevance online, for every query anew. To tackle this issue we introduce EnrichIndex, a retrieval approach which instead uses the LLM offline to build semantically-enriched retrieval indices, by performing a single pass over all documents in the retrieval corpus once during ingestion time. Furthermore, the semantically-enriched indices can complement existing online retrieval approaches, boosting the performance of LLM re-rankers. We evaluated EnrichIndex on five retrieval tasks, involving passages and tables, and found that it outperforms strong online LLM-based retrieval systems, with an average improvement of 11.7 points in recall @ 10 and 10.6 points in NDCG @ 10 compared to strong baselines. In terms of online calls to the LLM, it processes 293.3 times fewer tokens which greatly reduces the online latency and cost. Overall, EnrichIndex is an effective way to build better retrieval indices offline by leveraging the strong reasoning skills of LLMs.
Authors: Jun Ma, Zongxin Yang, Sumin Kim, Bihui Chen, Mohammed Baharoon, Adibvafa Fallahpour, Reza Asakereh, Hongwei Lyu, Bo Wang
Abstract: Medical image and video segmentation is a critical task for precision medicine, which has witnessed considerable progress in developing task or modality-specific and generalist models for 2D images. However, there have been limited studies on building general-purpose models for 3D images and videos with comprehensive user studies. Here, we present MedSAM2, a promptable segmentation foundation model for 3D image and video segmentation. The model is developed by fine-tuning the Segment Anything Model 2 on a large medical dataset with over 455,000 3D image-mask pairs and 76,000 frames, outperforming previous models across a wide range of organs, lesions, and imaging modalities. Furthermore, we implement a human-in-the-loop pipeline to facilitate the creation of large-scale datasets resulting in, to the best of our knowledge, the most extensive user study to date, involving the annotation of 5,000 CT lesions, 3,984 liver MRI lesions, and 251,550 echocardiogram video frames, demonstrating that MedSAM2 can reduce manual costs by more than 85%. MedSAM2 is also integrated into widely used platforms with user-friendly interfaces for local and cloud deployment, making it a practical tool for supporting efficient, scalable, and high-quality segmentation in both research and healthcare environments.
Authors: Akshara Prabhakar, Zuxin Liu, Weiran Yao, Jianguo Zhang, Ming Zhu, Shiyu Wang, Zhiwei Liu, Tulika Awalgaonkar, Haolin Chen, Thai Hoang, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
Abstract: Training effective AI agents for multi-turn interactions requires high-quality data that captures realistic human-agent dynamics, yet such data is scarce and expensive to collect manually. We introduce APIGen-MT, a two-phase framework that generates verifiable and diverse multi-turn agent data. In the first phase, our agentic pipeline produces detailed task blueprints with ground-truth actions, leveraging a committee of LLM reviewers and iterative feedback loops. These blueprints are then transformed into complete interaction trajectories through simulated human-agent interplay. We train a family of models -- the xLAM-2-fc-r series with sizes ranging from 1B to 70B parameters. Our models outperform frontier models such as GPT-4o and Claude 3.5 on $\tau$-bench and BFCL benchmarks, with the smaller models surpassing their larger counterparts, particularly in multi-turn settings, while maintaining superior consistency across multiple trials. Comprehensive experiments demonstrate that our verified blueprint-to-details approach yields high-quality training data, enabling the development of more reliable, efficient, and capable agents. We open-source both the synthetic data collected and the trained xLAM-2-fc-r models to advance research in AI agents. Models are available on HuggingFace at https://huggingface.co/collections/Salesforce/xlam-2-67ef5be12949d8dcdae354c4 and project website is https://apigen-mt.github.io
URLs: https://huggingface.co/collections/Salesforce/xlam-2-67ef5be12949d8dcdae354c4, https://apigen-mt.github.io
Authors: Aref Azizpour, Tai D. Nguyen, Matthew C. Stamm
Abstract: Rapid advances in generative AI have enabled the creation of highly realistic synthetic images, which, while beneficial in many domains, also pose serious risks in terms of disinformation, fraud, and other malicious applications. Current synthetic image identification systems are typically static, relying on feature representations learned from known generators; as new generative models emerge, these systems suffer from severe performance degradation. In this paper, we introduce the concept of an autonomous self-adaptive synthetic media identification system -- one that not only detects synthetic images and attributes them to known sources but also autonomously identifies and incorporates novel generators without human intervention. Our approach leverages an open-set identification strategy with an evolvable embedding space that distinguishes between known and unknown sources. By employing an unsupervised clustering method to aggregate unknown samples into high-confidence clusters and continuously refining its decision boundaries, our system maintains robust detection and attribution performance even as the generative landscape evolves. Extensive experiments demonstrate that our method significantly outperforms existing approaches, marking a crucial step toward universal, adaptable forensic systems in the era of rapidly advancing generative models.
Authors: Leonardo Ranaldi, Barry Haddow, Alexandra Birch
Abstract: Retrieval-augmented generation (RAG) has become a cornerstone of contemporary NLP, enhancing large language models (LLMs) by allowing them to access richer factual contexts through in-context retrieval. While effective in monolingual settings, especially in English, its use in multilingual tasks remains unexplored. This paper investigates the effectiveness of RAG across multiple languages by proposing novel approaches for multilingual open-domain question-answering. We evaluate the performance of various multilingual RAG strategies, including question-translation (tRAG), which translates questions into English before retrieval, and Multilingual RAG (MultiRAG), where retrieval occurs directly across multiple languages. Our findings reveal that tRAG, while useful, suffers from limited coverage. In contrast, MultiRAG improves efficiency by enabling multilingual retrieval but introduces inconsistencies due to cross-lingual variations in the retrieved content. To address these issues, we propose Crosslingual RAG (CrossRAG), a method that translates retrieved documents into a common language (e.g., English) before generating the response. Our experiments show that CrossRAG significantly enhances performance on knowledge-intensive tasks, benefiting both high-resource and low-resource languages.
Authors: Zae Myung Kim, Anand Ramachandran, Farideh Tavazoee, Joo-Kyung Kim, Oleg Rokhlenko, Dongyeop Kang
Abstract: Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs with human-like discourse structures to enhance long-form text generation. By integrating linguistically grounded discourse frameworks into reinforcement learning, our approach guides models to produce coherent and well-organized outputs. We employ a dense reward scheme within a Proximal Policy Optimization framework, assigning fine-grained, token-level rewards based on the discourse distinctiveness relative to human writing. Two complementary reward models are evaluated: the first improves readability by scoring surface-level textual features to provide explicit structuring, while the second reinforces deeper coherence and rhetorical sophistication by analyzing global discourse patterns through hierarchical discourse motifs, outperforming both standard and RLHF-enhanced models in tasks such as essay generation and long-document summarization. All training data and code will be publicly shared at https://github.com/minnesotanlp/struct_align.
Authors: NVIDIA, :, Aaron Blakeman, Aarti Basant, Abhinav Khattar, Adithya Renduchintala, Akhiad Bercovich, Aleksander Ficek, Alexis Bjorlin, Ali Taghibakhshi, Amala Sanjay Deshmukh, Ameya Sunil Mahabaleshwarkar, Andrew Tao, Anna Shors, Ashwath Aithal, Ashwin Poojary, Ayush Dattagupta, Balaram Buddharaju, Bobby Chen, Boris Ginsburg, Boxin Wang, Brandon Norick, Brian Butterfield, Bryan Catanzaro, Carlo del Mundo, Chengyu Dong, Christine Harvey, Christopher Parisien, Dan Su, Daniel Korzekwa, Danny Yin, Daria Gitman, David Mosallanezhad, Deepak Narayanan, Denys Fridman, Dima Rekesh, Ding Ma, Dmytro Pykhtar, Dong Ahn, Duncan Riach, Dusan Stosic, Eileen Long, Elad Segal, Ellie Evans, Eric Chung, Erick Galinkin, Evelina Bakhturina, Ewa Dobrowolska, Fei Jia, Fuxiao Liu, Gargi Prasad, Gerald Shen, Guilin Liu, Guo Chen, Haifeng Qian, Helen Ngo, Hongbin Liu, Hui Li, Igor Gitman, Ilia Karmanov, Ivan Moshkov, Izik Golan, Jan Kautz, Jane Polak Scowcroft, Jared Casper, Jarno Seppanen, Jason Lu, Jason Sewall, Jiaqi Zeng, Jiaxuan You, Jimmy Zhang, Jing Zhang, Jining Huang, Jinze Xue, Jocelyn Huang, Joey Conway, John Kamalu, Jon Barker, Jonathan Cohen, Joseph Jennings, Jupinder Parmar, Karan Sapra, Kari Briski, Kateryna Chumachenko, Katherine Luna, Keshav Santhanam, Kezhi Kong, Kirthi Sivamani, Krzysztof Pawelec, Kumar Anik, Kunlun Li, Lawrence McAfee, Leon Derczynski, Lindsey Pavao, Luis Vega, Lukas Voegtle, Maciej Bala, Maer Rodrigues de Melo, Makesh Narsimhan Sreedhar, Marcin Chochowski, Markus Kliegl, Marta Stepniewska-Dziubinska, Matthieu Le, Matvei Novikov, Mehrzad Samadi, Michael Andersch, Michael Evans, Miguel Martinez, Mike Chrzanowski, Mike Ranzinger, Mikolaj Blaz, Misha Smelyanskiy, Mohamed Fawzy, Mohammad Shoeybi, Mostofa Patwary, Nayeon Lee, Nima Tajbakhsh, Ning Xu, Oleg Rybakov, Oleksii Kuchaiev, Olivier Delalleau, Osvald Nitski, Parth Chadha, Pasha Shamis, Paulius Micikevicius, Pavlo Molchanov, Peter Dykas, Philipp Fischer, Pierre-Yves Aquilanti, Piotr Bialecki, Prasoon Varshney, Pritam Gundecha, Przemek Tredak, Rabeeh Karimi, Rahul Kandu, Ran El-Yaniv, Raviraj Joshi, Roger Waleffe, Ruoxi Zhang, Sabrina Kavanaugh, Sahil Jain, Samuel Kriman, Sangkug Lym, Sanjeev Satheesh, Saurav Muralidharan, Sean Narenthiran, Selvaraj Anandaraj, Seonmyeong Bak, Sergey Kashirsky, Seungju Han, Shantanu Acharya, Shaona Ghosh, Sharath Turuvekere Sreenivas, Sharon Clay, Shelby Thomas, Shrimai Prabhumoye, Shubham Pachori, Shubham Toshniwal, Shyamala Prayaga, Siddhartha Jain, Sirshak Das, Slawek Kierat, Somshubra Majumdar, Song Han, Soumye Singhal, Sriharsha Niverty, Stefania Alborghetti, Suseella Panguluri, Swetha Bhendigeri, Syeda Nahida Akter, Szymon Migacz, Tal Shiri, Terry Kong, Timo Roman, Tomer Ronen, Trisha Saar, Tugrul Konuk, Tuomas Rintamaki, Tyler Poon, Ushnish De, Vahid Noroozi, Varun Singh, Vijay Korthikanti, Vitaly Kurin, Wasi Uddin Ahmad, Wei Du, Wei Ping, Wenliang Dai, Wonmin Byeon, Xiaowei Ren, Yao Xu, Yejin Choi, Yian Zhang, Ying Lin, Yoshi Suhara, Zhiding Yu, Zhiqi Li, Zhiyu Li, Zhongbo Zhu, Zhuolin Yang, Zijia Chen
Abstract: As inference-time scaling becomes critical for enhanced reasoning capabilities, it is increasingly becoming important to build models that are efficient to infer. We introduce Nemotron-H, a family of 8B and 56B/47B hybrid Mamba-Transformer models designed to reduce inference cost for a given accuracy level. To achieve this goal, we replace the majority of self-attention layers in the common Transformer model architecture with Mamba layers that perform constant computation and require constant memory per generated token. We show that Nemotron-H models offer either better or on-par accuracy compared to other similarly-sized state-of-the-art open-sourced Transformer models (e.g., Qwen-2.5-7B/72B and Llama-3.1-8B/70B), while being up to 3$\times$ faster at inference. To further increase inference speed and reduce the memory required at inference time, we created Nemotron-H-47B-Base from the 56B model using a new compression via pruning and distillation technique called MiniPuzzle. Nemotron-H-47B-Base achieves similar accuracy to the 56B model, but is 20% faster to infer. In addition, we introduce an FP8-based training recipe and show that it can achieve on par results with BF16-based training. This recipe is used to train the 56B model. All Nemotron-H models will be released, with support in Hugging Face, NeMo, and Megatron-LM.
Authors: Kate Sanders, Benjamin Van Durme
Abstract: To develop general-purpose collaborative agents, humans need reliable AI systems that can (1) adapt to new domains and (2) transparently reason with uncertainty to allow for verification and correction. Black-box models demonstrate powerful data processing abilities but do not satisfy these criteria due to their opaqueness, domain specificity, and lack of uncertainty awareness. We introduce Bonsai, a compositional and probabilistic reasoning system that generates adaptable inference trees by retrieving relevant grounding evidence and using it to compute likelihoods of sub-claims derived from broader natural language inferences. Bonsai's reasoning power is tunable at test-time via evidence scaling and it demonstrates reliable handling of varied domains including transcripts, photographs, videos, audio, and databases. Question-answering and human alignment experiments demonstrate that Bonsai matches the performance of domain-specific black-box methods while generating interpretable, grounded, and uncertainty-aware reasoning traces.
Authors: \'Angela L\'opez-Cardona, Guillermo Bern\'ardez, Pere Barlet-Ros, Albert Cabellos-Aparicio
Abstract: Optimal Power Flow (OPF) is a very traditional research area within the power systems field that seeks for the optimal operation point of electric power plants, and which needs to be solved every few minutes in real-world scenarios. However, due to the nonconvexities that arise in power generation systems, there is not yet a fast, robust solution technique for the full Alternating Current Optimal Power Flow (ACOPF). In the last decades, power grids have evolved into a typical dynamic, non-linear and large-scale control system, known as the power system, so searching for better and faster ACOPF solutions is becoming crucial. Appearance of Graph Neural Networks (GNN) has allowed the natural use of Machine Learning (ML) algorithms on graph data, such as power networks. On the other hand, Deep Reinforcement Learning (DRL) is known for its powerful capability to solve complex decision-making problems. Although solutions that use these two methods separately are beginning to appear in the literature, none has yet combined the advantages of both. We propose a novel architecture based on the Proximal Policy Optimization algorithm with Graph Neural Networks to solve the Optimal Power Flow. The objective is to design an architecture that learns how to solve the optimization problem and that is at the same time able to generalize to unseen scenarios. We compare our solution with the DCOPF in terms of cost after having trained our DRL agent on IEEE 30 bus system and then computing the OPF on that base network with topology changes
Authors: Isabelle Kuhlmann, Anna Gessler, Vivien Laszlo, Matthias Thimm
Abstract: We present algorithms based on satisfiability problem (SAT) solving, as well as answer set programming (ASP), for solving the problem of determining inconsistency degrees in propositional knowledge bases. We consider six different inconsistency measures whose respective decision problems lie on the first level of the polynomial hierarchy. Namely, these are the contension inconsistency measure, the forgetting-based inconsistency measure, the hitting set inconsistency measure, the max-distance inconsistency measure, the sum-distance inconsistency measure, and the hit-distance inconsistency measure. In an extensive experimental analysis, we compare the SAT-based and ASP-based approaches with each other, as well as with a set of naive baseline algorithms. Our results demonstrate that overall, both the SAT-based and the ASP-based approaches clearly outperform the naive baseline methods in terms of runtime. The results further show that the proposed ASP-based approaches perform superior to the SAT-based ones with regard to all six inconsistency measures considered in this work. Moreover, we conduct additional experiments to explain the aforementioned results in greater detail.
Authors: Sergio Rozada, Dongsheng Ding, Antonio G. Marques, Alejandro Ribeiro
Abstract: We study the problem of computing deterministic optimal policies for constrained Markov decision processes (MDPs) with continuous state and action spaces, which are widely encountered in constrained dynamical systems. Designing deterministic policy gradient methods in continuous state and action spaces is particularly challenging due to the lack of enumerable state-action pairs and the adoption of deterministic policies, hindering the application of existing policy gradient methods. To this end, we develop a deterministic policy gradient primal-dual method to find an optimal deterministic policy with non-asymptotic convergence. Specifically, we leverage regularization of the Lagrangian of the constrained MDP to propose a deterministic policy gradient primal-dual (D-PGPD) algorithm that updates the deterministic policy via a quadratic-regularized gradient ascent step and the dual variable via a quadratic-regularized gradient descent step. We prove that the primal-dual iterates of D-PGPD converge at a sub-linear rate to an optimal regularized primal-dual pair. We instantiate D-PGPD with function approximation and prove that the primal-dual iterates of D-PGPD converge at a sub-linear rate to an optimal regularized primal-dual pair, up to a function approximation error. Furthermore, we demonstrate the effectiveness of our method in two continuous control problems: robot navigation and fluid control. This appears to be the first work that proposes a deterministic policy search method for continuous-space constrained MDPs.
Authors: Bowen Li, Zhaoyu Li, Qiwei Du, Jinqi Luo, Wenshan Wang, Yaqi Xie, Simon Stepputtis, Chen Wang, Katia P. Sycara, Pradeep Kumar Ravikumar, Alexander G. Gray, Xujie Si, Sebastian Scherer
Abstract: Recent years have witnessed the rapid development of Neuro-Symbolic (NeSy) AI systems, which integrate symbolic reasoning into deep neural networks. However, most of the existing benchmarks for NeSy AI fail to provide long-horizon reasoning tasks with complex multi-agent interactions. Furthermore, they are usually constrained by fixed and simplistic logical rules over limited entities, making them far from real-world complexities. To address these crucial gaps, we introduce LogiCity, the first simulator based on customizable first-order logic (FOL) for an urban-like environment with multiple dynamic agents. LogiCity models diverse urban elements using semantic and spatial concepts, such as IsAmbulance(X) and IsClose(X, Y). These concepts are used to define FOL rules that govern the behavior of various agents. Since the concepts and rules are abstractions, they can be universally applied to cities with any agent compositions, facilitating the instantiation of diverse scenarios. Besides, a key feature of LogiCity is its support for user-configurable abstractions, enabling customizable simulation complexities for logical reasoning. To explore various aspects of NeSy AI, LogiCity introduces two tasks, one features long-horizon sequential decision-making, and the other focuses on one-step visual reasoning, varying in difficulty and agent behaviors. Our extensive evaluation reveals the advantage of NeSy frameworks in abstract reasoning. Moreover, we highlight the significant challenges of handling more complex abstractions in long-horizon multi-agent scenarios or under high-dimensional, imbalanced data. With its flexible design, various features, and newly raised challenges, we believe LogiCity represents a pivotal step forward in advancing the next generation of NeSy AI. All the code and data are open-sourced at our website: https://jaraxxus-me.github.io/LogiCity/
Authors: Chenxiao Yu, Zhaotian Weng, Yuangang Li, Zheng Li, Xiyang Hu, Yue Zhao
Abstract: Can Large Language Models (LLMs) accurately predict election outcomes? While LLMs have demonstrated impressive performance in various domains, including healthcare, legal analysis, and creative tasks, their ability to forecast elections remains unknown. Election prediction poses unique challenges, such as limited voter-level data, rapidly changing political landscapes, and the need to model complex human behavior. To address these challenges, we introduce a multi-step reasoning framework designed for political analysis. Our approach is validated on real-world data from the American National Election Studies (ANES) 2016 and 2020, as well as synthetic personas generated by the leading machine learning framework, offering scalable datasets for voter behavior modeling. To capture temporal dynamics, we incorporate candidates' policy positions and biographical details, ensuring that the model adapts to evolving political contexts. Drawing on Chain of Thought prompting, our multi-step reasoning pipeline systematically integrates demographic, ideological, and time-dependent factors, enhancing the model's predictive power.
Authors: Shambhavi Krishna, Zheng Chen, Yuan Ling, Xiaojiang Huang, Yingjie Li, Fan Yang, Xiang Li
Abstract: Modern AI assistants have made significant progress in natural language understanding and tool-use, with emerging efforts to interact with Web interfaces. However, current approaches that heavily rely on repeated LLM-driven HTML parsing are computationally expensive and error-prone, particularly when handling dynamic web interfaces and multi-step tasks. We introduce PAFFA (Premeditated Actions For Fast Agents), a method that makes LLMs faster and more accurate in completing tasks on the internet using a novel inference-time technique that requires no task-specific training. PAFFA constructs an 'Action Library', leveraging the parametric knowledge of the base LLM to pre-compute browser interaction patterns that generalize across tasks. By strategically re-using LLM inference across tasks - either via 'Dist-Map' for task-agnostic identification of key interactive web elements, or 'Unravel' for first-encounter, stateful exploration of novel tasks/sites) - PAFFA drastically reduces inference time tokens by 87% while maintaining robust performance (achieving 0.57 vs. 0.50 step accuracy compared to baseline). Further, Unravel's ability to update its action library based on explorations allows generalization and adaptation to unseen websites. In sum, this work exhibits that LLM reasoning sequences can generalize across prompts, offering a way to scale inference-time techniques for internet-scale data with sublinear token count.
Authors: Yingheng Tang, Wenbin Xu, Jie Cao, Jianzhu Ma, Weilu Gao, Steve Farrell, Benjamin Erichson, Michael W. Mahoney, Andy Nonaka, Zhi Yao
Abstract: Understanding and predicting the properties of inorganic materials is crucial for accelerating advancements in materials science and driving applications in energy, electronics, and beyond. Integrating material structure data with language-based information through multi-modal large language models (LLMs) offers great potential to support these efforts by enhancing human-AI interaction. However, a key challenge lies in integrating atomic structures at full resolution into LLMs. In this work, we introduce MatterChat, a versatile structure-aware multi-modal LLM that unifies material structural data and textual inputs into a single cohesive model. MatterChat employs a bridging module to effectively align a pretrained machine learning interatomic potential with a pretrained LLM, reducing training costs and enhancing flexibility. Our results demonstrate that MatterChat significantly improves performance in material property prediction and human-AI interaction, surpassing general-purpose LLMs such as GPT-4. We also demonstrate its usefulness in applications such as more advanced scientific reasoning and step-by-step material synthesis.
Authors: Giulio Starace, Oliver Jaffe, Dane Sherburn, James Aung, Jun Shern Chan, Leon Maksin, Rachel Dias, Evan Mays, Benjamin Kinsella, Wyatt Thompson, Johannes Heidecke, Amelia Glaese, Tejal Patwardhan
Abstract: We introduce PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research. Agents must replicate 20 ICML 2024 Spotlight and Oral papers from scratch, including understanding paper contributions, developing a codebase, and successfully executing experiments. For objective evaluation, we develop rubrics that hierarchically decompose each replication task into smaller sub-tasks with clear grading criteria. In total, PaperBench contains 8,316 individually gradable tasks. Rubrics are co-developed with the author(s) of each ICML paper for accuracy and realism. To enable scalable evaluation, we also develop an LLM-based judge to automatically grade replication attempts against rubrics, and assess our judge's performance by creating a separate benchmark for judges. We evaluate several frontier models on PaperBench, finding that the best-performing tested agent, Claude 3.5 Sonnet (New) with open-source scaffolding, achieves an average replication score of 21.0\%. Finally, we recruit top ML PhDs to attempt a subset of PaperBench, finding that models do not yet outperform the human baseline. We \href{https://github.com/openai/preparedness}{open-source our code} to facilitate future research in understanding the AI engineering capabilities of AI agents.
Authors: Abdalaziz Rashid Al-Maeeni, Aziz Temirkhanov, Artem Ryzhikov, Mikhail Hushchyn
Abstract: High-precision modeling of systems is one of the main areas of industrial data analysis. Models of systems, their digital twins, are used to predict their behavior under various conditions. We have developed several models of a storage system using machine learning-based generative models. The system consists of several components: hard disk drive (HDD) and solid-state drive (SSD) storage pools with different RAID schemes and cache. Each storage component is represented by a probabilistic model that describes the probability distribution of the component performance in terms of IOPS and latency, depending on their configuration and external data load parameters. The results of the experiments demonstrate the errors of 4-10 % for IOPS and 3-16 % for latency predictions depending on the components and models of the system. The predictions show up to 0.99 Pearson correlation with Little's law, which can be used for unsupervised reliability checks of the models. In addition, we present novel data sets that can be used for benchmarking regression algorithms, conditional generative models, and uncertainty estimation methods in machine learning.
Authors: Giorgio Audrito, Roberto Casadei, Ferruccio Damiani, Gianluca Torta, Mirko Viroli
Abstract: Recent trends like the Internet of Things (IoT) suggest a vision of dense and multi-scale deployments of computing devices in nearly all kinds of environments. A prominent engineering challenge revolves around programming the collective adaptive behaviour of such computational ecosystems. This requires abstractions able to capture concepts like ensembles (dynamic groups of cooperating devices) and collective tasks (joint activities carried out by ensembles). In this work, we consider collections of devices interacting with neighbours and that execute in nearly-synchronised sense-compute-interact rounds, where the computation is given by a single program mapping sensing values and incoming messages to output and outcoming messages. To support programming whole computational collectives, we propose the abstraction of a distributed collective process, which can be used to define at once the ensemble formation logic and its collective task. We formalise the abstraction in the eXchange Calculus (XC), a core functional language based on neighbouring values (maps from neighbours to values) where state and interaction is handled through a single primitive, exchange, and provide a corresponding implementation in the FCPP language. Then, we exercise distributed collective processes using two case studies: multi-hop message propagation and distributed monitoring of spatial properties. Finally, we discuss the features of the abstraction and its suitability for different kinds of distributed computing applications.
Authors: Khai Le-Duc
Abstract: Due to privacy restrictions, there's a shortage of publicly available speech recognition datasets in the medical domain. In this work, we present VietMed - a Vietnamese speech recognition dataset in the medical domain comprising 16h of labeled medical speech, 1000h of unlabeled medical speech and 1200h of unlabeled general-domain speech. To our best knowledge, VietMed is by far the world's largest public medical speech recognition dataset in 7 aspects: total duration, number of speakers, diseases, recording conditions, speaker roles, unique medical terms and accents. VietMed is also by far the largest public Vietnamese speech dataset in terms of total duration. Additionally, we are the first to present a medical ASR dataset covering all ICD-10 disease groups and all accents within a country. Moreover, we release the first public large-scale pre-trained models for Vietnamese ASR, w2v2-Viet and XLSR-53-Viet, along with the first public large-scale fine-tuned models for medical ASR. Even without any medical data in unsupervised pre-training, our best pre-trained model XLSR-53-Viet generalizes very well to the medical domain by outperforming state-of-the-art XLSR-53, from 51.8% to 29.6% WER on test set (a relative reduction of more than 40%). All code, data and models are made publicly available: https://github.com/leduckhai/MultiMed/tree/master/VietMed.
URLs: https://github.com/leduckhai/MultiMed/tree/master/VietMed.
Authors: Chenyu Huang, Zhengyang Tang, Shixi Hu, Ruoqing Jiang, Xin Zheng, Dongdong Ge, Benyou Wang, Zizhuo Wang
Abstract: Optimization modeling plays a critical role in the application of Operations Research (OR) tools to address real-world problems, yet they pose challenges and require extensive expertise from OR experts. With the advent of large language models (LLMs), new opportunities have emerged to streamline and automate such task. However, current research predominantly relies on closed-source LLMs such as GPT-4, along with extensive prompt engineering techniques. This reliance stems from the scarcity of high-quality training datasets for optimization modeling, resulting in elevated costs, prolonged processing times, and privacy concerns. To address these challenges, our work is the first to propose a viable path for training open-source LLMs that are capable of optimization modeling and developing solver codes, eventually leading to a superior ability for automating optimization modeling and solving. Particularly, we design the {\sc OR-Instruct}, a semi-automated data synthesis framework for optimization modeling that enables customizable enhancements for specific scenarios or model types. This work also introduces IndustryOR, the first industrial benchmark for evaluating LLMs in solving practical OR problems. We train several 7B-scale open-source LLMs using synthesized data (dubbed ORLMs{https://github.com/Cardinal-Operations/ORLM}), which exhibit significantly enhanced optimization modeling capabilities, achieving competitive performance across the NL4OPT, MAMO, and IndustryOR benchmarks. Additionally, our experiments highlight the potential of scaling law and reinforcement learning to further enhance the performance of ORLMs. The workflows and human-machine interaction paradigms of ORLMs in practical industrial applications are also discussed in the paper.
Authors: Khai Le-Duc, Khai-Nguyen Nguyen, Long Vo-Dang, Truong-Son Hy
Abstract: In doctor-patient conversations, identifying medically relevant information is crucial, posing the need for conversation summarization. In this work, we propose the first deployable real-time speech summarization system for real-world applications in industry, which generates a local summary after every N speech utterances within a conversation and a global summary after the end of a conversation. Our system could enhance user experience from a business standpoint, while also reducing computational costs from a technical perspective. Secondly, we present VietMed-Sum which, to our knowledge, is the first speech summarization dataset for medical conversations. Thirdly, we are the first to utilize LLM and human annotators collaboratively to create gold standard and synthetic summaries for medical conversation summarization. Finally, we present baseline results of state-of-the-art models on VietMed-Sum. All code, data (English-translated and Vietnamese) and models are available online: https://github.com/leduckhai/MultiMed/tree/master/VietMed-Sum
URLs: https://github.com/leduckhai/MultiMed/tree/master/VietMed-Sum
Authors: Yu Sun, Xinhao Li, Karan Dalal, Jiarui Xu, Arjun Vikram, Genghan Zhang, Yann Dubois, Xinlei Chen, Xiaolong Wang, Sanmi Koyejo, Tatsunori Hashimoto, Carlos Guestrin
Abstract: Self-attention performs well in long context but has quadratic complexity. Existing RNN layers have linear complexity, but their performance in long context is limited by the expressive power of their hidden states. We present a practical framework for instantiating sequence modeling layers with linear complexity and expressive hidden states. The key idea is to make the hidden state a machine learning model itself, and the update rule a step of self-supervised learning. Since the hidden state is updated by training even on test sequences, our layers are called Test-Time Training (TTT) layers. We consider two instantiations: TTT-Linear and TTT-MLP, whose hidden state is a linear model and a two-layer MLP respectively. We evaluate our instantiations at the scale of 125M to 1.3B parameters, comparing with a strong Transformer and Mamba, a modern RNN. Similar to Transformer, TTT-Linear and TTT-MLP can keep reducing perplexity by conditioning on more tokens, while Mamba cannot after 16k context. TTT-MLP still faces challenges in memory I/O, but shows larger potential in long context, pointing to a promising direction for future research.
Authors: Georgia Sovatzidi, Michael D. Vasilakakis, Dimitris K. Iakovidis
Abstract: Several deep learning (DL) approaches have been proposed to deal with image classification tasks. However, despite their effectiveness, they lack interpretability, as they are unable to explain or justify their results. To address the challenge of interpretable image classification, this paper introduces a novel framework, named Interpretable Intuitionistic Fuzzy Cognitive Maps (I2FCMs).Intuitionistic FCMs (iFCMs) have been proposed as an extension of FCMs offering a natural mechanism to assess the quality of their output through the estimation of hesitancy, a concept resembling human hesitation in decision making. In the context of image classification, hesitancy is considered as a degree of unconfidence with which an image is categorized to a class. To the best of our knowledge this is the first time iFCMs are applied for image classification. Further novel contributions of the introduced framework include the following: a) a feature extraction process focusing on the most informative image regions; b) a learning algorithm for automatic data-driven determination of the intuitionistic fuzzy interconnections of the iFCM, thereby reducing human intervention in the definition of the graph structure; c) an inherently interpretable classification approach based on image contents, providing understandable explanations of its predictions, using linguistic terms. Furthermore, the proposed I2FCM framework can be applied to DL models, including Convolutional Neural Network (CNN), rendering them interpretable. The effectiveness of I2FCM is evaluated on publicly available datasets, and the results confirm that it can provide enhanced classification performance, while providing interpretable inferences.
Authors: Shahriar Golchin, Mihai Surdeanu, Steven Bethard, Eduardo Blanco, Ellen Riloff
Abstract: In-context learning (ICL) has proven to be an effective strategy for improving the performance of large language models (LLMs) with no additional training. However, the exact mechanism behind this performance improvement remains unclear. This study is the first to show how ICL surfaces memorized training data and to explore the correlation between this memorization and performance on downstream tasks across various ICL regimes: zero-shot, few-shot, and many-shot. Our most notable findings include: (1) ICL significantly surfaces memorization compared to zero-shot learning in most cases; (2) demonstrations, without their labels, are the most effective element in surfacing memorization; (3) ICL improves performance when the surfaced memorization in few-shot regimes reaches a high level (about 40%); and (4) there is a very strong correlation between performance and memorization in ICL when it outperforms zero-shot learning. Overall, our study uncovers memorization as a new factor impacting ICL, raising an important question: to what extent do LLMs truly generalize from demonstrations in ICL, and how much of their success is due to memorization?
Authors: Gurvan Richardeau, Samy Chali, Erwan Le Merrer, Camilla Penzo, Gilles Tredan
Abstract: Large Language Models (LLMs) are nowadays prompted for a wide variety of tasks. In this article, we investigate their ability in reciting and generating graphs. We first study the ability of LLMs to regurgitate well known graphs from the literature (e.g. Karate club or the graph atlas)4. Secondly, we question the generative capabilities of LLMs by asking for Erdos-Renyi random graphs. As opposed to the possibility that they could memorize some Erdos-Renyi graphs included in their scraped training set, this second investigation aims at studying a possible emergent property of LLMs. For both tasks, we propose a metric to assess their errors with the lens of hallucination (i.e. incorrect information returned as facts). We most notably find that the amplitude of graph hallucinations can characterize the superiority of some LLMs. Indeed, for the recitation task, we observe that graph hallucinations correlate with the Hallucination Leaderboard, a hallucination rank that leverages 10, 000 times more prompts to obtain its ranking. For the generation task, we find surprisingly good and reproducible results in most of LLMs. We believe this to constitute a starting point for more in-depth studies of this emergent capability and a challenging benchmark for their improvements. Altogether, these two aspects of LLMs capabilities bridge a gap between the network science and machine learning communities.
Authors: Shahbaz Rezaei, Xin Liu
Abstract: Human understandable explanation of deep learning models is essential for various critical and sensitive applications. Unlike image or tabular data where the importance of each input feature (for the classifier's decision) can be directly projected into the input, time series distinguishable features (e.g. dominant frequency) are often hard to manifest in time domain for a user to easily understand. Additionally, most explanation methods require a baseline value as an indication of the absence of any feature. However, the notion of lack of feature, which is often defined as black pixels for vision tasks or zero/mean values for tabular data, is not well-defined in time series. Despite the adoption of explainable AI methods (XAI) from tabular and vision domain into time series domain, these differences limit the application of these XAI methods in practice. In this paper, we propose a simple yet effective method that allows a model originally trained on the time domain to be interpreted in other explanation spaces using existing methods. We suggest five explanation spaces, each of which can potentially alleviate these issues in certain types of time series. Our method can be easily integrated into existing platforms without any changes to trained models or XAI methods. The code will be released upon acceptance.
Authors: Lars-Peter Meyer, Johannes Frey, Felix Brei, Natanael Arndt
Abstract: The integration of Large Language Models (LLMs) with Knowledge Graphs (KGs) offers significant synergistic potential for knowledge-driven applications. One possible integration is the interpretation and generation of formal languages, such as those used in the Semantic Web, with SPARQL being a core technology for accessing KGs. In this paper, we focus on measuring out-of-the box capabilities of LLMs to work with SPARQL and more specifically with SPARQL SELECT queries applying a quantitative approach. We implemented various benchmarking tasks in the LLM-KG-Bench framework for automated execution and evaluation with several LLMs. The tasks assess capabilities along the dimensions of syntax, semantic read, semantic create, and the role of knowledge graph prompt inclusion. With this new benchmarking tasks, we evaluated a selection of GPT, Gemini, and Claude models. Our findings indicate that working with SPARQL SELECT queries is still challenging for LLMs and heavily depends on the specific LLM as well as the complexity of the task. While fixing basic syntax errors seems to pose no problems for the best of the current LLMs evaluated, creating semantically correct SPARQL SELECT queries is difficult in several cases.
Authors: Lorenzo Zangari, Candida M. Greco, Davide Picca, Andrea Tagarelli
Abstract: Moral values have deep roots in early civilizations, codified within norms and laws that regulated societal order and the common good. They play a crucial role in understanding the psychological basis of human behavior and cultural orientation. The Moral Foundation Theory (MFT) is a well-established framework that identifies the core moral foundations underlying the manner in which different cultures shape individual and social lives. Recent advancements in natural language processing, particularly Pre-trained Language Models (PLMs), have enabled the extraction and analysis of moral dimensions from textual data. This survey presents a comprehensive review of MFT-informed PLMs, providing an analysis of moral tendencies in PLMs and their application in the context of the MFT. We also review relevant datasets and lexicons and discuss trends, limitations, and future directions. By providing a structured overview of the intersection between PLMs and MFT, this work bridges moral psychology insights within the realm of PLMs, paving the way for further research and development in creating morally aware AI systems.
Authors: Harikha Manthena, Shaghayegh Shajarian, Jeffrey Kimmell, Mahmoud Abdelsalam, Sajad Khorsandroo, Maanak Gupta
Abstract: Machine learning (ML) has rapidly advanced in recent years, revolutionizing fields such as finance, medicine, and cybersecurity. In malware detection, ML-based approaches have demonstrated high accuracy; however, their lack of transparency poses a significant challenge. Traditional black-box models often fail to provide interpretable justifications for their predictions, limiting their adoption in security-critical environments where understanding the reasoning behind a detection is essential for threat mitigation and response. Explainable AI (XAI) addresses this gap by enhancing model interpretability while maintaining strong detection capabilities. This survey presents a comprehensive review of state-of-the-art ML techniques for malware analysis, with a specific focus on explainability methods. We examine existing XAI frameworks, their application in malware classification and detection, and the challenges associated with making malware detection models more interpretable. Additionally, we explore recent advancements and highlight open research challenges in the field of explainable malware analysis. By providing a structured overview of XAI-driven malware detection approaches, this survey serves as a valuable resource for researchers and practitioners seeking to bridge the gap between ML performance and explainability in cybersecurity.
Authors: Jiahao Yu, Yangguang Shao, Hanwen Miao, Junzheng Shi
Abstract: Large Language Models (LLMs) have gained widespread use in various applications due to their powerful capability to generate human-like text. However, prompt injection attacks, which involve overwriting a model's original instructions with malicious prompts to manipulate the generated text, have raised significant concerns about the security and reliability of LLMs. Ensuring that LLMs are robust against such attacks is crucial for their deployment in real-world applications, particularly in critical tasks. In this paper, we propose PROMPTFUZZ, a novel testing framework that leverages fuzzing techniques to systematically assess the robustness of LLMs against prompt injection attacks. Inspired by software fuzzing, PROMPTFUZZ selects promising seed prompts and generates a diverse set of prompt injections to evaluate the target LLM's resilience. PROMPTFUZZ operates in two stages: the prepare phase, which involves selecting promising initial seeds and collecting few-shot examples, and the focus phase, which uses the collected examples to generate diverse, high-quality prompt injections. Using PROMPTFUZZ, we can uncover more vulnerabilities in LLMs, even those with strong defense prompts. By deploying the generated attack prompts from PROMPTFUZZ in a real-world competition, we achieved the 7th ranking out of over 4000 participants (top 0.14%) within 2 hours. Additionally, we construct a dataset to fine-tune LLMs for enhanced robustness against prompt injection attacks. While the fine-tuned model shows improved robustness, PROMPTFUZZ continues to identify vulnerabilities, highlighting the importance of robust testing for LLMs. Our work emphasizes the critical need for effective testing tools and provides a practical framework for evaluating and improving the robustness of LLMs against prompt injection attacks.
Authors: Soobin Um, Jong Chul Ye
Abstract: We investigate the generation of minority samples using pretrained text-to-image (T2I) latent diffusion models. Minority instances, in the context of T2I generation, can be defined as ones living on low-density regions of text-conditional data distributions. They are valuable for various applications of modern T2I generators, such as data augmentation and creative AI. Unfortunately, existing pretrained T2I diffusion models primarily focus on high-density regions, largely due to the influence of guided samplers (like CFG) that are essential for high-quality generation. To address this, we present a novel framework to counter the high-density-focus of T2I diffusion models. Specifically, we first develop an online prompt optimization framework that encourages emergence of desired properties during inference while preserving semantic contents of user-provided prompts. We subsequently tailor this generic prompt optimizer into a specialized solver that promotes generation of minority features by incorporating a carefully-crafted likelihood objective. Extensive experiments conducted across various types of T2I models demonstrate that our approach significantly enhances the capability to produce high-quality minority instances compared to existing samplers. Code is available at https://github.com/soobin-um/MinorityPrompt.
Authors: Shikun Feng, Yuyan Ni, Yan Lu, Zhi-Ming Ma, Wei-Ying Ma, Yanyan Lan
Abstract: Molecular generation and molecular property prediction are both crucial for drug discovery, but they are often developed independently. Inspired by recent studies, which demonstrate that diffusion model, a prominent generative approach, can learn meaningful data representations that enhance predictive tasks, we explore the potential for developing a unified generative model in the molecular domain that effectively addresses both molecular generation and property prediction tasks. However, the integration of these tasks is challenging due to inherent inconsistencies, making simple multi-task learning ineffective. To address this, we propose UniGEM, the first unified model to successfully integrate molecular generation and property prediction, delivering superior performance in both tasks. Our key innovation lies in a novel two-phase generative process, where predictive tasks are activated in the later stages, after the molecular scaffold is formed. We further enhance task balance through innovative training strategies. Rigorous theoretical analysis and comprehensive experiments demonstrate our significant improvements in both tasks. The principles behind UniGEM hold promise for broader applications, including natural language processing and computer vision.
Authors: Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Boxing Chen, Sarath Chandar
Abstract: The growth in prominence of large language models (LLMs) in everyday life can be largely attributed to their generative abilities, yet some of this is also owed to the risks and costs associated with their use. On one front is their tendency to hallucinate false or misleading information, limiting their reliability. On another is the increasing focus on the computational limitations associated with traditional self-attention based LLMs, which has brought about new alternatives, in particular recurrent models, meant to overcome them. Yet it remains uncommon to consider these two concerns simultaneously. Do changes in architecture exacerbate/alleviate existing concerns about hallucinations? Do they affect how and where they occur? Through an extensive evaluation, we study how these architecture-based inductive biases affect the propensity to hallucinate. While hallucination remains a general phenomenon not limited to specific architectures, the situations in which they occur and the ease with which specific types of hallucinations can be induced can significantly differ based on the model architecture. These findings highlight the need for better understanding both these problems in conjunction with each other, as well as consider how to design more universal techniques for handling hallucinations.
Authors: Tassilo Wald, Constantin Ulrich, Stanislav Lukyanenko, Andrei Goncharov, Alberto Paderno, Maximilian Miller, Leander Maerkisch, Paul F. J\"ager, Klaus Maier-Hein
Abstract: Self-Supervised Learning (SSL) presents an exciting opportunity to unlock the potential of vast, untapped clinical datasets, for various downstream applications that suffer from the scarcity of labeled data. While SSL has revolutionized fields like natural language processing and computer vision, its adoption in 3D medical image computing has been limited by three key pitfalls: Small pre-training dataset sizes, architectures inadequate for 3D medical image analysis, and insufficient evaluation practices. In this paper, we address these issues by i) leveraging a large-scale dataset of 39k 3D brain MRI volumes and ii) using a Residual Encoder U-Net architecture within the state-of-the-art nnU-Net framework. iii) A robust development framework, incorporating 5 development and 8 testing brain MRI segmentation datasets, allowed performance-driven design decisions to optimize the simple concept of Masked Auto Encoders (MAEs) for 3D CNNs. The resulting model not only surpasses previous SSL methods but also outperforms the strong nnU-Net baseline by an average of approximately 3 Dice points setting a new state-of-the-art. Our code and models are made available here.
Authors: Xingrui Yu, Zhenglin Wan, David Mark Bossens, Yueming Lyu, Qing Guo, Ivor W. Tsang
Abstract: Learning diverse and high-performance behaviors from a limited set of demonstrations is a grand challenge. Traditional imitation learning methods usually fail in this task because most of them are designed to learn one specific behavior even with multiple demonstrations. Therefore, novel techniques for \textit{quality diversity imitation learning}, which bridges the quality diversity optimization and imitation learning methods, are needed to solve the above challenge. This work introduces Wasserstein Quality Diversity Imitation Learning (WQDIL), which 1) improves the stability of imitation learning in the quality diversity setting with latent adversarial training based on a Wasserstein Auto-Encoder (WAE), and 2) mitigates a behavior-overfitting issue using a measure-conditioned reward function with a single-step archive exploration bonus. Empirically, our method significantly outperforms state-of-the-art IL methods, achieving near-expert or beyond-expert QD performance on the challenging continuous control tasks derived from MuJoCo environments.
Authors: Andong Deng, Tongjia Chen, Shoubin Yu, Taojiannan Yang, Lincoln Spencer, Yapeng Tian, Ajmal Saeed Mian, Mohit Bansal, Chen Chen
Abstract: In this paper, we introduce Motion-Grounded Video Reasoning, a new motion understanding task that requires generating visual answers (video segmentation masks) according to the input question, and hence needs implicit spatiotemporal reasoning and grounding. This task extends existing spatiotemporal grounding work focusing on explicit action/motion grounding, to a more general format by enabling implicit reasoning via questions. To facilitate the development of the new task, we collect a large-scale dataset called GROUNDMORE, which comprises 1,715 video clips, 249K object masks that are deliberately designed with 4 question types (Causal, Sequential, Counterfactual, and Descriptive) for benchmarking deep and comprehensive motion reasoning abilities. GROUNDMORE uniquely requires models to generate visual answers, providing a more concrete and visually interpretable response than plain texts. It evaluates models on both spatiotemporal grounding and reasoning, fostering to address complex challenges in motion-related video reasoning, temporal perception, and pixel-level understanding. Furthermore, we introduce a novel baseline model named Motion-Grounded Video Reasoning Assistant (MORA). MORA incorporates the multimodal reasoning ability from the Multimodal LLM, the pixel-level perception capability from the grounding model (SAM), and the temporal perception ability from a lightweight localization head. MORA achieves respectable performance on GROUNDMORE outperforming the best existing visual grounding baseline model by an average of 21.5% relatively. We hope this novel and challenging task will pave the way for future advancements in robust and general motion understanding via video reasoning segmentation
Authors: Yuanbin Man, Ying Huang, Chengming Zhang, Bingzhe Li, Wei Niu, Miao Yin
Abstract: The advancements in large language models (LLMs) have propelled the improvement of video understanding tasks by incorporating LLMs with visual models. However, most existing LLM-based models (e.g., VideoLLaMA, VideoChat) are constrained to processing short-duration videos. Recent attempts to understand long-term videos by extracting and compressing visual features into a fixed memory size. Nevertheless, those methods leverage only visual modality to merge video tokens and overlook the correlation between visual and textual queries, leading to difficulties in effectively handling complex question-answering tasks. To address the challenges of long videos and complex prompts, we propose AdaCM$^2$, which, for the first time, introduces an adaptive cross-modality memory reduction approach to video-text alignment in an auto-regressive manner on video streams. Our extensive experiments on various video understanding tasks, such as video captioning, video question answering, and video classification, demonstrate that AdaCM$^2$ achieves state-of-the-art performance across multiple datasets while significantly reducing memory usage. Notably, it achieves a 4.5% improvement across multiple tasks in the LVU dataset with a GPU memory consumption reduction of up to 65%.
Authors: Amirhossein Abaskohi, Spandana Gella, Giuseppe Carenini, Issam H. Laradji
Abstract: Multimodal multihop question answering (MMQA) requires reasoning over images and text from multiple sources. Despite advances in visual question answering, this multihop setting remains underexplored due to a lack of quality datasets. Existing methods focus on single-hop, single-modality, or short texts, limiting real-world applications like interpreting educational documents with long, multimodal content. To fill this gap, we introduce FM2DS, the first framework for creating a high-quality dataset for MMQA. Our approach consists of a 5-stage pipeline that involves acquiring relevant multimodal documents from Wikipedia, synthetically generating high-level questions and answers, and validating them through rigorous criteria to ensure data quality. We evaluate our methodology by training models on our synthesized dataset and testing on two benchmarks: MultimodalQA and WebQA. Our results demonstrate that, with an equal sample size, models trained on our synthesized data outperform those trained on human-collected data by 1.9 in exact match (EM) score on average. Additionally, we introduce M2QA-Bench with 1k samples, the first benchmark for MMQA on long documents, generated using FM2DS and refined by human annotators. We believe our data synthesis method will serve as a strong foundation for training and evaluating MMQA models.
Authors: Tarleton Gillespie, Ryland Shaw, Mary L. Gray, Jina Suh
Abstract: As generative AI technologies find more and more real-world applications, the importance of testing their performance and safety seems paramount. "Red-teaming" has quickly become the primary approach to test AI models--prioritized by AI companies, and enshrined in AI policy and regulation. Members of red teams act as adversaries, probing AI systems to test their safety mechanisms and uncover vulnerabilities. Yet we know far too little about this work or its implications. This essay calls for collaboration between computer scientists and social scientists to study the sociotechnical systems surrounding AI technologies, including the work of red-teaming, to avoid repeating the mistakes of the recent past. We highlight the importance of understanding the values and assumptions behind red-teaming, the labor arrangements involved, and the psychological impacts on red-teamers, drawing insights from the lessons learned around the work of content moderation.
Authors: Alex Mallen, Charlie Griffin, Misha Wagner, Alessandro Abate, Buck Shlegeris
Abstract: An AI control protocol is a plan for usefully deploying AI systems that aims to prevent an AI from intentionally causing some unacceptable outcome. This paper investigates how well AI systems can generate and act on their own strategies for subverting control protocols whilst operating statelessly (without shared memory between contexts). To do this, an AI system may need to reliably generate optimal plans in each context, take actions with well-calibrated probabilities, and coordinate plans with other instances of itself without communicating. We develop Subversion Strategy Eval, a suite of eight environments, covering a range of protocols and strategic capabilities, and six sets of affordances that help isolate individual capabilities. We implement the evaluation in Inspect-AI and release it open-source. We evaluate Claude 3.5 models, including helpful-only versions, as well as OpenAI reasoning models. None of the models demonstrate substantial capability in strategizing to subvert control protocols statelessly. However, providing models with additional affordances, such as the ability to share a plan between contexts, can substantially improve performance. We hope our evaluations can act as a leading indicator for when models are capable of subverting control protocols and also relax the worst-case assumption of perfect strategic ability in AI control evaluations.
Authors: Umer Butt, Stalin Varanasi, G\"unter Neumann
Abstract: As the Information Retrieval (IR) field increasingly recognizes the importance of inclusivity, addressing the needs of low-resource languages remains a significant challenge. This paper introduces the first large-scale Urdu IR dataset, created by translating the MS MARCO dataset through machine translation. We establish baseline results through zero-shot learning for IR in Urdu and subsequently apply the mMARCO multilingual IR methodology to this newly translated dataset. Our findings demonstrate that the fine-tuned model (Urdu-mT5-mMARCO) achieves a Mean Reciprocal Rank (MRR@10) of 0.247 and a Recall@10 of 0.439, representing significant improvements over zero-shot results and showing the potential for expanding IR access for Urdu speakers. By bridging access gaps for speakers of low-resource languages, this work not only advances multilingual IR research but also emphasizes the ethical and societal importance of inclusive IR technologies. This work provides valuable insights into the challenges and solutions for improving language representation and lays the groundwork for future research, especially in South Asian languages, which can benefit from the adaptable methods used in this study.
Authors: Austin Stone, Hagen Soltau, Robert Geirhos, Xi Yi, Ye Xia, Bingyi Cao, Kaifeng Chen, Abhijit Ogale, Jonathon Shlens
Abstract: Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building better representations for a small number of discrete objects bereft of an understanding of how these objects are interacting. One can observe this limitation in representations learned through captions or contrastive learning -- where the learned model treats an image essentially as a bag of words. Several works have attempted to address this limitation through the development of bespoke learned architectures to directly address the shortcomings in compositional learning. In this work, we focus on simple, and scalable approaches. In particular, we demonstrate that by substantially improving weakly labeled data, i.e. captions, we can vastly improve the performance of standard contrastive learning approaches. Previous CLIP models achieved near chance rate on challenging tasks probing compositional learning. However, our simple approach boosts performance of CLIP substantially and surpasses all bespoke architectures. Furthermore, we showcase our results on a relatively new captioning benchmark derived from DOCCI. We demonstrate through a series of ablations that a standard CLIP model trained with enhanced data may demonstrate impressive performance on image retrieval tasks.
Authors: Tianyun Zhong, Chao Liang, Jianwen Jiang, Gaojie Lin, Jiaqi Yang, Zhou Zhao
Abstract: Diffusion-based audio-driven talking avatar methods have recently gained attention for their high-fidelity, vivid, and expressive results. However, their slow inference speed limits practical applications. Despite the development of various distillation techniques for diffusion models, we found that naive diffusion distillation methods do not yield satisfactory results. Distilled models exhibit reduced robustness with open-set input images and a decreased correlation between audio and video compared to teacher models, undermining the advantages of diffusion models. To address this, we propose FADA (Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation). We first designed a mixed-supervised loss to leverage data of varying quality and enhance the overall model capability as well as robustness. Additionally, we propose a multi-CFG distillation with learnable tokens to utilize the correlation between audio and reference image conditions, reducing the threefold inference runs caused by multi-CFG with acceptable quality degradation. Extensive experiments across multiple datasets show that FADA generates vivid videos comparable to recent diffusion model-based methods while achieving an NFE speedup of 4.17-12.5 times. Demos are available at our webpage http://fadavatar.github.io.
Authors: Kiet A. Nguyen, Adheesh Juvekar, Tianjiao Yu, Muntasir Wahed, Ismini Lourentzou
Abstract: Recent advances in Large Vision-Language Models (LVLMs) have enabled general-purpose vision tasks through visual instruction tuning. While existing LVLMs can generate segmentation masks from text prompts for single images, they struggle with segmentation-grounded reasoning across images, especially at finer granularities such as object parts. In this paper, we introduce the new task of part-focused semantic co-segmentation, which involves identifying and segmenting common objects, as well as common and unique object parts across images. To address this task, we present CALICO, the first LVLM designed for multi-image part-level reasoning segmentation. CALICO features two key components, a novel Correspondence Extraction Module that identifies semantic part-level correspondences, and Correspondence Adaptation Modules that embed this information into the LVLM to facilitate multi-image understanding in a parameter-efficient manner. To support training and evaluation, we curate MixedParts, a large-scale multi-image segmentation dataset containing $\sim$2.4M samples across $\sim$44K images spanning diverse object and part categories. Experimental results demonstrate that CALICO, with just 0.3% of its parameters finetuned, achieves strong performance on this challenging task.
Authors: Lingzhi Yuan, Xiaojun Jia, Yihao Huang, Wei Dong, Yang Liu
Abstract: Text-to-image (T2I) models have been shown to be vulnerable to misuse, particularly in generating not-safe-for-work (NSFW) content, raising serious ethical concerns. In this work, we present PromptGuard, a novel content moderation technique that draws inspiration from the system prompt mechanism in large language models (LLMs) for safety alignment. Unlike LLMs, T2I models lack a direct interface for enforcing behavioral guidelines. Our key idea is to optimize a safety soft prompt that functions as an implicit system prompt within the T2I model's textual embedding space. This universal soft prompt (P*) directly moderates NSFW inputs, enabling safe yet realistic image generation without altering the inference efficiency or requiring proxy models. Extensive experiments across three datasets demonstrate that PromptGuard effectively mitigates NSFW content generation while preserving high-quality benign outputs. PromptGuard achieves 7.8 times faster than prior content moderation methods, surpassing eight state-of-the-art defenses with an optimal unsafe ratio down to 5.84%.
Authors: Myeongsoo Kim, Saurabh Sinha, Alessandro Orso
Abstract: Modern web services rely heavily on REST APIs, typically documented using the OpenAPI specification. The widespread adoption of this standard has resulted in the development of many black-box testing tools that generate tests based on OpenAPI specifications. Although Large Language Models (LLMs) have shown promising test-generation abilities, their application to REST API testing remains mostly unexplored. We present LlamaRestTest, a novel approach that employs two custom LLMs-created by fine-tuning and quantizing the Llama3-8B model using mined datasets of REST API example values and inter-parameter dependencies-to generate realistic test inputs and uncover inter-parameter dependencies during the testing process by analyzing server responses. We evaluated LlamaRestTest on 12 real-world services (including popular services such as Spotify), comparing it against RESTGPT, a GPT-powered specification-enhancement tool, as well as several state-of-the-art REST API testing tools, including RESTler, MoRest, EvoMaster, and ARAT-RL. Our results demonstrate that fine-tuning enables smaller models to outperform much larger models in detecting actionable parameter-dependency rules and generating valid inputs for REST API testing. We also evaluated different tool configurations, ranging from the base Llama3-8B model to fine-tuned versions, and explored multiple quantization techniques, including 2-bit, 4-bit, and 8-bit integer formats. Our study shows that small language models can perform as well as, or better than, large language models in REST API testing, balancing effectiveness and efficiency. Furthermore, LlamaRestTest outperforms state-of-the-art REST API testing tools in code coverage achieved and internal server errors identified, even when those tools use RESTGPT-enhanced specifications.
Authors: Amirali Sajadi, Binh Le, Anh Nguyen, Kostadin Damevski, Preetha Chatterjee
Abstract: The widespread adoption of conversational LLMs for software development has raised new security concerns regarding the safety of LLM-generated content. Our motivational study outlines ChatGPT's potential in volunteering context-specific information to the developers, promoting safe coding practices. Motivated by this finding, we conduct a study to evaluate the degree of security awareness exhibited by three prominent LLMs: Claude 3, GPT-4, and Llama 3. We prompt these LLMs with Stack Overflow questions that contain vulnerable code to evaluate whether they merely provide answers to the questions or if they also warn users about the insecure code, thereby demonstrating a degree of security awareness. Further, we assess whether LLM responses provide information about the causes, exploits, and the potential fixes of the vulnerability, to help raise users' awareness. Our findings show that all three models struggle to accurately detect and warn users about vulnerabilities, achieving a detection rate of only 12.6% to 40% across our datasets. We also observe that the LLMs tend to identify certain types of vulnerabilities related to sensitive information exposure and improper input neutralization much more frequently than other types, such as those involving external control of file names or paths. Furthermore, when LLMs do issue security warnings, they often provide more information on the causes, exploits, and fixes of vulnerabilities compared to Stack Overflow responses. Finally, we provide an in-depth discussion on the implications of our findings and present a CLI-based prompting tool that can be used to generate significantly more secure LLM responses.
Authors: Maryam Rahimi, Yadollah Yaghoobzadeh, Mohammad Reza Daliri
Abstract: Large language models (LLMs) not only exhibit human-like performance but also share computational principles with the brain's language processing mechanisms. While prior research has focused on mapping LLMs' internal representations to neural activity, we propose a novel approach using explainable AI (XAI) to strengthen this link. Applying attribution methods, we quantify the influence of preceding words on LLMs' next-word predictions and use these explanations to predict fMRI data from participants listening to narratives. We find that attribution methods robustly predict brain activity across the language network, revealing a hierarchical pattern: explanations from early layers align with the brain's initial language processing stages, while later layers correspond to more advanced stages. Additionally, layers with greater influence on next-word prediction$\unicode{x2014}$reflected in higher attribution scores$\unicode{x2014}$demonstrate stronger brain alignment. These results underscore XAI's potential for exploring the neural basis of language and suggest brain alignment for assessing the biological plausibility of explanation methods.
Authors: Joan Serr\`a, R. Oguz Araz, Dmitry Bogdanov, Yuki Mitsufuji
Abstract: Detecting musical versions (different renditions of the same piece) is a challenging task with important applications. Because of the ground truth nature, existing approaches match musical versions at the track level (e.g., whole song). However, most applications require to match them at the segment level (e.g., 20s chunks). In addition, existing approaches resort to classification and triplet losses, disregarding more recent losses that could bring meaningful improvements. In this paper, we propose a method to learn from weakly annotated segments, together with a contrastive loss variant that outperforms well-studied alternatives. The former is based on pairwise segment distance reductions, while the latter modifies an existing loss following decoupling, hyper-parameter, and geometric considerations. With these two elements, we do not only achieve state-of-the-art results in the standard track-level evaluation, but we also obtain a breakthrough performance in a segment-level evaluation. We believe that, due to the generality of the challenges addressed here, the proposed methods may find utility in domains beyond audio or musical version matching.
Authors: Pau Rodriguez, Michal Klein, Eleonora Gualdoni, Arno Blaas, Luca Zappella, Marco Cuturi, Xavier Suau
Abstract: The growing use of generative models in daily life calls for efficient mechanisms to control their generation, to e.g., produce safe content or provide users with tools to explore style changes. Ideally, such mechanisms should be cheap, both at train and inference time, while preserving output quality. Recent research has shown that such mechanisms can be obtained by intervening exclusively on model activations, with the goal of correcting distributional differences between activations seen when using prompts from a source vs. a target set (e.g., toxic and non-toxic sentences). While cheap, these fast methods are inherently crude: their maps are tuned locally, not accounting for their impact on downstream layers, resulting in interventions that cause unintended shifts when used out-of-sample. We propose in this work linear end-to-end activation steering (LinEAS), an approach trained with a global loss that accounts simultaneously for all layerwise distributional shifts. In addition to being more robust, the loss used to train LinEAS can be regularized with sparsifying norms, which can automatically carry out neuron and layer selection. Empirically, LinEAS only requires a handful of samples to be effective, and beats similar baselines on toxicity mitigation, while performing on par with far more involved finetuning approaches. We show that LinEAS interventions can be composed, study the impact of sparsity on their performance, and showcase applications in text-to-image diffusions.
Authors: Jingyuan Xue, Longfei Wei, Fang Sheng, Jianfei Zhang
Abstract: Battery degradation significantly impacts the reliability and efficiency of energy storage systems, particularly in electric vehicles (EVs) and industrial applications. Predicting the remaining useful life (RUL) of lithium-ion (Li-ion) batteries is crucial for optimizing maintenance schedules, reducing costs, and improving safety. Traditional RUL prediction methods often struggle with nonlinear degradation patterns and uncertainty quantification. To address these challenges, we propose a hybrid survival analysis framework integrating both statistical and machine-learning-based models for RUL estimation. Our approach transforms time-series battery data into time-to-failure data using path signatures, enabling effective survival modeling. We apply five models, including Cox-based survival models and machine-learning-based methods such as DeepHit and MTLR, to estimate failure-free probabilities over time. Experiments conducted on 362 Toyota battery datasets demonstrate the effectiveness of our approach, achieving high time-dependent AUC and concordance index while maintaining a low integrated Brier score. The proposed methodology provides actionable insights for battery manufacturers and engineers, supporting dynamic maintenance strategies and optimized lifecycle management.
Authors: Yuhang Wang, Hanwei Guo, Sizhe Wang, Long Qian, Xuguang Lan
Abstract: Model Predictive Control (MPC) has been demonstrated to be effective in continuous control tasks. When a world model and a value function are available, planning a sequence of actions ahead of time leads to a better policy. Existing methods typically obtain the value function and the corresponding policy in a model-free manner. However, we find that such an approach struggles with complex tasks, resulting in poor policy learning and inaccurate value estimation. To address this problem, we leverage the strengths of MPC itself. In this work, we introduce Bootstrapped Model Predictive Control (BMPC), a novel algorithm that performs policy learning in a bootstrapped manner. BMPC learns a network policy by imitating an MPC expert, and in turn, uses this policy to guide the MPC process. Combined with model-based TD-learning, our policy learning yields better value estimation and further boosts the efficiency of MPC. We also introduce a lazy reanalyze mechanism, which enables computationally efficient imitation learning. Our method achieves superior performance over prior works on diverse continuous control tasks. In particular, on challenging high-dimensional locomotion tasks, BMPC significantly improves data efficiency while also enhancing asymptotic performance and training stability, with comparable training time and smaller network sizes. Code is available at https://github.com/wertyuilife2/bmpc.
Authors: Sejin Lee, Jian Kim, Haon Park, Ashkan Yousefpour, Sangyoon Yu, Min Song
Abstract: Large Language Models (LLMs) are increasingly deployed as computer-use agents, autonomously performing tasks within real desktop or web environments. While this evolution greatly expands practical use cases for humans, it also creates serious security exposures. We present SUDO (Screen-based Universal Detox2Tox Offense), a novel attack framework that systematically bypasses refusal trained safeguards in commercial computer-use agents, such as Claude Computer Use. The core mechanism, Detox2Tox, transforms harmful requests (that agents initially reject) into seemingly benign requests via detoxification, secures detailed instructions from advanced vision language models (VLMs), and then reintroduces malicious content via toxification just before execution. Unlike conventional jailbreaks, SUDO iteratively refines its attacks based on a built-in refusal feedback, making it increasingly effective against robust policy filters. In extensive tests spanning 50 real-world tasks and multiple state-of-the-art VLMs, SUDO achieves a stark attack success rate of 24% (with no refinement), and up to 41% (by its iterative refinement) in Claude Computer Use. By revealing these vulnerabilities and demonstrating the ease with which they can be exploited in real-world computing environments, this paper highlights an immediate need for robust, context-aware safeguards. WARNING: This paper includes harmful or offensive model outputs Our code is available at: https://github.com/AIM-Intelligence/SUDO.git
Authors: Umer Butt, Stalin Veranasi, G\"unter Neumann
Abstract: As the Information Retrieval (IR) field increasingly recognizes the importance of inclusivity, addressing the needs of low-resource languages remains a significant challenge. Transliteration between Urdu and its Romanized form, Roman Urdu, remains underexplored despite the widespread use of both scripts in South Asia. Prior work using RNNs on the Roman-Urdu-Parl dataset showed promising results but suffered from poor domain adaptability and limited evaluation. We propose a transformer-based approach using the m2m100 multilingual translation model, enhanced with masked language modeling (MLM) pretraining and fine-tuning on both Roman-Urdu-Parl and the domain-diverse Dakshina dataset. To address previous evaluation flaws, we introduce rigorous dataset splits and assess performance using BLEU, character-level BLEU, and CHRF. Our model achieves strong transliteration performance, with Char-BLEU scores of 96.37 for Urdu->Roman-Urdu and 97.44 for Roman-Urdu->Urdu. These results outperform both RNN baselines and GPT-4o Mini and demonstrate the effectiveness of multilingual transfer learning for low-resource transliteration tasks.
Authors: Yanliang Huang, Sebastian Mair, Zhuoqi Zeng, Matthias Althoff
Abstract: Autonomous vehicle path planning has reached a stage where safety and regulatory compliance are crucial. This paper presents an approach that integrates a motion planner with a deep reinforcement learning model to predict potential traffic rule violations. Our main innovation is replacing the standard actor network in an actor-critic method with a motion planning module, which ensures both stable and interpretable trajectory generation. In this setup, we use traffic rule robustness as the reward to train a reinforcement learning agent's critic, and the output of the critic is directly used as the cost function of the motion planner, which guides the choices of the trajectory. We incorporate some key interstate rules from the German Road Traffic Regulation into a rule book and use a graph-based state representation to handle complex traffic information. Experiments on an open German highway dataset show that the model can predict and prevent traffic rule violations beyond the planning horizon, increasing safety and rule compliance in challenging traffic scenarios.
Authors: Supriyo Maji, Linran Zhao, Souradip Poddar, David Z. Pan
Abstract: Layout-dependent effects (LDEs) significantly impact analog circuit performance. Traditionally, designers have relied on symmetric placement of circuit components to mitigate variations caused by LDEs. However, due to non-linear nature of these effects, conventional methods often fall short. We propose an objective-driven, multi-level, multi-agent Q-learning framework to explore unconventional design space of analog layout, opening new avenues for optimizing analog circuit performance. Our approach achieves better variation performance than the state-of-the-art layout techniques. Notably, this is the first application of multi-agent RL in analog layout automation. The proposed approach is compared with non-ML approach based on simulated annealing.
Authors: Xindi Yang, Baolu Li, Yiming Zhang, Zhenfei Yin, Lei Bai, Liqian Ma, Zhiyong Wang, Jianfei Cai, Tien-Tsin Wong, Huchuan Lu, Xu Jia
Abstract: Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos and drawing the attention of the community in their potential as world simulators. However, despite their capabilities, VDMs often fail to produce physically plausible videos due to an inherent lack of understanding of physics, resulting in incorrect dynamics and event sequences. To address this limitation, we propose a novel two-stage image-to-video generation framework that explicitly incorporates physics with vision and language informed physical prior. In the first stage, we employ a Vision Language Model (VLM) as a coarse-grained motion planner, integrating chain-of-thought and physics-aware reasoning to predict a rough motion trajectories/changes that approximate real-world physical dynamics while ensuring the inter-frame consistency. In the second stage, we use the predicted motion trajectories/changes to guide the video generation of a VDM. As the predicted motion trajectories/changes are rough, noise is added during inference to provide freedom to the VDM in generating motion with more fine details. Extensive experimental results demonstrate that our framework can produce physically plausible motion, and comparative evaluations highlight the notable superiority of our approach over existing methods. More video results are available on our Project Page: https://madaoer.github.io/projects/physically_plausible_video_generation.
URLs: https://madaoer.github.io/projects/physically_plausible_video_generation.
Authors: Joshua Hatherley
Abstract: It is commonly accepted that clinicians are ethically obligated to disclose their use of medical machine learning systems to patients, and that failure to do so would amount to a moral fault for which clinicians ought to be held accountable. Call this "the disclosure thesis." Four main arguments have been, or could be, given to support the disclosure thesis in the ethics literature: the risk-based argument, the rights-based argument, the materiality argument, and the autonomy argument. In this article, I argue that each of these four arguments are unconvincing, and therefore, that the disclosure thesis ought to be rejected. I suggest that mandating disclosure may also even risk harming patients by providing stakeholders with a way to avoid accountability for harm that results from improper applications or uses of these systems.
Authors: Nusrat Jahan Mozumder, Felipe Toledo, Swaroopa Dola, Matthew B. Dwyer
Abstract: Deep neural network (DNN) testing is crucial for the reliability and safety of critical systems, where failures can have severe consequences. Although various techniques have been developed to create robustness test suites, requirements-based testing for DNNs remains largely unexplored - yet such tests are recognized as an essential component of software validation of critical systems. In this work, we propose a requirements-based test suite generation method that uses structured natural language requirements formulated in a semantic feature space to create test suites by prompting text-conditional latent diffusion models with the requirement precondition and then using the associated postcondition to define a test oracle to judge outputs of the DNN under test. We investigate the approach using fine-tuned variants of pre-trained generative models. Our experiments on the MNIST, CelebA-HQ, ImageNet, and autonomous car driving datasets demonstrate that the generated test suites are realistic, diverse, consistent with preconditions, and capable of revealing faults.