Authors: Duong Q. Nguyen, Quy P. Nguyen, Nguyen Van Nhon, Quang-Thinh Bui, H. Nguyen-Xuan
Abstract: This paper develops an autonomous agentic framework called V-Math that aims to assist Vietnamese high school students in preparing for the National High School Graduation Mathematics Exams (NHSGMEs). The salient framework integrates three specialized AI agents: a specification-matrix-conditioned question generator, a solver/explainer for detailed step-by-step reasoning, and a personalized tutor that adapts to student performance. Beyond enabling self-paced student practice, V-Math supports teachers by generating innovative, compliant exam questions and building diverse, high-quality question banks. This reduces manual workload and enriches instructional resources. We describe the system architecture, focusing on practice modes for learners and teacher-oriented features for question generation. Preliminary evaluations demonstrate that V-Math produces matrix-aligned exams with high solution accuracy, delivers coherent explanations, and enhances the variety of practice materials. These results highlight its potential to support scalable, equitable mathematics preparation aligned with national standards while also empowering teachers through AI-assisted exam creation.
Authors: Oddvar Kloster, Bj{\o}rnar Luteberget, Carlo Mannino, Giorgio Sartor
Abstract: Optimization-based decision support systems have a significant potential to reduce delays, and thus improve efficiency on the railways, by automatically re-routing and re-scheduling trains after delays have occurred. The operations research community has dedicated a lot of effort to developing optimization algorithms for this problem, but each study is typically tightly connected with a specific industrial use case. Code and data are seldom shared publicly. This fact hinders reproducibility, and has led to a proliferation of papers describing algorithms for more or less compatible problem definitions, without any real opportunity for readers to assess their relative performance. Inspired by the successful communities around MILP, SAT, TSP, VRP, etc., we introduce a common problem definition and file format, DISPLIB, which captures all the main features of train re-routing and re-scheduling. We have gathered problem instances from multiple real-world use cases and made them openly available. In this paper, we describe the problem definition, the industrial instances, and a reference solver implementation. This allows any researcher or developer to work on the train dispatching problem without an industrial connection, and enables the research community to perform empirical comparisons between solvers. All materials are available online at https://displib.github.io.
Authors: Gautam Sreekumar, Vishnu Naresh Boddeti
Abstract: Large multimodal models (LMMs) encode universal physical laws observed during training, such as momentum conservation, as parametric knowledge. It allows LMMs to answer physical reasoning queries, such as the outcome of a potential collision event from visual input. However, since parametric knowledge includes only the physical laws seen during training, it is insufficient for reasoning when the inference scenario violates these physical laws. In contrast, humans possess the skill to adapt their physical reasoning to unseen physical environments from a few visual examples. This ability, which we refer to as inductive physical reasoning, is indispensable for LMMs if they are to replace human agents in safety-critical applications. Despite its importance, existing visual benchmarks evaluate only the parametric knowledge in LMMs, and not inductive physical reasoning. To this end, we propose InPhyRe, the first visual question answering benchmark to measure inductive physical reasoning in LMMs. InPhyRe evaluates LMMs on their ability to predict the outcome of collision events in algorithmically generated synthetic collision videos. By inspecting 13 LMMs, InPhyRe informs us that (1) LMMs struggle to apply their limited parametric knowledge about universal physical laws to reasoning, (2) inductive physical reasoning in LMMs is weak when demonstration samples violate universal physical laws, and (3) inductive physical reasoning in LMMs suffers from language bias and largely ignores the visual inputs, questioning the trustworthiness of LMMs regarding visual inputs.
Authors: Liangqi Yuan, Dong-Jun Han, Christopher G. Brinton, Sabine Brunswicker
Abstract: The rise of large language models (LLMs) has made natural language-driven route planning an emerging research area that encompasses rich user objectives. Current research exhibits two distinct approaches: direct route planning using LLM-as-Agent and graph-based searching strategies. However, LLMs in the former approach struggle to handle extensive map data, while the latter shows limited capability in understanding natural language preferences. Additionally, a more critical challenge arises from the highly heterogeneous and unpredictable spatio-temporal distribution of users across the globe. In this paper, we introduce a novel LLM-Assisted route Planning (LLMAP) system that employs an LLM-as-Parser to comprehend natural language, identify tasks, and extract user preferences and recognize task dependencies, coupled with a Multi-Step Graph construction with iterative Search (MSGS) algorithm as the underlying solver for optimal route finding. Our multi-objective optimization approach adaptively tunes objective weights to maximize points of interest (POI) quality and task completion rate while minimizing route distance, subject to three key constraints: user time limits, POI opening hours, and task dependencies. We conduct extensive experiments using 1,000 routing prompts sampled with varying complexity across 14 countries and 27 cities worldwide. The results demonstrate that our approach achieves superior performance with guarantees across multiple constraints.
Authors: Mohammadreza Narimani, Ali Hajiahmad, Ali Moghimi, Reza Alimardani, Shahin Rafiee, Amir Hossein Mirzabe
Abstract: Controlling environmental conditions and monitoring plant status in greenhouses is critical to promptly making appropriate management decisions aimed at promoting crop production. The primary objective of this research study was to develop and test a smart aeroponic greenhouse on an experimental scale where the status of Geranium plant and environmental conditions are continuously monitored through the integration of the internet of things (IoT) and artificial intelligence (AI). An IoT-based platform was developed to control the environmental conditions of plants more efficiently and provide insights to users to make informed management decisions. In addition, we developed an AI-based disease detection framework using VGG-19, InceptionResNetV2, and InceptionV3 algorithms to analyze the images captured periodically after an intentional inoculation. The performance of the AI framework was compared with an expert's evaluation of disease status. Preliminary results showed that the IoT system implemented in the greenhouse environment is able to publish data such as temperature, humidity, water flow, and volume of charge tanks online continuously to users and adjust the controlled parameters to provide an optimal growth environment for the plants. Furthermore, the results of the AI framework demonstrate that the VGG-19 algorithm was able to identify drought stress and rust leaves from healthy leaves with the highest accuracy, 92% among the other algorithms.
Authors: Sasi Kiran Gaddipati, Farhana Keya, Gollam Rabby, S\"oren Auer
Abstract: Advances in AI-assisted research have introduced powerful tools for literature retrieval, hypothesis generation, experimentation, and manuscript preparation. However, systems remain fragmented and lack human-centred workflows. To address these gaps, we introduce AIssistant, an agentic, open-source Human-AI collaborative framework designed to simplify the end-to-end creation of scientific workflows. Since our development is still in an early stage, we present here the first experiments with AIssistant for perspective and review research papers in machine learning. Our system integrates modular tools and agents for literature synthesis, section-wise experimentation, citation management, and automatic LaTeX paper text generation, while maintaining human oversight at every stage to ensure accuracy, coherence, and scholarly rigour. We conducted a comprehensive evaluation across three layers: (1) Independent Human Review, following NeurIPS double-blind standards; (2) Automated LLM Review, using GPT-5 as a scalable human review proxy; and (3) Program Chair Oversight, where the chair monitors the entire review process and makes final validation and acceptance decisions. The results demonstrate that AIssistant improves drafting efficiency and thematic consistency. Nonetheless, Human-AI collaboration remains essential for maintaining factual correctness, methodological soundness, and ethical compliance. Despite its effectiveness, we identify key limitations, including hallucinated citations, difficulty adapting to dynamic paper structures, and incomplete integration of multimodal content.
Authors: Danielle Cohen, Yoni Halpern, Noam Kahlon, Joel Oren, Omri Berkovitch, Sapir Caduri, Ido Dagan, Anatoly Efros
Abstract: Understanding user intents from UI interaction trajectories remains a challenging, yet crucial, frontier in intelligent agent development. While massive, datacenter-based, multi-modal large language models (MLLMs) possess greater capacity to handle the complexities of such sequences, smaller models which can run on-device to provide a privacy-preserving, low-cost, and low-latency user experience, struggle with accurate intent inference. We address these limitations by introducing a novel decomposed approach: first, we perform structured interaction summarization, capturing key information from each user action. Second, we perform intent extraction using a fine-tuned model operating on the aggregated summaries. This method improves intent understanding in resource-constrained models, even surpassing the base performance of large MLLMs.
Authors: Jiahao Yu, Zelei Cheng, Xian Wu, Xinyu Xing
Abstract: Software engineering presents complex, multi-step challenges for Large Language Models (LLMs), requiring reasoning over large codebases and coordinated tool use. The difficulty of these tasks is exemplified by benchmarks like SWE-bench, where current LLMs still struggle to resolve real-world issues. A promising approach to enhance performance is test-time scaling (TTS), but its gains are heavily dependent on the diversity of model outputs. While standard alignment methods such as Direct Preference Optimization (DPO) and Kahneman-Tversky Optimization (KTO) are effective at aligning model outputs with human preferences, this process can come at the cost of reduced diversity, limiting the effectiveness of TTS. Additionally, existing preference optimization algorithms are typically designed for single-turn tasks and do not fully address the complexities of multi-turn reasoning and tool integration required for interactive coding agents. To bridge this gap, we introduce \sys, an entropy-enhanced framework that adapts existing preference optimization algorithms to the multi-turn, tool-assisted setting. \sys augments the preference objective to explicitly preserve policy entropy and generalizes learning to optimize over multi-turn interactions rather than single-turn responses. We validate \sys by fine-tuning a diverse suite of models from different families and sizes (up to 106B parameters). To maximize performance gains from TTS, we further propose a hybrid best-trajectory selection scheme combining a learned verifier model with model free approaches. On the \swebench leaderboard, our approach establishes new state-of-the-art results among open-weight models. A 30B parameter model trained with \sys ranks 1st on \lite and 4th on \verified on the open-weight leaderboard, surpassed only by models with over 10x more parameters(\eg$>$350B).
Authors: Dingrui Wang, Zhexiao Sun, Zhouheng Li, Cheng Wang, Youlun Peng, Hongyuan Ye, Baha Zarrouki, Wei Li, Mattia Piccinini, Lei Xie, Johannes Betz
Abstract: A major challenge in deploying world models is the trade-off between size and performance. Large world models can capture rich physical dynamics but require massive computing resources, making them impractical for edge devices. Small world models are easier to deploy but often struggle to learn accurate physics, leading to poor predictions. We propose the Physics-Informed BEV World Model (PIWM), a compact model designed to efficiently capture physical interactions in bird's-eye-view (BEV) representations. PIWM uses Soft Mask during training to improve dynamic object modeling and future prediction. We also introduce a simple yet effective technique, Warm Start, for inference to enhance prediction quality with a zero-shot model. Experiments show that at the same parameter scale (400M), PIWM surpasses the baseline by 60.6% in weighted overall score. Moreover, even when compared with the largest baseline model (400M), the smallest PIWM (130M Soft Mask) achieves a 7.4% higher weighted overall score with a 28% faster inference speed.
Authors: Ryan Lucas, Kayhan Behdin, Zhipeng Wang, Qingquan Song, Shao Tang, Rahul Mazumder
Abstract: Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression techniques such as neural network pruning produces greater performance loss than in typical language modeling tasks, and in some cases can make the model slower since they cause the model to produce more thinking tokens but with worse performance. We show that this is partly due to the fact that standard LLM pruning methods often focus on input reconstruction, whereas reasoning is a decode-dominated task. We introduce a simple, drop-in fix: during pruning we jointly reconstruct activations from the input and the model's on-policy chain-of-thought traces. This "Reasoning-Aware Compression" (RAC) integrates seamlessly into existing pruning workflows such as SparseGPT, and boosts their performance significantly. Code reproducing the results in the paper can be found at: https://github.com/RyanLucas3/RAC
Authors: Yiwen Lu, Lu Li, Dazheng Zhang, Xinyao Jian, Tingyin Wang, Siqi Chen, Yuqing Lei, Jiayi Tong, Zhaohan Xi, Haitao Chu, Chongliang Luo, Alexis Ogdie, Brian Athey, Alparslan Turan, Michael Abramoff, Joseph C Cappelleri, Hua Xu, Yun Lu, Jesse Berlin, Daniel I. Sessler, David A. Asch, Xiaoqian Jiang, Yong Chen
Abstract: Sample size calculations for power analysis are critical for clinical research and trial design, yet their complexity and reliance on statistical expertise create barriers for many researchers. We introduce PowerGPT, an AI-powered system integrating large language models (LLMs) with statistical engines to automate test selection and sample size estimation in trial design. In a randomized trial to evaluate its effectiveness, PowerGPT significantly improved task completion rates (99.3% vs. 88.9% for test selection, 99.3% vs. 77.8% for sample size calculation) and accuracy (94.1% vs. 55.4% in sample size estimation, p < 0.001), while reducing average completion time (4.0 vs. 9.3 minutes, p < 0.001). These gains were consistent across various statistical tests and benefited both statisticians and non-statisticians as well as bridging expertise gaps. Already under deployment across multiple institutions, PowerGPT represents a scalable AI-driven approach that enhances accessibility, efficiency, and accuracy in statistical power analysis for clinical research.
Authors: G\"ulce Karde\c{s}, David Krakauer, Joshua Grochow
Abstract: Cognitive science and theoretical computer science both seek to classify and explain the difficulty of tasks. Mechanisms of intelligence are those that reduce task difficulty. Here we map concepts from the computational complexity of a physical puzzle, the Soma Cube, onto cognitive problem-solving strategies through a ``Principle of Materiality''. By analyzing the puzzle's branching factor, measured through search tree outdegree, we quantitatively assess task difficulty and systematically examine how different strategies modify complexity. We incrementally refine a trial-and-error search by layering preprocessing (cognitive chunking), value ordering (cognitive free-sorting), variable ordering (cognitive scaffolding), and pruning (cognitive inference). We discuss how the competent use of artifacts reduces effective time complexity by exploiting physical constraints and propose a model of intelligence as a library of algorithms that recruit the capabilities of both mind and matter.
Authors: Rohit Chakraborty, Subasish Das
Abstract: Roundabouts reduce severe crashes, yet risk patterns vary by conditions. This study analyzes 2017-2021 Ohio roundabout crashes using a two-step, explainable workflow. Cluster Correspondence Analysis (CCA) identifies co-occurring factors and yields four crash patterns. A tree-based severity model is then interpreted with SHAP to quantify drivers of injury within and across patterns. Results show higher severity when darkness, wet surfaces, and higher posted speeds coincide with fixed-object or angle events, and lower severity in clear, low-speed settings. Pattern-specific explanations highlight mechanisms at entries (fail-to-yield, gap acceptance), within multi-lane circulation (improper maneuvers), and during slow-downs (rear-end). The workflow links pattern discovery with case-level explanations, supporting site screening, countermeasure selection, and audit-ready reporting. The contribution to Information Systems is a practical template for usable XAI in public safety analytics.
Authors: Nicholas Pipitone, Ghita Houir Alami, Advaith Avadhanam, Anton Kaminskyi, Ashley Khoo
Abstract: We introduce a novel training methodology named zELO, which optimizes retrieval performance via the analysis that ranking tasks are statically equivalent to a Thurstone model. Based on the zELO method, we use unsupervised data in order train a suite of state-of-the-art open-weight reranker models: zerank-1 and zerank-1-small. These models achieve the highest retrieval scores in multiple domains, including finance, legal, code, and STEM, outperforming closed-source proprietary rerankers on both NDCG@10 and Recall. These models also demonstrate great versatility, maintaining their 0-shot performance on out-of-domain and private customer datasets. The training data included 112,000 queries and 100 documents per query, and was trained end-to-end from unannotated queries and documents in less than 10,000 H100-hours.
Authors: Harshit Rajgarhia, Shivali Dalmia, Mengyang Zhao, Mukherji Abhishek, Kiran Ganesh
Abstract: Adapting advertisements for multilingual audiences requires more than simple text translation; it demands preservation of visual consistency, spatial alignment, and stylistic integrity across diverse languages and formats. We introduce a structured framework that combines automated components with human oversight to address the complexities of advertisement localization. To the best of our knowledge, this is the first work to integrate scene text detection, inpainting, machine translation (MT), and text reimposition specifically for accelerating ad localization evaluation workflows. Qualitative results across six locales demonstrate that our approach produces semantically accurate and visually coherent localized advertisements, suitable for deployment in real-world workflows.
Authors: Garima Agrawal, Riccardo De Maria, Kiran Davuluri, Daniele Spera, Charlie Read, Cosimo Spera, Jack Garrett, Don Miller
Abstract: Despite advances in AI for contact centers, customer experience (CX) continues to suffer from high average handling time (AHT), low first-call resolution, and poor customer satisfaction (CSAT). A key driver is the cognitive load on agents, who must navigate fragmented systems, troubleshoot manually, and frequently place customers on hold. Existing AI-powered agent-assist tools are often reactive driven by static rules, simple prompting, or retrieval-augmented generation (RAG) without deeper contextual reasoning. We introduce Agentic AI goal-driven, autonomous, tool-using systems that proactively support agents in real time. Unlike conventional approaches, Agentic AI identifies customer intent, triggers modular workflows, maintains evolving context, and adapts dynamically to conversation state. This paper presents a case study of Minerva CQ, a real-time Agent Assist product deployed in voice-based customer support. Minerva CQ integrates real-time transcription, intent and sentiment detection, entity recognition, contextual retrieval, dynamic customer profiling, and partial conversational summaries enabling proactive workflows and continuous context-building. Deployed in live production, Minerva CQ acts as an AI co-pilot, delivering measurable improvements in agent efficiency and customer experience across multiple deployments.
Authors: Aaron Baughman, Gozde Akay, Eduardo Morales, Rahul Agarwal, Preetika Srivastava
Abstract: We present Match Chat, a real-time, agent-driven assistant designed to enhance the tennis fan experience by delivering instant, accurate responses to match-related queries. Match Chat integrates Generative Artificial Intelligence (GenAI) with Generative Computing (GenComp) techniques to synthesize key insights during live tennis singles matches. The system debuted at the 2025 Wimbledon Championships and the 2025 US Open, where it provided about 1 million users with seamless access to streaming and static data through natural language queries. The architecture is grounded in an Agent-Oriented Architecture (AOA) combining rule engines, predictive models, and agents to pre-process and optimize user queries before passing them to GenAI components. The Match Chat system had an answer accuracy of 92.83% with an average response time of 6.25 seconds under loads of up to 120 requests per second (RPS). Over 96.08% of all queries were guided using interactive prompt design, contributing to a user experience that prioritized clarity, responsiveness, and minimal effort. The system was designed to mask architectural complexity, offering a frictionless and intuitive interface that required no onboarding or technical familiarity. Across both Grand Slam deployments, Match Chat maintained 100% uptime and supported nearly 1 million unique users, underscoring the scalability and reliability of the platform. This work introduces key design patterns for real-time, consumer-facing AI systems that emphasize speed, precision, and usability that highlights a practical path for deploying performant agentic systems in dynamic environments.
Authors: Minyu Chen, Guoqiang Li
Abstract: The performance of Conflict-Driven Clause Learning solvers hinges on internal heuristics, yet the heterogeneity of SAT problems makes a single, universally optimal configuration unattainable. While prior automated methods can find specialized configurations for specific problem families, this dataset-specific approach lacks generalizability and requires costly re-optimization for new problem types. We introduce DaSAThco, a framework that addresses this challenge by learning a generalizable mapping from instance features to tailored heuristic ensembles, enabling a train-once, adapt-broadly model. Our framework uses a Large Language Model, guided by systematically defined Problem Archetypes, to generate a diverse portfolio of specialized heuristic ensembles and subsequently learns an adaptive selection mechanism to form the final mapping. Experiments show that DaSAThco achieves superior performance and, most notably, demonstrates robust out-of-domain generalization where non-adaptive methods show limitations. Our work establishes a more scalable and practical path toward automated algorithm design for complex, configurable systems.
Authors: Anmol Singhal Navya Singhal
Abstract: Financial news sentiment analysis is crucial for anticipating market movements. With the rise of AI techniques such as Large Language Models (LLMs), which demonstrate strong text understanding capabilities, there has been renewed interest in enhancing these systems. Existing methods, however, often struggle to capture the complex economic context of news and lack transparent reasoning, which undermines their reliability. We propose Analogy-Driven Financial Chain-of-Thought (AD-FCoT), a prompting framework that integrates analogical reasoning with chain-of-thought (CoT) prompting for sentiment prediction on historical financial news. AD-FCoT guides LLMs to draw parallels between new events and relevant historical scenarios with known outcomes, embedding these analogies into a structured, step-by-step reasoning chain. To our knowledge, this is among the first approaches to explicitly combine analogical examples with CoT reasoning in finance. Operating purely through prompting, AD-FCoT requires no additional training data or fine-tuning and leverages the model's internal financial knowledge to generate rationales that mirror human analytical reasoning. Experiments on thousands of news articles show that AD-FCoT outperforms strong baselines in sentiment classification accuracy and achieves substantially higher correlation with market returns. Its generated explanations also align with domain expertise, providing interpretable insights suitable for real-world financial analysis.
Authors: Daojun Chen, Xi Wang, Shenyuan Ren, Qingzhi Ma, Pengpeng Zhao, An Liu
Abstract: While Large Language Models have significantly advanced Text2SQL generation, a critical semantic gap persists where syntactically valid queries often misinterpret user intent. To mitigate this challenge, we propose GBV-SQL, a novel multi-agent framework that introduces Guided Generation with SQL2Text Back-translation Validation. This mechanism uses a specialized agent to translate the generated SQL back into natural language, which verifies its logical alignment with the original question. Critically, our investigation reveals that current evaluation is undermined by a systemic issue: the poor quality of the benchmarks themselves. We introduce a formal typology for "Gold Errors", which are pervasive flaws in the ground-truth data, and demonstrate how they obscure true model performance. On the challenging BIRD benchmark, GBV-SQL achieves 63.23% execution accuracy, a 5.8% absolute improvement. After removing flawed examples, GBV-SQL achieves 96.5% (dev) and 97.6% (test) execution accuracy on the Spider benchmark. Our work offers both a robust framework for semantic validation and a critical perspective on benchmark integrity, highlighting the need for more rigorous dataset curation.
Authors: Muhammad Riaz Hasib Hossain, Rafiqul Islam, Shawn R McGrath, Md Zahidul Islam, David Lamb
Abstract: Forecasting mob based cattle weight gain (MB CWG) may benefit large livestock farms, allowing farmers to refine their feeding strategies, make educated breeding choices, and reduce risks linked to climate variability and market fluctuations. In this paper, a novel technique termed MB CWG is proposed to forecast the one month advanced weight gain of herd based cattle using historical data collected from the Charles Sturt University Farm. This research employs a Random Forest (RF) model, comparing its performance against Support Vector Regression (SVR) and Long Short Term Memory (LSTM) models for monthly weight gain prediction. Four datasets were used to evaluate the performance of models, using 756 sample data from 108 herd-based cattle, along with weather data (rainfall and temperature) influencing CWG. The RF model performs better than the SVR and LSTM models across all datasets, achieving an R^2 of 0.973, RMSE of 0.040, and MAE of 0.033 when both weather and age factors were included. The results indicate that including both weather and age factors significantly improves the accuracy of weight gain predictions, with the RF model outperforming the SVR and LSTM models in all scenarios. These findings demonstrate the potential of RF as a robust tool for forecasting cattle weight gain in variable conditions, highlighting the influence of age and climatic factors on herd based weight trends. This study has also developed an innovative automated pre processing tool to generate a benchmark dataset for MB CWG predictive models. The tool is publicly available on GitHub and can assist in preparing datasets for current and future analytical research..
Authors: Yong Xia, Jingxuan Li, YeTeng Sun, Jiarui Bu
Abstract: Large Language Models (LLMs) hold significant promise for electrocardiogram (ECG) analysis, yet challenges remain regarding transferability, time-scale information learning, and interpretability. Current methods suffer from model-specific ECG encoders, hindering transfer across LLMs. Furthermore, LLMs struggle to capture crucial time-scale information inherent in ECGs due to Transformer limitations. And their black-box nature limits clinical adoption. To address these limitations, we introduce ECG-aBcDe, a novel ECG encoding method that transforms ECG signals into a universal ECG language readily interpretable by any LLM. By constructing a hybrid dataset of ECG language and natural language, ECG-aBcDe enables direct fine-tuning of pre-trained LLMs without architectural modifications, achieving "construct once, use anywhere" capability. Moreover, the bidirectional convertibility between ECG and ECG language of ECG-aBcDe allows for extracting attention heatmaps from ECG signals, significantly enhancing interpretability. Finally, ECG-aBcDe explicitly represents time-scale information, mitigating Transformer limitations. This work presents a new paradigm for integrating ECG analysis with LLMs. Compared with existing methods, our method achieves competitive performance on ROUGE-L and METEOR. Notably, it delivers significant improvements in the BLEU-4, with improvements of 2.8 times and 3.9 times in in-dataset and cross-dataset evaluations, respectively, reaching scores of 42.58 and 30.76. These results provide strong evidence for the feasibility of the new paradigm.
Authors: Beidan Liu, Zhengqiu Zhu, Chen Gao, Yong Zhao, Wei Qi, Quanjun Yin
Abstract: Nonlinear Combinatorial Optimization Problems (NCOPs) present a formidable computational hurdle in practice, as their nonconvex nature gives rise to multi-modal solution spaces that defy efficient optimization. Traditional constraint relaxation approaches rely heavily on expert-driven, iterative design processes that lack systematic automation and scalable adaptability. While recent Large Language Model (LLM)-based optimization methods show promise for autonomous problem-solving, they predominantly function as passive constraint validators rather than proactive strategy architects, failing to handle the sophisticated constraint interactions inherent to NCOPs.To address these limitations, we introduce the first end-to-end \textbf{Auto}mated \textbf{C}onstraint \textbf{O}ptimization (AutoCO) method, which revolutionizes NCOPs resolution through learning to relax with LLMs.Specifically, we leverage structured LLM reasoning to generate constraint relaxation strategies, which are dynamically evolving with algorithmic principles and executable code through a unified triple-representation scheme. We further establish a novel bidirectional (global-local) coevolution mechanism that synergistically integrates Evolutionary Algorithms for intensive local refinement with Monte Carlo Tree Search for systematic global strategy space exploration, ensuring optimal balance between intensification and diversification in fragmented solution spaces. Finally, comprehensive experiments on three challenging NCOP benchmarks validate AutoCO's consistent effectiveness and superior performance over the baselines.
Authors: Lachlan McGinness, Peter Baumgartner
Abstract: We present a longitudinal study which evaluates the reasoning capability of frontier Large Language Models over an eighteen month period. We measured the accuracy of three leading models from December 2023, September 2024 and June 2025 on true or false questions from the PrOntoQA dataset and their faithfulness to reasoning strategies provided through in-context learning. The improvement in performance from 2023 to 2024 can be attributed to hidden Chain of Thought prompting. The introduction of thinking models allowed for significant improvement in model performance between 2024 and 2025. We then present a neuro-symbolic architecture which uses LLMs of less than 15 billion parameters to translate the problems into a standardised form. We then parse the standardised forms of the problems into a program to be solved by Z3, an SMT solver, to determine the satisfiability of the query. We report the number of prompt and completion tokens as well as the computational cost in FLOPs for open source models. The neuro-symbolic approach significantly reduces the computational cost while maintaining near perfect performance. The common approximation that the number of inference FLOPs is double the product of the active parameters and total tokens was accurate within 10\% for all experiments.
Authors: Hanqing Li, Kiran Sheena Jyothi, Henry Liang, Sharika Mahadevan, Diego Klabjan
Abstract: We propose a new, training-free method, Graph Reasoning via Retrieval Augmented Framework (GRRAF), that harnesses retrieval-augmented generation (RAG) alongside the code-generation capabilities of large language models (LLMs) to address a wide range of graph reasoning tasks. In GRRAF, the target graph is stored in a graph database, and the LLM is prompted to generate executable code queries that retrieve the necessary information. This approach circumvents the limitations of existing methods that require extensive finetuning or depend on predefined algorithms, and it incorporates an error feedback loop with a time-out mechanism to ensure both correctness and efficiency. Experimental evaluations on the GraphInstruct dataset reveal that GRRAF achieves 100% accuracy on most graph reasoning tasks, including cycle detection, bipartite graph checks, shortest path computation, and maximum flow, while maintaining consistent token costs regardless of graph sizes. Imperfect but still very high performance is observed on subgraph matching. Notably, GRRAF scales effectively to large graphs with up to 10,000 nodes.
Authors: Shicheng Ye, Chao Yu, Kaiqiang Ke, Chengdong Xu, Yinqi Wei
Abstract: Large language model (LLM)-based agents have shown strong potential in multi-task scenarios, owing to their ability to transfer knowledge across diverse tasks. However, existing approaches often treat prior experiences and knowledge as monolithic units, leading to inefficient and coarse-grained knowledge transfer. In this work, we propose a novel hierarchical memory architecture that enables fine-grained knowledge transfer by decoupling high-level planning memory from low-level execution memory. To construct and refine these hierarchical memories, we introduce Hierarchical Hindsight Reflection (H$^2$R), a mechanism that distills reusable and hierarchical knowledge from past agent-environment interactions. At test time, H$^2$R performs retrievals of high-level and low-level memories separately, allowing LLM-based agents to efficiently access and utilize task-relevant knowledge for new tasks.Experimental results across two benchmarks demonstrate that H$^2$R can improve generalization and decision-making performance, outperforming prior baselines such as Expel.
Authors: Jiaqi Wang, Binquan Ji, Haibo Luo, Yiyang Qi, Ruiting Li, Huiyan Wang, Yuantao Han, Cangyi Yang, jiaxu Zhang, Feiliang Ren
Abstract: Complex Reasoning in Large Language Models can be dynamically optimized using Test-Time Scaling (TTS) to mitigate Overthinking. Methods such as Coconut, SoftCoT and its variant are effective in continuous latent space inference, the core bottleneck still lies in the efficient generation and utilization of high-quality Latent Thought. Drawing from the theory of SoftCoT++ that a larger variance in the generated Latent Thought distribution more closely approximates the golden truth distribution, we propose a Latent Thought-Augmented Training Framework--LTA-Thinker, which improves distributional variance and enhances reasoning performance from two perspectives. First, LTA-Thinker constructs a Latent Thought generation architecture based on a learnable prior. This architecture aims to increase the variance distribution of generated Latent Thought Vectors in order to simplify the overall structure and raise the performance ceiling. Second, LTA-Thinker introduces a distribution-based directional optimization paradigm that jointly constrains both distribution locality and distribution scale. This mechanism improves information efficiency and computational cost through a multi-objective co-training strategy, which combines standard Supervised Fine-Tuning (SFT) loss with two novel losses: Semantic Alignment Loss, which utilizes KL divergence to ensure that the Latent Thought is highly relevant to the semantics of the question; Reasoning Focus Loss, which utilizes a contrastive learning mechanism to guide the model to focus on the most critical reasoning steps. Experiments show that LTA-thinker achieves state-of-the-art (SOTA) performance among various baselines and demonstrates a higher performance ceiling and better scaling effects.
Authors: Tairan Fu, David Campo-Nazareno, Javier Coronado-Bl\'azquez, Javier Conde, Pedro Reviriego, Fabrizio Lombardi
Abstract: Large Language Models (LLMs) are capable of solving complex math problems or answer difficult questions on almost any topic, but can they generate random street addresses for European cities?
Authors: Jai Singla, Peal Jotania, Keivalya Pandya
Abstract: Population estimation is crucial for various applications, from resource allocation to urban planning. Traditional methods such as surveys and censuses are expensive, time-consuming and also heavily dependent on human resources, requiring significant manpower for data collection and processing. In this study a deep learning solution is proposed to estimate population using high resolution (0.3 m) satellite imagery, Digital Elevation Models (DEM) of 0.5m resolution and vector boundaries. Proposed method combines Convolution Neural Network (CNN) architecture for classification task to classify buildings as residential and non-residential and Artificial Neural Network (ANN) architecture to estimate the population. Approx. 48k building footprints over Gandhinagar urban area are utilized containing both residential and non-residential, with residential categories further used for building-level population estimation. Experimental results on a large-scale dataset demonstrate the effectiveness of our model, achieving an impressive overall F1-score of 0.9936. The proposed system employs advanced geospatial analysis with high spatial resolution to estimate Gandhinagar population at 278,954. By integrating real-time data updates, standardized metrics, and infrastructure planning capabilities, this automated approach addresses critical limitations of conventional census-based methodologies. The framework provides municipalities with a scalable and replicable tool for optimized resource management in rapidly urbanizing cities, showcasing the efficiency of AI-driven geospatial analytics in enhancing data-driven urban governance.
Authors: Xingxing Hong, Yungong Wang, Dexin Jin, Ye Yuan, Ximing Huang, Zijian Wu, Wenxin Li
Abstract: Benchmarks are crucial for assessing multi-agent reinforcement learning (MARL) algorithms. While StarCraft II-related environments have driven significant advances in MARL, existing benchmarks like SMAC focus primarily on micromanagement, limiting comprehensive evaluation of high-level strategic intelligence. To address this, we introduce HLSMAC, a new cooperative MARL benchmark with 12 carefully designed StarCraft II scenarios based on classical stratagems from the Thirty-Six Stratagems. Each scenario corresponds to a specific stratagem and is designed to challenge agents with diverse strategic elements, including tactical maneuvering, timing coordination, and deception, thereby opening up avenues for evaluating high-level strategic decision-making capabilities. We also propose novel metrics across multiple dimensions beyond conventional win rate, such as ability utilization and advancement efficiency, to assess agents' overall performance within the HLSMAC environment. We integrate state-of-the-art MARL algorithms and LLM-based agents with our benchmark and conduct comprehensive experiments. The results demonstrate that HLSMAC serves as a robust testbed for advancing multi-agent strategic decision-making.
Authors: Jeremias Ferrao, Matthijs van der Lende, Ilija Lichkovski, Clement Neo
Abstract: Aligning large language models is critical for their usability and safety. However, the prevailing approach of Reinforcement Learning from Human Feedback (RLHF) induces diffuse, opaque parameter changes, making it difficult to discern what the model has internalized. Hence, we introduce Feature Steering with Reinforcement Learning (FSRL), a transparent alignment framework that trains a lightweight adapter to steer behavior by modulating interpretable features from a Sparse Autoencoder (SAE). First, we demonstrate that FSRL is an effective method for preference optimization and is comparable with current RLHF methods. We then perform mechanistic analysis on the trained adapter, and find that its policy systematically promotes style features over explicit alignment concepts, suggesting that the preference optimization process rewards stylistic presentation as a proxy for quality. Ultimately, we hope that FSRL provides a tool for both interpretable model control and diagnosing the internal mechanisms of alignment.
Authors: Shilian Chen, Jie Zhou, Tianyu Huai, Yujiang Lu, Junsong Li, Bihao Zhan, Qianjun Pan, Yutao Yang, Xin Li, Qin Chen, Hang Yan, Liang He
Abstract: Model merging refers to the process of integrating multiple distinct models into a unified model that preserves and combines the strengths and capabilities of the individual models. Most existing approaches rely on task vectors to combine models, typically under the assumption that model parameters are accessible. However, for extremely large language models (LLMs) such as GPT-4, which are often provided solely as black-box services through API interfaces (Language-Model-as-a-Service), model weights are not available to end users. This presents a significant challenge, which we refer to as black-box model merging (BMM) with massive LLMs. To address this challenge, we propose a derivative-free optimization framework based on the evolutionary algorithm (Evo-Merging) that enables effective model merging using only inference-time API queries. Our method consists of two key components: (1) sparsity-based denoising, designed to identify and filter out irrelevant or redundant information across models, and (2) sign-aware scaling, which dynamically computes optimal combination weights for the relevant models based on their performance. We also provide a formal justification, along with a theoretical analysis, for our asymmetric sparsification. Extensive experimental evaluations demonstrate that our approach achieves state-of-the-art results on a range of tasks, significantly outperforming existing strong baselines.
Authors: Bihao Zhan, Jie Zhou, Junsong Li, Yutao Yang, Shilian Chen, Qianjun Pan, Xin Li, Wen Wu, Xingjiao Wu, Qin Chen, Hang Yan, Liang He
Abstract: Continual Learning (CL) models, while adept at sequential knowledge acquisition, face significant and often overlooked privacy challenges due to accumulating diverse information. Traditional privacy methods, like a uniform Differential Privacy (DP) budget, indiscriminately protect all data, leading to substantial model utility degradation and hindering CL deployment in privacy-sensitive areas. To overcome this, we propose a privacy-enhanced continual learning (PeCL) framework that forgets what's sensitive and remembers what matters. Our approach first introduces a token-level dynamic Differential Privacy strategy that adaptively allocates privacy budgets based on the semantic sensitivity of individual tokens. This ensures robust protection for private entities while minimizing noise injection for non-sensitive, general knowledge. Second, we integrate a privacy-guided memory sculpting module. This module leverages the sensitivity analysis from our dynamic DP mechanism to intelligently forget sensitive information from the model's memory and parameters, while explicitly preserving the task-invariant historical knowledge crucial for mitigating catastrophic forgetting. Extensive experiments show that PeCL achieves a superior balance between privacy preserving and model utility, outperforming baseline models by maintaining high accuracy on previous tasks while ensuring robust privacy.
Authors: Yarin Benyamin, Argaman Mordoch, Shahaf S. Shperberg, Roni Stern
Abstract: Large Language Models (LLMs) are increasingly being used as autonomous agents capable of performing complicated tasks. However, they lack the ability to perform reliable long-horizon planning on their own. This paper bridges this gap by introducing the Planning Copilot, a chatbot that integrates multiple planning tools and allows users to invoke them through instructions in natural language. The Planning Copilot leverages the Model Context Protocol (MCP), a recently developed standard for connecting LLMs with external tools and systems. This approach allows using any LLM that supports MCP without domain-specific fine-tuning. Our Planning Copilot supports common planning tasks such as checking the syntax of planning problems, selecting an appropriate planner, calling it, validating the plan it generates, and simulating their execution. We empirically evaluate the ability of our Planning Copilot to perform these tasks using three open-source LLMs. The results show that the Planning Copilot highly outperforms using the same LLMs without the planning tools. We also conducted a limited qualitative comparison of our tool against Chat GPT-5, a very recent commercial LLM. Our results shows that our Planning Copilot significantly outperforms GPT-5 despite relying on a much smaller LLM. This suggests dedicated planning tools may be an effective way to enable LLMs to perform planning tasks.
Authors: Shinichi Honna, Taichi Murayama, Akira Matsui
Abstract: The Anna Karenina Principle (AKP) holds that success requires satisfying a small set of essential conditions, whereas failure takes diverse forms. We test AKP, its reverse, and two further patterns described as ordered and noisy across novels, online encyclopedias, research papers, and movies. Texts are represented as sequences of functional blocks, and convergence is assessed in transition order and position. Results show that structural principles vary by medium: novels follow reverse AKP in order, Wikipedia combines AKP with ordered patterns, academic papers display reverse AKP in order but remain noisy in position, and movies diverge by genre. Success therefore depends on structural constraints that are specific to each medium, while failure assumes different shapes across domains.
Authors: Yuyang Tian, Shunqiang Mao, Wenchang Gao, Lanlan Qiu, Tianxing He
Abstract: Large Language Models (LLMs) have revolutionized the simulation of agent societies, enabling autonomous planning, memory formation, and social interactions. However, existing frameworks often overlook systematic evaluations for event organization and lack visualized integration with physically grounded environments, limiting agents' ability to navigate spaces and interact with items realistically. We develop MiniAgentPro, a visualization platform featuring an intuitive map editor for customizing environments and a simulation player with smooth animations. Based on this tool, we introduce a comprehensive test set comprising eight diverse event scenarios with basic and hard variants to assess agents' ability. Evaluations using GPT-4o demonstrate strong performance in basic settings but highlight coordination challenges in hard variants.
Authors: Marylou Fauchard, Florian Carichon, Margarida Carvalho, Golnoosh Farnadi
Abstract: Recent advances in reasoning with large language models (LLMs) have demonstrated strong performance on complex mathematical tasks, including combinatorial optimization. Techniques such as Chain-of-Thought and In-Context Learning have further enhanced this capability, making LLMs both powerful and accessible tools for a wide range of users, including non-experts. However, applying LLMs to matching problems, which require reasoning under preferential and structural constraints, remains underexplored. To address this gap, we introduce a novel benchmark of 369 instances of the College Admission Problem, a canonical example of a matching problem with preferences, to evaluate LLMs across key dimensions: feasibility, stability, and optimality. We employ this benchmark to assess the performance of several open-weight LLMs. Our results first reveal that while LLMs can satisfy certain constraints, they struggle to meet all evaluation criteria consistently. They also show that reasoning LLMs, like QwQ and GPT-oss, significantly outperform traditional models such as Llama, Qwen or Mistral, defined here as models used without any dedicated reasoning mechanisms. Moreover, we observed that LLMs reacted differently to the various prompting strategies tested, which include Chain-of-Thought, In-Context Learning and role-based prompting, with no prompt consistently offering the best performance. Finally, we report the performances from iterative prompting with auto-generated feedback and show that they are not monotonic; they can peak early and then significantly decline in later attempts. Overall, this work offers a new perspective on model reasoning performance and the effectiveness of prompting strategies in combinatorial optimization problems with preferential constraints.
Authors: Henrik Axelsen, Valdemar Licht, Jan Damsgaard
Abstract: The cost and complexity of financial crime compliance (FCC) continue to rise, often without measurable improvements in effectiveness. While AI offers potential, most solutions remain opaque and poorly aligned with regulatory expectations. This paper presents the design and deployment of an agentic AI system for FCC in digitally native financial platforms. Developed through an Action Design Research (ADR) process with a fintech firm and regulatory stakeholders, the system automates onboarding, monitoring, investigation, and reporting, emphasizing explainability, traceability, and compliance-by-design. Using artifact-centric modeling, it assigns clearly bounded roles to autonomous agents and enables task-specific model routing and audit logging. The contribution includes a reference architecture, a real-world prototype, and insights into how Agentic AI can reconfigure FCC workflows under regulatory constraints. Our findings extend IS literature on AI-enabled compliance by demonstrating how automation, when embedded within accountable governance structures, can support transparency and institutional trust in high-stakes, regulated environments.
Authors: Kanishk Garg, Saranya D., Sanal Kumar, Saurabh Singh, Anupam Purwar
Abstract: Workforce scheduling involves a variety of rule-based constraints-such as shift limits, staffing policies, working hour restrictions, and many similar scheduling rules-which can interact in conflicting ways, leading to infeasible models. Identifying the underlying causes of such infeasibility is critical for resolving scheduling issues and restoring feasibility. A common diagnostic approach is to compute Irreducible Infeasible Subsets (IISs): minimal sets of constraints that are jointly infeasible but become feasible when any one is removed. We consider models formulated using pseudo-Boolean constraints with inequality relations over binary variables, which naturally encode scheduling logic. Existing IIS extraction methods such as Additive Deletion and QuickXplain rely on repeated feasibility checks, often incurring large numbers of solver calls. Dual ray analysis, while effective for LP-based models, may fail when the relaxed problem is feasible but the underlying pseudo-Boolean model is not. To address these limitations, we propose Graph-based Conflict Set Extraction Algorithm (G-CSEA) to extract a conflict set, an approach inspired by Conflict-Driven Clause Learning (CDCL) in SAT solvers. Our method constructs an implication graph during constraint propagation and, upon detecting a conflict, traces all contributing constraints across both decision branches. The resulting conflict set can optionally be minimized using QuickXplain to produce an IIS.
Authors: Nadim Barakat, William Lotter
Abstract: Diabetic retinopathy (DR) is a leading cause of blindness worldwide, and AI systems can expand access to fundus photography screening. Current FDA-cleared systems primarily provide binary referral outputs, where this minimal output may limit clinical trust and utility. Yet, determining the most effective output format to enhance clinician-AI performance is an empirical challenge that is difficult to assess at scale. We evaluated multimodal large language models (MLLMs) for DR detection and their ability to simulate clinical AI assistance across different output types. Two models were tested on IDRiD and Messidor-2: GPT-4o, a general-purpose MLLM, and MedGemma, an open-source medical model. Experiments included: (1) baseline evaluation, (2) simulated AI assistance with synthetic predictions, and (3) actual AI-to-AI collaboration where GPT-4o incorporated MedGemma outputs. MedGemma outperformed GPT-4o at baseline, achieving higher sensitivity and AUROC, while GPT-4o showed near-perfect specificity but low sensitivity. Both models adjusted predictions based on simulated AI inputs, but GPT-4o's performance collapsed with incorrect ones, whereas MedGemma remained more stable. In actual collaboration, GPT-4o achieved strong results when guided by MedGemma's descriptive outputs, even without direct image access (AUROC up to 0.96). These findings suggest MLLMs may improve DR screening pipelines and serve as scalable simulators for studying clinical AI assistance across varying output configurations. Open, lightweight models such as MedGemma may be especially valuable in low-resource settings, while descriptive outputs could enhance explainability and clinician trust in clinical workflows.
Authors: Linyue Cai, Yuyang Cheng, Xiaoding Shao, Huiming Wang, Yong Zhao, Wei Zhang, Kang Li
Abstract: As artificial intelligence advances toward artificial general intelligence (AGI), the need for robust and human-like memory systems has become increasingly evident. Current memory architectures often suffer from limited adaptability, insufficient multimodal integration, and an inability to support continuous learning. To address these limitations, we propose a scenario-driven methodology that extracts essential functional requirements from representative cognitive scenarios, leading to a unified set of design principles for next-generation AI memory systems. Based on this approach, we introduce the \textbf{COgnitive Layered Memory Architecture (COLMA)}, a novel framework that integrates cognitive scenarios, memory processes, and storage mechanisms into a cohesive design. COLMA provides a structured foundation for developing AI systems capable of lifelong learning and human-like reasoning, thereby contributing to the pragmatic development of AGI.
Authors: Vincent Siu, Nathan W. Henry, Nicholas Crispino, Yang Liu, Dawn Song, Chenguang Wang
Abstract: While activation steering in large language models (LLMs) is a growing area of research, methods can often incur broader effects than desired. This motivates isolation of purer concept vectors to enable targeted interventions and understand LLM behavior at a more granular level. We present RepIt, a simple and data-efficient framework for isolating concept-specific representations. Across five frontier LLMs, RepIt enables precise interventions: it selectively suppresses refusal on targeted concepts while preserving refusal elsewhere, producing models that answer WMD-related questions while still scoring as safe on standard benchmarks. We further show that the corrective signal localizes to just 100-200 neurons and that robust target representations can be extracted from as few as a dozen examples on a single A6000. This efficiency raises a dual concern: manipulations can be performed with modest compute and data to extend to underrepresented data-scarce topics while evading existing benchmarks. By disentangling refusal vectors with RepIt, this work demonstrates that targeted interventions can counteract overgeneralization, laying the foundation for more granular control of model behavior.
Authors: Marjorie McShane, Sergei Nirenburg, Sanjay Oruganti, Jesse English
Abstract: Shapes of cognition is a new conceptual paradigm for the computational cognitive modeling of Language-Endowed Intelligent Agents (LEIAs). Shapes are remembered constellations of sensory, linguistic, conceptual, episodic, and procedural knowledge that allow agents to cut through the complexity of real life the same way as people do: by expecting things to be typical, recognizing patterns, acting by habit, reasoning by analogy, satisficing, and generally minimizing cognitive load to the degree situations permit. Atypical outcomes are treated using shapes-based recovery methods, such as learning on the fly, asking a human partner for help, or seeking an actionable, even if imperfect, situational understanding. Although shapes is an umbrella term, it is not vague: shapes-based modeling involves particular objectives, hypotheses, modeling strategies, knowledge bases, and actual models of wide-ranging phenomena, all implemented within a particular cognitive architecture. Such specificity is needed both to vet our hypotheses and to achieve our practical aims of building useful agent systems that are explainable, extensible, and worthy of our trust, even in critical domains. However, although the LEIA example of shapes-based modeling is specific, the principles can be applied more broadly, giving new life to knowledge-based and hybrid AI.
Authors: Zhiwei Zheng, Dongyin Hu, Mingmin Zhao
Abstract: Radio Frequency (RF) sensing has emerged as a powerful, privacy-preserving alternative to vision-based methods for indoor perception tasks. However, collecting high-quality RF data in dynamic and diverse indoor environments remains a major challenge. To address this, we introduce WaveVerse, a prompt-based, scalable framework that simulates realistic RF signals from generated indoor scenes with human motions. WaveVerse introduces a language-guided 4D world generator, which includes a state-aware causal transformer for human motion generation conditioned on spatial constraints and texts, and a phase-coherent ray tracing simulator that enables the simulation of accurate and coherent RF signals. Experiments demonstrate the effectiveness of our approach in conditioned human motion generation and highlight how phase coherence is applied to beamforming and respiration monitoring. We further present two case studies in ML-based high-resolution imaging and human activity recognition, demonstrating that WaveVerse not only enables data generation for RF imaging for the first time, but also consistently achieves performance gain in both data-limited and data-adequate scenarios.
Authors: Dong Liu, Yanxuan Yu
Abstract: Serving large language models (LLMs) efficiently remains challenging due to the high memory and latency overhead of key-value (KV) cache access during autoregressive decoding. We present \textbf{TinyServe}, a lightweight and extensible serving system for deploying tiny LLMs (e.g., TinyLLaMA, GPT2-345M) with support for structured KV sparsity, plugin-based token selection, and hardware-efficient attention kernels. Unlike prior simulation frameworks, TinyServe executes real-time decoding with configurable sparsity strategies and fine-grained instrumentation. To reduce decoding cost, we introduce a \textit{query-aware page selection} mechanism that leverages bounding-box metadata to estimate attention relevance between the query and KV cache blocks. This enables selective KV loading with minimal overhead and no model modifications. Our fused CUDA kernel integrates page scoring, sparse memory access, and masked attention in a single pass. Experiments show that TinyServe achieves up to \textbf{3.4x} speedup and over \textbf{2x} memory savings with negligible accuracy drop. Additional analysis of cache reuse, page hit rate, and multi-GPU scaling confirms its practicality as an efficient system-level design for LLM training and inference research on resource-constrained hardware.
Authors: Xinyu He, Chenhan Xiao, Haoran Li, Ruizhong Qiu, Zhe Xu, Yang Weng, Jingrui He, Hanghang Tong
Abstract: Modern power systems are becoming increasingly dynamic, with changing topologies and time-varying loads driven by renewable energy variability, electric vehicle adoption, and active grid reconfiguration. Despite these changes, publicly available test cases remain scarce, due to security concerns and the significant effort required to anonymize real systems. Such limitations call for generative tools that can jointly synthesize grid structure and nodal dynamics. However, modeling the joint distribution of network topology, branch attributes, bus properties, and dynamic load profiles remains a major challenge, while preserving physical feasibility and avoiding prohibitive computational costs. We present PowerGrow, a co-generative framework that significantly reduces computational overhead while maintaining operational validity. The core idea is dependence decomposition: the complex joint distribution is factorized into a chain of conditional distributions over feasible grid topologies, time-series bus loads, and other system attributes, leveraging their mutual dependencies. By constraining the generation process at each stage, we implement a hierarchical graph beta-diffusion process for structural synthesis, paired with a temporal autoencoder that embeds time-series data into a compact latent space, improving both training stability and sample fidelity. Experiments across benchmark settings show that PowerGrow not only outperforms prior diffusion models in fidelity and diversity but also achieves a 98.9\% power flow convergence rate and improved N-1 contingency resilience. This demonstrates its ability to generate operationally valid and realistic power grid scenarios.
Authors: Bing Xie, Junqi Yin, Zhenyu Zhou, Sarp Oral, Feiyi Wang
Abstract: Although it has been extensively explored in theory, decentralized learning is not yet green-lighted for production use, largely due to a lack of stability, scalability, and generality in large scale DNN training. To shed light on the production use of decentralized learning, this work studies decentralized data parallel training at scale. To this end, we introduce a benchmarking framework, namely DBench, to host both centralized and decentralized DNN training. Building upon DBench, we introduce a benchmarking methodology to uncover the correlations between model accuracy and the variances of parameter tensors by varying communication graphs and training scales. Based on the benchmarking results, we observe that, (1) Similar to centralized learning, decentralized data parallel training also presents the issues of scalability and generality when the training scales up; (2) The model accuracy of decentralized learning is correlated to the number of connections in a communication graph; (3) The model accuracy of decentralized learning is surprisingly sensitive to the variance of parameter tensors across model replicas. Built upon the observations, we propose Ada, a decentralized adaptive approach that performs large scale DNN training following a decentralized SGD method and adapting the communication graph in use dynamically throughout training iterations. We apply Ada on large scale training and observe that Ada can obtain the best convergence rates consistently in decentralized DNN training, and delivers equally or comparably good model accuracy for all sample applications as centralized learning does, even when training ResNet50 for ImageNet-1K on the scale of 1008 GPUs.
Authors: Xin Tong, Zhi Lin, Jingya Wang, Meng Han, Bo Jin
Abstract: Large language models (LLMs) enforce safety alignment to reliably refuse malicious requests, yet the same blanket safeguards also block legitimate uses in policing, defense, and other high-stakes settings. Earlier "refusal-direction" edits can bypass those layers, but they rely on a single vector that indiscriminately unlocks all hazardous topics, offering no semantic control. We introduce Mutually Exclusive Unlock Vectors (MEUV), a lightweight framework that factorizes the monolithic refusal direction into topic-aligned, nearly orthogonal vectors, each dedicated to one sensitive capability. MEUV is learned in a single epoch with a multi-task objective that blends a differential-ablation margin, cross-topic and orthogonality penalties, and several auxiliary terms. On bilingual malicious-prompt benchmarks, MEUV achieves an attack success rate of no less than 87% on Gemma-2-2B, LLaMA-3-8B, and Qwen-7B, yet cuts cross-topic leakage by up to 90% compared with the best single-direction baseline. Vectors trained in Chinese transfer almost unchanged to English (and vice versa), suggesting a language-agnostic refusal subspace. The results show that fine-grained, topic-level capability activation is achievable with minimal utility loss, paving the way for controlled LLMs deployment in security-sensitive domains.
Authors: Binquan Guo, Junteng Cao, Marie Siew, Binbin Chen, Tony Q. S. Quek, Zhu Han
Abstract: Large-scale low-Earth-orbit (LEO) satellite systems are increasingly valued for their ability to enable rapid and wide-area data exchange, thereby facilitating the collaborative training of artificial intelligence (AI) models across geographically distributed regions. Due to privacy concerns and regulatory constraints, raw data collected at remote clients cannot be centrally aggregated, posing a major obstacle to traditional AI training methods. Federated learning offers a privacy-preserving alternative by training local models on distributed devices and exchanging only model parameters. However, the dynamic topology and limited bandwidth of satellite systems will hinder timely parameter aggregation and distribution, resulting in prolonged training times. To address this challenge, we investigate the problem of scheduling federated learning over satellite networks and identify key bottlenecks that impact the overall duration of each training round. We propose a discrete temporal graph-based on-demand scheduling framework that dynamically allocates communication resources to accelerate federated learning. Simulation results demonstrate that the proposed approach achieves significant performance gains over traditional statistical multiplexing-based model exchange strategies, reducing overall round times by 14.20% to 41.48%. Moreover, the acceleration effect becomes more pronounced for larger models and higher numbers of clients, highlighting the scalability of the proposed approach.
Authors: Andrei Damian, Petrica Butusina, Alessandro De Franceschi, Vitalii Toderian, Marius Grigoras, Cristian Bleotiu
Abstract: We propose the Ratio1 AI meta-operating system (meta-OS), a decentralized MLOps protocol that unifies AI model development, deployment, and inference across heterogeneous edge devices. Its key innovation is an integrated blockchain-based framework that transforms idle computing resources (laptops, smartphones, cloud VMs) into a trustless global supercomputer. The architecture includes novel components: a decentralized authentication layer (dAuth), an in-memory state database (CSTORE), a distributed storage system (R1FS), homomorphic encrypted federated learning (EDIL), decentralized container orchestration (Deeploy) and an oracle network (OracleSync), which collectively ensure secure, resilient execution of AI pipelines and other container based apps at scale. The protocol enforces a formal circular token-economic model combining Proof-of-Availability (PoA) and Proof-of-AI (PoAI) consensus. Compared to centralized heterogeneous cloud MLOps and existing decentralized compute platforms, which often lack integrated AI toolchains or trusted Ratio1 node operators (R1OP) mechanics, Ratio1's holistic design lowers barriers for AI deployment and improves cost-efficiency. We provide mathematical formulations of its secure licensing and reward protocols, and include descriptive information for the system architecture and protocol flow. We argue that our proposed fully functional ecosystem proposes and demonstrates significant improvements in accessibility, scalability, and security over existing alternatives.
Authors: Marzieh Ajirak, Oded Bein, Ellen Rose Bowen, Dora Kanellopoulos, Avital Falk, Faith M. Gunning, Nili Solomonov, Logan Grosenick
Abstract: We propose a unified framework for adaptive routing in multitask, multimodal prediction settings where data heterogeneity and task interactions vary across samples. Motivated by applications in psychotherapy where structured assessments and unstructured clinician notes coexist with partially missing data and correlated outcomes, we introduce a routing-based architecture that dynamically selects modality processing pathways and task-sharing strategies on a per-sample basis. Our model defines multiple modality paths, including raw and fused representations of text and numeric features and learns to route each input through the most informative expert combination. Task-specific predictions are produced by shared or independent heads depending on the routing decision, and the entire system is trained end-to-end. We evaluate the model on both synthetic data and real-world psychotherapy notes predicting depression and anxiety outcomes. Our experiments show that our method consistently outperforms fixed multitask or single-task baselines, and that the learned routing policy provides interpretable insights into modality relevance and task structure. This addresses critical challenges in personalized healthcare by enabling per-subject adaptive information processing that accounts for data heterogeneity and task correlations. Applied to psychotherapy, this framework could improve mental health outcomes, enhance treatment assignment precision, and increase clinical cost-effectiveness through personalized intervention strategies.
Authors: MSR Avinash
Abstract: Fine-tuning large language models (LLMs) with parameter-efficient techniques such as LoRA and QLoRA has enabled adaptation of foundation models on modest hardware. Yet the efficiency of such training on consumer-grade GPUs, especially under strict 8 GB VRAM limits, remains underexplored. We present a controlled profiling study of LoRA/QLoRA fine-tuning using the Qwen2.5-1.5B-Instruct model on a single NVIDIA RTX 4060. Across three representative configurations, we systematically vary batch size, sequence length, optimizer choice (AdamW vs. PagedAdamW), and precision (fp16 vs. bf16). We report throughput (tokens/s), time per 10k tokens, and VRAM footprint, alongside energy estimates derived from GPU board power limits. Our results show that paged optimizers improve throughput by up to 25% (628 tok/s vs. 500 tok/s baseline), while bf16 degrades efficiency relative to fp16. Despite 8 GB constraints, sequence lengths up to 2048 tokens were feasible using parameter-efficient strategies. To our knowledge, this is the first systematic case study of LLM fine- tuning efficiency on consumer GPUs, providing reproducible benchmarks and practical guidelines for resource-constrained researchers and practitioners.
Authors: Meryem Malak Dif, Mouhamed Amine Bouchiha, Abdelaziz Amara Korba, Yacine Ghamri-Doudane
Abstract: The Internet of Electric Vehicles (IoEV) envisions a tightly coupled ecosystem of electric vehicles (EVs), charging infrastructure, and grid services, yet it remains vulnerable to cyberattacks, unreliable battery-state predictions, and opaque decision processes that erode trust and performance. To address these challenges, we introduce a novel Agentic Artificial Intelligence (AAI) framework tailored for IoEV, where specialized agents collaborate to deliver autonomous threat mitigation, robust analytics, and interpretable decision support. Specifically, we design an AAI architecture comprising dedicated agents for cyber-threat detection and response at charging stations, real-time State of Charge (SoC) estimation, and State of Health (SoH) anomaly detection, all coordinated through a shared, explainable reasoning layer; develop interpretable threat-mitigation mechanisms that proactively identify and neutralize attacks on both physical charging points and learning components; propose resilient SoC and SoH models that leverage continuous and adversarial-aware learning to produce accurate, uncertainty-aware forecasts with human-readable explanations; and implement a three-agent pipeline, where each agent uses LLM-driven reasoning and dynamic tool invocation to interpret intent, contextualize tasks, and execute formal optimizations for user-centric assistance. Finally, we validate our framework through comprehensive experiments across diverse IoEV scenarios, demonstrating significant improvements in security and prediction accuracy. All datasets, models, and code will be released publicly.
Authors: Benjamin Burns, Yuan Xue, Douglas W. Scharre, Xia Ning
Abstract: Alzheimer's disease (AD) is a progressive neurodegenerative disease with high inter-patient variance in rate of cognitive decline. AD progression prediction aims to forecast patient cognitive decline and benefits from incorporating multiple neuroimaging modalities. However, existing multimodal models fail to make accurate predictions when many modalities are missing during inference, as is often the case in clinical settings. To increase multimodal model flexibility under high modality missingness, we introduce PerM-MoE, a novel sparse mixture-of-experts method that uses independent routers for each modality in place of the conventional, single router. Using T1-weighted MRI, FLAIR, amyloid beta PET, and tau PET neuroimaging data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), we evaluate PerM-MoE, state-of-the-art Flex-MoE, and unimodal neuroimaging models on predicting two-year change in Clinical Dementia Rating-Sum of Boxes (CDR-SB) scores under varying levels of modality missingness. PerM-MoE outperforms the state of the art in most variations of modality missingness and demonstrates more effective utility of experts than Flex-MoE.
Authors: Hangzhan Jin, Sitao Luan, Sicheng Lyu, Guillaume Rabusseau, Reihaneh Rabbany, Doina Precup, Mohammad Hamdaqa
Abstract: The two-stage fine-tuning paradigm of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has empirically shown better reasoning performance than one-stage SFT for the post-training of Large Language Models (LLMs). However, the evolution and mechanism behind the synergy of SFT and RL are still under-explored and inconclusive. In our study, we find the well-known claim "SFT memorizes, RL generalizes" is over-simplified, and discover that: (1) OOD performance peaks at the early stage of SFT and then declines (OOD forgetting), the best SFT checkpoint cannot be captured by training/test loss; (2) the subsequent RL stage does not generate fundamentally better OOD capability, instead it plays an \textbf{OOD restoration} role, recovering the lost reasoning ability during SFT; (3) The recovery ability has boundaries, \ie{} \textbf{if SFT trains for too short or too long, RL cannot recover the lost OOD ability;} (4) To uncover the underlying mechanisms behind the forgetting and restoration process, we employ SVD analysis on parameter matrices, manually edit them, and observe their impacts on model performance. Unlike the common belief that the shift of model capacity mainly results from the changes of singular values, we find that they are actually quite stable throughout fine-tuning. Instead, the OOD behavior strongly correlates with the \textbf{rotation of singular vectors}. Our findings re-identify the roles of SFT and RL in the two-stage fine-tuning and discover the rotation of singular vectors as the key mechanism. %reversing the rotations induced by SFT, which shows recovery from forgetting, whereas imposing the SFT parameter directions onto a RL-tuned model results in performance degradation. Code is available at https://github.com/xiaodanguoguo/RL_Heals_SFT
Authors: Lu Cai, Fei Xu, Min Xian, Yalei Tang, Shoukun Sun, John Stempien
Abstract: During irradiation, phenomena such as kernel swelling and buffer densification may impact the performance of tristructural isotropic (TRISO) particle fuel. Post-irradiation microscopy is often used to identify these irradiation-induced morphologic changes. However, each fuel compact generally contains thousands of TRISO particles. Manually performing the work to get statistical information on these phenomena is cumbersome and subjective. To reduce the subjectivity inherent in that process and to accelerate data analysis, we used convolutional neural networks (CNNs) to automatically segment cross-sectional images of microscopic TRISO layers. CNNs are a class of machine-learning algorithms specifically designed for processing structured grid data. They have gained popularity in recent years due to their remarkable performance in various computer vision tasks, including image classification, object detection, and image segmentation. In this research, we generated a large irradiated TRISO layer dataset with more than 2,000 microscopic images of cross-sectional TRISO particles and the corresponding annotated images. Based on these annotated images, we used different CNNs to automatically segment different TRISO layers. These CNNs include RU-Net (developed in this study), as well as three existing architectures: U-Net, Residual Network (ResNet), and Attention U-Net. The preliminary results show that the model based on RU-Net performs best in terms of Intersection over Union (IoU). Using CNN models, we can expedite the analysis of TRISO particle cross sections, significantly reducing the manual labor involved and improving the objectivity of the segmentation results.
Authors: Abigail R. Cohen, Yuming Sun, Zhihao Qin, Harsh S. Muriki, Zihao Xiao, Yeonju Lee, Matthew Housley, Andrew F. Sharkey, Rhuanito S. Ferrarezi, Jing Li, Lu Gan, Yongsheng Chen
Abstract: Efficient nutrient management is critical for crop growth and sustainable resource consumption (e.g., nitrogen, energy). Current approaches require lengthy analyses, preventing real-time optimization; similarly, imaging facilitates rapid phenotyping but can be computationally intensive, preventing deployment under resource constraints. This study proposes a flexible, tiered pipeline for anomaly detection and status estimation (fresh weight, dry mass, and tissue nutrients), including a comprehensive energy analysis of approaches that span the efficiency-accuracy spectrum. Using a nutrient depletion experiment with three treatments (T1-100%, T2-50%, and T3-25% fertilizer strength) and multispectral imaging (MSI), we developed a hierarchical pipeline using an autoencoder (AE) for early warning. Further, we compared two status estimation modules of different complexity for more detailed analysis: vegetation index (VI) features with machine learning (Random Forest, RF) and raw whole-image deep learning (Vision Transformer, ViT). Results demonstrated high-efficiency anomaly detection (73% net detection of T3 samples 9 days after transplanting) at substantially lower energy than embodied energy in wasted nitrogen. The state estimation modules show trade-offs, with ViT outperforming RF on phosphorus and calcium estimation (R2 0.61 vs. 0.58, 0.48 vs. 0.35) at higher energy cost. With our modular pipeline, this work opens opportunities for edge diagnostics and practical opportunities for agricultural sustainability.
Authors: Yuriel Ryan, Rui Yang Tan, Kenny Tsu Wei Choo, Roy Ka-Wei Lee
Abstract: Understanding humor is a core aspect of social intelligence, yet it remains a significant challenge for Large Multimodal Models (LMMs). We introduce PixelHumor, a benchmark dataset of 2,800 annotated multi-panel comics designed to evaluate LMMs' ability to interpret multimodal humor and recognize narrative sequences. Experiments with state-of-the-art LMMs reveal substantial gaps: for instance, top models achieve only 61% accuracy in panel sequencing, far below human performance. This underscores critical limitations in current models' integration of visual and textual cues for coherent narrative and humor understanding. By providing a rigorous framework for evaluating multimodal contextual and narrative reasoning, PixelHumor aims to drive the development of LMMs that better engage in natural, socially aware interactions.
Authors: Jiacan Yu, Siyi Chen, Mingrui Liu, Nono Horiuchi, Vladimir Braverman, Zicheng Xu, Dan Haramati, Randall Balestriero
Abstract: Joint-Embedding Predictive Architecture (JEPA) is increasingly used for visual representation learning and as a component in model-based RL, but its behavior remains poorly understood. We provide a theoretical characterization of a simple, practical JEPA variant that has an auxiliary regression head trained jointly with latent dynamics. We prove a No Unhealthy Representation Collapse theorem: in deterministic MDPs, if training drives both the latent-transition consistency loss and the auxiliary regression loss to zero, then any pair of non-equivalent observations, i.e., those that do not have the same transition dynamics or auxiliary label, must map to distinct latent representations. Thus, the auxiliary task anchors which distinctions the representation must preserve. Controlled ablations in a counting environment corroborate the theory and show that training the JEPA model jointly with the auxiliary head generates a richer representation than training them separately. Our work indicates a path to improve JEPA encoders: training them with an auxiliary function that, together with the transition dynamics, encodes the right equivalence relations.
Authors: Yihong Ji, Yunze Liu, Yiyao Zhuo, Weijiang Yu, Fei Ma, Joshua Huang, Fei Yu
Abstract: The perception and generation of Human-Object Interaction (HOI) are crucial for fields such as robotics, AR/VR, and human behavior understanding. However, current approaches model this task in an offline setting, where information at each time step can be drawn from the entire interaction sequence. In contrast, in real-world scenarios, the information available at each time step comes only from the current moment and historical data, i.e., an online setting. We find that offline methods perform poorly in an online context. Based on this observation, we propose two new tasks: Online HOI Generation and Perception. To address this task, we introduce the OnlineHOI framework, a network architecture based on the Mamba framework that employs a memory mechanism. By leveraging Mamba's powerful modeling capabilities for streaming data and the Memory mechanism's efficient integration of historical information, we achieve state-of-the-art results on the Core4D and OAKINK2 online generation tasks, as well as the online HOI4D perception task.
Authors: Riyaadh Gani
Abstract: Non-invasive glucose monitors often fail outside the lab because existing datasets ignore hardware noise, environmental drift, and person-to-person physiology. We introduce the first ultra-realistic near-infrared (NIR) simulator that injects 12-bit ADC quantisation, +/-0.1% LED ageing, photodiode dark noise, 15-45 C temperature, 30-90% relative humidity, contact-pressure variation, Fitzpatrick I-VI melanin, and diurnal glucose excursions (dawn phenomenon). Using this platform (rho glucose-NIR = 0.21), we benchmark six methods: Enhanced Beer-Lambert (physics-engineered ridge regression), three physics-informed neural networks (PINNs), a selective radiative-transfer PINN, and a shallow DNN. Beer-Lambert achieves 13.6 mg/dL RMSE, 95.8% Clarke-A and 93.8% +/-15% accuracy with only 56 parameters and 0.01 ms inference, outperforming the best PINN (14.6 mg/dL) and the SDNN baseline (35.1 mg/dL). Results overturn the assumption that deeper PINNs dominate and supply an open, end-to-end reference stack for rapid prototyping of embedded optical glucose sensors.
Authors: Mihir Tare, Clemens Rattasits, Yiming Wu, Euan Wielewski
Abstract: Financial institutions increasingly require scalable tools to analyse complex transactional networks, yet traditional graph embedding methods struggle with dynamic, real-world banking data. This paper demonstrates the practical application of GraphSAGE, an inductive Graph Neural Network framework, to non-bipartite heterogeneous transaction networks within a banking context. Unlike transductive approaches, GraphSAGE scales well to large networks and can generalise to unseen nodes which is critical for institutions working with temporally evolving transactional data. We construct a transaction network using anonymised customer and merchant transactions and train a GraphSAGE model to generate node embeddings. Our exploratory work on the embeddings reveals interpretable clusters aligned with geographic and demographic attributes. Additionally, we illustrate their utility in downstream classification tasks by applying them to a money mule detection model where using these embeddings improves the prioritisation of high-risk accounts. Beyond fraud detection, our work highlights the adaptability of this framework to banking-scale networks, emphasising its inductive capability, scalability, and interpretability. This study provides a blueprint for financial organisations to harness graph machine learning for actionable insights in transactional ecosystems.
Authors: Kenneth G. Young II
Abstract: The Quantum-Inspired Stacked Integrated Concept Graph Model (QISICGM) is an innovative machine learning framework that harnesses quantum-inspired techniques to predict diabetes risk with exceptional accuracy and efficiency. Utilizing the PIMA Indians Diabetes dataset augmented with 2,000 synthetic samples to mitigate class imbalance (total: 2,768 samples, 1,949 positives), QISICGM integrates a self-improving concept graph with a stacked ensemble comprising Random Forests (RF), Extra Trees (ET), transformers, convolutional neural networks (CNNs), and feed-forward neural networks (FFNNs). This approach achieves an out-of-fold (OOF) F1 score of 0.8933 and an AUC of 0.8699, outperforming traditional methods. Quantum inspired elements, such as phase feature mapping and neighborhood sequence modeling, enrich feature representations, enabling CPU-efficient inference at 8.5 rows per second. This paper presents a detailed architecture, theoretical foundations, code insights, and performance evaluations, including visualizations from the outputs subfolder. The open-source implementation (v1.0.0) is available at https://github.com/keninayoung/QISICGM, positioning QISICGM as a potential benchmark for AI-assisted clinical triage in diabetes and beyond. Ultimately, this work emphasizes trustworthy AI through calibration, interpretability, and open-source reproducibility.
Authors: Xiaoguang Chang, Teng Wang, Changyin Sun
Abstract: The simplicity Bias (SB) of neural networks, i.e.\ their tendency to represent simple functions, is a key factor in their generalization capabilities. Recent studies show that an excessive SB may harm performance on complex tasks, and the need for this bias varies across tasks. Many of these studies focus on simple models or synthetic tasks. It remains challenging to measure the SB in large models and little is known about the relevance of the SB to various image classification tasks. In this paper, we investigate the relationship between the SB in CLIP models and their performance across image classification tasks. First, we theoretically analyze the potential limitation of existing measures of complexity that have been used to characterize small models. To address this, we propose a frequency-aware measure capturing finer-grained SB differences. We validate this measure on CLIP models subjected to two recent SB-modulation methods, demonstrating that it is more informative and consistent than previous measures. Second, we examine the relation between the SB of those models and their performance across a range of image classification tasks, including zero-shot and fine-tuning settings. These experiments reveal a range of behaviors. For example, a stronger SB correlates with a better performance on OOD generalization than on adversarial robustness. These results highlight the benefits of aligning a model's inductive biases with the characteristics of the target task.
Authors: Vijay Kumar, Gautam Singh
Abstract: This work proposes a Variational Physics-Informed Neural Network (VPINN) framework that integrates the Petrov-Galerkin formulation with deep neural networks (DNNs) for solving one-dimensional singularly perturbed boundary value problems (BVPs) and parabolic partial differential equations (PDEs) involving one or two small parameters. The method adopts a nonlinear approximation in which the trial space is defined by neural network functions, while the test space is constructed from hat functions. The weak formulation is constructed using localized test functions, with interface penalty terms introduced to enhance numerical stability and accurately capture boundary layers. Dirichlet boundary conditions are imposed via hard constraints, and source terms are computed using automatic differentiation. Numerical experiments on benchmark problems demonstrate the effectiveness of the proposed method, showing significantly improved accuracy in both the $L_2$ and maximum norms compared to the standard VPINN approach for one-dimensional singularly perturbed differential equations (SPDEs).
Authors: Jinghua Zhao, Hang Su, Lichun Fan, Zhenbo Luo, Jian Luan, Hui Wang, Haoqin Sun, Yong Qin
Abstract: We propose Omni-CLST, an error-aware Curriculum Learning framework with guided Selective Chain-of-Thought for audio question answering. The framework efficiently leverages existing high-quality dataset through two key strategies: an error-aware curriculum that organizes samples by difficulty, and a guided thought dropout mechanism that focuses reasoning on challenging cases. Integrated with GRPO training, these strategies enable the model to learn more effectively from informative samples. Experiments on MMAU-mini and MMAR demonstrate that Omni-CLST achieves competitive accuracy (73.80% on MMAU-mini) and establishes a new state of the art (64.30% on MMAR), highlighting its robustness and generalization capability in multimodal audio-language understanding.
Authors: Mehdi Yousefzadeh, Parsa Esfahanian, Sara Rashidifar, Hossein Salahshoor Gavalan, Negar Sadat Rafiee Tabatabaee, Saeid Gorgin, Dara Rahmati, Maryam Daneshpazhooh
Abstract: Introduction. Dermoscopy aids melanoma triage, yet image-only AI often ignores patient metadata (age, sex, site) and the physical scale needed for geometric analysis. We present GraphDerm, a population-graph framework that fuses imaging, millimeter-scale calibration, and metadata for multiclass dermoscopic classification, to the best of our knowledge the first ISIC-scale application of GNNs to dermoscopy. Methods. We curate ISIC 2018/2019, synthesize ruler-embedded images with exact masks, and train U-Nets (SE-ResNet-18) for lesion and ruler segmentation. Pixels-per-millimeter are regressed from the ruler-mask two-point correlation via a lightweight 1D-CNN. From lesion masks we compute real-scale descriptors (area, perimeter, radius of gyration). Node features use EfficientNet-B3; edges encode metadata/geometry similarity (fully weighted or thresholded). A spectral GNN performs semi-supervised node classification; an image-only ANN is the baseline. Results. Ruler and lesion segmentation reach Dice 0.904 and 0.908; scale regression attains MAE 1.5 px (RMSE 6.6). The graph attains AUC 0.9812, with a thresholded variant using about 25% of edges preserving AUC 0.9788 (vs. 0.9440 for the image-only baseline); per-class AUCs typically fall in the 0.97-0.99 range. Conclusion. Unifying calibrated scale, lesion geometry, and metadata in a population graph yields substantial gains over image-only pipelines on ISIC-2019. Sparser graphs retain near-optimal accuracy, suggesting efficient deployment. Scale-aware, graph-based AI is a promising direction for dermoscopic decision support; future work will refine learned edge semantics and evaluate on broader curated benchmarks.
Authors: Wanru Zhuang, Wenbo Li, Zhibin Lan, Xu Han, Peng Li, Jinsong Su
Abstract: Text Image Machine Translation (TIMT) aims to translate texts embedded within an image into another language. Current TIMT studies primarily focus on providing translations for all the text within an image, while neglecting to provide bounding boxes and covering limited scenarios. In this work, we extend traditional TIMT into position-aware TIMT (PATIMT), aiming to support fine-grained and layoutpreserving translation, which holds great practical value but remains largely unexplored. This task comprises two key sub-tasks: regionspecific translation and full-image translation with grounding. To support existing models on PATIMT and conduct fair evaluation, we construct the PATIMT benchmark (PATIMTBench), which consists of 10 diverse real-world scenarios. Specifically, we introduce an Adaptive Image OCR Refinement Pipeline, which adaptively selects appropriate OCR tools based on scenario and refines the results of text-rich images. To ensure evaluation reliability, we further construct a test set, which contains 1,200 high-quality instances manually annotated and reviewed by human experts. After fine-tuning on our data, compact Large Vision-Language Models (LVLMs) achieve state-of-the-art performance on both sub-tasks. Experimental results also highlight the scalability and generalizability of our training data
Authors: He Gao, Baoxiang Huang, Milena Radenkovic, Borui Li, Ge Chen
Abstract: Synthetic Aperture Radar (SAR), with its all- weather and wide-area observation capabilities, serves as a crucial tool for wake detection. However, due to its complex imaging mechanism, wake features in SAR images often appear abstract and noisy, posing challenges for accurate annotation. In contrast, optical images provide more distinct visual cues, but models trained on optical data suffer from performance degradation when applied to SAR images due to domain shift. To address this cross-modal domain adaptation challenge, we propose a Similarity-Guided and Memory-Guided Domain Adap- tation (termed SimMemDA) framework for unsupervised domain adaptive ship wake detection via instance-level feature similarity filtering and feature memory guidance. Specifically, to alleviate the visual discrepancy between optical and SAR images, we first utilize WakeGAN to perform style transfer on optical images, generating pseudo-images close to the SAR style. Then, instance-level feature similarity filtering mechanism is designed to identify and prioritize source samples with target-like dis- tributions, minimizing negative transfer. Meanwhile, a Feature- Confidence Memory Bank combined with a K-nearest neighbor confidence-weighted fusion strategy is introduced to dynamically calibrate pseudo-labels in the target domain, improving the reliability and stability of pseudo-labels. Finally, the framework further enhances generalization through region-mixed training, strategically combining source annotations with calibrated tar- get pseudo-labels. Experimental results demonstrate that the proposed SimMemDA method can improve the accuracy and robustness of cross-modal ship wake detection tasks, validating the effectiveness and feasibility of the proposed method.
Authors: Jiyong Ma
Abstract: In this paper, we present a maximum likelihood estimation approach to determine the value vector in transformer models. We model the sequence of value vectors, key vectors, and the query vector as a sequence of Gaussian distributions. The variance in each Gaussian distribution depends on the time step, the corresponding key vector, and the query vector. The mean value in each Gaussian distribution depends on the time step, and the corresponding value vector. This analysis may offer a new explanation of the scaled-dot-product function or softmax function used in transformer architectures [1]. Another explanation, inspired by [4], is based on the maximum entropy approach in natural language processing [5]. In this approach, a query vector and key vectors are used to derive the feature functions for the maximum entropy model.
Authors: Kanlun Wang, Zhe Fu, Wangjiaxuan Xin, Lina Zhou, Shashi Kiran Chandrappa
Abstract: Domestic Violence (DV) is a pervasive public health problem characterized by patterns of coercive and abusive behavior within intimate relationships. With the rise of social media as a key outlet for DV victims to disclose their experiences, online self-disclosure has emerged as a critical yet underexplored avenue for support-seeking. In addition, existing research lacks a comprehensive and nuanced understanding of DV self-disclosure, support provisions, and their connections. To address these gaps, this study proposes a novel computational framework for modeling DV support-seeking behavior alongside community support mechanisms. The framework consists of four key components: self-disclosure detection, post clustering, topic summarization, and support extraction and mapping. We implement and evaluate the framework with data collected from relevant social media communities. Our findings not only advance existing knowledge on DV self-disclosure and online support provisions but also enable victim-centered digital interventions.
Authors: Yuting Liu, Qiang Zhou, Hanzhe Li, Chenqi Gong, Jingjing Gu
Abstract: Long-term urban crowd flow prediction suffers significantly from cumulative sampling errors, due to increased sequence lengths and sampling intervals, which inspired us to leverage Neural Controlled Differential Equations (NCDEs) to mitigate this issue. However, regarding the crucial influence of Points of Interest (POIs) evolution on long-term crowd flow, the multi-timescale asynchronous dynamics between crowd flow and POI distribution, coupled with latent spurious causality, poses challenges to applying NCDEs for long-term urban crowd flow prediction. To this end, we propose Causal-aware Collaborative neural CDE (C3DE) to model the long-term dynamic of crowd flow. Specifically, we introduce a dual-path NCDE as the backbone to effectively capture the asynchronous evolution of collaborative signals across multiple time scales. Then, we design a dynamic correction mechanism with the counterfactual-based causal effect estimator to quantify the causal impact of POIs on crowd flow and minimize the accumulation of spurious correlations. Finally, we leverage a predictor for long-term prediction with the fused collaborative signals of POI and crowd flow. Extensive experiments on three real-world datasets demonstrate the superior performance of C3DE, particularly in cities with notable flow fluctuations.
Authors: Vijay Kumar Butte, Sujata Butte
Abstract: There is an exponential growth of connected Internet of Things (IoT) devices. These have given rise to applications that rely on real time data to make critical decisions quickly. Enterprises today are adopting cloud at a rapid pace. There is a critical need to develop secure and efficient strategy and architectures to best leverage capabilities of cloud and edge assets. This paper provides an end to end secure edge to cloud data and analytics strategy. To enable real life implementation, the paper provides reference architectures for device layer, edge layer and cloud layer.
Authors: Xianchen Liu (Department of Electrical and Computer Engineering, Florida International University, Miami, FL, 33199 USA), Tianhui Zhang (College of Engineering, Northeastern University, Boston, MA, 02169 USA), Xinyu Zhang (Department of Computer Science, Rochester Institute of Technology, Rochester, USA), Lingmin Hou (Department of Computer Science, Rochester Institute of Technology, Rochester, USA), Zhen Guo (Department of Mechanical and Materials Engineering, Florida International University, Miami, FL, 33199 USA), Yuanhao Tian (Department of Politics & International Relations, Florida International University, Miami, FL, 33199 USA), Yang Liu (College of Arts & Sciences, University of Miami, Miami, FL 33124, USA)
Abstract: This paper presents a novel approach to optimizing pricing and replenishment strategies in fresh food supermarkets by combining Long Short-Term Memory (LSTM) networks with Particle Swarm Optimization (PSO). The LSTM model, enhanced with an attention mechanism, is used to predict sales volumes, pricing trends, and spoilage rates over a seven-day period. The predictions generated by the LSTM model serve as inputs for the PSO algorithm, which iteratively optimizes pricing and replenishment strategies to maximize profitability while adhering to inventory constraints. The integration of cost-plus pricing allows for dynamic adjustments based on fixed and variable costs, ensuring real-time adaptability to market fluctuations. The framework not only maximizes profits but also reduces food waste, contributing to more sustainable supermarket operations. The attention mechanism enhances the interpretability of the LSTM model by identifying key time points and factors influencing sales, improving decision-making accuracy. This methodology bridges the gap between predictive modeling and optimization, offering a scalable solution for dynamic pricing and inventory management in fresh food retail and other industries dealing with perishable goods.
Authors: Liam Ressel, Hamza A. A. Gardi
Abstract: The Engineers' Salary Prediction Challenge requires classifying salary categories into three classes based on tabular data. The job description is represented as a 300-dimensional word embedding incorporated into the tabular features, drastically increasing dimensionality. Additionally, the limited number of training samples makes classification challenging. Linear dimensionality reduction of word embeddings for tabular data classification remains underexplored. This paper studies Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). We show that PCA, with an appropriate subspace dimension, can outperform raw embeddings. LDA without regularization performs poorly due to covariance estimation errors, but applying shrinkage improves performance significantly, even with only two dimensions. We propose Partitioned-LDA, which splits embeddings into equal-sized blocks and performs LDA separately on each, thereby reducing the size of the covariance matrices. Partitioned-LDA outperforms regular LDA and, combined with shrinkage, achieves top-10 accuracy on the competition public leaderboard. This method effectively enhances word embedding performance in tabular data classification with limited training samples.
Authors: Ritesh Janga, Rushit Dave
Abstract: The agricultural sector is undergoing a transformation with the integration of advanced technologies, particularly in data-driven decision-making. This work proposes a federated learning framework for smart farming, aiming to develop a scalable, efficient, and secure solution for crop disease detection tailored to the environmental and operational conditions of Minnesota farms. By maintaining sensitive farm data locally and enabling collaborative model updates, our proposed framework seeks to achieve high accuracy in crop disease classification without compromising data privacy. We outline a methodology involving data collection from Minnesota farms, application of local deep learning algorithms, transfer learning, and a central aggregation server for model refinement, aiming to achieve improved accuracy in disease detection, good generalization across agricultural scenarios, lower costs in communication and training time, and earlier identification and intervention against diseases in future implementations. We outline a methodology and anticipated outcomes, setting the stage for empirical validation in subsequent studies. This work comes in a context where more and more demand for data-driven interpretations in agriculture has to be weighed with concerns about privacy from farms that are hesitant to share their operational data. This will be important to provide a secure and efficient disease detection method that can finally revolutionize smart farming systems and solve local agricultural problems with data confidentiality. In doing so, this paper bridges the gap between advanced machine learning techniques and the practical, privacy-sensitive needs of farmers in Minnesota and beyond, leveraging the benefits of federated learning.
Authors: Daniel Lindmark, Jonas Andersson, Kenneth Bodin, Tora Bodin, Hugo B\"orjesson, Fredrik Nordfeldth, Martin Servin
Abstract: We envision an integrated process for developing lunar construction equipment, where physical design and control are explored in parallel. In this paper, we describe a technical framework that supports this process. It relies on OpenPLX, a readable/writable declarative language that links CAD-models and autonomous systems to high-fidelity, real-time 3D simulations of contacting multibody dynamics, machine regolith interaction forces, and non-ideal sensors. To demonstrate its capabilities, we present two case studies, including an autonomous lunar rover that combines a vision-language model for navigation with a reinforcement learning-based control policy for locomotion.
Authors: Matteo Marcuzzo, Alessandro Zangari, Andrea Albarelli, Jose Camacho-Collados, Mohammad Taher Pilehvar
Abstract: As LLMs excel on standard reading comprehension benchmarks, attention is shifting toward evaluating their capacity for complex abstract reasoning and inference. Literature-based benchmarks, with their rich narrative and moral depth, provide a compelling framework for evaluating such deeper comprehension skills. Here, we present MORABLES, a human-verified benchmark built from fables and short stories drawn from historical literature. The main task is structured as multiple-choice questions targeting moral inference, with carefully crafted distractors that challenge models to go beyond shallow, extractive question answering. To further stress-test model robustness, we introduce adversarial variants designed to surface LLM vulnerabilities and shortcuts due to issues such as data contamination. Our findings show that, while larger models outperform smaller ones, they remain susceptible to adversarial manipulation and often rely on superficial patterns rather than true moral reasoning. This brittleness results in significant self-contradiction, with the best models refuting their own answers in roughly 20% of cases depending on the framing of the moral choice. Interestingly, reasoning-enhanced models fail to bridge this gap, suggesting that scale - not reasoning ability - is the primary driver of performance.
Authors: Divyam Goel, Yufei Wang, Tiancheng Wu, Guixiu Qiao, Pavel Piliptchak, David Held, Zackory Erickson
Abstract: Standard evaluation protocols in robotic manipulation typically assess policy performance over curated, in-distribution test sets, offering limited insight into how systems fail under plausible variation. We introduce Geometric Red-Teaming (GRT), a red-teaming framework that probes robustness through object-centric geometric perturbations, automatically generating CrashShapes -- structurally valid, user-constrained mesh deformations that trigger catastrophic failures in pre-trained manipulation policies. The method integrates a Jacobian field-based deformation model with a gradient-free, simulator-in-the-loop optimization strategy. Across insertion, articulation, and grasping tasks, GRT consistently discovers deformations that collapse policy performance, revealing brittle failure modes missed by static benchmarks. By combining task-level policy rollouts with constraint-aware shape exploration, we aim to build a general purpose framework for structured, object-centric robustness evaluation in robotic manipulation. We additionally show that fine-tuning on individual CrashShapes, a process we refer to as blue-teaming, improves task success by up to 60 percentage points on those shapes, while preserving performance on the original object, demonstrating the utility of red-teamed geometries for targeted policy refinement. Finally, we validate both red-teaming and blue-teaming results with a real robotic arm, observing that simulated CrashShapes reduce task success from 90% to as low as 22.5%, and that blue-teaming recovers performance to up to 90% on the corresponding real-world geometry -- closely matching simulation outcomes. Videos and code can be found on our project website: https://georedteam.github.io/ .
Authors: Florian Zager, Hamza A. A. Gardi
Abstract: Deep neural networks have achieved remarkable success across a range of tasks, however their computational demands often make them unsuitable for deployment on resource-constrained edge devices. This paper explores strategies for compressing and adapting models to enable efficient inference in such environments. We focus on GhostNetV3, a state-of-the-art architecture for mobile applications, and propose GhostNetV3-Small, a modified variant designed to perform better on low-resolution inputs such as those in the CIFAR-10 dataset. In addition to architectural adaptation, we provide a comparative evaluation of knowledge distillation techniques, including traditional knowledge distillation, teacher assistants, and teacher ensembles. Experimental results show that GhostNetV3-Small significantly outperforms the original GhostNetV3 on CIFAR-10, achieving an accuracy of 93.94%. Contrary to expectations, all examined distillation strategies led to reduced accuracy compared to baseline training. These findings indicate that architectural adaptation can be more impactful than distillation in small-scale image classification tasks, highlighting the need for further research on effective model design and advanced distillation techniques for low-resolution domains.
Authors: Asim Waheed, Vasisht Duddu, Rui Zhang, Sebastian Szyller, N. Asokan
Abstract: ML models are susceptible to risks to security, privacy, and fairness. Several defenses are designed to protect against their intended risks, but can inadvertently affect susceptibility to other unrelated risks, known as unintended interactions. Several jurisdictions are preparing ML regulatory frameworks that require ML practitioners to assess the susceptibility of ML models to different risks. A library for valuating unintended interactions that can be used by (a) practitioners to evaluate unintended interactions at scale prior to model deployment and (b) researchers to design defenses which do not suffer from an unintended increase in unrelated risks. Ideally, such a library should be i) comprehensive by including representative attacks, defenses and metrics for different risks, ii) extensible to new modules due to its modular design, iii) consistent with a user-friendly API template for inputs and outputs, iv) applicable to evaluate previously unexplored unintended interactions. We present AMULET, a Python library that covers risks to security, privacy, and fairness, which satisfies all these requirements. AMULET can be used to evaluate unexplored unintended interactions, compare effectiveness between defenses or attacks, and include new attacks and defenses.
Authors: Mohamed Zayaan S
Abstract: Modern deep learning models excel at pattern recognition but remain fundamentally limited by their reliance on spurious correlations, leading to poor generalization and a demand for massive datasets. We argue that a key ingredient for human-like intelligence-robust, sample-efficient learning-stems from an understanding of causal mechanisms. In this work, we introduce Causal-Symbolic Meta-Learning (CSML), a novel framework that learns to infer the latent causal structure of a task distribution. CSML comprises three key modules: a perception module that maps raw inputs to disentangled symbolic representations; a differentiable causal induction module that discovers the underlying causal graph governing these symbols and a graph-based reasoning module that leverages this graph to make predictions. By meta-learning a shared causal world model across a distribution of tasks, CSML can rapidly adapt to novel tasks, including those requiring reasoning about interventions and counterfactuals, from only a handful of examples. We introduce CausalWorld, a new physics-based benchmark designed to test these capabilities. Our experiments show that CSML dramatically outperforms state-of-the-art meta-learning and neuro-symbolic baselines, particularly on tasks demanding true causal inference.
Authors: Janik Henn, Adrian Hauptmannl, Hamza A. A. Gardi
Abstract: 3D printing has long been a technology for industry professionals and enthusiasts willing to tinker or even build their own machines. This stands in stark contrast to today's market, where recent developments have prioritized ease of use to attract a broader audience. Slicing software nowadays has a few ways to sanity check the input file as well as the output gcode. Our approach introduces a novel layer of support by training an AI model to detect common issues in 3D models. The goal is to assist less experienced users by identifying features that are likely to cause print failures due to difficult to print geometries before printing even begins.
Authors: Yash Mundhra, Max Valk, Maliheh Izadi
Abstract: Large language models have shown impressive performance in various domains, including code generation across diverse open-source domains. However, their applicability in proprietary industrial settings, where domain-specific constraints and code interdependencies are prevalent, remains largely unexplored. We present a case study conducted in collaboration with the leveling department at ASML to investigate the performance of LLMs in generating functional, maintainable code within a closed, highly specialized software environment. We developed an evaluation framework tailored to ASML's proprietary codebase and introduced a new benchmark. Additionally, we proposed a new evaluation metric, build@k, to assess whether LLM-generated code successfully compiles and integrates within real industrial repositories. We investigate various prompting techniques, compare the performance of generic and code-specific LLMs, and examine the impact of model size on code generation capabilities, using both match-based and execution-based metrics. The findings reveal that prompting techniques and model size have a significant impact on output quality, with few-shot and chain-of-thought prompting yielding the highest build success rates. The difference in performance between the code-specific LLMs and generic LLMs was less pronounced and varied substantially across different model families.
Authors: Hao Li, Hicham Masri, Filipe R. Cogo, Abdul Ali Bangash, Bram Adams, Ahmed E. Hassan
Abstract: The rapid adoption of foundation models (e.g., large language models) has given rise to promptware, i.e., software built using natural language prompts. Effective management of prompts, such as organization and quality assurance, is essential yet challenging. In this study, we perform an empirical analysis of 24,800 open-source prompts from 92 GitHub repositories to investigate prompt management practices and quality attributes. Our findings reveal critical challenges such as considerable inconsistencies in prompt formatting, substantial internal and external prompt duplication, and frequent readability and spelling issues. Based on these findings, we provide actionable recommendations for developers to enhance the usability and maintainability of open-source prompts within the rapidly evolving promptware ecosystem.
Authors: Yinzhanghao Zhou, Tsung-Han Lee, Ao Chen, Nicola Lanat\`a, Hong Guo
Abstract: Neural quantum states (NQS) have emerged as a promising approach to solve second-quantised Hamiltonians, because of their scalability and flexibility. In this work, we design and benchmark an NQS impurity solver for the quantum embedding methods, focusing on the ghost Gutzwiller Approximation (gGA) framework. We introduce a graph transformer-based NQS framework able to represent arbitrarily connected impurity orbitals and develop an error control mechanism to stabilise iterative updates throughout the quantum embedding loops. We validate the accuracy of our approach with benchmark gGA calculations of the Anderson Lattice Model, yielding results in excellent agreement with the exact diagonalisation impurity solver. Finally, our analysis of the computational budget reveals the method's principal bottleneck to be the high-accuracy sampling of physical observables required by the embedding loop, rather than the NQS variational optimisation, directly highlighting the critical need for more efficient inference techniques.
Authors: Jiayi He, Yangmin Huang, Qianyun Du, Xiangying Zhou, Zhiyang He, Jiaxue Hu, Xiaodong Tao, Lixian Lai
Abstract: The increasing deployment of Large Language Models (LLMs) in healthcare necessitates a rigorous evaluation of their factual reliability. However, existing benchmarks are often limited by narrow domains of data, failing to capture the complexity of real-world medical information. To address this critical gap, we introduce MedFact, a new and challenging benchmark for Chinese medical fact-checking. MedFact comprises 2,116 expert-annotated instances curated from diverse real-world texts, spanning 13 medical specialties, 8 fine-grained error types, 4 writing styles, and multiple difficulty levels. Its construction employs a hybrid AI-human framework where iterative expert feedback refines an AI-driven, multi-criteria filtering process, ensuring both high data quality and difficulty. We conduct a comprehensive evaluation of 20 leading LLMs, benchmarking their performance on veracity classification and error localization against a human expert baseline. Our results reveal that while models can often determine if a text contains an error, precisely localizing it remains a substantial challenge, with even top-performing models falling short of human performance. Furthermore, our analysis uncovers a frequent ``over-criticism'' phenomenon, a tendency for models to misidentify correct information as erroneous, which is exacerbated by advanced reasoning techniques such as multi-agent collaboration and inference-time scaling. By highlighting these critical challenges for deploying LLMs in medical applications, MedFact provides a robust resource to drive the development of more factually reliable and medically aware models.
Authors: Dawei Xiang, Wenyan Xu, Kexin Chu, Zixu Shen, Tianqi Ding, Wei Zhang
Abstract: The rapid advancement of generative AI has democratized access to powerful tools such as Text-to-Image models. However, to generate high-quality images, users must still craft detailed prompts specifying scene, style, and context-often through multiple rounds of refinement. We propose PromptSculptor, a novel multi-agent framework that automates this iterative prompt optimization process. Our system decomposes the task into four specialized agents that work collaboratively to transform a short, vague user prompt into a comprehensive, refined prompt. By leveraging Chain-of-Thought reasoning, our framework effectively infers hidden context and enriches scene and background details. To iteratively refine the prompt, a self-evaluation agent aligns the modified prompt with the original input, while a feedback-tuning agent incorporates user feedback for further refinement. Experimental results demonstrate that PromptSculptor significantly enhances output quality and reduces the number of iterations needed for user satisfaction. Moreover, its model-agnostic design allows seamless integration with various T2I models, paving the way for industrial applications.
Authors: Rafael Zimmer, Oswaldo Luiz do Valle Costa
Abstract: Reinforcement Learning has emerged as a promising framework for developing adaptive and data-driven strategies, enabling market makers to optimize decision-making policies based on interactions with the limit order book environment. This paper explores the integration of a reinforcement learning agent in a market-making context, where the underlying market dynamics have been explicitly modeled to capture observed stylized facts of real markets, including clustered order arrival times, non-stationary spreads and return drifts, stochastic order quantities and price volatility. These mechanisms aim to enhance stability of the resulting control agent, and serve to incorporate domain-specific knowledge into the agent policy learning process. Our contributions include a practical implementation of a market making agent based on the Proximal-Policy Optimization (PPO) algorithm, alongside a comparative evaluation of the agent's performance under varying market conditions via a simulator-based environment. As evidenced by our analysis of the financial return and risk metrics when compared to a closed-form optimal solution, our results suggest that the reinforcement learning agent can effectively be used under non-stationary market conditions, and that the proposed simulator-based environment can serve as a valuable tool for training and pre-training reinforcement learning agents in market-making scenarios.
Authors: Keyu An, Yanni Chen, Chong Deng, Changfeng Gao, Zhifu Gao, Bo Gong, Xiangang Li, Yabin Li, Xiang Lv, Yunjie Ji, Yiheng Jiang, Bin Ma, Haoneng Luo, Chongjia Ni, Zexu Pan, Yiping Peng, Zhendong Peng, Peiyao Wang, Hao Wang, Wen Wang, Wupeng Wang, Biao Tian, Zhentao Tan, Nan Yang, Bin Yuan, Jieping Ye, Jixing Yu, Qinglin Zhang, Kun Zou, Han Zhao, Shengkui Zhao, Jingren Zhou
Abstract: In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model size scaling, and deep integration with large language models (LLMs). However, LLMs are prone to hallucination, which can significantly degrade user experience in real-world ASR applications. In this paper, we present FunAudio-ASR, a large-scale, LLM-based ASR system that synergistically combines massive data, large model capacity, LLM integration, and reinforcement learning to achieve state-of-the-art performance across diverse and complex speech recognition scenarios. Moreover, FunAudio-ASR is specifically optimized for practical deployment, with enhancements in streaming capability, noise robustness, code-switching, hotword customization, and satisfying other real-world application requirements. Experimental results show that while most LLM-based ASR systems achieve strong performance on open-source benchmarks, they often underperform on real industry evaluation sets. Thanks to production-oriented optimizations, FunAudio-ASR achieves SOTA performance on real application datasets, demonstrating its effectiveness and robustness in practical settings.
Authors: Fazle Rafsani, Jay Shah, Catherine D. Chong, Todd J. Schwedt, Teresa Wu
Abstract: Anomaly detection and classification in medical imaging are critical for early diagnosis but remain challenging due to limited annotated data, class imbalance, and the high cost of expert labeling. Emerging vision foundation models such as DINOv2, pretrained on extensive, unlabeled datasets, offer generalized representations that can potentially alleviate these limitations. In this study, we propose an attention-based global aggregation framework tailored specifically for 3D medical image anomaly classification. Leveraging the self-supervised DINOv2 model as a pretrained feature extractor, our method processes individual 2D axial slices of brain MRIs, assigning adaptive slice-level importance weights through a soft attention mechanism. To further address data scarcity, we employ a composite loss function combining supervised contrastive learning with class-variance regularization, enhancing inter-class separability and intra-class consistency. We validate our framework on the ADNI dataset and an institutional multi-class headache cohort, demonstrating strong anomaly classification performance despite limited data availability and significant class imbalance. Our results highlight the efficacy of utilizing pretrained 2D foundation models combined with attention-based slice aggregation for robust volumetric anomaly detection in medical imaging. Our implementation is publicly available at https://github.com/Rafsani/DinoAtten3D.git.
Authors: Scott Jones, Liyou Zhou, Sebastian W. Pattinson
Abstract: In visuomotor policy learning, the control policy for the robotic agent is derived directly from visual inputs. The typical approach, where a policy and vision encoder are trained jointly from scratch, generalizes poorly to novel visual scene changes. Using pre-trained vision models (PVMs) to inform a policy network improves robustness in model-free reinforcement learning (MFRL). Recent developments in Model-based reinforcement learning (MBRL) suggest that MBRL is more sample-efficient than MFRL. However, counterintuitively, existing work has found PVMs to be ineffective in MBRL. Here, we investigate PVM's effectiveness in MBRL, specifically on generalization under visual domain shifts. We show that, in scenarios with severe shifts, PVMs perform much better than a baseline model trained from scratch. We further investigate the effects of varying levels of fine-tuning of PVMs. Our results show that partial fine-tuning can maintain the highest average task performance under the most extreme distribution shifts. Our results demonstrate that PVMs are highly successful in promoting robustness in visual policy learning, providing compelling evidence for their wider adoption in model-based robotic learning applications.
Authors: Jia-Hong Huang
Abstract: The increasing prevalence of retinal diseases poses a significant challenge to the healthcare system, as the demand for ophthalmologists surpasses the available workforce. This imbalance creates a bottleneck in diagnosis and treatment, potentially delaying critical care. Traditional methods of generating medical reports from retinal images rely on manual interpretation, which is time-consuming and prone to errors, further straining ophthalmologists' limited resources. This thesis investigates the potential of Artificial Intelligence (AI) to automate medical report generation for retinal images. AI can quickly analyze large volumes of image data, identifying subtle patterns essential for accurate diagnosis. By automating this process, AI systems can greatly enhance the efficiency of retinal disease diagnosis, reducing doctors' workloads and enabling them to focus on more complex cases. The proposed AI-based methods address key challenges in automated report generation: (1) A multi-modal deep learning approach captures interactions between textual keywords and retinal images, resulting in more comprehensive medical reports; (2) Improved methods for medical keyword representation enhance the system's ability to capture nuances in medical terminology; (3) Strategies to overcome RNN-based models' limitations, particularly in capturing long-range dependencies within medical descriptions; (4) Techniques to enhance the interpretability of the AI-based report generation system, fostering trust and acceptance in clinical practice. These methods are rigorously evaluated using various metrics and achieve state-of-the-art performance. This thesis demonstrates AI's potential to revolutionize retinal disease diagnosis by automating medical report generation, ultimately improving clinical efficiency, diagnostic accuracy, and patient care.
Authors: Qi Wang, Shuliang Zhu, Jinjia Zhou
Abstract: Consistent distillation methods have evolved into effective techniques that significantly accelerate the sampling process of diffusion models. Although existing methods have achieved remarkable results, the selection of target timesteps during distillation mainly relies on deterministic or stochastic strategies, which often require sampling schedulers to be designed specifically for different distillation processes. Moreover, this pattern severely limits flexibility, thereby restricting the full sampling potential of diffusion models in practical applications. To overcome these limitations, this paper proposes an adaptive sampling scheduler that is applicable to various consistency distillation frameworks. The scheduler introduces three innovative strategies: (i) dynamic target timestep selection, which adapts to different consistency distillation frameworks by selecting timesteps based on their computed importance; (ii) Optimized alternating sampling along the solution trajectory by guiding forward denoising and backward noise addition based on the proposed time step importance, enabling more effective exploration of the solution space to enhance generation performance; and (iii) Utilization of smoothing clipping and color balancing techniques to achieve stable and high-quality generation results at high guidance scales, thereby expanding the applicability of consistency distillation models in complex generation scenarios. We validated the effectiveness and flexibility of the adaptive sampling scheduler across various consistency distillation methods through comprehensive experimental evaluations. Experimental results consistently demonstrated significant improvements in generative performance, highlighting the strong adaptability achieved by our method.
Authors: Yizhen Lao, Yu Zhang, Ziting Wang, Chengbo Wang, Yifei Xue, Wanpeng Shao
Abstract: Deep learning models have been shown to be susceptible to adversarial attacks with visually imperceptible perturbations. Even this poses a serious security challenge for the localization of self-driving cars, there has been very little exploration of attack on it, as most of adversarial attacks have been applied to 3D perception. In this work, we propose a novel adversarial attack framework called DisorientLiDAR targeting LiDAR-based localization. By reverse-engineering localization models (e.g., feature extraction networks), adversaries can identify critical keypoints and strategically remove them, thereby disrupting LiDAR-based localization. Our proposal is first evaluated on three state-of-the-art point-cloud registration models (HRegNet, D3Feat, and GeoTransformer) using the KITTI dataset. Experimental results demonstrate that removing regions containing Top-K keypoints significantly degrades their registration accuracy. We further validate the attack's impact on the Autoware autonomous driving platform, where hiding merely a few critical regions induces noticeable localization drift. Finally, we extended our attacks to the physical world by hiding critical regions with near-infrared absorptive materials, thereby successfully replicate the attack effects observed in KITTI data. This step has been closer toward the realistic physical-world attack that demonstrate the veracity and generality of our proposal.
Authors: Huajun Zhou, Fengtao Zhou, Jiabo Ma, Yingxue Xu, Xi Wang, Xiuming Zhang, Li Liang, Zhenhui Li, Hao Chen
Abstract: Multimodal data provides heterogeneous information for a holistic understanding of the tumor microenvironment. However, existing AI models often struggle to harness the rich information within multimodal data and extract poorly generalizable representations. Here we present MICE (Multimodal data Integration via Collaborative Experts), a multimodal foundation model that effectively integrates pathology images, clinical reports, and genomics data for precise pan-cancer prognosis prediction. Instead of conventional multi-expert modules, MICE employs multiple functionally diverse experts to comprehensively capture both cross-cancer and cancer-specific insights. Leveraging data from 11,799 patients across 30 cancer types, we enhanced MICE's generalizability by coupling contrastive and supervised learning. MICE outperformed both unimodal and state-of-the-art multi-expert-based multimodal models, demonstrating substantial improvements in C-index ranging from 3.8% to 11.2% on internal cohorts and 5.8% to 8.8% on independent cohorts, respectively. Moreover, it exhibited remarkable data efficiency across diverse clinical scenarios. With its enhanced generalizability and data efficiency, MICE establishes an effective and scalable foundation for pan-cancer prognosis prediction, holding strong potential to personalize tailored therapies and improve treatment outcomes.
Authors: Mukai Li, Linfeng Song, Zhenwen Liang, Jiahao Xu, Shansan Gong, Qi Liu, Haitao Mi, Dong Yu
Abstract: Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP), attaining substantial performance gains through widely adopted test-time scaling strategies, notably reflective Chain-of-Thought (CoT) reasoning and increased sampling passes. However, they both introduce significant computational overhead for inference. Moreover, existing cost analyses typically regulate only the number of sampling passes, while neglecting the substantial disparities in sampling costs introduced by different scaling strategies. In this paper, we systematically compare the efficiency of different test-time scaling strategies for ATP models and demonstrate the inefficiency of the current state-of-the-art (SOTA) open-source approaches. We then investigate approaches to significantly reduce token usage and sample passes while maintaining the original performance. Specifically, we propose two complementary methods that can be integrated into a unified EconRL pipeline for amplified benefits: (1) a dynamic Chain-of-Thought (CoT) switching mechanism designed to mitigate unnecessary token consumption, and (2) Diverse parallel-scaled reinforcement learning (RL) with trainable prefixes to enhance pass rates under constrained sampling passes. Experiments on miniF2F and ProofNet demonstrate that our EconProver achieves comparable performance to baseline methods with only 12% of the computational cost. This work provides actionable insights for deploying lightweight ATP models without sacrificing performance.
Authors: Hengrui Zhang, Yulong Hui, Yihao Liu, Huanchen Zhang
Abstract: Predicates are foundational components in data analysis systems. However, modern workloads increasingly involve unstructured documents, which demands semantic understanding, beyond traditional value-based predicates. Given enormous documents and ad-hoc queries, while Large Language Models (LLMs) demonstrate powerful zero-shot capabilities, their high inference cost leads to unacceptable overhead. Therefore, we introduce \textsc{ScaleDoc}, a novel system that addresses this by decoupling predicate execution into an offline representation phase and an optimized online filtering phase. In the offline phase, \textsc{ScaleDoc} leverages a LLM to generate semantic representations for each document. Online, for each query, it trains a lightweight proxy model on these representations to filter the majority of documents, forwarding only the ambiguous cases to the LLM for final decision. Furthermore, \textsc{ScaleDoc} proposes two core innovations to achieve significant efficiency: (1) a contrastive-learning-based framework that trains the proxy model to generate reliable predicating decision scores; (2) an adaptive cascade mechanism that determines the effective filtering policy while meeting specific accuracy targets. Our evaluations across three datasets demonstrate that \textsc{ScaleDoc} achieves over a 2$\times$ end-to-end speedup and reduces expensive LLM invocations by up to 85\%, making large-scale semantic analysis practical and efficient.
Authors: Zekai Zhang, Weiye Zhu, Hewei Pan, Xiangchen Wang, Rongtao Xu, Xing Sun, Feng Zheng
Abstract: The Vision-and-Language Navigation (VLN) task requires an agent to follow natural language instructions and navigate through complex environments. Existing MLLM-based VLN methods primarily rely on imitation learning (IL) and often use DAgger for post-training to mitigate covariate shift. While effective, these approaches incur substantial data collection and training costs. Reinforcement learning (RL) offers a promising alternative. However, prior VLN RL methods lack dynamic interaction with the environment and depend on expert trajectories for reward shaping, rather than engaging in open-ended active exploration. This restricts the agent's ability to discover diverse and plausible navigation routes. To address these limitations, we propose ActiveVLN, a VLN framework that explicitly enables active exploration through multi-turn RL. In the first stage, a small fraction of expert trajectories is used for IL to bootstrap the agent. In the second stage, the agent iteratively predicts and executes actions, automatically collects diverse trajectories, and optimizes multiple rollouts via the GRPO objective. To further improve RL efficiency, we introduce a dynamic early-stopping strategy to prune long-tail or likely failed trajectories, along with additional engineering optimizations. Experiments show that ActiveVLN achieves the largest performance gains over IL baselines compared to both DAgger-based and prior RL-based post-training methods, while reaching competitive performance with state-of-the-art approaches despite using a smaller model. Code and data will be released soon.
Authors: Tao Long, Xuanming Zhang, Sitong Wang, Zhou Yu, Lydia B Chilton
Abstract: Agentic workflows promise efficiency, but adoption hinges on whether people actually trust systems that act on their behalf. We present DoubleAgents, an agentic planning tool that embeds transparency and control through user intervention, value-reflecting policies, rich state visualizations, and uncertainty flagging for human coordination tasks. A built-in respondent simulation generates realistic scenarios, allowing users to rehearse, refine policies, and calibrate their reliance before live use. We evaluate DoubleAgents in a two-day lab study (n=10), two deployments (n=2), and a technical evaluation. Results show that participants initially hesitated to delegate but grew more reliant as they experienced transparency, control, and adaptive learning during simulated cases. Deployment results demonstrate DoubleAgents' real-world relevance and usefulness, showing that the effort required scaled appropriately with task complexity and contextual data. We contribute trust-by-design patterns and mechanisms for proactive AI -- consistency, controllability, and explainability -- along with simulation as a safe path to build and calibrate trust over time.
Authors: Liming Lu, Shuchao Pang, Xu Zheng, Xiang Gu, Anan Du, Yunhuai Liu, Yongbin Zhou
Abstract: Adversarial robustness distillation (ARD) aims to transfer both performance and robustness from teacher model to lightweight student model, enabling resilient performance on resource-constrained scenarios. Though existing ARD approaches enhance student model's robustness, the inevitable by-product leads to the degraded performance on clean examples. We summarize the causes of this problem inherent in existing methods with dual-teacher framework as: 1. The divergent optimization objectives of dual-teacher models, i.e., the clean and robust teachers, impede effective knowledge transfer to the student model, and 2. The iteratively generated adversarial examples during training lead to performance deterioration of the robust teacher model. To address these challenges, we propose a novel Cyclic Iterative ARD (CIARD) method with two key innovations: a. A multi-teacher framework with contrastive push-loss alignment to resolve conflicts in dual-teacher optimization objectives, and b. Continuous adversarial retraining to maintain dynamic teacher robustness against performance degradation from the varying adversarial examples. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that CIARD achieves remarkable performance with an average 3.53 improvement in adversarial defense rates across various attack scenarios and a 5.87 increase in clean sample accuracy, establishing a new benchmark for balancing model robustness and generalization. Our code is available at https://github.com/eminentgu/CIARD
Authors: Yu (Sid), Wang, Sheng Shen, R\'emi Munos, Hongyuan Zhan, Yuandong Tian
Abstract: We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scores that limits RoPE's ability to model long-context. RoPE extension methods may alleviate this issue, but they typically require post-hoc adjustments after pretraining, such as rescaling or hyperparameters retuning. This paper introduces Token-Aware Phase Attention (TAPA), a new positional encoding method that incorporates a learnable phase function into the attention mechanism. TAPA preserves token interactions over long range, extends to longer contexts with direct and light fine-tuning, extrapolates to unseen lengths, and attains significantly lower perplexity on long-context than RoPE families.
Authors: Kiho Lee, Jungkon Kim, Doowon Kim, Hyoungshick Kim
Abstract: Code-generating Large Language Models (LLMs) significantly accelerate software development. However, their frequent generation of insecure code presents serious risks. We present a comprehensive evaluation of seven parameter-efficient fine-tuning (PEFT) techniques, demonstrating substantial gains in secure code generation without compromising functionality. Our research identifies prompt-tuning as the most effective PEFT method, achieving an 80.86% Overall-Secure-Rate on CodeGen2 16B, a 13.5-point improvement over the 67.28% baseline. Optimizing decoding strategies through sampling temperature further elevated security to 87.65%. This equates to a reduction of approximately 203,700 vulnerable code snippets per million generated. Moreover, prompt and prefix tuning increase robustness against poisoning attacks in our TrojanPuzzle evaluation, with strong performance against CWE-79 and CWE-502 attack vectors. Our findings generalize across Python and Java, confirming prompt-tuning's consistent effectiveness. This study provides essential insights and practical guidance for building more resilient software systems with LLMs.
Authors: Chan Sik Han, Keon Myung Lee
Abstract: Detecting anomalies in time series data is essential for the reliable operation of many real-world systems. Recently, time series foundation models (TSFMs) have emerged as a powerful tool for anomaly detection. However, existing methods typically rely on the final layer's representations of TSFMs, computing the anomaly score as a reconstruction or forecasting error via a task-specific head. Instead, we propose TimeRep, a novel anomaly detection approach that leverages the intermediate layer's representations of TSFMs, computing the anomaly score as the distance between these representations. Given a pre-trained TSFM, TimeRep selects the intermediate layer and patch-token position that yield the most informative representation. TimeRep forms a reference collection of intermediate representations from the training data and applies a core-set strategy to reduce its size while maintaining distributional coverage. During inference, TimeRep computes the anomaly score for incoming data by measuring the distance between its intermediate representations and those of the collection. To address concept drift, TimeRep integrates an adaptation mechanism that, at inference time, augments the collection exclusively with non-redundant intermediate representations from incoming data. We conducted extensive experiments on the UCR Anomaly Archive, which contains 250 univariate time series. TimeRep consistently outperforms a broad spectrum of state-of-the-art baselines, including non-DL, DL, and foundation model-based methods.
Authors: Paul Kr\"oger, Emilio Barkett
Abstract: As large language models (LLMs) become increasingly embedded in products used by millions, their outputs may influence individual beliefs and, cumulatively, shape public opinion. If the behavior of LLMs can be intentionally steered toward specific ideological positions, such as political or religious views, then those who control these systems could gain disproportionate influence over public discourse. Although it remains an open question whether LLMs can reliably be guided toward coherent ideological stances and whether such steering can be effectively prevented, a crucial first step is to develop methods for detecting when such steering attempts occur. In this work, we adapt a previously proposed statistical method to the new context of ideological bias auditing. Our approach carries over the model-agnostic design of the original framework, which does not require access to the internals of the language model. Instead, it identifies potential ideological steering by analyzing distributional shifts in model outputs across prompts that are thematically related to a chosen topic. This design makes the method particularly suitable for auditing proprietary black-box systems. We validate our approach through a series of experiments, demonstrating its practical applicability and its potential to support independent post hoc audits of LLM behavior.
Authors: Jinjie Shen, Yaxiong Wang, Lechao Cheng, Nan Pu, Zhun Zhong
Abstract: The detection and grounding of manipulated content in multimodal data has emerged as a critical challenge in media forensics. While existing benchmarks demonstrate technical progress, they suffer from misalignment artifacts that poorly reflect real-world manipulation patterns: practical attacks typically maintain semantic consistency across modalities, whereas current datasets artificially disrupt cross-modal alignment, creating easily detectable anomalies. To bridge this gap, we pioneer the detection of semantically-coordinated manipulations where visual edits are systematically paired with semantically consistent textual descriptions. Our approach begins with constructing the first Semantic-Aligned Multimodal Manipulation (SAMM) dataset, generated through a two-stage pipeline: 1) applying state-of-the-art image manipulations, followed by 2) generation of contextually-plausible textual narratives that reinforce the visual deception. Building on this foundation, we propose a Retrieval-Augmented Manipulation Detection and Grounding (RamDG) framework. RamDG commences by harnessing external knowledge repositories to retrieve contextual evidence, which serves as the auxiliary texts and encoded together with the inputs through our image forgery grounding and deep manipulation detection modules to trace all manipulations. Extensive experiments demonstrate our framework significantly outperforms existing methods, achieving 2.06\% higher detection accuracy on SAMM compared to state-of-the-art approaches. The dataset and code are publicly available at https://github.com/shen8424/SAMM-RamDG-CAP.
Authors: Amin Ghodousian, Sara Zal, Minoo Ahmadi
Abstract: In this paper, we study a latticized optimization problem with fuzzy relational inequality constraints where the feasible region is formed as the intersection of two inequality fuzzy systems and Sugeno-Weber family of t-norms is considered as fuzzy composition. Sugeno-Weber family of t-norms and t-conorms is one of the most applied one in various fuzzy modelling problems. This family of t-norms and t-conorms was suggested by Weber for modeling intersection and union of fuzzy sets. Also, the t-conorms were suggested as addition rules by Sugeno for so-called alpha-fuzzy measures. The resolution of the feasible region of the problem is firstly investigated when it is defined with max-Sugeno-Weber composition and a necessary and sufficient condition is presented for determining the feasibility. Then, based on some theoretical properties of the problem, an algorithm is presented for solving this nonlinear problem. It is proved that the algorithm can find the exact optimal solution and an example is presented to illustrate the proposed algorithm.
Authors: YiTong Liu, TianZhu Liu, YanFeng GU
Abstract: Cross-view geo-localization aims to determine the geographical location of a query image by matching it against a gallery of images. This task is challenging due to the significant appearance variations of objects observed from variable views, along with the difficulty in extracting discriminative features. Existing approaches often rely on extracting features through feature map segmentation while neglecting spatial and semantic information. To address these issues, we propose the EVA02-based Multi-scale Frequency Attention Fusion (MFAF) method. The MFAF method consists of Multi-Frequency Branch-wise Block (MFB) and the Frequency-aware Spatial Attention (FSA) module. The MFB block effectively captures both low-frequency structural features and high-frequency edge details across multiple scales, improving the consistency and robustness of feature representations across various viewpoints. Meanwhile, the FSA module adaptively focuses on the key regions of frequency features, significantly mitigating the interference caused by background noise and viewpoint variability. Extensive experiments on widely recognized benchmarks, including University-1652, SUES-200, and Dense-UAV, demonstrate that the MFAF method achieves competitive performance in both drone localization and drone navigation tasks.
Authors: Yiyang Li, Yonghuang Wu, Ying Luo, Liangtai Sun, Zishu Qin, Lin Qiu, Xuezhi Cao, Xunliang Cai
Abstract: Evaluations of large language models (LLMs) suffer from instability, where small changes of random factors such as few-shot examples can lead to drastic fluctuations of scores and even model rankings. Moreover, different LLMs can have different preferences for a certain setting of random factors. As a result, using a fixed setting of random factors, which is often adopted as the paradigm of current evaluations, can lead to potential unfair comparisons between LLMs. To mitigate the volatility of evaluations, we first theoretically analyze the sources of variance induced by changes in random factors. Targeting these specific sources, we then propose the instance-level randomization (ILR) method to reduce variance and enhance fairness in model comparisons. Instead of using a fixed setting across the whole benchmark in a single experiment, we randomize all factors that affect evaluation scores for every single instance, run multiple experiments and report the averaged score. Theoretical analyses and empirical results demonstrate that ILR can reduce the variance and unfair comparisons caused by random factors, as well as achieve similar robustness level with less than half computational cost compared with previous methods.
Authors: Gordon Hung, Ivan Felipe Rodriguez
Abstract: Autonomous underwater vehicles (AUVs) increasingly rely on on-board computer-vision systems for tasks such as habitat mapping, ecological monitoring, and infrastructure inspection. However, underwater imagery is hindered by light attenuation, turbidity, and severe class imbalance, while the computational resources available on AUVs are limited. One-stage detectors from the YOLO family are attractive because they fuse localization and classification in a single, low-latency network; however, their terrestrial benchmarks (COCO, PASCAL-VOC, Open Images) leave open the question of how successive YOLO releases perform in the marine domain. We curate two openly available datasets that span contrasting operating conditions: a Coral Disease set (4,480 images, 18 classes) and a Fish Species set (7,500 images, 20 classes). For each dataset, we create four training regimes (25 %, 50 %, 75 %, 100 % of the images) while keeping balanced validation and test partitions fixed. We train YOLOv8-s, YOLOv9-s, YOLOv10-s, and YOLOv11-s with identical hyperparameters (100 epochs, 640 px input, batch = 16, T4 GPU) and evaluate precision, recall, mAP50, mAP50-95, per-image inference time, and frames-per-second (FPS). Post-hoc Grad-CAM visualizations probe feature utilization and localization faithfulness. Across both datasets, accuracy saturates after YOLOv9, suggesting architectural innovations primarily target efficiency rather than accuracy. Inference speed, however, improves markedly. Our results (i) provide the first controlled comparison of recent YOLO variants on underwater imagery, (ii) show that lightweight YOLOv10 offers the best speed-accuracy trade-off for embedded AUV deployment, and (iii) deliver an open, reproducible benchmark and codebase to accelerate future marine-vision research.
Authors: Zifan Lang, Guixia Liu, Geng Sun, Jiahui Li, Jiacheng Wang, Weijie Yuan, Dusit Niyato, Dong In Kim
Abstract: Despite the widespread deployment of terrestrial networks, providing reliable communication services to remote areas and maintaining connectivity during emergencies remains challenging. Low Earth orbit (LEO) satellite constellations offer promising solutions with their global coverage capabilities and reduced latency, yet struggle with intermittent coverage and limited communication windows due to orbital dynamics. This paper introduces an age of information (AoI)-aware space-air-ground integrated network (SAGIN) architecture that leverages a high-altitude platform (HAP) as intelligent relay between the LEO satellites and ground terminals. Our three-layer design employs hybrid free-space optical (FSO) links for high-capacity satellite-to-HAP communication and reliable radio frequency (RF) links for HAP-to-ground transmission, and thus addressing the temporal discontinuity in LEO satellite coverage while serving diverse user priorities. Specifically, we formulate a joint optimization problem to simultaneously minimize the AoI and satellite handover frequency through optimal transmit power distribution and satellite selection decisions. This highly dynamic, non-convex problem with time-coupled constraints presents significant computational challenges for traditional approaches. To address these difficulties, we propose a novel diffusion model (DM)-enhanced dueling double deep Q-network with action decomposition and state transformer encoder (DD3QN-AS) algorithm that incorporates transformer-based temporal feature extraction and employs a DM-based latent prompt generative module to refine state-action representations through conditional denoising. Simulation results highlight the superior performance of the proposed approach compared with policy-based methods and some other deep reinforcement learning (DRL) benchmarks.
Authors: Yunhan Zhao, Xiang Zheng, Xingjun Ma
Abstract: Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, their effectiveness and efficiency can still be improved. In this work, we reveal an interesting phenomenon: incorporating weak defense into the attack pipeline can significantly enhance both the effectiveness and the efficiency of jailbreaks on VLMs. Building on this insight, we propose Defense2Attack, a novel jailbreak method that bypasses the safety guardrails of VLMs by leveraging defensive patterns to guide jailbreak prompt design. Specifically, Defense2Attack consists of three key components: (1) a visual optimizer that embeds universal adversarial perturbations with affirmative and encouraging semantics; (2) a textual optimizer that refines the input using a defense-styled prompt; and (3) a red-team suffix generator that enhances the jailbreak through reinforcement fine-tuning. We empirically evaluate our method on four VLMs and four safety benchmarks. The results demonstrate that Defense2Attack achieves superior jailbreak performance in a single attempt, outperforming state-of-the-art attack methods that often require multiple tries. Our work offers a new perspective on jailbreaking VLMs.
Authors: Jie Yin, Ke Sun, Han Wu
Abstract: Graph continual learning (GCL) aims to learn from a continuous sequence of graph-based tasks. Regularization methods are vital for preventing catastrophic forgetting in GCL, particularly in the challenging replay-free, class-incremental setting, where each task consists of a set of unique classes. In this work, we first establish a general regularization framework for GCL based on the curved parameter space induced by the Fisher information matrix (FIM). We show that the dominant Elastic Weight Consolidation (EWC) and its variants are a special case within this framework, using a diagonal approximation of the empirical FIM based on parameters from previous tasks. To overcome their limitations, we propose a new unbiased online curvature approximation of the full FIM based on the model's current learning state. Our method directly estimates the regularization term in an online manner without explicitly evaluating and storing the FIM itself. This enables the model to better capture the loss landscape during learning new tasks while retaining the knowledge learned from previous tasks. Extensive experiments on three graph datasets demonstrate that our method significantly outperforms existing regularization-based methods, achieving a superior trade-off between stability (retaining old knowledge) and plasticity (acquiring new knowledge).
Authors: Francesco Zola, Jon Ander Medina, Andrea Venturi, Amaia Gil, Raul Orduna
Abstract: The rise of digital ecosystems has exposed the financial sector to evolving abuse and criminal tactics that share operational knowledge and techniques both within and across different environments (fiat-based, crypto-assets, etc.). Traditional rule-based systems lack the adaptability needed to detect sophisticated or coordinated criminal behaviors (patterns), highlighting the need for strategies that analyze actors' interactions to uncover suspicious activities and extract their modus operandi. For this reason, in this work, we propose an approach that integrates graph machine learning and network analysis to improve the detection of well-known topological patterns within transactional graphs. However, a key challenge lies in the limitations of traditional financial datasets, which often provide sparse, unlabeled information that is difficult to use for graph-based pattern analysis. Therefore, we firstly propose a four-step preprocessing framework that involves (i) extracting graph structures, (ii) considering data temporality to manage large node sets, (iii) detecting communities within, and (iv) applying automatic labeling strategies to generate weak ground-truth labels. Then, once the data is processed, Graph Autoencoders are implemented to distinguish among the well-known topological patterns. Specifically, three different GAE variants are implemented and compared in this analysis. Preliminary results show that this pattern-focused, topology-driven method is effective for detecting complex financial crime schemes, offering a promising alternative to conventional rule-based detection systems.
Authors: Trung Kien La, Eric Guiffo Kaigom
Abstract: In this work, deep neural networks made up of multiple hidden Long Short-Term Memory (LSTM) and Feedforward layers are trained to predict the thermal behavior of the joint motors of robot manipulators. A model-free and scalable approach is adopted. It accommodates complexity and uncertainty challenges stemming from the derivation, identification, and validation of a large number of parameters of an approximation model that is hardly available. To this end, sensed joint torques are collected and processed to foresee the thermal behavior of joint motors. Promising prediction results of the machine learning based capture of the temperature dynamics of joint motors of a redundant robot with seven joints are presented.
Authors: Eric Guiffo Kaigom
Abstract: Robots are unrelentingly used to achieve operational efficiency in Industry 4.0 along with symbiotic and sustainable assistance for the work-force in Industry 5.0. As resilience, robustness, and well-being are required in anti-fragile manufacturing and human-centric societal tasks, an autonomous anticipation and adaption to thermal saturation and burns due to motors overheating become instrumental for human safety and robot availability. Robots are thereby expected to self-sustain their performance and deliver user experience, in addition to communicating their capability to other agents in advance to ensure fully automated thermally feasible tasks, and prolong their lifetime without human intervention. However, the traditional robot shutdown, when facing an imminent thermal saturation, inhibits productivity in factories and comfort in the society, while cooling strategies are hard to implement after the robot acquisition. In this work, smart digital twins endowed with generative AI, i.e., variational autoencoders, are leveraged to manage thermally anomalous and generate uncritical robot states. The notion of thermal difficulty is derived from the reconstruction error of variational autoencoders. A robot can use this score to predict, anticipate, and share the thermal feasibility of desired motion profiles to meet requirements from emerging applications in Industry 6.0 and Society 6.0.
Authors: Alexis Yihong Hao, Yufei Wang, Navin Sriram Ravie, Bharath Hegde, David Held, Zackory Erickson
Abstract: Robot-assisted dressing has the potential to significantly improve the lives of individuals with mobility impairments. To ensure an effective and comfortable dressing experience, the robot must be able to handle challenging deformable garments, apply appropriate forces, and adapt to limb movements throughout the dressing process. Prior work often makes simplifying assumptions -- such as static human limbs during dressing -- which limits real-world applicability. In this work, we develop a robot-assisted dressing system capable of handling partial observations with visual occlusions, as well as robustly adapting to arm motions during the dressing process. Given a policy trained in simulation with partial observations, we propose a method to fine-tune it in the real world using a small amount of data and multi-modal feedback from vision and force sensing, to further improve the policy's adaptability to arm motions and enhance safety. We evaluate our method in simulation with simplified articulated human meshes and in a real world human study with 12 participants across 264 dressing trials. Our policy successfully dresses two long-sleeve everyday garments onto the participants while being adaptive to various kinds of arm motions, and greatly outperforms prior baselines in terms of task completion and user feedback. Video are available at https://dressing-motion.github.io/.
Authors: Saki Hashimoto, Shoichi Hasegawa, Tomochika Ishikawa, Akira Taniguchi, Yoshinobu Hagiwara, Lotfi El Hafi, Tadahiro Taniguchi
Abstract: Robots operating in domestic and office environments must understand object ownership to correctly execute instructions such as ``Bring me my cup.'' However, ownership cannot be reliably inferred from visual features alone. To address this gap, we propose Active Ownership Learning (ActOwL), a framework that enables robots to actively generate and ask ownership-related questions to users. ActOwL employs a probabilistic generative model to select questions that maximize information gain, thereby acquiring ownership knowledge efficiently to improve learning efficiency. Additionally, by leveraging commonsense knowledge from Large Language Models (LLM), objects are pre-classified as either shared or owned, and only owned objects are targeted for questioning. Through experiments in a simulated home environment and a real-world laboratory setting, ActOwL achieved significantly higher ownership clustering accuracy with fewer questions than baseline methods. These findings demonstrate the effectiveness of combining active inference with LLM-guided commonsense reasoning, advancing the capability of robots to acquire ownership knowledge for practical and socially appropriate task execution.
Authors: Zihan Wang, Zihan Liang, Zhou Shao, Yufei Ma, Huangyu Dai, Ben Chen, Lingtao Mao, Chenyi Lei, Yuqing Ding, Han Li
Abstract: Retrieval-Augmented Generation (RAG) has emerged as a promising approach to address key limitations of Large Language Models (LLMs), such as hallucination, outdated knowledge, and lacking reference. However, current RAG frameworks often struggle with identifying whether retrieved documents meaningfully contribute to answer generation. This shortcoming makes it difficult to filter out irrelevant or even misleading content, which notably impacts the final performance. In this paper, we propose Document Information Gain (DIG), a novel metric designed to quantify the contribution of retrieved documents to correct answer generation. DIG measures a document's value by computing the difference of LLM's generation confidence with and without the document augmented. Further, we introduce InfoGain-RAG, a framework that leverages DIG scores to train a specialized reranker, which prioritizes each retrieved document from exact distinguishing and accurate sorting perspectives. This approach can effectively filter out irrelevant documents and select the most valuable ones for better answer generation. Extensive experiments across various models and benchmarks demonstrate that InfoGain-RAG can significantly outperform existing approaches, on both single and multiple retrievers paradigm. Specifically on NaturalQA, it achieves the improvements of 17.9%, 4.5%, 12.5% in exact match accuracy against naive RAG, self-reflective RAG and modern ranking-based RAG respectively, and even an average of 15.3% increment on advanced proprietary model GPT-4o across all datasets. These results demonstrate the feasibility of InfoGain-RAG as it can offer a reliable solution for RAG in multiple applications.
Authors: Damola Agbelese, Krishna Chaitanya, Pushpak Pati, Chaitanya Parmar, Pooya Mobadersany, Shreyas Fadnavis, Lindsey Surace, Shadi Yarandi, Louis R. Ghanem, Molly Lucas, Tommaso Mansi, Oana Gabriela Cula, Pablo F. Damasceno, Kristopher Standish
Abstract: Reliable uncertainty quantification (UQ) is essential in medical AI. Evidential Deep Learning (EDL) offers a computationally efficient way to quantify model uncertainty alongside predictions, unlike traditional methods such as Monte Carlo (MC) Dropout and Deep Ensembles (DE). However, all these methods often rely on a single expert's annotations as ground truth for model training, overlooking the inter-rater variability in healthcare. To address this issue, we propose MEGAN, a Multi-Expert Gating Network that aggregates uncertainty estimates and predictions from multiple AI experts via EDL models trained with diverse ground truths and modeling strategies. MEGAN's gating network optimally combines predictions and uncertainties from each EDL model, enhancing overall prediction confidence and calibration. We extensively benchmark MEGAN on endoscopy videos for Ulcerative colitis (UC) disease severity estimation, assessed by visual labeling of Mayo Endoscopic Subscore (MES), where inter-rater variability is prevalent. In large-scale prospective UC clinical trial, MEGAN achieved a 3.5% improvement in F1-score and a 30.5% reduction in Expected Calibration Error (ECE) compared to existing methods. Furthermore, MEGAN facilitated uncertainty-guided sample stratification, reducing the annotation burden and potentially increasing efficiency and consistency in UC trials.
Authors: Halil H\"useyin \c{C}al{\i}\c{s}kan, Talha Koruk
Abstract: Machine learning models and libraries can train datasets of different sizes and perform prediction and classification operations, but machine learning models and libraries cause slow and long training times on large datasets. This article introduces EmbeddedML, a training-time-optimized and mathematically enhanced machine learning library. The speed was increased by approximately times compared to scikit-learn without any loss in terms of accuracy in regression models such as Multiple Linear Regression. Logistic Regression and Support Vector Machines (SVM) algorithms have been mathematically rewritten to reduce training time and increase accuracy in classification models. With the applied mathematical improvements, training time has been reduced by approximately 2 times for SVM on small datasets and by around 800 times on large datasets, and by approximately 4 times for Logistic Regression, compared to the scikit-learn implementation. In summary, the EmbeddedML library offers regression, classification, clustering, and dimensionality reduction algorithms that are mathematically rewritten and optimized to reduce training time.
Authors: Zhifang Gong, Shuo Gao, Ben Zhao, Yingjing Xu, Yijun Yang, Shenghong Ju, Guangquan Zhou
Abstract: Contrast-enhanced computed tomography (CECT) is the primary imaging technique that provides valuable spatial-temporal information about lesions, enabling the accurate diagnosis and subclassification of pancreatic tumors. However, the high heterogeneity and variability of pancreatic tumors still pose substantial challenges for precise subtyping diagnosis. Previous methods fail to effectively explore the contextual information across multiple CECT phases commonly used in radiologists' diagnostic workflows, thereby limiting their performance. In this paper, we introduce, for the first time, an automatic way to combine the multi-phase CECT data to discriminate between pancreatic tumor subtypes, among which the key is using Mamba with promising learnability and simplicity to encourage both temporal and spatial modeling from multi-phase CECT. Specifically, we propose a dual hierarchical contrast-enhanced-aware Mamba module incorporating two novel spatial and temporal sampling sequences to explore intra and inter-phase contrast variations of lesions. A similarity-guided refinement module is also imposed into the temporal scanning modeling to emphasize the learning on local tumor regions with more obvious temporal variations. Moreover, we design the space complementary integrator and multi-granularity fusion module to encode and aggregate the semantics across different scales, achieving more efficient learning for subtyping pancreatic tumors. The experimental results on an in-house dataset of 270 clinical cases achieve an accuracy of 97.4% and an AUC of 98.6% in distinguishing between pancreatic ductal adenocarcinoma (PDAC) and pancreatic neuroendocrine tumors (PNETs), demonstrating its potential as a more accurate and efficient tool.
Authors: Nenad Petrovic, Lukasz Mazur, Alois Knoll
Abstract: There are many bottlenecks that decrease the flexibility of automotive systems, making their long-term maintenance, as well as updates and extensions in later lifecycle phases increasingly difficult, mainly due to long re-engineering, standardization, and compliance procedures, as well as heterogeneity and numerosity of devices and underlying software components involved. In this paper, we explore the potential of Large Language Models (LLMs) when it comes to the automation of tasks and processes that aim to increase the flexibility of automotive systems. Three case studies towards achieving this goal are considered as outcomes of early-stage research: 1) updates, hardware abstraction, and compliance, 2) interface compatibility checking, and 3) architecture modification suggestions. For proof-of-concept implementation, we rely on OpenAI's GPT-4o model.
Authors: Axel Wiebe Werner, Jonas Beskow, Anna Deichler
Abstract: Gestures are central to human communication, enriching interactions through non-verbal expression. Virtual avatars increasingly use AI-generated gestures to enhance life-likeness, yet evaluations have largely been confined to 2D. Virtual Reality (VR) provides an immersive alternative that may affect how gestures are perceived. This paper presents a comparative evaluation of computer-generated gestures in VR and 2D, examining three models from the 2023 GENEA Challenge. Results show that gestures viewed in VR were rated slightly higher on average, with the strongest effect observed for motion-capture "true movement." While model rankings remained consistent across settings, VR influenced participants' overall perception and offered unique benefits over traditional 2D evaluation.
Authors: Maximilian Ilse, Harshita Sharma, Anton Schwaighofer, Sam Bond-Taylor, Fernando P\'erez-Garc\'ia, Olesya Melnichenko, Anne-Marie G. Sykes, Kelly K. Horst, Ashish Khandelwal, Maxwell Reynolds, Maria T. Wetscherek, Noel C. F. Codella, Javier Alvarez-Valle, Korfiatis Panagiotis, Valentina Salvatelli
Abstract: Foundation vision encoders such as CLIP and DINOv2, trained on web-scale data, exhibit strong transfer performance across tasks and datasets. However, medical imaging foundation models remain constrained by smaller datasets, limiting our understanding of how data scale and pretraining paradigms affect performance in this setting. In this work, we systematically study continual pretraining of two vision encoders, MedImageInsight (MI2) and RAD-DINO representing the two major encoder paradigms CLIP and DINOv2, on up to 3.5M chest x-rays from a single institution, holding compute and evaluation protocols constant. We evaluate on classification (radiology findings, lines and tubes), segmentation (lines and tubes), and radiology report generation. While prior work has primarily focused on tasks related to radiology findings, we include lines and tubes tasks to counterbalance this bias and evaluate a model's ability to extract features that preserve continuity along elongated structures. Our experiments show that MI2 scales more effectively for finding-related tasks, while RAD-DINO is stronger on tube-related tasks. Surprisingly, continually pretraining MI2 with both reports and structured labels using UniCL improves performance, underscoring the value of structured supervision at scale. We further show that for some tasks, as few as 30k in-domain samples are sufficient to surpass open-weights foundation models. These results highlight the utility of center-specific continual pretraining, enabling medical institutions to derive significant performance gains by utilizing in-domain data.
Authors: Curt Stutsman, Eliot W. Robson, Abhishek K. Umrawal
Abstract: In many real-world scenarios, an individual's local social network carries significant influence over the opinions they form and subsequently propagate to others. In this paper, we propose a novel diffusion model -- the Pressure Threshold model (PT) -- for dynamically simulating the spread of influence through a social network. This new model extends the popular Linear Threshold Model (LT) by adjusting a node's outgoing influence proportional to the influence it receives from its activated neighbors. We address the Influence Maximization (IM) problem, which involves selecting the most effective seed nodes to achieve maximal graph coverage after a diffusion process, and how the problem manifests with the PT Model. Experiments conducted on real-world networks, facilitated by enhancements to the open-source network-diffusion Python library, CyNetDiff, demonstrate unique seed node selection for the PT Model when compared to the LT Model. Moreover, analyses demonstrate that densely connected networks amplify pressure effects more significantly than sparse networks.
Authors: Javeria Amir, Farwa Attaria, Mah Jabeen, Umara Noor, Zahid Rashid
Abstract: Recent developments in voice cloning and talking head generation demonstrate impressive capabilities in synthesizing natural speech and realistic lip synchronization. Current methods typically require and are trained on large scale datasets and computationally intensive processes using clean studio recorded inputs that is infeasible in noisy or low resource environments. In this paper, we introduce a new modular pipeline comprising Tortoise text to speech. It is a transformer based latent diffusion model that can perform high fidelity zero shot voice cloning given only a few training samples. We use a lightweight generative adversarial network architecture for robust real time lip synchronization. The solution will contribute to many essential tasks concerning less reliance on massive pre training generation of emotionally expressive speech and lip synchronization in noisy and unconstrained scenarios. The modular structure of the pipeline allows an easy extension for future multi modal and text guided voice modulation and it could be used in real world systems.
Authors: Kento Murata, Shoichi Hasegawa, Tomochika Ishikawa, Yoshinobu Hagiwara, Akira Taniguchi, Lotfi El Hafi, Tadahiro Taniguchi
Abstract: It is crucial to efficiently execute instructions such as "Find an apple and a banana" or "Get ready for a field trip," which require searching for multiple objects or understanding context-dependent commands. This study addresses the challenging problem of determining which robot should be assigned to which part of a task when each robot possesses different situational on-site knowledge-specifically, spatial concepts learned from the area designated to it by the user. We propose a task planning framework that leverages large language models (LLMs) and spatial concepts to decompose natural language instructions into subtasks and allocate them to multiple robots. We designed a novel few-shot prompting strategy that enables LLMs to infer required objects from ambiguous commands and decompose them into appropriate subtasks. In our experiments, the proposed method achieved 47/50 successful assignments, outperforming random (28/50) and commonsense-based assignment (26/50). Furthermore, we conducted qualitative evaluations using two actual mobile manipulators. The results demonstrated that our framework could handle instructions, including those involving ad hoc categories such as "Get ready for a field trip," by successfully performing task decomposition, assignment, sequential planning, and execution.
Authors: Xin Fang, Guirui Zhong, Qing Wang, Fan Chu, Lei Wang, Mengui Qian, Mingqi Cai, Jiangzhao Wu, Jianqing Gao, Jun Du
Abstract: Anomalous Sound Detection (ASD) is often formulated as a machine attribute classification task, a strategy necessitated by the common scenario where only normal data is available for training. However, the exhaustive collection of machine attribute labels is laborious and impractical. To address the challenge of missing attribute labels, this paper proposes an agglomerative hierarchical clustering method for the assignment of pseudo-attribute labels using representations derived from a domain-adaptive pre-trained model, which are expected to capture machine attribute characteristics. We then apply model adaptation to this pre-trained model through supervised fine-tuning for machine attribute classification, resulting in a new state-of-the-art performance. Evaluation on the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge dataset demonstrates that our proposed approach yields significant performance gains, ultimately outperforming our previous top-ranking system in the challenge.
Authors: Pedro Garcia Lopez, Daniel Barcelona Pons, Marcin Copik, Torsten Hoefler, Eduardo Qui\~nones, Maciej Malawski, Peter Pietzutch, Alberto Marti, Thomas Ohlson Timoudas, Aleksander Slominski
Abstract: The strategic importance of artificial intelligence is driving a global push toward Sovereign AI initiatives. Nationwide governments are increasingly developing dedicated infrastructures, called AI Factories (AIF), to achieve technological autonomy and secure the resources necessary to sustain robust local digital ecosystems. In Europe, the EuroHPC Joint Undertaking is investing hundreds of millions of euros into several AI Factories, built atop existing high-performance computing (HPC) supercomputers. However, while HPC systems excel in raw performance, they are not inherently designed for usability, accessibility, or serving as public-facing platforms for AI services such as inference or agentic applications. In contrast, AI practitioners are accustomed to cloud-native technologies like Kubernetes and object storage, tools that are often difficult to integrate within traditional HPC environments. This article advocates for a dual-stack approach within supercomputers: integrating both HPC and cloud-native technologies. Our goal is to bridge the divide between HPC and cloud computing by combining high performance and hardware acceleration with ease of use and service-oriented front-ends. This convergence allows each paradigm to amplify the other. To this end, we will study the cloud challenges of HPC (Serverless HPC) and the HPC challenges of cloud technologies (High-performance Cloud).
Authors: Yubo Zhu, Dongrui Liu, Zecheng Lin, Wei Tong, Sheng Zhong, Jing Shao
Abstract: Estimating the difficulty of input questions as perceived by large language models (LLMs) is essential for accurate performance evaluation and adaptive inference. Existing methods typically rely on repeated response sampling, auxiliary models, or fine-tuning the target model itself, which may incur substantial computational costs or compromise generality. In this paper, we propose a novel approach for difficulty estimation that leverages only the hidden representations produced by the target LLM. We model the token-level generation process as a Markov chain and define a value function to estimate the expected output quality given any hidden state. This allows for efficient and accurate difficulty estimation based solely on the initial hidden state, without generating any output tokens. Extensive experiments across both textual and multimodal tasks demonstrate that our method consistently outperforms existing baselines in difficulty estimation. Moreover, we apply our difficulty estimates to guide adaptive reasoning strategies, including Self-Consistency, Best-of-N, and Self-Refine, achieving higher inference efficiency with fewer generated tokens.
Authors: Weiming Chen, Zhihan Zhu, Yijia Wang, Zhihai He
Abstract: Rectified flow (RF) models have recently demonstrated superior generative performance compared to DDIM-based diffusion models. However, in real-world applications, they suffer from two major challenges: (1) low inversion accuracy that hinders the consistency with the source image, and (2) entangled multimodal attention in diffusion transformers, which hinders precise attention control. To address the first challenge, we propose an efficient high-order inversion method for rectified flow models based on the Runge-Kutta solver of differential equations. To tackle the second challenge, we introduce Decoupled Diffusion Transformer Attention (DDTA), a novel mechanism that disentangles text and image attention inside the multimodal diffusion transformers, enabling more precise semantic control. Extensive experiments on image reconstruction and text-guided editing tasks demonstrate that our method achieves state-of-the-art performance in terms of fidelity and editability. Code is available at https://github.com/wmchen/RKSovler_DDTA.
Authors: Shiyu Li, Yang Tang, Ruijie Liu, Shi-Zhe Chen, Xi Chen
Abstract: Large language models (LLMs) have recently demonstrated excellent performance in text embedding tasks. Previous work usually use LoRA to fine-tune existing LLMs, which are limited by the data and training gap between LLMs and embedding models. In this work, we introduce Conan-embedding-v2, a new 1.4B-parameter LLM trained from scratch and fine-tuned as a text embedder. First, we add news data and multilingual pairs for LLM pretraining to bridge the data gap. Based on this, we propose a cross-lingual retrieval dataset that enables the LLM to better integrate embeddings across different languages. Second, whereas LLMs use a causal mask with token-level loss, embedding models use a bidirectional mask with sentence-level loss. This training gap makes full fine-tuning less effective than LoRA. We introduce a soft-masking mechanism to gradually transition between these two types of masks, enabling the model to learn more comprehensive representations. Based on this, we propose a dynamic hard negative mining method that exposes the model to more difficult negative examples throughout the training process. Being intuitive and effective, with only approximately 1.4B parameters, Conan-embedding-v2 achieves SOTA performance on both the Massive Text Embedding Benchmark (MTEB) and Chinese MTEB (May 19, 2025).
Authors: Jianfei Zhao, Feng Zhang, Xin Sun, Lingxing Kong, Zhixing Tan, Chong Feng
Abstract: Large Vision-Language Models (LVLMs) can accurately locate key objects in images, yet their attention to these objects tends to be very brief. Motivated by the hypothesis that sustained focus on key objects can improve LVLMs' visual capabilities, we propose Cross-Layer Vision Smoothing (CLVS). The core idea of CLVS is to incorporate a vision memory that smooths the attention distribution across layers. Specifically, we initialize this vision memory with position-unbiased visual attention in the first layer. In subsequent layers, the model's visual attention jointly considers the vision memory from previous layers, while the memory is updated iteratively, thereby maintaining smooth attention on key objects. Given that visual understanding primarily occurs in the early and middle layers of the model, we use uncertainty as an indicator of completed visual understanding and terminate the smoothing process accordingly. Experiments on four benchmarks across three LVLMs confirm the effectiveness and generalizability of our method. CLVS achieves state-of-the-art performance on a variety of visual understanding tasks, with particularly significant improvements in relation and attribute understanding.
Authors: Caiqi Zhang, Chang Shu, Ehsan Shareghi, Nigel Collier
Abstract: Confidence estimation is essential for the reliable deployment of large language models (LLMs). Existing methods are primarily designed for factual QA tasks and often fail to generalize to reasoning tasks. To address this gap, we propose a set of training-free, graph-based confidence estimation methods tailored to reasoning tasks. Our approach models reasoning paths as directed graphs and estimates confidence by exploiting graph properties such as centrality, path convergence, and path weighting. Experiments with two LLMs on three reasoning datasets demonstrate improved confidence estimation and enhanced performance on two downstream tasks.
Authors: Magnus Wiik Eckhoff, Peter Marius Flydal, Siem Peters, Martin Eian, Jonas Halvorsen, Vasileios Mavroeidis, Gudmund Grov
Abstract: Interpreting the massive volume of security alerts is a significant challenge in Security Operations Centres (SOCs). Effective contextualisation is important, enabling quick distinction between genuine threats and benign activity to prioritise what needs further analysis.This paper proposes a graph-based approach to enhance alert contextualisation in a SOC by aggregating alerts into graph-based alert groups, where nodes represent alerts and edges denote relationships within defined time-windows. By grouping related alerts, we enable analysis at a higher abstraction level, capturing attack steps more effectively than individual alerts. Furthermore, to show that our format is well suited for downstream machine learning methods, we employ Graph Matching Networks (GMNs) to correlate incoming alert groups with historical incidents, providing analysts with additional insights.
Authors: Johan Wahr\'eus, Ahmed Hussain, Panos Papadimitratos
Abstract: Large Language Models (LLMs) are increasingly deployed for task automation and content generation, yet their safety mechanisms remain vulnerable to circumvention through different jailbreaking techniques. In this paper, we introduce \textit{Content Concretization} (CC), a novel jailbreaking technique that iteratively transforms abstract malicious requests into concrete, executable implementations. CC is a two-stage process: first, generating initial LLM responses using lower-tier, less constrained safety filters models, then refining them through higher-tier models that process both the preliminary output and original prompt. We evaluate our technique using 350 cybersecurity-specific prompts, demonstrating substantial improvements in jailbreak Success Rates (SRs), increasing from 7\% (no refinements) to 62\% after three refinement iterations, while maintaining a cost of 7.5\textcent~per prompt. Comparative A/B testing across nine different LLM evaluators confirms that outputs from additional refinement steps are consistently rated as more malicious and technically superior. Moreover, manual code analysis reveals that generated outputs execute with minimal modification, although optimal deployment typically requires target-specific fine-tuning. With eventual improved harmful code generation, these results highlight critical vulnerabilities in current LLM safety frameworks.
Authors: Haneen Najjar, Eyal Ronen, Mahmood Sharif
Abstract: Security-critical machine-learning (ML) systems, such as face-recognition systems, are susceptible to adversarial examples, including real-world physically realizable attacks. Various means to boost ML's adversarial robustness have been proposed; however, they typically induce unfair robustness: It is often easier to attack from certain classes or groups than from others. Several techniques have been developed to improve adversarial robustness while seeking perfect fairness between classes. Yet, prior work has focused on settings where security and fairness are less critical. Our insight is that achieving perfect parity in realistic fairness-critical tasks, such as face recognition, is often infeasible -- some classes may be highly similar, leading to more misclassifications between them. Instead, we suggest that seeking symmetry -- i.e., attacks from class $i$ to $j$ would be as successful as from $j$ to $i$ -- is more tractable. Intuitively, symmetry is a desirable because class resemblance is a symmetric relation in most domains. Additionally, as we prove theoretically, symmetry between individuals induces symmetry between any set of sub-groups, in contrast to other fairness notions where group-fairness is often elusive. We develop Sy-FAR, a technique to encourage symmetry while also optimizing adversarial robustness and extensively evaluate it using five datasets, with three model architectures, including against targeted and untargeted realistic attacks. The results show Sy-FAR significantly improves fair adversarial robustness compared to state-of-the-art methods. Moreover, we find that Sy-FAR is faster and more consistent across runs. Notably, Sy-FAR also ameliorates another type of unfairness we discover in this work -- target classes that adversarial examples are likely to be classified into become significantly less vulnerable after inducing symmetry.
Authors: Zongyu Yang, Zhenghao Yang, Wenjing Tian, Jiyuan Li, Xiang Sun, Guohui Zheng, Songfen Liu, Niannian Wu, Rongpeng Li, Zhaohe Xu, Bo Li, Zhongbing Shi, Zhe Gao, Wei Chen, Xiaoquan Ji, Min Xu, Wulyu Zhong
Abstract: In magnetically confined fusion device, the complex, multiscale, and nonlinear dynamics of plasmas necessitate the integration of extensive diagnostic systems to effectively monitor and control plasma behaviour. The complexity and uncertainty arising from these extensive systems and their tangled interrelations has long posed a significant obstacle to the acceleration of fusion energy development. In this work, a large-scale model, fusion masked auto-encoder (FusionMAE) is pre-trained to compress the information from 88 diagnostic signals into a concrete embedding, to provide a unified interface between diagnostic systems and control actuators. Two mechanisms are proposed to ensure a meaningful embedding: compression-reduction and missing-signal reconstruction. Upon completion of pre-training, the model acquires the capability for 'virtual backup diagnosis', enabling the inference of missing diagnostic data with 96.7% reliability. Furthermore, the model demonstrates three emergent capabilities: automatic data analysis, universal control-diagnosis interface, and enhancement of control performance on multiple tasks. This work pioneers large-scale AI model integration in fusion energy, demonstrating how pre-trained embeddings can simplify the system interface, reducing necessary diagnostic systems and optimize operation performance for future fusion reactors.
Authors: Yuval Weiss, David Demitri Africa, Paula Buttery, Richard Diehl Martinez
Abstract: Parameter-efficient methods such as LoRA have revolutionised the fine-tuning of LLMs. Still, their extension to pretraining via ReLoRA is less well understood, especially for small language models (SLMs), which offer lower computational and environmental costs. This work is the first systematic study of ReLoRA in SLMs (11M-66M parameters), evaluating both performance and learning dynamics. Through ablation experiments, we find that ReLoRA generally performs worse than standard training on loss, Paloma perplexity and BLiMP, with the gap widening for the larger models. Further analysis of the learning dynamics of the models indicates that ReLoRA reinforces the rank deficiencies found in smaller models. These results indicate that low-rank update strategies may not transfer easily to SLM pretraining, highlighting the need for more research in the low-compute regime.
Authors: Erblin Isaku, Hassan Sartaj, Shaukat Ali, Beatriz Sanguino, Tongtong Wang, Guoyuan Li, Houxiang Zhang, Thomas Peyrucain
Abstract: Self-adaptive robots (SARs) in complex, uncertain environments must proactively detect and address abnormal behaviors, including out-of-distribution (OOD) cases. To this end, digital twins offer a valuable solution for OOD detection. Thus, we present a digital twin-based approach for OOD detection (ODiSAR) in SARs. ODiSAR uses a Transformer-based digital twin to forecast SAR states and employs reconstruction error and Monte Carlo dropout for uncertainty quantification. By combining reconstruction error with predictive variance, the digital twin effectively detects OOD behaviors, even in previously unseen conditions. The digital twin also includes an explainability layer that links potential OOD to specific SAR states, offering insights for self-adaptation. We evaluated ODiSAR by creating digital twins of two industrial robots: one navigating an office environment, and another performing maritime ship navigation. In both cases, ODiSAR forecasts SAR behaviors (i.e., robot trajectories and vessel motion) and proactively detects OOD events. Our results showed that ODiSAR achieved high detection performance -- up to 98\% AUROC, 96\% TNR@TPR95, and 95\% F1-score -- while providing interpretable insights to support self-adaptation.
Authors: Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Sicong Li, Qingming Huang
Abstract: In this report, we address the problem of determining whether a user performs an action incorrectly from egocentric video data. To handle the challenges posed by subtle and infrequent mistakes, we propose a Dual-Stage Reweighted Mixture-of-Experts (DR-MoE) framework. In the first stage, features are extracted using a frozen ViViT model and a LoRA-tuned ViViT model, which are combined through a feature-level expert module. In the second stage, three classifiers are trained with different objectives: reweighted cross-entropy to mitigate class imbalance, AUC loss to improve ranking under skewed distributions, and label-aware loss with sharpness-aware minimization to enhance calibration and generalization. Their predictions are fused using a classification-level expert module. The proposed method achieves strong performance, particularly in identifying rare and ambiguous mistake instances. The code is available at https://github.com/boyuh/DR-MoE.
Authors: Ya Zhou, Yujie Yang, Xiaohan Fan, Wei Zhao
Abstract: ECG foundation models are increasingly popular due to their adaptability across various tasks. However, their clinical applicability is often limited by performance gaps compared to task-specific models, even after pre-training on large ECG datasets and fine-tuning on target data. This limitation is likely due to the lack of an effective post-training strategy. In this paper, we propose a simple yet effective post-training approach to enhance ECGFounder, a state-of-the-art ECG foundation model pre-trained on over 7 million ECG recordings. Experiments on the PTB-XL benchmark show that our approach improves the baseline fine-tuning strategy by 1.2%-3.3% in macro AUROC and 5.3%-20.9% in macro AUPRC. Additionally, our method outperforms several recent state-of-the-art approaches, including task-specific and advanced architectures. Further evaluation reveals that our method is more stable and sample-efficient compared to the baseline, achieving a 9.1% improvement in macro AUROC and a 34.9% improvement in macro AUPRC using just 10% of the training data. Ablation studies identify key components, such as stochastic depth and preview linear probing, that contribute to the enhanced performance. These findings underscore the potential of post-training strategies to improve ECG foundation models, and we hope this work will contribute to the continued development of foundation models in the ECG domain.
Authors: Phung Duc Luong, Le Tran Gia Bao, Nguyen Vu Khai Tam, Dong Huu Nguyen Khoa, Nguyen Huu Quyen, Van-Hau Pham, Phan The Duy
Abstract: This work introduces xOffense, an AI-driven, multi-agent penetration testing framework that shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable workflows capable of scaling seamlessly with computational infrastructure. At its core, xOffense leverages a fine-tuned, mid-scale open-source LLM (Qwen3-32B) to drive reasoning and decision-making in penetration testing. The framework assigns specialized agents to reconnaissance, vulnerability scanning, and exploitation, with an orchestration layer ensuring seamless coordination across phases. Fine-tuning on Chain-of-Thought penetration testing data further enables the model to generate precise tool commands and perform consistent multi-step reasoning. We evaluate xOffense on two rigorous benchmarks: AutoPenBench and AI-Pentest-Benchmark. The results demonstrate that xOffense consistently outperforms contemporary methods, achieving a sub-task completion rate of 79.17%, decisively surpassing leading systems such as VulnBot and PentestGPT. These findings highlight the potential of domain-adapted mid-scale LLMs, when embedded within structured multi-agent orchestration, to deliver superior, cost-efficient, and reproducible solutions for autonomous penetration testing.
Authors: \c{S}tefan-Claudiu Susan ("Alexandru Ioan Cuza", University of Ia\c{s}i, Department of Computer Science), Andrei Arusoaie ("Alexandru Ioan Cuza", University of Ia\c{s}i, Department of Computer Science), Dorel Lucanu ("Alexandru Ioan Cuza", University of Ia\c{s}i, Department of Computer Science)
Abstract: The high rate of false alarms from static analysis tools and Large Language Models (LLMs) complicates vulnerability detection in Solidity Smart Contracts, demanding methods that can formally or empirically prove the presence of defects. This paper introduces a novel detection pipeline that integrates custom Slither-based detectors, LLMs, Kontrol, and Forge. Our approach is designed to reliably detect defects and generate proofs. We currently perform experiments with promising results for seven types of critical defects. We demonstrate the pipeline's efficacy by presenting our findings for three vulnerabilities -- Reentrancy, Complex Fallback, and Faulty Access Control Policies -- that are challenging for current verification solutions, which often generate false alarms or fail to detect them entirely. We highlight the potential of either symbolic or concrete execution in correctly classifying such code faults. By chaining these instruments, our method effectively validates true positives, significantly reducing the manual verification burden. Although we identify potential limitations, such as the inconsistency and the cost of LLMs, our findings establish a robust framework for combining heuristic analysis with formal verification to achieve more reliable and automated smart contract auditing.
Authors: Raul Zaharia (Al. I. Cuza University,Bitdefender), Drago\c{s} Gavrilu\c{t} (Al. I. Cuza University,Bitdefender), Gheorghi\c{t}\u{a} Mutu (Al. I. Cuza University,Bitdefender)
Abstract: Cybersecurity threats continue to become more sophisticated and diverse in their artifacts, boosting both their volume and complexity. To overcome those challenges, we present GView, an open-source forensic analysis framework with visual and AI-enhanced reasoning. It started with focus on the practical cybersecurity industry. It has evolved significantly, incorporating large language models (LLMs) to dynamically enhance reasoning and ease the forensic workflows. This paper surveys both the current state of GView with its published papers alongside those that are in the publishing process. It also includes its innovative use of logical inference through predicates and inference rules for both the analyzed documents and the user's actions for better suggestions. We highlight the extensible architecture, showcasing its potential as a bridge between the practical forensics worlds with the academic research.
Authors: Yan Chen, Long Li, Teng Xi, Long Zeng, Jingdong Wang
Abstract: Reinforcement learning (RL) has proven highly effective in eliciting the reasoning capabilities of large language models (LLMs). Inspired by this success, recent studies have explored applying similar techniques to vision-language models (VLMs), aiming to enhance their reasoning performance. However, directly transplanting RL methods from LLMs to VLMs is suboptimal, as the tasks faced by VLMs are inherently more complex. Specifically, VLMs must first accurately perceive and understand visual inputs before reasoning can be effectively performed. To address this challenge, we propose a two-stage reinforcement learning framework designed to jointly enhance both the perceptual and reasoning capabilities of VLMs. To mitigate the vanishing advantage issue commonly observed in RL training, we first perform dataset-level sampling to selectively strengthen specific capabilities using distinct data sources. During training, the first stage focuses on improving the model's visual perception through coarse- and fine-grained visual understanding, while the second stage targets the enhancement of reasoning abilities. After the proposed two-stage reinforcement learning process, we obtain PeBR-R1, a vision-language model with significantly enhanced perceptual and reasoning capabilities. Experimental results on seven benchmark datasets demonstrate the effectiveness of our approach and validate the superior performance of PeBR-R1 across diverse visual reasoning tasks.
Authors: Simon Wallace, Sean Rehaag
Abstract: The Access to Algorithmic Justice project (A2AJ) is an open-source alternative to the Canadian Legal Information Institute (CanLII). At a moment when technology promises to enable new ways of working with law, CanLII is becoming an impediment to the free access of law and access to justice movements because it restricts bulk and programmatic access to Canadian legal data. This means that Canada is staring down a digital divide: well-resourced actors have the best new technological tools and, because CanLII has disclaimed leadership, the public only gets second-rate tools. This article puts CanLII in its larger historical context and shows how long and deep efforts to democratize access to Canadian legal data are, and how often they are thwarted by private industry. We introduce the A2AJ's Canadian Legal Data project, which provides open access to over 116,000 court decisions and 5,000 statutes through multiple channels including APIs, machine learning datasets, and AI integration protocols. Through concrete examples, we demonstrate how open legal data enables courts to conduct evidence-based assessments and allows developers to create tools for practitioners serving low-income communities.
Authors: Eyal German, Daniel Samira, Yuval Elovici, Asaf Shabtai
Abstract: Synthetic data generation plays an important role in enabling data sharing, particularly in sensitive domains like healthcare and finance. Recent advances in diffusion models have made it possible to generate realistic, high-quality tabular data, but they may also memorize training records and leak sensitive information. Membership inference attacks (MIAs) exploit this vulnerability by determining whether a record was used in training. While MIAs have been studied in images and text, their use against tabular diffusion models remains underexplored despite the unique risks of structured attributes and limited record diversity. In this paper, we introduce MIAEPT, Membership Inference Attack via Error Prediction for Tabular Data, a novel black-box attack specifically designed to target tabular diffusion models. MIA-EPT constructs errorbased feature vectors by masking and reconstructing attributes of target records, disclosing membership signals based on how well these attributes are predicted. MIA-EPT operates without access to the internal components of the generative model, relying only on its synthetic data output, and was shown to generalize across multiple state-of-the-art diffusion models. We validate MIA-EPT on three diffusion-based synthesizers, achieving AUC-ROC scores of up to 0.599 and TPR@10% FPR values of 22.0% in our internal tests. Under the MIDST 2025 competition conditions, MIA-EPT achieved second place in the Black-box Multi-Table track (TPR@10% FPR = 20.0%). These results demonstrate that our method can uncover substantial membership leakage in synthetic tabular data, challenging the assumption that synthetic data is inherently privacy-preserving. Our code is publicly available at https://github.com/eyalgerman/MIA-EPT.
Authors: Nolan Platt, Pragyansmita Nayak
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across many domains, yet their appli- cation to specialized fields remains constrained by the scarcity and complexity of domain-specific training data. We present a novel approach that achieves a 261x cost reduction for maritime intelligence by using LLMs as one-time teachers rather than using them directly for inference. Our method transforms 3.2 billion Automatic Identification System (AIS) vessel tracking records into 21,543 synthetic question and answer pairs through multi-model generation (GPT-4o and o3-mini), preventing over- fitting and ensuring accurate reasoning. The resulting fine-tuned Qwen2.5-7B model achieves 75% accuracy on maritime tasks, while being substantially cheaper than using a larger model for inference. We show that smaller, cheaper models - when fine tuned properly - can provide similar accuracy compared to larger models that are prohibitively expensive. Our work contributes to the growing field of synthetic dataset generation for specialized AI applications and presents a highly reproducible framework for domains where manual annotation is infeasible. Beyond expand- ing research in the growing field of specialized small language models, our approach has immediate applications in maritime safety, security operations, and vessel traffic management systems in various industries.
Authors: Qianqi Lu, Yuxiang Xie, Jing Zhang, Shiwei Zou, Yan Chen, Xidao Luan
Abstract: Referring Image Segmentation (RIS) is a task that segments image regions based on language expressions, requiring fine-grained alignment between two modalities. However, existing methods often struggle with multimodal misalignment and language semantic loss, especially in complex scenes containing multiple visually similar objects, where uniquely described targets are frequently mislocalized or incompletely segmented. To tackle these challenges, this paper proposes TFANet, a Three-stage Image-Text Feature Alignment Network that systematically enhances multimodal alignment through a hierarchical framework comprising three stages: Knowledge Plus Stage (KPS), Knowledge Fusion Stage (KFS), and Knowledge Intensification Stage (KIS). In the first stage, we design the Multiscale Linear Cross-Attention Module (MLAM), which facilitates bidirectional semantic exchange between visual features and textual representations across multiple scales. This establishes rich and efficient alignment between image regions and different granularities of linguistic descriptions. Subsequently, the KFS further strengthens feature alignment through the Cross-modal Feature Scanning Module (CFSM), which applies multimodal selective scanning to capture long-range dependencies and construct a unified multimodal representation. This is essential for modeling long-range cross-modal dependencies and enhancing alignment accuracy in complex scenes. Finally, in the KIS, we propose the Word-level Linguistic Feature-guided Semantic Deepening Module (WFDM) to compensate for semantic degradation introduced in earlier stages.
Authors: Jonathan K\"ulz, Sehoon Ha, Matthias Althoff
Abstract: Although robotic manipulators are used in an ever-growing range of applications, robot manufacturers typically follow a ``one-fits-all'' philosophy, employing identical manipulators in various settings. This often leads to suboptimal performance, as general-purpose designs fail to exploit particularities of tasks. The development of custom, task-tailored robots is hindered by long, cost-intensive development cycles and the high cost of customized hardware. Recently, various computational design methods have been devised to overcome the bottleneck of human engineering. In addition, a surge of modular robots allows quick and economical adaptation to changing industrial settings. This work proposes an approach to automatically designing and optimizing robot morphologies tailored to a specific environment. To this end, we learn the inverse kinematics for a wide range of different manipulators. A fully differentiable framework realizes gradient-based fine-tuning of designed robots and inverse kinematics solutions. Our generative approach accelerates the generation of specialized designs from hours with optimization-based methods to seconds, serving as a design co-pilot that enables instant adaptation and effective human-AI collaboration. Numerical experiments show that our approach finds robots that can navigate cluttered environments, manipulators that perform well across a specified workspace, and can be adapted to different hardware constraints. Finally, we demonstrate the real-world applicability of our method by setting up a modular robot designed in simulation that successfully moves through an obstacle course.
Authors: Francesco Pappone, Ruggero Marino Lazzaroni, Federico Califano, Niccol\`o Gentile, Roberto Marras
Abstract: While Large Language Models (LLMs) excel at generating human-like text, aligning their outputs with complex, qualitative goals like pedagogical soundness remains a significant challenge. Standard reinforcement learning techniques often rely on slow and expensive LLM-as-a-judge evaluations or on brittle, keyword-based metrics like ROUGE, which fail to capture the semantic essence of a high-quality explanation. In this work, we introduce a novel approach to reward shaping within the Group Relative Policy Optimisation (GRPO) framework. Our central contribution is the use of a small, efficient encoder-only transformer as a semantic reward model. This model provides a dense, semantically rich reward signal based on the cosine similarity between a generated explanation and a ground-truth reference, guiding the policy towards explanations that are not just factually correct but also structurally and conceptually aligned with expert reasoning. We apply this method to the task of training a model for the Italian medical-school entrance examinations, following standard domain-adaptive continued pre-training (CPT) and supervised fine-tuning (SFT). Our results demonstrate that GRPO with our proposed semantic reward significantly improves explanation faithfulness and clarity over a strong SFT baseline, showcasing the power of using lightweight encoder models for nuanced reward shaping in complex generation tasks
Authors: Kohou Wang, Huan Hu, Xiang Liu, Zezhou Chen, Ping Chen, Zhaoxiang Liu, Shiguo Lian
Abstract: The proliferation of sophisticated deepfake technology poses significant challenges to digital security and authenticity. Detecting these forgeries, especially across a wide spectrum of manipulation techniques, requires robust and generalized models. This paper introduces the Hierarchical Deep Fusion Framework (HDFF), an ensemble-based deep learning architecture designed for high-performance facial forgery detection. Our framework integrates four diverse pre-trained sub-models, Swin-MLP, CoAtNet, EfficientNetV2, and DaViT, which are meticulously fine-tuned through a multi-stage process on the MultiFFDI dataset. By concatenating the feature representations from these specialized models and training a final classifier layer, HDFF effectively leverages their collective strengths. This approach achieved a final score of 0.96852 on the competition's private leaderboard, securing the 20th position out of 184 teams, demonstrating the efficacy of hierarchical fusion for complex image classification tasks.
Authors: Zhihao Zhang, Chengyang Peng, Minghao Zhu, Ekim Yurtsever, Keith A. Redmill
Abstract: Autonomous driving in dense, dynamic environments requires decision-making systems that can exploit both spatial structure and long-horizon temporal dependencies while remaining robust to uncertainty. This work presents a novel framework that integrates multi-channel bird's-eye-view occupancy grids with transformer-based sequence modeling for tactical driving in complex roundabout scenarios. To address the imbalance between frequent low-risk states and rare safety-critical decisions, we propose the Uncertainty-Weighted Decision Transformer (UWDT). UWDT employs a frozen teacher transformer to estimate per-token predictive entropy, which is then used as a weight in the student model's loss function. This mechanism amplifies learning from uncertain, high-impact states while maintaining stability across common low-risk transitions. Experiments in a roundabout simulator, across varying traffic densities, show that UWDT consistently outperforms other baselines in terms of reward, collision rate, and behavioral stability. The results demonstrate that uncertainty-aware, spatial-temporal transformers can deliver safer and more efficient decision-making for autonomous driving in complex traffic environments.
Authors: Liang Hu, Jianpeng Jiao, Jiashuo Liu, Yanle Ren, Zhoufutu Wen, Kaiyuan Zhang, Xuanliang Zhang, Xiang Gao, Tianci He, Fei Hu, Yali Liao, Zaiyuan Wang, Chenghao Yang, Qianyu Yang, Mingren Yin, Zhiyuan Zeng, Ge Zhang, Xinyi Zhang, Xiying Zhao, Zhenwei Zhu, Hongseok Namkoong, Wenhao Huang, Yuwen Tang
Abstract: Search has emerged as core infrastructure for LLM-based agents and is widely viewed as critical on the path toward more general intelligence. Finance is a particularly demanding proving ground: analysts routinely conduct complex, multi-step searches over time-sensitive, domain-specific data, making it ideal for assessing both search proficiency and knowledge-grounded reasoning. Yet no existing open financial datasets evaluate data searching capability of end-to-end agents, largely because constructing realistic, complicated tasks requires deep financial expertise and time-sensitive data is hard to evaluate. We present FinSearchComp, the first fully open-source agent benchmark for realistic, open-domain financial search and reasoning. FinSearchComp comprises three tasks -- Time-Sensitive Data Fetching, Simple Historical Lookup, and Complex Historical Investigation -- closely reproduce real-world financial analyst workflows. To ensure difficulty and reliability, we engage 70 professional financial experts for annotation and implement a rigorous multi-stage quality-assurance pipeline. The benchmark includes 635 questions spanning global and Greater China markets, and we evaluate 21 models (products) on it. Grok 4 (web) tops the global subset, approaching expert-level accuracy. DouBao (web) leads on the Greater China subset. Experimental analyses show that equipping agents with web search and financial plugins substantially improves results on FinSearchComp, and the country origin of models and tools impact performance significantly.By aligning with realistic analyst tasks and providing end-to-end evaluation, FinSearchComp offers a professional, high-difficulty testbed for complex financial search and reasoning.
Authors: Alessandro Antonucci, Eric Rossetto, Ivan Duvnjak
Abstract: We investigate individual fairness in generative probabilistic classifiers by analysing the robustness of posterior inferences to perturbations in private features. Building on established results in robustness analysis, we hypothesise a correlation between robustness and predictive accuracy, specifically, instances exhibiting greater robustness are more likely to be classified accurately. We empirically assess this hypothesis using a benchmark of fourteen datasets with fairness concerns, employing Bayesian networks as the underlying generative models. To address the computational complexity associated with robustness analysis over multiple private features with Bayesian networks, we reformulate the problem as a most probable explanation task in an auxiliary Markov random field. Our experiments confirm the hypothesis about the correlation, suggesting novel directions to mitigate the traditional trade-off between fairness and accuracy.
Authors: Yunchuan Guan, Yu Liu, Ke Zhou, Zhiqi Shen, Jenq-Neng Hwang, Serge Belongie, Lei Li
Abstract: Meta-learning is a powerful paradigm for tackling few-shot tasks. However, recent studies indicate that models trained with the whole-class training strategy can achieve comparable performance to those trained with meta-learning in few-shot classification tasks. To demonstrate the value of meta-learning, we establish an entropy-limited supervised setting for fair comparisons. Through both theoretical analysis and experimental validation, we establish that meta-learning has a tighter generalization bound compared to whole-class training. We unravel that meta-learning is more efficient with limited entropy and is more robust to label noise and heterogeneous tasks, making it well-suited for unsupervised tasks. Based on these insights, We propose MINO, a meta-learning framework designed to enhance unsupervised performance. MINO utilizes the adaptive clustering algorithm DBSCAN with a dynamic head for unsupervised task construction and a stability-based meta-scaler for robustness against label noise. Extensive experiments confirm its effectiveness in multiple unsupervised few-shot and zero-shot tasks.
Authors: Francis Ndikum Nji, Vandana Janaja, Jianwu Wang
Abstract: Clustering high-dimensional multivariate spatiotemporal climate data is challenging due to complex temporal dependencies, evolving spatial interactions, and non-stationary dynamics. Conventional clustering methods, including recurrent and convolutional models, often struggle to capture both local and global temporal relationships while preserving spatial context. We present a time-distributed hybrid U-Net autoencoder that integrates a Bi-directional Temporal Graph Attention Transformer (B-TGAT) to guide efficient temporal clustering of multidimensional spatiotemporal climate datasets. The encoder and decoder are equipped with ConvLSTM2D modules that extract joint spatial--temporal features by modeling localized dynamics and spatial correlations over time, and skip connections that preserve multiscale spatial details during feature compression and reconstruction. At the bottleneck, B-TGAT integrates graph-based spatial modeling with attention-driven temporal encoding, enabling adaptive weighting of temporal neighbors and capturing both short and long-range dependencies across regions. This architecture produces discriminative latent embeddings optimized for clustering. Experiments on three distinct spatiotemporal climate datasets demonstrate superior cluster separability, temporal stability, and alignment with known climate transitions compared to state-of-the-art baselines. The integration of ConvLSTM2D, U-Net skip connections, and B-TGAT enhances temporal clustering performance while providing interpretable insights into complex spatiotemporal variability, advancing both methodological development and climate science applications.
Authors: Santanu Banerjee, Goutam Sen, Siddhartha Mukhopadhyay
Abstract: A rich vehicle routing problem is considered allowing multiple trips of heterogeneous vehicles stationed at distributed vehicle depots spread across diverse geographies having access to different modes of transportation. The problem arises from the real world requirement of optimizing the disaster response/preparedness time and minimizes the route duration of the vehicles to achieve the solution with the minimum highest-vehicle-route-duration. Multiple diversely-functional vertices are considered including the concept of Transhipment Ports as inter-modal resource transfer stations. Both simultaneous and split pickup and transferring of different types of delivery and pickup cargo is considered, along with Vehicle-Cargo and Transhipment Port-Cargo Compatibility. The superiority of the proposed cascaded minimization approach is shown over existing makespan minimization approaches through the developed MILP formulation. To solve the problem quickly for practical implementation within Disaster Management-specific Decision Support Systems, an extensive Heuristic Algorithm is devised. The Heuristic utilizes Decision Tree based structuring of possible routes and is able to inherently consider the compatibility issues. Preferential generation of small route elements are performed, which are integrated into route clusters; we consider multiple different logical integration approaches, as well as shuffling the logics to simultaneously produce multiple independent solutions. Finally perturbation of the different solutions are done to find better neighbouring solutions. The computational performance of the PSR-GIP Heuristic, on our created novel datasets, indicate that it is able to give good solutions swiftly for practical problems involving large integer instances which the MILP is unable to solve.
Authors: Hugo Carlesso, Josiane Mothe, Radu Tudor Ionescu
Abstract: Hyperspectral imaging (HSI) captures detailed spectral signatures across hundreds of contiguous bands per pixel, being indispensable for remote sensing applications such as land-cover classification, change detection, and environmental monitoring. Due to the high dimensionality of HSI data and the slow rate of data transfer in satellite-based systems, compact and efficient models are required to support onboard processing and minimize the transmission of redundant or low-value data, e.g. cloud-covered areas. To this end, we introduce a novel curriculum multi-task self-supervised learning (CMTSSL) framework designed for lightweight architectures for HSI analysis. CMTSSL integrates masked image modeling with decoupled spatial and spectral jigsaw puzzle solving, guided by a curriculum learning strategy that progressively increases data complexity during self-supervision. This enables the encoder to jointly capture fine-grained spectral continuity, spatial structure, and global semantic features. Unlike prior dual-task SSL methods, CMTSSL simultaneously addresses spatial and spectral reasoning within a unified and computationally efficient design, being particularly suitable for training lightweight models for onboard satellite deployment. We validate our approach on four public benchmark datasets, demonstrating consistent gains in downstream segmentation tasks, using architectures that are over 16,000x lighter than some state-of-the-art models. These results highlight the potential of CMTSSL in generalizable representation learning with lightweight architectures for real-world HSI applications. Our code is publicly available at https://github.com/hugocarlesso/CMTSSL.
Authors: Zhongwen Xu, Zihan Ding
Abstract: We revisit policy-gradient optimization for Large Language Models (LLMs) from a single-stream perspective. Prevailing group-based methods like GRPO reduce variance with on-the-fly baselines but suffer from critical flaws: frequent degenerate groups erase learning signals, and synchronization barriers hinder scalability. We introduce Single-stream Policy Optimization (SPO), which eliminates these issues by design. SPO replaces per-group baselines with a persistent, KL-adaptive value tracker and normalizes advantages globally across the batch, providing a stable, low-variance learning signal for every sample. Being group-free, SPO enables higher throughput and scales effectively in long-horizon or tool-integrated settings where generation times vary. Furthermore, the persistent value tracker naturally enables an adaptive curriculum via prioritized sampling. Experiments using Qwen3-8B show that SPO converges more smoothly and attains higher accuracy than GRPO, while eliminating computation wasted on degenerate groups. Ablation studies confirm that SPO's gains stem from its principled approach to baseline estimation and advantage normalization, offering a more robust and efficient path for LLM reasoning. Across five hard math benchmarks with Qwen3 8B, SPO improves the average maj@32 by +3.4 percentage points (pp) over GRPO, driven by substantial absolute point gains on challenging datasets, including +7.3 pp on BRUMO 25, +4.4 pp on AIME 25, +3.3 pp on HMMT 25, and achieves consistent relative gain in pass@$k$ across the evaluated $k$ values. SPO's success challenges the prevailing trend of adding incidental complexity to RL algorithms, highlighting a path where fundamental principles, not architectural workarounds, drive the next wave of progress in LLM reasoning.
Authors: Fitsum Sileshi Beyene, Christopher L. Dancy
Abstract: Despite their cultural and historical significance, Black digital archives continue to be a structurally underrepresented area in AI research and infrastructure. This is especially evident in efforts to digitize historical Black newspapers, where inconsistent typography, visual degradation, and limited annotated layout data hinder accurate transcription, despite the availability of various systems that claim to handle optical character recognition (OCR) well. In this short paper, we present a layout-aware OCR pipeline tailored for Black newspaper archives and introduce an unsupervised evaluation framework suited to low-resource archival contexts. Our approach integrates synthetic layout generation, model pretraining on augmented data, and a fusion of state-of-the-art You Only Look Once (YOLO) detectors. We used three annotation-free evaluation metrics, the Semantic Coherence Score (SCS), Region Entropy (RE), and Textual Redundancy Score (TRS), which quantify linguistic fluency, informational diversity, and redundancy across OCR regions. Our evaluation on a 400-page dataset from ten Black newspaper titles demonstrates that layout-aware OCR improves structural diversity and reduces redundancy compared to full-page baselines, with modest trade-offs in coherence. Our results highlight the importance of respecting cultural layout logic in AI-driven document understanding and lay the foundation for future community-driven and ethically grounded archival AI systems.
Authors: Aniket Didolkar, Nicolas Ballas, Sanjeev Arora, Anirudh Goyal
Abstract: Large language models (LLMs) now solve multi-step problems by emitting extended chains of thought. During the process, they often re-derive the same intermediate steps across problems, inflating token usage and latency. This saturation of the context window leaves less capacity for exploration. We study a simple mechanism that converts recurring reasoning fragments into concise, reusable "behaviors" (name + instruction) via the model's own metacognitive analysis of prior traces. These behaviors are stored in a "behavior handbook" which supplies them to the model in-context at inference or distills them into parameters via supervised fine-tuning. This approach achieves improved test-time reasoning across three different settings - 1) Behavior-conditioned inference: Providing the LLM relevant behaviors in-context during reasoning reduces number of reasoning tokens by up to 46% while matching or improving baseline accuracy; 2) Behavior-guided self-improvement: Without any parameter updates, the model improves its own future reasoning by leveraging behaviors from its own past problem solving attempts. This yields up to 10% higher accuracy than a naive critique-and-revise baseline; and 3) Behavior-conditioned SFT: SFT on behavior-conditioned reasoning traces is more effective at converting non-reasoning models into reasoning models as compared to vanilla SFT. Together, these results indicate that turning slow derivations into fast procedural hints enables LLMs to remember how to reason, not just what to conclude.
Authors: Mattia Soldan, Fabian Caba Heilbron, Bernard Ghanem, Josef Sivic, Bryan Russell
Abstract: Several video understanding tasks, such as natural language temporal video grounding, temporal activity localization, and audio description generation, require "temporally dense" reasoning over frames sampled at high temporal resolution. However, computing frame-level features for these tasks is computationally expensive given the temporal resolution requirements. In this paper, we make three contributions to reduce the cost of computing features for temporally dense tasks. First, we introduce a vision transformer (ViT) architecture, dubbed ResidualViT, that leverages the large temporal redundancy in videos to efficiently compute temporally dense frame-level features. Our architecture incorporates (i) learnable residual connections that ensure temporal consistency across consecutive frames and (ii) a token reduction module that enhances processing speed by selectively discarding temporally redundant information while reusing weights of a pretrained foundation model. Second, we propose a lightweight distillation strategy to approximate the frame-level features of the original foundation model. Finally, we evaluate our approach across four tasks and five datasets, in both zero-shot and fully supervised settings, demonstrating significant reductions in computational cost (up to 60%) and improvements in inference speed (up to 2.5x faster), all while closely approximating the accuracy of the original foundation model.
Authors: Jiahao Zhang, Xiaobing Pei, Zhaokun Zhong, Wenqiang Hao, Zhenghao Tang
Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable performance across various applications, yet they are vulnerable to sophisticated adversarial attacks, particularly node injection attacks. The success of such attacks heavily relies on their stealthiness, the ability to blend in with the original graph and evade detection. However, existing methods often achieve stealthiness by relying on indirect proxy metrics, lacking consideration for the fundamental characteristics of the injected content, or focusing only on imitating local structures, which leads to the problem of local myopia. To overcome these limitations, we propose a dual-constraint stealthy node injection framework, called Joint Alignment of Nodal and Universal Structures (JANUS). At the local level, we introduce a local feature manifold alignment strategy to achieve geometric consistency in the feature space. At the global level, we incorporate structured latent variables and maximize the mutual information with the generated structures, ensuring the injected structures are consistent with the semantic patterns of the original graph. We model the injection attack as a sequential decision process, which is optimized by a reinforcement learning agent. Experiments on multiple standard datasets demonstrate that the JANUS framework significantly outperforms existing methods in terms of both attack effectiveness and stealthiness.
Authors: Mohammed Baharoon, Siavash Raissi, John S. Jun, Thibault Heintz, Mahmoud Alabbad, Ali Alburkani, Sung Eun Kim, Kent Kleinschmidt, Abdulrahman O. Alhumaydhi, Mohannad Mohammed G. Alghamdi, Jeremy Francis Palacio, Mohammed Bukhaytan, Noah Michael Prudlo, Rithvik Akula, Brady Chrisler, Benjamin Galligos, Mohammed O. Almutairi, Mazeen Mohammed Alanazi, Nasser M. Alrashdi, Joel Jihwan Hwang, Sri Sai Dinesh Jaliparthi, Luke David Nelson, Nathaniel Nguyen, Sathvik Suryadevara, Steven Kim, Mohammed F. Mohammed, Yevgeniy R. Semenov, Kun-Hsing Yu, Abdulrhman Aljouie, Hassan AlOmaish, Adam Rodman, Pranav Rajpurkar
Abstract: We introduce RadGame, an AI-powered gamified platform for radiology education that targets two core skills: localizing findings and generating reports. Traditional radiology training is based on passive exposure to cases or active practice with real-time input from supervising radiologists, limiting opportunities for immediate and scalable feedback. RadGame addresses this gap by combining gamification with large-scale public datasets and automated, AI-driven feedback that provides clear, structured guidance to human learners. In RadGame Localize, players draw bounding boxes around abnormalities, which are automatically compared to radiologist-drawn annotations from public datasets, and visual explanations are generated by vision-language models for user missed findings. In RadGame Report, players compose findings given a chest X-ray, patient age and indication, and receive structured AI feedback based on radiology report generation metrics, highlighting errors and omissions compared to a radiologist's written ground truth report from public datasets, producing a final performance and style score. In a prospective evaluation, participants using RadGame achieved a 68% improvement in localization accuracy compared to 17% with traditional passive methods and a 31% improvement in report-writing accuracy compared to 4% with traditional methods after seeing the same cases. RadGame highlights the potential of AI-driven gamification to deliver scalable, feedback-rich radiology training and reimagines the application of medical AI resources in education.
Authors: Sanjay Oruganti, Sergei Nirenburg, Marjorie McShane, Jesse English, Michael K. Roberts, Christian Arndt, Carlos Gonzalez, Mingyo Seo, Luis Sentis
Abstract: This paper introduces HARMONIC, a cognitive-robotic architecture designed for robots in human-robotic teams. HARMONIC supports semantic perception interpretation, human-like decision-making, and intentional language communication. It addresses the issues of safety and quality of results; aims to solve problems of data scarcity, explainability, and safety; and promotes transparency and trust. Two proof-of-concept HARMONIC-based robotic systems are demonstrated, each implemented in both a high-fidelity simulation environment and on physical robotic platforms.
Authors: Gwendal Le Vaillant, Yannick Molle
Abstract: Efficiently retrieving specific instrument timbres from audio mixtures remains a challenge in digital music production. This paper introduces a contrastive learning framework for musical instrument retrieval, enabling direct querying of instrument databases using a single model for both single- and multi-instrument sounds. We propose techniques to generate realistic positive/negative pairs of sounds for virtual musical instruments, such as samplers and synthesizers, addressing limitations in common audio data augmentation methods. The first experiment focuses on instrument retrieval from a dataset of 3,884 instruments, using single-instrument audio as input. Contrastive approaches are competitive with previous works based on classification pre-training. The second experiment considers multi-instrument retrieval with a mixture of instruments as audio input. In this case, the proposed contrastive framework outperforms related works, achieving 81.7\% top-1 and 95.7\% top-5 accuracies for three-instrument mixtures.
Authors: Jinhua Zhu, Javier Conde, Zhen Gao, Pedro Reviriego, Shanshan Liu, Fabrizio Lombardi
Abstract: The wide adoption of Large language models (LLMs) makes their dependability a pressing concern. Detection of errors is the first step to mitigating their impact on a system and thus, efficient error detection for LLMs is an important issue. In many settings, the LLM is considered as a black box with no access to the internal nodes; this prevents the use of many error detection schemes that need access to the model's internal nodes. An interesting observation is that the output of LLMs in error-free operation should be valid and normal text. Therefore, when the text is not valid or differs significantly from normal text, it is likely that there is an error. Based on this observation we propose to perform Concurrent Linguistic Error Detection (CLED); this scheme extracts some linguistic features of the text generated by the LLM and feeds them to a concurrent classifier that detects errors. Since the proposed error detection mechanism only relies on the outputs of the model, then it can be used on LLMs in which there is no access to the internal nodes. The proposed CLED scheme has been evaluated on the T5 model when used for news summarization and on the OPUS-MT model when used for translation. In both cases, the same set of linguistic features has been used for error detection to illustrate the applicability of the proposed scheme beyond a specific case. The results show that CLED can detect most of the errors at a low overhead penalty. The use of the concurrent classifier also enables a trade-off between error detection effectiveness and its associated overhead, so providing flexibility to a designer.
Authors: Zhuang Qi, Lei Meng, Ruohan Zhang, Yu Wang, Xin Qi, Xiangxu Meng, Han Yu, Qiang Yang
Abstract: Federated learning benefits from cross-training strategies, which enables models to train on data from distinct sources to improve generalization capability. However, due to inherent differences in data distributions, the optimization goals of local models remain misaligned, and this mismatch continues to manifest as feature space heterogeneity even after cross-training. We argue that knowledge distillation from the personalized view preserves client-specific characteristics and expands the local knowledge base, while distillation from the global view provides consistent semantic anchors that facilitate feature alignment across clients. To achieve this goal, this paper presents a cross-training scheme, termed FedCT, includes three main modules, where the consistency-aware knowledge broadcasting module aims to optimize model assignment strategies, which enhances collaborative advantages between clients and achieves an efficient federated learning process. The multi-view knowledge-guided representation learning module leverages fused prototypical knowledge from both global and local views to enhance the preservation of local knowledge before and after model exchange, as well as to ensure consistency between local and global knowledge. The mixup-based feature augmentation module aggregates rich information to further increase the diversity of feature spaces, which enables the model to better discriminate complex samples. Extensive experiments were conducted on four datasets in terms of performance comparison, ablation study, in-depth analysis and case study. The results demonstrated that FedCT alleviates knowledge forgetting from both local and global views, which enables it outperform state-of-the-art methods.
Authors: Kazuki Irie, Brenden M. Lake
Abstract: Since the earliest proposals for artificial neural network (ANN) models of the mind and brain, critics have pointed out key weaknesses in these models compared to human cognitive abilities. Here we review recent work that uses metalearning to overcome several classic challenges, which we characterize as addressing the Problem of Incentive and Practice -- that is, providing machines with both incentives to improve specific skills and opportunities to practice those skills. This explicit optimization contrasts with more conventional approaches that hope the desired behaviour will emerge through optimizing related but different objectives. We review applications of this principle to addressing four classic challenges for ANNs: systematic generalization, catastrophic forgetting, few-shot learning and multi-step reasoning. We also discuss how large language models incorporate key aspects of this metalearning framework (namely, sequence prediction with feedback trained on diverse data), which helps to explain some of their successes on these classic challenges. Finally, we discuss the prospects for understanding aspects of human development through this framework, and whether natural environments provide the right incentives and practice for learning how to make challenging generalizations.
Authors: Seongmin Lee, Hsiang Hsu, Chun-Fu Chen, Duen Horng Chau
Abstract: LLM hallucination, where unfaithful text is generated, presents a critical challenge for LLMs' practical applications. Current detection methods often resort to external knowledge, LLM fine-tuning, or supervised training with large hallucination-labeled datasets. Moreover, these approaches do not distinguish between different types of hallucinations, which is crucial for enhancing detection performance. To address such limitations, we introduce hallucination probing, a new task that classifies LLM-generated text into three categories: aligned, misaligned, and fabricated. Driven by our novel discovery that perturbing key entities in prompts affects LLM's generation of these three types of text differently, we propose SHINE, a novel hallucination probing method that does not require external knowledge, supervised training, or LLM fine-tuning. SHINE is effective in hallucination probing across three modern LLMs, and achieves state-of-the-art performance in hallucination detection, outperforming seven competing methods across four datasets and four LLMs, underscoring the importance of probing for accurate detection.
Authors: Haoyu Jiang, Xuhong Wang, Ping Yi, Shanzhe Lei, Yilun Lin
Abstract: Large Language Models (LLMs) are widely used in complex natural language processing tasks but raise privacy and security concerns due to the lack of identity recognition. This paper proposes a multi-party credible watermarking framework (CredID) involving a trusted third party (TTP) and multiple LLM vendors to address these issues. In the watermark embedding stage, vendors request a seed from the TTP to generate watermarked text without sending the user's prompt. In the extraction stage, the TTP coordinates each vendor to extract and verify the watermark from the text. This provides a credible watermarking scheme while preserving vendor privacy. Furthermore, current watermarking algorithms struggle with text quality, information capacity, and robustness, making it challenging to meet the diverse identification needs of LLMs. Thus, we propose a novel multi-bit watermarking algorithm and an open-source toolkit to facilitate research. Experiments show our CredID enhances watermark credibility and efficiency without compromising text quality. Additionally, we successfully utilized this framework to achieve highly accurate identification among multiple LLM vendors.
Authors: Allahkaram Shafiei, Hozefa Jesawada, Karl Friston, Giovanni Russo
Abstract: Despite their groundbreaking performance, state-of-the-art autonomous agents can misbehave when training and environmental conditions become inconsistent, with minor mismatches leading to undesirable behaviors or even catastrophic failures. Robustness towards these training/environment ambiguities is a core requirement for intelligent agents and its fulfillment is a long-standing challenge when deploying agents in the real world. Here, we introduce a Distributionally Robust Free Energy model (DR-FREE) that instills this core property by design. It directly wires robustness into the agent decision-making mechanisms via free energy minimization. By combining a robust extension of the free energy principle with a novel resolution engine, DR-FREE returns a policy that is optimal-yet-robust against ambiguity. The policy has an explicit, soft-max, structure that reveals the mechanistic role of ambiguity on optimal decisions and requisite Bayesian belief updating. We evaluate DR-FREE on an experimental testbed involving real rovers navigating an ambiguous environment filled with obstacles. Across all the experiments, DR-FREE enables robots to successfully navigate towards their goal even when, in contrast, state-of-the-art free energy models fail. In short, DR-FREE can tackle scenarios that elude previous methods: this milestone may inspire both deployment in multi-agent settings and, at a perhaps deeper level, the quest for a biologically plausible explanation of how natural agents -- with little or no training -- survive in capricious environments.
Authors: Weiliang Zhang, Xiaohan Huang, Yi Du, Ziyue Qiao, Qingqing Long, Zhen Meng, Yuanchun Zhou, Meng Xiao
Abstract: Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning (RL)-based subspace exploration strategy provides a novel objective optimization-directed perspective and promising performance. Nevertheless, even with improved performance, current reinforcement learning approaches face challenges similar to conventional methods when dealing with complex datasets. These challenges stem from the inefficient paradigm of using one agent per feature and the inherent complexities present in the datasets. This observation motivates us to investigate and address the above issue and propose a novel approach, namely HRLFS. Our methodology initially employs a Large Language Model (LLM)-based hybrid state extractor to capture each feature's mathematical and semantic characteristics. Based on this information, features are clustered, facilitating the construction of hierarchical agents for each cluster and sub-cluster. Extensive experiments demonstrate the efficiency, scalability, and robustness of our approach. Compared to contemporary or the one-feature-one-agent RL-based approaches, HRLFS improves the downstream ML performance with iterative feature subspace exploration while accelerating total run time by reducing the number of agents involved.
Authors: Ben Griffin, Diego Vidaurre, Ugur Koyluoglu, Joseph Ternasky, Fuat Alican, Yigit Ihlamur
Abstract: Predicting rare outcomes such as startup success is central to venture capital, demanding models that are both accurate and interpretable. We introduce Random Rule Forest (RRF), a lightweight ensemble method that uses a large language model (LLM) to generate simple YES/NO questions in natural language. Each question functions as a weak learner, and their responses are combined using a threshold-based voting rule to form a strong, interpretable predictor. Applied to a dataset of 9,892 founders, RRF achieves a 6.9x improvement over a random baseline on held-out data; adding expert-crafted questions lifts this to 8x and highlights the value of human-LLM collaboration. Compared with zero- and few-shot baselines across three LLM architectures, RRF attains an F0.5 of 0.121, versus 0.086 for the best baseline (+0.035 absolute, +41% relative). By combining the creativity of LLMs with the rigor of ensemble learning, RRF delivers interpretable, high-precision predictions suitable for decision-making in high-stakes domains.
Authors: Artemis Panagopoulou, Le Xue, Honglu Zhou, silvio savarese, Ran Xu, Caiming Xiong, Chris Callison-Burch, Mark Yatskar, Juan Carlos Niebles
Abstract: Real-world decision-making often begins with identifying which modality contains the most relevant information for a given query. While recent multimodal models have made impressive progress in processing diverse inputs, it remains unclear whether they can reason contrastively across multiple modalities to select the one that best satisfies a natural language prompt. We argue this capability is foundational, especially in retrieval-augmented and decision-time contexts, where systems must evaluate multiple signals and identify which one conveys the relevant information. To evaluate this skill, we introduce Contra4, a dataset for contrastive cross-modal reasoning across four modalities: image, audio, video, and 3D. Each example presents a natural language question alongside multiple candidate modality instances, and the model must select the one that semantically aligns with the prompt. Contra4 combines human-annotated captions with a mixture-of-models round-trip-consistency filter to ensure high-quality supervision, resulting in 174k training examples and a manually verified test set of 2.3k samples. While task-specific fine-tuning helps improve performance by 56% relative to baseline, state-of-the-art models still achieve only an absolute of 56% accuracy overall and 42% in four-modality settings, underscoring a significant limitation in current multimodal models.
Authors: Peter Belcak, Greg Heinrich, Shizhe Diao, Yonggan Fu, Xin Dong, Saurav Muralidharan, Yingyan Celine Lin, Pavlo Molchanov
Abstract: Large language models (LLMs) are often praised for exhibiting near-human performance on a wide range of tasks and valued for their ability to hold a general conversation. The rise of agentic AI systems is, however, ushering in a mass of applications in which language models perform a small number of specialized tasks repetitively and with little variation. Here we lay out the position that small language models (SLMs) are sufficiently powerful, inherently more suitable, and necessarily more economical for many invocations in agentic systems, and are therefore the future of agentic AI. Our argumentation is grounded in the current level of capabilities exhibited by SLMs, the common architectures of agentic systems, and the economy of LM deployment. We further argue that in situations where general-purpose conversational abilities are essential, heterogeneous agentic systems (i.e., agents invoking multiple different models) are the natural choice. We discuss the potential barriers for the adoption of SLMs in agentic systems and outline a general LLM-to-SLM agent conversion algorithm. Our position, formulated as a value statement, highlights the significance of the operational and economic impact even a partial shift from LLMs to SLMs is to have on the AI agent industry. We aim to stimulate the discussion on the effective use of AI resources and hope to advance the efforts to lower the costs of AI of the present day. Calling for both contributions to and critique of our position, we commit to publishing all such correspondence at https://research.nvidia.com/labs/lpr/slm-agents.
Authors: Shaina Raza, Ranjan Sapkota, Manoj Karkee, Christos Emmanouilidis
Abstract: Agentic AI systems, built upon large language models (LLMs) and deployed in multi-agent configurations, are redefining intelligence, autonomy, collaboration, and decision-making across enterprise and societal domains. This review presents a structured analysis of Trust, Risk, and Security Management (TRiSM) in the context of LLM-based Agentic Multi-Agent Systems (AMAS). We begin by examining the conceptual foundations of Agentic AI and highlight its architectural distinctions from traditional AI agents. We then adapt and extend the AI TRiSM framework for Agentic AI, structured around key pillars: \textit{ Explainability, ModelOps, Security, Privacy} and \textit{their Lifecycle Governance}, each contextualized to the challenges of AMAS. A risk taxonomy is proposed to capture the unique threats and vulnerabilities of Agentic AI, ranging from coordination failures to prompt-based adversarial manipulation. To support practical assessment in Agentic AI works, we introduce two novel metrics: the Component Synergy Score (CSS), which quantifies the quality of inter-agent collaboration, and the Tool Utilization Efficacy (TUE), which evaluates the efficiency of tool use within agent workflows. We further discuss strategies for improving explainability in Agentic AI, as well as approaches to enhancing security and privacy through encryption, adversarial robustness, and regulatory compliance. The review concludes with a research roadmap for the responsible development and deployment of Agentic AI, highlighting key directions to align emerging systems with TRiSM principles-ensuring safety, transparency, and accountability in their operation.
Authors: Boheng Liu, Ziyu Li, Xia Wu
Abstract: Despite remarkable capabilities, artificial neural networks exhibit limited flexible, generalizable intelligence. This limitation stems from their fundamental divergence from biological cognition that overlooks both neural regions' functional specialization and the temporal dynamics critical for coordinating these specialized systems. We propose a tripartite brain-inspired architecture comprising functionally specialized perceptual, auxiliary, and executive systems. Moreover, the integration of temporal dynamics through the simulation of multi-frequency neural oscillation and synaptic dynamic adaptation mechanisms enhances the architecture, thereby enabling more flexible and efficient artificial cognition. Initial evaluations demonstrate superior performance compared to state-of-the-art temporal processing approaches, with 2.18\% accuracy improvements while reducing required computation iterations by 48.44\%, and achieving higher correlation with human confidence patterns. Though currently demonstrated on visual processing tasks, this architecture establishes a theoretical foundation for brain-like intelligence across cognitive domains, potentially bridging the gap between artificial and biological intelligence.
Authors: Cl\'ement Contet, Umberto Grandi, J\'er\^ome Mengin
Abstract: Tournaments are widely used models to represent pairwise dominance between candidates, alternatives, or teams. We study the problem of providing certified explanations for why a candidate appears among the winners under various tournament rules. To this end, we identify minimal supports, minimal sub-tournaments in which the candidate is guaranteed to win regardless of how the rest of the tournament is completed (that is, the candidate is a necessary winner of the sub-tournament). This notion corresponds to an abductive explanation for the question,"Why does the winner win the tournament", a central concept in formal explainable AI. We focus on common tournament solutions: the top cycle, the uncovered set, the Copeland rule, the Borda rule, the maximin rule, and the weighted uncovered set. For each rule we determine the size of the smallest minimal supports, and we present polynomial-time algorithms to compute them for all but the weighted uncovered set, for which the problem is NP-complete. Finally, we show how minimal supports can serve to produce compact, certified, and intuitive explanations.
Authors: Aleksandr Boldachev
Abstract: This paper presents boldsea, Boldachev's semantic-event approach -- an architecture for modeling complex dynamic systems using executable ontologies -- semantic models that act as dynamic structures, directly controlling process execution. We demonstrate that integrating event semantics with a dataflow architecture addresses the limitations of traditional Business Process Management (BPM) systems and object-oriented semantic technologies. The paper presents the formal BSL (boldsea Semantic Language), including its BNF grammar, and outlines the boldsea-engine's architecture, which directly interprets semantic models as executable algorithms without compilation. It enables the modification of event models at runtime, ensures temporal transparency, and seamlessly merges data and business logic within a unified semantic framework.
Authors: Liangxuan Guo, Bin Zhu, Qingqian Tao, Kangning Liu, Xun Zhao, Xianzhe Qin, Jin Gao, Guangfu Hao
Abstract: Autonomous agents for desktop automation struggle with complex multi-step tasks due to poor coordination and inadequate quality control. We introduce Agentic Lybic, a novel multi-agent system where the entire architecture operates as a finite-state machine (FSM). This core innovation enables dynamic orchestration. Our system comprises four components: a Controller, a Manager, three Workers (Technician for code-based operations, Operator for GUI interactions, and Analyst for decision support), and an Evaluator. The critical mechanism is the FSM-based routing between these components, which provides flexibility and generalization by dynamically selecting the optimal execution strategy for each subtask. This principled orchestration, combined with robust quality gating, enables adaptive replanning and error recovery. Evaluated officially on the OSWorld benchmark, Agentic Lybic achieves a state-of-the-art 57.07% success rate in 50 steps, substantially outperforming existing methods. Results demonstrate that principled multi-agent orchestration with continuous quality control provides superior reliability for generalized desktop automation in complex computing environments.
Authors: Wei Cai, Shujuan Liu, Jian Zhao, Ziyan Shi, Yusheng Zhao, Yuchen Yuan, Tianle Zhang, Chi Zhang, Xuelong Li
Abstract: Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that produce harmful outputs. We attribute this vulnerability to the difficulty of MLLMs maintaining safety alignment through long-chain reasoning. To address this issue, we introduce Safe-Semantics-but-Unsafe-Interpretation (SSUI), the first dataset featuring interpretable reasoning paths tailored for such a cross-modal challenge. A novel training framework, Safety-aware Reasoning Path Optimization (SRPO), is also designed based on the SSUI dataset to align the MLLM's internal reasoning process with human safety values. Experimental results show that our SRPO-trained models achieve state-of-the-art results on key safety benchmarks, including the proposed Reasoning Path Benchmark (RSBench), significantly outperforming both open-source and top-tier commercial MLLMs.
Authors: Yubo Li, Weiyi Song
Abstract: Current AI alignment through RLHF follows a single directional paradigm that AI conforms to human preferences while treating human cognition as fixed. We propose a shift to co-alignment through Bidirectional Cognitive Alignment (BiCA), where humans and AI mutually adapt. BiCA uses learnable protocols, representation mapping, and KL-budget constraints for controlled co-evolution. In collaborative navigation, BiCA achieved 85.5% success versus 70.3% baseline, with 230% better mutual adaptation and 332% better protocol convergence. Emergent protocols outperformed handcrafted ones by 84%, while bidirectional adaptation unexpectedly improved safety (+23% out-of-distribution robustness). The 46% synergy improvement demonstrates optimal collaboration exists at the intersection, not union, of human and AI capabilities, validating the shift from single-directional to co-alignment paradigms.
Authors: Ruihai Wu, Kai Cheng, Yan Shen, Chuanruo Ning, Guanqi Zhan, Hao Dong
Abstract: Perceiving and manipulating 3D articulated objects in diverse environments is essential for home-assistant robots. Recent studies have shown that point-level affordance provides actionable priors for downstream manipulation tasks. However, existing works primarily focus on single-object scenarios with homogeneous agents, overlooking the realistic constraints imposed by the environment and the agent's morphology, e.g., occlusions and physical limitations. In this paper, we propose an environment-aware affordance framework that incorporates both object-level actionable priors and environment constraints. Unlike object-centric affordance approaches, learning environment-aware affordance faces the challenge of combinatorial explosion due to the complexity of various occlusions, characterized by their quantities, geometries, positions and poses. To address this and enhance data efficiency, we introduce a novel contrastive affordance learning framework capable of training on scenes containing a single occluder and generalizing to scenes with complex occluder combinations. Experiments demonstrate the effectiveness of our proposed approach in learning affordance considering environment constraints. Project page at https://chengkaiacademycity.github.io/EnvAwareAfford/
Authors: Jiexia Ye, Yongzi Yu, Weiqi Zhang, Le Wang, Jia Li, Fugee Tsung
Abstract: Time series data are ubiquitous across diverse real-world applications, making time series analysis critically important. Traditional approaches are largely task-specific, offering limited functionality and poor transferability. In recent years, foundation models have revolutionized NLP and CV with their remarkable cross-task transferability, zero-/few-shot learning capabilities, and multimodal integration capacity. This success has motivated increasing efforts to explore foundation models for addressing time series modeling challenges. Although some tutorials and surveys were published in the early stages of this field, the rapid pace of recent developments necessitates a more comprehensive and in-depth synthesis to cover the latest advances. Our survey aims to fill this gap by introducing a modality-aware, challenge-oriented perspective, which reveals how foundation models pre-trained on different modalities face distinct hurdles when adapted to time series tasks. Building on this perspective, we propose a taxonomy of existing works organized by pre-training modality (time series, language, and vision), analyze modality-specific challenges and categorize corresponding solutions, discussing their advantages and limitations. Beyond this, we review real-world applications to illustrate domain-specific advancements, provide open-source codes, and conclude with potential future research directions in this rapidly evolving field.
Authors: Yunni Qu (Department of Computer Science, University of North Carolina at Chapel Hill), James Wellnitz (Eshelman School of Pharmacy, University of North Carolina at Chapel Hill), Dzung Dinh (Department of Computer Science, University of North Carolina at Chapel Hill), Bhargav Vaduri (Department of Computer Science, University of North Carolina at Chapel Hill), Alexander Tropsha (Eshelman School of Pharmacy, University of North Carolina at Chapel Hill), Junier Oliva (Department of Computer Science, University of North Carolina at Chapel Hill)
Abstract: Expansive Matching of Experts (EMOE) is a novel framework that utilizes support-expanding, extrapolatory pseudo-labeling to improve prediction and uncertainty based rejection on out-of-distribution(OOD) points. EMOE utilizes a diverse set of multiple base experts as pseudo-labelers on the augmented data to improve OOD performance through multiple MLP heads (one per expert) with shared embedding train with a novel per-head matching loss. Unlike prior methods that rely on modality-specific augmentations or assume access to OOD data, EMOE introduces extrapolatory pseudo-labeling on latent-space augmentations, enabling robust OOD generalization with any real-valued vector data. In contrast to prior modality agnostic methods with neural backbones, EMOE is model-agnostic, working effectively with methods from simple tree-based models to complex OOD generalization models. We demonstrate that EMOE achieves superior performance compared to state-of-the-art method on diverse datasets in single-source domain generalization setting.
Authors: Yixiu Zhao, Jiaxin Shi, Feng Chen, Shaul Druckmann, Lester Mackey, Scott Linderman
Abstract: Discrete diffusion has emerged as a powerful framework for generative modeling in discrete domains, yet efficiently sampling from these models remains challenging. Existing sampling strategies often struggle to balance computation and sample quality when the number of sampling steps is reduced, even when the model has learned the data distribution well. To address these limitations, we propose a predictor-corrector sampling scheme where the corrector is informed by the diffusion model to more reliably counter the accumulating approximation errors. To further enhance the effectiveness of our informed corrector, we introduce complementary architectural modifications based on hollow transformers and a simple tailored training objective that leverages more training signal. We use a synthetic example to illustrate the failure modes of existing samplers and show how informed correctors alleviate these problems. On the text8 and tokenized ImageNet 256x256 datasets, our informed corrector consistently produces superior samples with fewer errors or improved FID scores for discrete diffusion models. These results underscore the potential of informed correctors for fast and high-fidelity generation using discrete diffusion. Our code is available at https://github.com/lindermanlab/informed-correctors.
Authors: Manav Vora, Jonas Liang, Michael N. Grussing, Melkior Ornik
Abstract: Monotonic Partially Observable Markov Decision Processes (POMDPs), where the system state progressively decreases until a restorative action is performed, can be used to model sequential repair problems effectively. This paper considers the problem of solving budget-constrained multi-component monotonic POMDPs, where a finite budget limits the maximal number of restorative actions. For a large number of components, solving such a POMDP using current methods is computationally intractable due to the exponential growth in the state space with an increasing number of components. To address this challenge, we propose a two-step approach. Since the individual components of a budget-constrained multi-component monotonic POMDP are only connected via the shared budget, we first approximate the optimal budget allocation among these components using an approximation of each component POMDP's optimal value function which is obtained through a random forest model. Subsequently, we introduce an oracle-guided meta-trained Proximal Policy Optimization (PPO) algorithm to solve each of the independent budget-constrained single-component monotonic POMDPs. The oracle policy is obtained by performing value iteration on the corresponding monotonic Markov Decision Process (MDP). This two-step method provides scalability in solving truly massive multi-component monotonic POMDPs. To demonstrate the efficacy of our approach, we consider a real-world maintenance scenario that involves inspection and repair of an administrative building by a team of agents within a maintenance budget. Finally, we perform a computational complexity analysis for a varying number of components to show the scalability of the proposed approach.
Authors: Wenhui Diao, Haichen Yu, Kaiyue Kang, Tong Ling, Di Liu, Yingchao Feng, Hanbo Bi, Libo Ren, Xuexue Li, Yongqiang Mao, Xian Sun
Abstract: Aerial Remote Sensing (ARS) vision tasks present significant challenges due to the unique viewing angle characteristics. Existing research has primarily focused on algorithms for specific tasks, which have limited applicability in a broad range of ARS vision applications. This paper proposes RingMo-Aerial, aiming to fill the gap in foundation model research in the field of ARS vision. A Frequency-Enhanced Multi-Head Self-Attention (FE-MSA) mechanism is introduced to strengthen the model's capacity for small-object representation. Complementarily, an affine transformation-based contrastive learning method improves its adaptability to the tilted viewing angles inherent in ARS tasks. Furthermore, the ARS-Adapter, an efficient parameter fine-tuning method, is proposed to improve the model's adaptability and performance in various ARS vision tasks. Experimental results demonstrate that RingMo-Aerial achieves SOTA performance on multiple downstream tasks. This indicates the practicality and efficacy of RingMo-Aerial in enhancing the performance of ARS vision tasks.
Authors: Hongyan Chang, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Reza Shokri
Abstract: Membership Inference Attacks (MIAs) on pre-trained Large Language Models (LLMs) aim at determining if a data point was part of the model's training set. Prior MIAs that are built for classification models fail at LLMs, due to ignoring the generative nature of LLMs across token sequences. In this paper, we present a novel attack on pre-trained LLMs that adapts MIA statistical tests to the perplexity dynamics of subsequences within a data point. Our method significantly outperforms prior approaches, revealing context-dependent memorization patterns in pre-trained LLMs.
Authors: Zhiqiang Yuan, Weitong Chen, Hanlin Wang, Kai Yu, Xin Peng, Yiling Lou
Abstract: Code translation converts code from one programming language to another while maintaining its original functionality, which is crucial for software migration, system refactoring, and cross-platform development. Traditional rule-based methods rely on manually-written rules, which can be time-consuming and often result in less readable code. To overcome this, learning-based methods have been developed, leveraging parallel data to train models for automated code translation. More recently, the advance of Large Language Models (LLMs) further boosts learning-based code translation. Although promising, LLM-translated program still suffers from diverse quality issues (e.g., syntax errors and semantic errors). In particular, it can be challenging for LLMs to self-debug these errors when simply provided with the corresponding error messages. In this work, we propose a novel LLM-based multi-agent system TRANSAGENT, which enhances LLM-based code translation by fixing the syntax errors and semantic errors with the synergy between four LLM-based agents, including Initial Code Translator, Syntax Error Fixer, Code Aligner, and Semantic Error Fixer. The main insight of TRANSAGENT is to first localize the error code block in the target program based on the execution alignment between the target and source program, which can narrow down the fixing space and thus lower down the fixing difficulties. To evaluate TRANSAGENT, we first construct a new benchmark from recent programming tasks to mitigate the potential data leakage issue. On our benchmark, TRANSAGENT outperforms the latest LLM-based code translation technique UniTrans in both translation effectiveness and efficiency; additionally, our evaluation on different LLMs show the generalization of TRANSAGENT and our ablation study shows the contribution of each agent.
Authors: Jiachen Li, Qian Long, Jian Zheng, Xiaofeng Gao, Robinson Piramuthu, Wenhu Chen, William Yang Wang
Abstract: In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model. Our proposed method, T2V-Turbo-v2, introduces a significant advancement by integrating various supervision signals, including high-quality training data, reward model feedback, and conditional guidance, into the consistency distillation process. Through comprehensive ablation studies, we highlight the crucial importance of tailoring datasets to specific learning objectives and the effectiveness of learning from diverse reward models for enhancing both the visual quality and text-video alignment. Additionally, we highlight the vast design space of conditional guidance strategies, which centers on designing an effective energy function to augment the teacher ODE solver. We demonstrate the potential of this approach by extracting motion guidance from the training datasets and incorporating it into the ODE solver, showcasing its effectiveness in improving the motion quality of the generated videos with the improved motion-related metrics from VBench and T2V-CompBench. Empirically, our T2V-Turbo-v2 establishes a new state-of-the-art result on VBench, with a Total score of 85.13, surpassing proprietary systems such as Gen-3 and Kling.
Authors: Maximus Powers, Shaina Raza, Alex Chang, Rehana Riaz, Umang Mavani, Harshitha Reddy Jonala, Ansh Tiwari, Hua Wei
Abstract: Representational harms in language technologies often occur in short spans within otherwise neutral text, where phrases may simultaneously convey generalizations, unfairness, or stereotypes. Framing bias detection as sentence-level classification obscures which words carry bias and what type is present, limiting both auditability and targeted mitigation. We introduce the GUS-Net Framework, comprising the GUS dataset and a multi-label token-level detector for span-level analysis of social bias. The GUS dataset contains 3,739 unique snippets across multiple domains, with over 69,000 token-level annotations. Each token is labeled using BIO tags (Begin, Inside, Outside) for three pathways of representational harm: Generalizations, Unfairness, and Stereotypes. To ensure reliable data annotation, we employ an automated multi-agent pipeline that proposes candidate spans which are subsequently verified and corrected by human experts. We formulate bias detection as multi-label token-level classification and benchmark both encoder-based models (e.g., BERT family variants) and decoder-based large language models (LLMs). Our evaluations cover token-level identification and span-level entity recognition on our test set, and out-of-distribution generalization. Empirical results show that encoder-based models consistently outperform decoder-based baselines on nuanced and overlapping spans while being more computationally efficient. The framework delivers interpretable, fine-grained diagnostics that enable systematic auditing and mitigation of representational harms in real-world NLP systems.
Authors: Saptarshi Chakraborty, Peter L. Bartlett
Abstract: Despite significant research on the optimization aspects of federated learning, the exploration of generalization error, especially in the realm of heterogeneous federated learning, remains an area that has been insufficiently investigated, primarily limited to developments in the parametric regime. This paper delves into the generalization properties of deep federated regression within a two-stage sampling model. Our findings reveal that the intrinsic dimension, characterized by the entropic dimension, plays a pivotal role in determining the convergence rates for deep learners when appropriately chosen network sizes are employed. Specifically, when the true relationship between the response and explanatory variables is described by a $\beta$-H\"older function and one has access to $n$ independent and identically distributed (i.i.d.) samples from $m$ participating clients, for participating clients, the error rate scales at most as $\Tilde{O}((mn)^{-2\beta/(2\beta + \bar{d}_{2\beta}(\lambda))})$, whereas for non-participating clients, it scales as $\Tilde{O}(\Delta \cdot m^{-2\beta/(2\beta + \bar{d}_{2\beta}(\lambda))} + (mn)^{-2\beta/(2\beta + \bar{d}_{2\beta}(\lambda))})$. Here $\bar{d}_{2\beta}(\lambda)$ denotes the corresponding $2\beta$-entropic dimension of $\lambda$, the marginal distribution of the explanatory variables. The dependence between the two stages of the sampling scheme is characterized by $\Delta$. Consequently, our findings not only explicitly incorporate the ``heterogeneity" of the clients, but also highlight that the convergence rates of errors of deep federated learners are not contingent on the nominal high dimensionality of the data but rather on its intrinsic dimension.
Authors: Edward S. Hu, Kwangjun Ahn, Qinghua Liu, Haoran Xu, Manan Tomar, Ada Langford, Jayden Teoh, Bryon Xu, David Yan, Dinesh Jayaraman, Alex Lamb, John Langford
Abstract: We introduce the "Belief State Transformer", a next-token predictor that takes both a prefix and suffix as inputs, with a novel objective of predicting both the next token for the prefix and the previous token for the suffix. The Belief State Transformer effectively learns to solve challenging problems that conventional forward-only transformers struggle with, in a domain-independent fashion. Key to this success is learning a compact belief state that captures all relevant information necessary for accurate predictions. Empirical ablations show that each component of the model is essential in difficult scenarios where standard Transformers fall short. For the task of story writing with known prefixes and suffixes, our approach outperforms the Fill-in-the-Middle method for reaching known goals and demonstrates improved performance even when the goals are unknown. Altogether, the Belief State Transformer enables more efficient goal-conditioned decoding, better test-time inference, and high-quality text representations on small scale problems. Website: https://edwhu.github.io/bst-website
Authors: Xianlong Wang, Hewen Pan, Hangtao Zhang, Minghui Li, Shengshan Hu, Ziqi Zhou, Lulu Xue, Aishan Liu, Yunpeng Jiang, Leo Yu Zhang, Xiaohua Jia
Abstract: Robotic manipulation in the physical world is increasingly empowered by \textit{large language models} (LLMs) and \textit{vision-language models} (VLMs), leveraging their understanding and perception capabilities. Recently, various attacks against such robotic policies have been proposed, with backdoor attacks drawing considerable attention for their high stealth and strong persistence capabilities. However, existing backdoor efforts are limited to simulators and suffer from physical-world realization. To address this, we propose \textit{TrojanRobot}, a highly stealthy and broadly effective robotic backdoor attack in the physical world. Specifically, we introduce a module-poisoning approach by embedding a backdoor module into the modular robotic policy, enabling backdoor control over the policy's visual perception module thereby backdooring the entire robotic policy. Our vanilla implementation leverages a backdoor-finetuned VLM to serve as the backdoor module. To enhance its generalization in physical environments, we propose a prime implementation, leveraging the LVLM-as-a-backdoor paradigm and developing three types of prime attacks, \ie, \textit{permutation}, \textit{stagnation}, and \textit{intentional} attacks, thus achieving finer-grained backdoors. Extensive experiments on the UR3e manipulator with 18 task instructions using robotic policies based on four VLMs demonstrate the broad effectiveness and physical-world stealth of TrojanRobot. Our attack's video demonstrations are available via a github link https://trojanrobot.github.io.
Authors: Lin Luo, Xin Wang, Bojia Zi, Shihao Zhao, Xingjun Ma, Yu-Gang Jiang
Abstract: Large pre-trained Vision-Language Models (VLMs) such as Contrastive Language-Image Pre-training (CLIP) have been shown to be susceptible to adversarial attacks, raising concerns about their deployment in safety-critical applications like autonomous driving and medical diagnosis. One promising approach for robustifying pre-trained VLMs is Adversarial Prompt Tuning (APT), which applies adversarial training during the process of prompt tuning. However, existing APT methods are mostly single-modal methods that design prompt(s) for only the visual or textual modality, limiting their effectiveness in either robustness or clean accuracy. In this work, we propose Adversarial Prompt Distillation (APD), a bimodal knowledge distillation framework that enhances APT by integrating it with multi-modal knowledge transfer. APD optimizes prompts for both visual and textual modalities while distilling knowledge from a clean pre-trained teacher CLIP model. Extensive experiments on multiple benchmark datasets demonstrate the superiority of our APD method over the current state-of-the-art APT methods in terms of both adversarial robustness and clean accuracy. The effectiveness of APD also validates the possibility of using a non-robust teacher to improve the generalization and robustness of fine-tuned VLMs.
Authors: Pekka Malo, Lauri Viitasaari, Antti Suominen, Eeva Vilkkumaa, Olli Tahvonen
Abstract: This paper examines reinforcement learning (RL) in infinite-horizon decision processes with almost-sure safety constraints, crucial for applications like autonomous systems, finance, and resource management. We propose a doubly-regularized RL framework combining reward and parameter regularization to address safety constraints in continuous state-action spaces. The problem is formulated as a convex regularized objective with parametrized policies in the mean-field regime. Leveraging mean-field theory and Wasserstein gradient flows, policies are modeled on an infinite-dimensional statistical manifold, with updates governed by parameter distribution gradient flows. Key contributions include solvability conditions for safety-constrained problems, smooth bounded approximations for gradient flows, and exponential convergence guarantees under sufficient regularization. General regularization conditions, including entropy regularization, support practical particle method implementations. This framework provides robust theoretical insights and guarantees for safe RL in complex, high-dimensional settings.
Authors: Luca Barsellotti, Lorenzo Bianchi, Nicola Messina, Fabio Carrara, Marcella Cornia, Lorenzo Baraldi, Fabrizio Falchi, Rita Cucchiara
Abstract: Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP can generate segmentation masks by leveraging coarse spatial information from Vision Transformers, they face challenges in spatial localization due to their global alignment of image and text features. Conversely, self-supervised visual models like DINO excel in fine-grained visual encoding but lack integration with language. To bridge this gap, we present Talk2DINO, a novel hybrid approach that combines the spatial accuracy of DINOv2 with the language understanding of CLIP. Our approach aligns the textual embeddings of CLIP to the patch-level features of DINOv2 through a learned mapping function without the need to fine-tune the underlying backbones. At training time, we exploit the attention maps of DINOv2 to selectively align local visual patches with textual embeddings. We show that the powerful semantic and localization abilities of Talk2DINO can enhance the segmentation process, resulting in more natural and less noisy segmentations, and that our approach can also effectively distinguish foreground objects from the background. Experimental results demonstrate that Talk2DINO achieves state-of-the-art performance across several unsupervised OVS benchmarks. Source code and models are publicly available at: https://lorebianchi98.github.io/Talk2DINO/.
Authors: Ruibang Liu, Minyu Chen, Ling-I Wu, Jingyu Ke, Guoqiang Li
Abstract: Automated program verification has always been an important component of building trustworthy software. While the analysis of real-world programs remains a theoretical challenge, the automation of loop invariant analysis has effectively resolved the problem. However, real-world programs that often mix complex data structures and control flows pose challenges to traditional loop invariant generation tools. To enhance the applicability of invariant generation techniques, we proposed ACInv, an Automated Complex program loop Invariant generation tool, which combines static analysis with Large Language Models (LLMs) to generate the proper loop invariants. We utilize static analysis to extract the necessary information for each loop and embed it into prompts for the LLM to generate invariants for each loop. Subsequently, we employ an LLM-based evaluator to assess the generated invariants, refining them by either strengthening, weakening, or rejecting them based on their correctness, ultimately obtaining enhanced invariants. We conducted experiments on ACInv, which showed that ACInv outperformed previous tools on data sets with data structures, and maintained similar performance to the state-of-the-art tool AutoSpec on numerical programs without data structures. For the total data set, ACInv can solve 21% more examples than AutoSpec and can generate reference data structure templates.
Authors: Kaichen Ouyang, Zong Ke, Shengwei Fu, Lingjie Liu, Puning Zhao, Dayu Hu
Abstract: Evolutionary algorithms (EAs) simulate natural selection but have two main limitations: (1) they rarely update individuals based on global correlations, limiting comprehensive learning; (2) they struggle with balancing exploration and exploitation, where excessive exploitation causes premature convergence, and excessive exploration slows down the search. Moreover, EAs often depend on manual parameter settings, which can disrupt the exploration-exploitation balance. To address these issues, we propose Graph Neural Evolution (GNE), a novel EA framework. GNE represents the population as a graph, where nodes represent individuals, and edges capture their relationships, enabling global information usage. GNE utilizes spectral graph neural networks (GNNs) to decompose evolutionary signals into frequency components, applying a filtering function to fuse these components. High-frequency components capture diverse global information, while low-frequency ones capture more consistent information. This explicit frequency filtering strategy directly controls global-scale features through frequency components, overcoming the limitations of manual parameter settings and making the exploration-exploitation control more interpretable and manageable. Tests on nine benchmark functions (e.g., Sphere, Rastrigin, Rosenbrock) show that GNE outperforms classical (GA, DE, CMA-ES) and advanced algorithms (SDAES, RL-SHADE) under various conditions, including noise-corrupted and optimal solution deviation scenarios. GNE achieves solutions several orders of magnitude better (e.g., 3.07e-20 mean on Sphere vs. 1.51e-07).
Authors: Mohammad Wali Ur Rahman, Yu-Zheng Lin, Carter Weeks, David Ruddell, Jeff Gabriellini, Bill Hayes, Salim Hariri, Pratik Satam, Edward V. Ziegler Jr
Abstract: The flexibility and complexity of IPv6 extension headers allow attackers to create covert channels or bypass security mechanisms, leading to potential data breaches or system compromises. The mature development of machine learning has become the primary detection technology option used to mitigate covert communication threats. However, the complexity of detecting covert communication, evolving injection techniques, and scarcity of data make building machine-learning models challenging. In previous related research, machine learning has shown good performance in detecting covert communications, but oversimplified attack scenario assumptions cannot represent the complexity of modern covert technologies and make it easier for machine learning models to detect covert communications. To bridge this gap, in this study, we analyzed the packet structure and network traffic behavior of IPv6, used encryption algorithms, and performed covert communication injection without changing network packet behavior to get closer to real attack scenarios. In addition to analyzing and injecting methods for covert communications, this study also uses comprehensive machine learning techniques to train the model proposed in this study to detect threats, including traditional decision trees such as random forests and gradient boosting, as well as complex neural network architectures such as CNNs and LSTMs, to achieve detection accuracy of over 90\%. This study details the methods used for dataset augmentation and the comparative performance of the applied models, reinforcing insights into the adaptability and resilience of the machine learning application in IPv6 covert communication. We further introduce a Generative AI-driven script refinement framework, leveraging prompt engineering as a preliminary exploration of how generative agents can assist in covert communication detection and model enhancement.
Authors: Chenyu Gao, Kaiwen Xu, Michael E. Kim, Lianrui Zuo, Zhiyuan Li, Derek B. Archer, Timothy J. Hohman, Ann Zenobia Moore, Luigi Ferrucci, Lori L. Beason-Held, Susan M. Resnick, Christos Davatzikos, Jerry L. Prince, Bennett A. Landman
Abstract: Defacing is often applied to head magnetic resonance image (MRI) datasets prior to public release to address privacy concerns. The alteration of facial and nearby voxels has provoked discussions about the true capability of these techniques to ensure privacy as well as their impact on downstream tasks. With advancements in deep generative models, the extent to which defacing can protect privacy is uncertain. Additionally, while the altered voxels are known to contain valuable anatomical information, their potential to support research beyond the anatomical regions directly affected by defacing remains uncertain. To evaluate these considerations, we develop a refacing pipeline that recovers faces in defaced head MRIs using cascaded diffusion probabilistic models (DPMs). The DPMs are trained on images from 180 subjects and tested on images from 484 unseen subjects, 469 of whom are from a different dataset. To assess whether the altered voxels in defacing contain universally useful information, we also predict computed tomography (CT)-derived skeletal muscle radiodensity from facial voxels in both defaced and original MRIs. The results show that DPMs can generate high-fidelity faces that resemble the original faces from defaced images, with surface distances to the original faces significantly smaller than those of a population average face (p < 0.05). This performance also generalizes well to previously unseen datasets. For skeletal muscle radiodensity predictions, using defaced images results in significantly weaker Spearman's rank correlation coefficients compared to using original images (p < 10-4). For shin muscle, the correlation is statistically significant (p < 0.05) when using original images but not statistically significant (p > 0.05) when any defacing method is applied, suggesting that defacing might not only fail to protect privacy but also eliminate valuable information.
Authors: Mohsinul Kabir, Ajwad Abrar, Sophia Ananiadou
Abstract: A large number of studies rely on closed-style multiple-choice surveys to evaluate cultural alignment in Large Language Models (LLMs). In this work, we challenge this constrained evaluation paradigm and explore more realistic, unconstrained approaches. Using the World Values Survey (WVS) and Hofstede Cultural Dimensions as case studies, we demonstrate that LLMs exhibit stronger cultural alignment in less constrained settings, where responses are not forced. Additionally, we show that even minor changes, such as reordering survey choices, lead to inconsistent outputs, exposing the limitations of closed-style evaluations. Our findings advocate for more robust and flexible evaluation frameworks that focus on specific cultural proxies, encouraging more nuanced and accurate assessments of cultural alignment in LLMs.
Authors: Heming Xia, Chak Tou Leong, Wenjie Wang, Yongqi Li, Wenjie Li
Abstract: Chain-of-Thought (CoT) has been proven effective in enhancing the reasoning capabilities of large language models (LLMs). Recent advancements, such as OpenAI's o1 and DeepSeek-R1, suggest that scaling up the length of CoT sequences during inference could further boost LLM reasoning performance. However, due to the autoregressive nature of LLM decoding, longer CoT outputs lead to a linear increase in inference latency, adversely affecting user experience, particularly when the CoT exceeds 10,000 tokens. To address this limitation, we analyze the semantic importance of tokens within CoT outputs and reveal that their contributions to reasoning vary. Building on this insight, we propose TokenSkip, a simple yet effective approach that enables LLMs to selectively skip less important tokens, allowing for controllable CoT compression. Extensive experiments across various models and tasks demonstrate the effectiveness of TokenSkip in reducing CoT token usage while preserving strong reasoning performance. Notably, when applied to Qwen2.5-14B-Instruct, TokenSkip reduces reasoning tokens by 40% (from 313 to 181) on GSM8K, with less than a 0.4% performance drop. We release our code and checkpoints in https://github.com/hemingkx/TokenSkip.
Authors: Saad Obaid ul Islam, Anne Lauscher, Goran Glava\v{s}
Abstract: In the age of misinformation, hallucination -- the tendency of Large Language Models (LLMs) to generate non-factual or unfaithful responses -- represents the main risk for their global utility. Despite LLMs becoming increasingly multilingual, the vast majority of research on detecting and quantifying LLM hallucination are (a) English-centric and (b) focus on machine translation (MT) and summarization, tasks that are less common ``in the wild'' than open information seeking. In contrast, we aim to quantify the extent of LLM hallucination across languages in knowledge-intensive long-form question answering. To this end, we train a multilingual hallucination detection model and conduct a large-scale study across 30 languages and 6 open-source LLM families. We start from an English hallucination detection dataset and rely on MT to generate (noisy) training data in other languages. We also manually annotate gold data for five high-resource languages; we then demonstrate, for these languages, that the estimates of hallucination rates are similar between silver (LLM-generated) and gold test sets, validating the use of silver data for estimating hallucination rates for other languages. For the final rates estimation, we build a knowledge-intensive QA dataset for 30 languages with LLM-generated prompts and Wikipedia articles as references. We find that, while LLMs generate longer responses with more hallucinated tokens for higher-resource languages, there is no correlation between length-normalized hallucination rates of languages and their digital representation. Further, we find that smaller LLMs exhibit larger hallucination rates than larger models.
Authors: Jingbiao Mei, Jinghong Chen, Guangyu Yang, Weizhe Lin, Bill Byrne
Abstract: Hateful memes have become a significant concern on the Internet, necessitating robust automated detection systems. While Large Multimodal Models (LMMs) have shown promise in hateful meme detection, they face notable challenges like sub-optimal performance and limited out-of-domain generalization capabilities. Recent studies further reveal the limitations of both supervised fine-tuning (SFT) and in-context learning when applied to LMMs in this setting. To address these issues, we propose a robust adaptation framework for hateful meme detection that enhances in-domain accuracy and cross-domain generalization while preserving the general vision-language capabilities of LMMs. Analysis reveals that our approach achieves improved robustness under adversarial attacks compared to SFT models. Experiments on six meme classification datasets show that our approach achieves state-of-the-art performance, outperforming larger agentic systems. Moreover, our method generates higher-quality rationales for explaining hateful content compared to standard SFT, enhancing model interpretability. Code available at https://github.com/JingbiaoMei/RGCL
Authors: Benjamin Plaut, Juan Li\'evano-Karim, Hanlin Zhu, Stuart Russell
Abstract: Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and to transfer knowledge between similar states. We show that this combination enables the agent to learn both safely and effectively. Under standard online learning assumptions, we provide an algorithm whose regret and number of mentor queries are both sublinear in the time horizon for any Markov Decision Process (MDP), including MDPs with irreversible dynamics. Our proof involves a sequence of three reductions which may be of independent interest. Conceptually, our result may be the first formal proof that it is possible for an agent to obtain high reward while becoming self-sufficient in an unknown, unbounded, and high-stakes environment without resets.
Authors: Mingsheng Cai, Jiuming Jiang, Wenhao Huang, Che Liu, Rossella Arcucci
Abstract: Cardiovascular diseases are a leading cause of death and disability worldwide. Electrocardiogram (ECG) is critical for diagnosing and monitoring cardiac health, but obtaining large-scale annotated ECG datasets is labor-intensive and time-consuming. Recent ECG Self-Supervised Learning (eSSL) methods mitigate this by learning features without extensive labels but fail to capture fine-grained clinical semantics and require extensive task-specific fine-tuning. To address these challenges, we propose $\textbf{SuPreME}$, a $\textbf{Su}$pervised $\textbf{Pre}$-training framework for $\textbf{M}$ultimodal $\textbf{E}$CG representation learning. SuPreME is pre-trained using structured diagnostic labels derived from ECG report entities through a one-time offline extraction with Large Language Models (LLMs), which help denoise, standardize cardiac concepts, and improve clinical representation learning. By fusing ECG signals with textual cardiac queries instead of fixed labels, SuPreME enables zero-shot classification of unseen conditions without further fine-tuning. We evaluate SuPreME on six downstream datasets covering 106 cardiac conditions, achieving superior zero-shot AUC performance of $77.20\%$, surpassing state-of-the-art eSSLs by $4.98\%$. Results demonstrate SuPreME's effectiveness in leveraging structured, clinically relevant knowledge for high-quality ECG representations.
Authors: Yingkai Sha, John S. Schreck, William Chapman, David John Gagne II
Abstract: Artificial Intelligence (AI) weather prediction (AIWP) models often produce ``blurry'' precipitation forecasts. This study presents a novel solution to tackle this problem -- integrating terrain-following coordinates into AIWP models. Forecast experiments are conducted to evaluate the effectiveness of terrain-following coordinates using FuXi, an example AIWP model, adapted to 1.0 degree grid spacing data. Verification results show a largely improved estimation of extreme events and precipitation intensity spectra. Terrain-following coordinates are also found to collaborate well with global mass and energy conservation constraints, with a clear reduction of drizzle bias. Case studies reveal that terrain-following coordinates can represent near-surface winds better, which helps AIWP models in learning the relationships between precipitation and other prognostic variables. The result of this study suggests that terrain-following coordinates are worth considering for AIWP models in producing more accurate precipitation forecasts.
Authors: Jie Wu, Haoling Li, Xin Zhang, Jianwen Luo, Yangyu Huang, Ruihang Chu, Yujiu Yang, Scarlett Li
Abstract: Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success rates, with the candidate demonstrating a higher pass rate being labeled as positive and its counterpart with a lower pass rate as negative. However, because this approach aligns entire failing code blocks rather than pinpointing specific errors, it lacks the granularity necessary to capture meaningful error-correction relationships. As a result, the model is unable to learn more informative error-correction patterns. To address these issues, we propose Target-DPO, a new preference alignment framework that mimics human iterative debugging to refine Code LLMs. Target-DPO explicitly locates error regions and aligns the corresponding tokens via a tailored DPO algorithm. To facilitate it, we introduce the CodeFlow dataset, where samples are iteratively refined until passing tests, with modifications capturing error corrections. Extensive experiments show that a diverse suite of Code LLMs equipped with Target-DPO achieves significant performance gains in code generation and improves on challenging tasks like BigCodeBench. In-depth analysis reveals that Target-DPO yields fewer errors. Code, model and datasets are in: https://github.com/JieWu02/Target-DPO.
Authors: Yu-Seung Roh, Joo-Young Kim, Jin-Duk Park, Won-Yong Shin
Abstract: Multimodal recommender systems improve the performance of canonical recommender systems with no item features by utilizing diverse content types such as text, images, and videos, while alleviating inherent sparsity of user-item interactions and accelerating user engagement. However, current neural network-based models often incur significant computational overhead due to the complex training process required to learn and integrate information from multiple modalities. To address this challenge,we propose MultiModal-Graph Filtering (MM-GF), a training-free method grounded in graph filtering (GF) for efficient and accurate multimodal recommendations. Specifically, MM-GF first constructs multiple similarity graphs for two distinct modalities as well as user-item interaction data. Then, MM-GF optimally fuses these multimodal signals using a polynomial graph filter that allows for precise control of the frequency response by adjusting frequency bounds. Furthermore, the filter coefficients are treated as hyperparameters, enabling flexible and data-driven adaptation. Extensive experiments on real-world benchmark datasets demonstrate that MM-GF not only improves recommendation accuracy by up to 22.25% compared to the best competitor but also dramatically reduces computational costs by achieving the runtime of less than 10 seconds.
Authors: Simon A. Aytes, Jinheon Baek, Sung Ju Hwang
Abstract: Recent advances in large language models (LLMs) have enabled strong reasoning capabilities through Chain-of-Thought (CoT) prompting, which elicits step-by-step problem solving, but often at the cost of excessive verbosity in intermediate outputs, leading to increased computational overhead. We propose Sketch-of-Thought (SoT), a prompting framework that integrates cognitively inspired reasoning paradigms with linguistic constraints to reduce token usage while preserving reasoning accuracy. SoT is designed as a flexible, modular approach and is instantiated with three paradigms--Conceptual Chaining, Chunked Symbolism, and Expert Lexicons--each tailored to distinct reasoning tasks and selected dynamically at test-time by a lightweight routing model. Across 18 reasoning datasets spanning multiple domains, languages, and modalities, SoT achieves token reductions of up to 84% with minimal accuracy loss. In tasks such as mathematical and multi-hop reasoning, it even improves accuracy while shortening outputs.
Authors: Melanie Subbiah, Akankshya Mishra, Grace Kim, Liyan Tang, Greg Durrett, Kathleen McKeown
Abstract: Determining faithfulness of a claim to a source document is an important problem across many domains. This task is generally treated as a binary judgment of whether the claim is supported or unsupported in relation to the source. In many cases, though, whether a claim is supported can be ambiguous. For instance, it may depend on making inferences from given evidence, and different people can reasonably interpret the claim as either supported or unsupported based on their agreement with those inferences. Forcing binary labels upon such claims lowers the reliability of evaluation. In this work, we reframe the task to manage the subjectivity involved with factuality judgments of ambiguous claims. We introduce LLM-generated edits of summaries as a method of providing a nuanced evaluation of claims: how much does a summary need to be edited to be unambiguous? Whether a claim gets rewritten and how much it changes can be used as an automatic evaluation metric, the Ambiguity Rewrite Metric (ARM), with a much richer feedback signal than a binary judgment of faithfulness. We focus on the area of narrative summarization as it is particularly rife with ambiguity and subjective interpretation. We show that ARM produces a 21% absolute improvement in annotator agreement on claim faithfulness, indicating that subjectivity is reduced.
Authors: Vinay Shukla, Prachee Sharma, Ryan Rossi, Sungchul Kim, Tong Yu, Aditya Grover
Abstract: The ability to embed watermarks in images is a fundamental problem of interest for computer vision, and is exacerbated by the rapid rise of generated imagery in recent times. Current state-of-the-art techniques suffer from computational and statistical challenges such as the slow execution speed for practical deployments. In addition, other works trade off fast watermarking speeds but suffer greatly in their robustness or perceptual quality. In this work, we propose WaterFlow (WF), a fast and extremely robust approach for high fidelity visual watermarking based on a learned latent-dependent watermark. Our approach utilizes a pretrained latent diffusion model to encode an arbitrary image into a latent space and produces a learned watermark that is then planted into the Fourier Domain of the latent. The transformation is specified via invertible flow layers that enhance the expressivity of the latent space of the pre-trained model to better preserve image quality while permitting robust and tractable detection. Most notably, WaterFlow demonstrates state-of-the-art performance on general robustness and is the first method capable of effectively defending against difficult combination attacks. We validate our findings on three widely used real and generated datasets: MS-COCO, DiffusionDB, and WikiArt.
Authors: Wenqing Zheng, Noah Fatsi, Daniel Barcklow, Dmitri Kalaev, Steven Yao, Owen Reinert, C. Bayan Bruss, Daniele Rosa
Abstract: Recent advances in recommendation with large language models (LLMs) often rely on either commonsense augmentation at the item-category level or implicit intent modeling on existing knowledge graphs. However, such approaches struggle to capture grounded user intents and to handle sparsity and cold-start scenarios. In this work, we present LLM-based Intent Knowledge Graph Recommender (IKGR), a novel framework that constructs an intent-centric knowledge graph where both users and items are explicitly linked to intent nodes extracted by a tuning-free, RAG-guided LLM pipeline. By grounding intents in external knowledge sources and user profiles, IKGR canonically represents what a user seeks and what an item satisfies as first-class entities. To alleviate sparsity, we further introduce a mutual-intent connectivity densification strategy, which shortens semantic paths between users and long-tail items without requiring cross-graph fusion. Finally, a lightweight GNN layer is employed on top of the intent-enhanced graph to produce recommendation signals with low latency. Extensive experiments on public and enterprise datasets demonstrate that IKGR consistently outperforms strong baselines, particularly on cold-start and long-tail slices, while remaining efficient through a fully offline LLM pipeline.
Authors: Reza Marzban, Hamed Abiri, Raphael Pestourie, Ali Adibi
Abstract: HiLAB (Hybrid inverse-design with Latent-space learning, Adjoint-based partial optimizations, and Bayesian optimization) is a new paradigm for inverse design of nanophotonic structures. Combining early-terminated topological optimization (TO) with a Vision Transformer-based variational autoencoder (VAE) and a Bayesian search, HiLAB addresses multi-functional device design by generating diverse freeform configurations at reduced simulation costs. Shortened adjoint-driven TO runs, coupled with randomized physical parameters, produce robust initial structures. These structures are compressed into a compact latent space by the VAE, enabling Bayesian optimization to co-optimize geometry and physical hyperparameters. Crucially, the trained VAE can be reused for alternative objectives or constraints by adjusting only the acquisition function. Compared to conventional TO pipelines prone to local optima, HiLAB systematically explores near-global optima with considerably fewer electromagnetic simulations. Even after accounting for training overhead, the total number of full simulations decreases by over an order of magnitude, accelerating the discovery of fabrication-friendly devices. Demonstrating its efficacy, HiLAB is used to design an achromatic beam deflector for red, green, and blue wavelengths, achieving balanced diffraction efficiencies of ~25% while mitigating chromatic aberrations-a performance surpassing existing demonstrations. Overall, HiLAB provides a flexible platform for robust, multi-parameter photonic designs and rapid adaptation to next-generation nanophotonic challenges.
Authors: Yongmin Yoo, Qiongkai Xu, Longbing Cao
Abstract: High-stakes texts such as patent claims, medical records, and technical reports are structurally complex and demand a high degree of reliability and precision. While large language models (LLMs) have recently been applied to automate their generation in high-stakes domains, reliably evaluating such outputs remains a major challenge. Conventional natural language generation (NLG) metrics are effective for generic documents but fail to capture the structural and legal characteristics essential to evaluating complex high-stakes documents. To address this gap, we propose PatentScore, a multi-dimensional evaluation framework specifically designed for one of the most intricate and rigorous domains, patent claims. PatentScore integrates hierarchical decomposition of claim elements, validation patterns grounded in legal and technical standards, and scoring across structural, semantic, and legal dimensions. In experiments on our dataset which consists of 400 Claim1, PatentScore achieved the highest correlation with expert annotations ($r = 0.819$), significantly outperforming widely used NLG metrics. This work establishes a new standard for evaluating LLM-generated patent claims, providing a solid foundation for research on patent generation and validation.
Authors: Marvin Limpijankit, Yanda Chen, Melanie Subbiah, Nicholas Deas, Kathleen McKeown
Abstract: LLMs can be unpredictable, as even slight alterations to the prompt can cause the output to change in unexpected ways. Thus, the ability of models to accurately explain their behavior is critical, especially in high-stakes settings. One approach for evaluating explanations is counterfactual simulatability, how well an explanation allows users to infer the model's output on related counterfactuals. Counterfactual simulatability has been previously studied for yes/no question answering tasks. We provide a general framework for extending this method to generation tasks, using news summarization and medical suggestion as example use cases. We find that while LLM explanations do enable users to better predict LLM outputs on counterfactuals in the summarization setting, there is significant room for improvement for medical suggestion. Furthermore, our results suggest that the evaluation for counterfactual simulatability may be more appropriate for skill-based tasks as opposed to knowledge-based tasks.
Authors: Minghao Liu (May), Zhitao He (May), Zhiyuan Fan (May), Qingyun Wang (May), Yi R. (May), Fung
Abstract: Text-guided image editing has seen significant progress in natural image domains, but its application in medical imaging remains limited and lacks standardized evaluation frameworks. Such editing could revolutionize clinical practices by enabling personalized surgical planning, enhancing medical education, and improving patient communication. To bridge this gap, we introduce MedEBench1, a robust benchmark designed to diagnose reliability in text-guided medical image editing. MedEBench consists of 1,182 clinically curated image-prompt pairs covering 70 distinct editing tasks and 13 anatomical regions. It contributes in three key areas: (1) a clinically grounded evaluation framework that measures Editing Accuracy, Context Preservation, and Visual Quality, complemented by detailed descriptions of intended edits and corresponding Region-of-Interest (ROI) masks; (2) a comprehensive comparison of seven state-of-theart models, revealing consistent patterns of failure; and (3) a diagnostic error analysis technique that leverages attention alignment, using Intersection-over-Union (IoU) between model attention maps and ROI masks to identify mislocalization issues, where models erroneously focus on incorrect anatomical regions. MedEBench sets the stage for developing more reliable and clinically effective text-guided medical image editing tools.
Authors: Daniel Koh, Yannic Noller, Corina S. Pasareanu, Adrians Skapars, Youcheng Sun
Abstract: Large language models (LLMs) have demonstrated strong performance on coding tasks such as generation, completion and repair, but their ability to handle complex symbolic reasoning over code still remains underexplored. We introduce the task of worst-case symbolic constraints analysis, which requires inferring the symbolic constraints that characterise worst-case program executions; these constraints can be solved to obtain inputs that expose performance bottlenecks or denial-of-service vulnerabilities in software systems. We show that even state-of-the-art LLMs (e.g., GPT-5) struggle when applied directly on this task. To address this challenge, we propose WARP, an innovative neurosymbolic approach that computes worst-case constraints on smaller concrete input sizes using existing program analysis tools, and then leverages LLMs to generalise these constraints to larger input sizes. Concretely, WARP comprises: (1) an incremental strategy for LLM-based worst-case reasoning, (2) a solver-aligned neurosymbolic framework that integrates reinforcement learning with SMT (Satisfiability Modulo Theories) solving, and (3) a curated dataset of symbolic constraints. Experimental results show that WARP consistently improves performance on worst-case constraint reasoning. Leveraging the curated constraint dataset, we use reinforcement learning to fine-tune a model, WARP-1.0-3B, which significantly outperforms size-matched and even larger baselines. These results demonstrate that incremental constraint reasoning enhances LLMs' ability to handle symbolic reasoning and highlight the potential for deeper integration between neural learning and formal methods in rigorous program analysis.
Authors: Chihiro Taguchi, Seiji Maekawa, Nikita Bhutani
Abstract: Retrieval-augmented generation (RAG) and long-context language models (LCLMs) both address context limitations of LLMs in open-domain question answering (QA). However, optimal external context to retrieve remains an open problem: fixing the retrieval size risks either wasting tokens or omitting key evidence. Existing adaptive methods like Self-RAG and Self-Route rely on iterative LLM prompting and perform well on factoid QA, but struggle with aggregation QA, where the optimal context size is both unknown and variable. We present Adaptive-$k$ retrieval, a simple and effective single-pass method that adaptively selects the number of passages based on the distribution of the similarity scores between the query and the candidate passages. It does not require model fine-tuning, extra LLM inferences or changes to existing retriever-reader pipelines. On both factoid and aggregation QA benchmarks, Adaptive-$k$ matches or outperforms fixed-$k$ baselines while using up to 10x fewer tokens than full-context input, yet still retrieves 70% of relevant passages. It improves accuracy across five LCLMs and two embedding models, highlighting that dynamically adjusting context size leads to more efficient and accurate QA.
Authors: Yuan Zhong, Ruinan Jin, Qi Dou, Xiaoxiao Li
Abstract: Vision Language Models (VLMs) have shown promise in automating image diagnosis and interpretation in clinical settings. However, developing specialist medical VLMs requires substantial computational resources and carefully curated datasets, and it remains unclear under which conditions generalist and specialist medical VLMs each perform best. This study highlights the complementary strengths of specialist medical and generalist VLMs. Specialists remain valuable in modality-aligned use cases, but we find that efficiently fine-tuned generalist VLMs can achieve comparable or even superior performance in most tasks, particularly when transferring to unseen or rare OOD medical modalities. These results suggest that generalist VLMs, rather than being constrained by their lack of specialist medical pretraining, may offer a scalable and cost-effective pathway for advancing clinical AI development.
Authors: Federico Tavella, Amber Drinkwater, Angelo Cangelosi
Abstract: Vision-Language Models (VLMs) have emerged as powerful tools for generating textual descriptions from visual data. While these models excel on web-scale datasets, their robustness to the domain shifts inherent in many real-world applications remains under-explored. This paper presents a systematic evaluation of VLM performance on a single-view object captioning task when faced with a controlled, physical domain shift. We compare captioning accuracy across two distinct object sets: a collection of multi-material, real-world tools and a set of single-material, 3D-printed items. The 3D-printed set introduces a significant domain shift in texture and material properties, challenging the models' generalization capabilities. Our quantitative results demonstrate that all tested VLMs show a marked performance degradation when describing the 3D-printed objects compared to the real-world tools. This underscores a critical limitation in the ability of current models to generalize beyond surface-level features and highlights the need for more robust architectures for real-world signal processing applications.
Authors: Miroslav Cibula, Krist\'ina Malinovsk\'a, Matthias Kerzel
Abstract: Trajectory planning in robotics is understood as generating a sequence of joint configurations that will lead a robotic agent, or its manipulator, from an initial state to the desired final state, thus completing a manipulation task while considering constraints like robot kinematics and the environment. Typically, this is achieved via sampling-based planners, which are computationally intensive. Recent advances demonstrate that trajectory planning can also be performed by supervised sequence learning of trajectories, often requiring only a single or fixed number of passes through a neural architecture, thus ensuring a bounded computation time. Such fully supervised approaches, however, perform imitation learning; they do not learn based on whether the trajectories can successfully reach a goal, but try to reproduce observed trajectories. In our work, we build on this approach and propose a cognitively inspired self-supervised learning scheme based on a recurrent architecture for building a trajectory model. We evaluate the feasibility of the proposed method on a task of kinematic planning for a robotic arm. The results suggest that the model is able to learn to generate trajectories only using given paired forward and inverse kinematics models, and indicate that this novel method could facilitate planning for more complex manipulation tasks requiring adaptive solutions.
Authors: Chenhao Xue, Kezhi Li, Jiaxing Zhang, Yi Ren, Zhengyuan Shi, Chen Zhang, Yibo Lin, Lining Zhang, Qiang Xu, Guangyu Sun
Abstract: Arithmetic circuits, such as adders and multipliers, are fundamental components of digital systems, directly impacting the performance, power efficiency, and area footprint. However, optimizing these circuits remains challenging due to the vast design space and complex physical constraints. While recent deep learning-based approaches have shown promise, they struggle to consistently explore high-potential design variants, limiting their optimization efficiency. To address this challenge, we propose AC-Refiner, a novel arithmetic circuit optimization framework leveraging conditional diffusion models. Our key insight is to reframe arithmetic circuit synthesis as a conditional image generation task. By carefully conditioning the denoising diffusion process on target quality-of-results (QoRs), AC-Refiner consistently produces high-quality circuit designs. Furthermore, the explored designs are used to fine-tune the diffusion model, which focuses the exploration near the Pareto frontier. Experimental results demonstrate that AC-Refiner generates designs with superior Pareto optimality, outperforming state-of-the-art baselines. The performance gain is further validated by integrating AC-Refiner into practical applications.
Authors: Tom Hickling, Jonathan F. MacArt, Justin Sirignano, Den Waidmann
Abstract: Turbulent flows are chaotic and unsteady, but their statistical distribution converges to a statistical steady state. Engineering quantities of interest typically take the form of time-average statistics such as $ \frac{1}{t} \int_0^t f ( u(x,\tau; \theta) ) d\tau \overset{t \rightarrow \infty}{\rightarrow} F(x; \theta)$, where $u(x,t; \theta)$ are solutions of the Navier--Stokes equations with parameters $\theta$. Optimizing over $F(x; \theta)$ has many engineering applications including geometric optimization, flow control, and closure modeling. However, this remains an open challenge, as existing computational approaches are incapable of scaling to physically representative numbers of grid points. The fundamental obstacle is the chaoticity of turbulent flows: gradients calculated with the adjoint method diverge exponentially as $t \rightarrow \infty$. We develop a new online gradient-flow (OGF) method that is scalable to large degree-of-freedom systems and enables optimizing for the steady-state statistics of chaotic, unsteady, turbulence-resolving simulations. The method forward-propagates an online estimate for the gradient of $F(x; \theta)$ while simultaneously performing online updates of the parameters $\theta$. A key feature is the fully online nature of the algorithm to facilitate faster optimization progress and its combination with a finite-difference estimator to avoid the divergence of gradients due to chaoticity. The proposed OGF method is demonstrated for optimizations over three chaotic ordinary and partial differential equations: the Lorenz-63 equation, the Kuramoto--Sivashinsky equation, and Navier--Stokes solutions of compressible, forced, homogeneous isotropic turbulence. In each case, the OGF method successfully reduces the loss based on $F(x; \theta)$ by several orders of magnitude and accurately recovers the optimal parameters.
Authors: Yaodong Su, Yixiang Fang, Yingli Zhou, Quanqing Xu, Chuanhui Yang
Abstract: Despite the remarkable progress of Large Language Models (LLMs), their performance in question answering (QA) remains limited by the lack of domain-specific and up-to-date knowledge. Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external information, often from graph-structured data. However, existing graph-based RAG methods suffer from poor graph quality due to incomplete extraction and insufficient utilization of query information during retrieval. To overcome these limitations, we propose Clue-RAG, a novel approach that introduces (1) a multi-partite graph index incorporates Chunk, knowledge unit, and entity to capture semantic content at multiple levels of granularity, coupled with a hybrid extraction strategy that reduces LLM token usage while still producing accurate and disambiguated knowledge units, and (2) Q-Iter, a query-driven iterative retrieval strategy that enhances relevance through semantic search and constrained graph traversal. Experiments on three QA benchmarks show that Clue-RAG significantly outperforms state-of-the-art baselines, achieving up to 99.33% higher Accuracy and 113.51% higher F1 score while reducing indexing costs by 72.58%. Remarkably, Clue-RAG matches or outperforms baselines even without using an LLM for indexing. These results demonstrate the effectiveness and cost-efficiency of Clue-RAG in advancing graph-based RAG systems.
Authors: Gaurav R. Ghosal, Pratyush Maini, Aditi Raghunathan
Abstract: Large language models are susceptible to memorizing repeated sequences, posing privacy and copyright concerns. A popular mitigation strategy is to remove memorized information from specific neurons post-hoc. However, such approaches have shown limited success so far. In a controlled setting, we show that the memorization of natural sequences (those that resemble linguistically plausible text) become mechanistically entangled with general language abilities, thereby becoming challenging to remove post-hoc. In this work, we put forward a new paradigm of MemSinks that promotes isolation of memorization by design. We leverage a sequence identifier that activates a unique set of memorization neurons for each sequence across repetitions. By analyzing the dynamics of learning and forgetting, we argue that MemSinks facilitates isolation of memorized content, making it easier to remove without compromising general language capabilities. We implement MemSinks at the billion-parameter and billion-token scale, and observe both effective isolation and strong generalization. To our knowledge, this is the first proof-of-concept on real data demonstrating that simultaneous generalization and isolation is achievable. We open-source our code at http://github.com/grghosal/MemSinks.
Authors: Seth Ockerman, Amal Gueroudji, Tanwi Mallick, Yixuan He, Line Pouchard, Robert Ross, Shivaram Venkataraman
Abstract: Spatiotemporal graph neural networks (ST-GNNs) are powerful tools for modeling spatial and temporal data dependencies. However, their applications have been limited primarily to small-scale datasets because of memory constraints. While distributed training offers a solution, current frameworks lack support for spatiotemporal models and overlook the properties of spatiotemporal data. Informed by a scaling study on a large-scale workload, we present PyTorch Geometric Temporal Index (PGT-I), an extension to PyTorch Geometric Temporal that integrates distributed data parallel training and two novel strategies: index-batching and distributed-index-batching. Our index techniques exploit spatiotemporal structure to construct snapshots dynamically at runtime, significantly reducing memory overhead, while distributed-index-batching extends this approach by enabling scalable processing across multiple GPUs. Our techniques enable the first-ever training of an ST-GNN on the entire PeMS dataset without graph partitioning, reducing peak memory usage by up to 89% and achieving up to a 11.78x speedup over standard DDP with 128 GPUs.
Authors: Yufan Song, Jiatao Zhang, Zeng Gu, Qingmiao Liang, Tuocheng Hu, Wei Song, Shiqiang Zhu
Abstract: Autonomous error correction is critical for domestic robots to achieve reliable execution of complex long-horizon tasks. Prior work has explored self-reflection in Large Language Models (LLMs) for task planning error correction; however, existing methods are constrained by inflexible self-reflection mechanisms that limit their effectiveness. Motivated by these limitations and inspired by human cognitive adaptation, we propose the Flexible Constructivism Reflection Framework (FCRF), a novel Mentor-Actor architecture that enables LLMs to perform flexible self-reflection based on task difficulty, while constructively integrating historical valuable experience with failure lessons. We evaluated FCRF on diverse domestic tasks through simulation in AlfWorld and physical deployment in the real-world environment. Experimental results demonstrate that FCRF significantly improves overall performance and self-reflection flexibility in complex long-horizon robotic tasks.
Authors: Taeyoung Kim
Abstract: Fourier Neural Operators (FNOs) have emerged as leading surrogates for solver operators for various functional problems, yet their stability, generalization and frequency behavior lack a principled explanation. We present a systematic effective field theory analysis of FNOs in an infinite dimensional function space, deriving closed recursion relations for the layer kernel and four point vertex and then examining three practically important settings-analytic activations, scale invariant cases and architectures with residual connections. The theory shows that nonlinear activations inevitably couple frequency inputs to high frequency modes that are otherwise discarded by spectral truncation, and experiments confirm this frequency transfer. For wide networks, we derive explicit criticality conditions on the weight initialization ensemble that ensure small input perturbations maintain a uniform scale across depth, and we confirm experimentally that the theoretically predicted ratio of kernel perturbations matches the measurements. Taken together, our results quantify how nonlinearity enables neural operators to capture non-trivial features, supply criteria for hyperparameter selection via criticality analysis, and explain why scale invariant activations and residual connections enhance feature learning in FNOs.
Authors: Sergio Rojas-Galeano
Abstract: The arrival of AI coding assistants in educational settings presents a paradigm shift, introducing a "new kid in the classroom" for both students and instructors. Thus, understanding the perceptions of these key actors about this new dynamic is critical. This exploratory study contributes to this area by investigating how these tools are shaping the experiences of novice programmers in an introductory programming course. Through a two-part exam, we investigated student perceptions by first providing access to AI support for a programming task and then requiring an extension of the solution without it. We collected Likert-scale and open-ended responses from 20 students to understand their perceptions on the challenges they faced. Our findings reveal that students perceived AI tools as helpful for grasping code concepts and boosting their confidence during the initial development phase. However, a noticeable difficulty emerged when students were asked to work unaided, pointing to potential overreliance and gaps in foundational knowledge transfer. These insights highlight a critical need for new pedagogical approaches that integrate AI effectively while effectively enhancing core programming skills, rather than impersonating them.
Authors: Jiajun Cao, Qizhe Zhang, Peidong Jia, Xuhui Zhao, Bo Lan, Xiaoan Zhang, Zhuo Li, Xiaobao Wei, Sixiang Chen, Liyun Li, Xianming Liu, Ming Lu, Yang Wang, Shanghang Zhang
Abstract: Vision-Language-Action (VLA) models have demonstrated significant potential in complex scene understanding and action reasoning, leading to their increasing adoption in end-to-end autonomous driving systems. However, the long visual tokens of VLA models greatly increase computational costs. Current visual token pruning methods in Vision-Language Models (VLM) rely on either visual token similarity or visual-text attention, but both have shown poor performance in autonomous driving scenarios. Given that human drivers concentrate on relevant foreground areas while driving, we assert that retaining visual tokens containing this foreground information is essential for effective decision-making. Inspired by this, we propose FastDriveVLA, a novel reconstruction-based vision token pruning framework designed specifically for autonomous driving. FastDriveVLA includes a plug-and-play visual token pruner called ReconPruner, which prioritizes foreground information through MAE-style pixel reconstruction. A novel adversarial foreground-background reconstruction strategy is designed to train ReconPruner for the visual encoder of VLA models. Once trained, ReconPruner can be seamlessly applied to different VLA models with the same visual encoder without retraining. To train ReconPruner, we also introduce a large-scale dataset called nuScenes-FG, consisting of 241K image-mask pairs with annotated foreground regions. Our approach achieves state-of-the-art results on the nuScenes open-loop planning benchmark across different pruning ratios.
Authors: Nuno Fachada, Daniel Fernandes, Carlos M. Fernandes, Bruno D. Ferreira-Saraiva, Jo\~ao P. Matos-Carvalho
Abstract: Large Language Models (LLMs) have advanced rapidly as tools for automating code generation in scientific research, yet their ability to interpret and use unfamiliar Python APIs for complex computational experiments remains poorly characterized. This study systematically benchmarks a selection of state-of-the-art LLMs in generating functional Python code for two increasingly challenging scenarios: conversational data analysis with the \textit{ParShift} library, and synthetic data generation and clustering using \textit{pyclugen} and \textit{scikit-learn}. Both experiments use structured, zero-shot prompts specifying detailed requirements but omitting in-context examples. Model outputs are evaluated quantitatively for functional correctness and prompt compliance over multiple runs, and qualitatively by analyzing the errors produced when code execution fails. Results show that only a small subset of models consistently generate correct, executable code. GPT-4.1 achieved a 100\% success rate across all runs in both experimental tasks, whereas most other models succeeded in fewer than half of the runs, with only Grok-3 and Mistral-Large approaching comparable performance. In addition to benchmarking LLM performance, this approach helps identify shortcomings in third-party libraries, such as unclear documentation or obscure implementation bugs. Overall, these findings highlight current limitations of LLMs for end-to-end scientific automation and emphasize the need for careful prompt design, comprehensive library documentation, and continued advances in language model capabilities.
Authors: Irene Iele, Francesco Di Feola, Valerio Guarrasi, Paolo Soda
Abstract: Image-to-image translation has emerged as a powerful technique in medical imaging, enabling tasks such as image denoising and cross-modality conversion. However, it suffers from limitations in handling out-of-distribution samples without causing performance degradation. To address this limitation, we propose a novel Test-Time Adaptation (TTA) framework that dynamically adjusts the translation process based on the characteristics of each test sample. Our method introduces a Reconstruction Module to quantify the domain shift and a Dynamic Adaptation Block that selectively modifies the internal features of a pretrained translation model to mitigate the shift without compromising the performance on in-distribution samples that do not require adaptation. We evaluate our approach on two medical image-to-image translation tasks: low-dose CT denoising and T1 to T2 MRI translation, showing consistent improvements over both the baseline translation model without TTA and prior TTA methods. Our analysis highlights the limitations of the state-of-the-art that uniformly apply the adaptation to both out-of-distribution and in-distribution samples, demonstrating that dynamic, sample-specific adjustment offers a promising path to improve model resilience in real-world scenarios. The code is available at: https://github.com/Sample-Aware-TTA/Code.
Authors: Zhangquan Chen, Ruihui Zhao, Chuwei Luo, Mingze Sun, Xinlei Yu, Yangyang Kang, Ruqi Huang
Abstract: Current multimodal large language models (MLLMs) still face significant challenges in complex visual tasks (e.g., spatial understanding, fine-grained perception). Prior methods have tried to incorporate visual reasoning, however, they fail to leverage attention correction with spatial cues to iteratively refine their focus on prompt-relevant regions. In this paper, we introduce SIFThinker, a spatially-aware "think-with-images" framework that mimics human visual perception. Specifically, SIFThinker enables attention correcting and image region focusing by interleaving depth-enhanced bounding boxes and natural language. Our contributions are twofold: First, we introduce a reverse-expansion-forward-inference strategy that facilitates the generation of interleaved image-text chains of thought for process-level supervision, which in turn leads to the construction of the SIF-50K dataset. Besides, we propose GRPO-SIF, a reinforced training paradigm that integrates depth-informed visual grounding into a unified reasoning pipeline, teaching the model to dynamically correct and focus on prompt-relevant regions. Extensive experiments demonstrate that SIFThinker outperforms state-of-the-art methods in spatial understanding and fine-grained visual perception, while maintaining strong general capabilities, highlighting the effectiveness of our method. Code: https://github.com/zhangquanchen/SIFThinker.
Authors: Rapha\"el Merx, Hanna Suominen, Trevor Cohn, Ekaterina Vylomova
Abstract: In machine translation (MT), health is a high-stakes domain characterised by widespread deployment and domain-specific vocabulary. However, there is a lack of MT evaluation datasets for low-resource languages in this domain. To address this gap, we introduce OpenWHO, a document-level parallel corpus of 2,978 documents and 26,824 sentences from the World Health Organization's e-learning platform. Sourced from expert-authored, professionally translated materials shielded from web-crawling, OpenWHO spans a diverse range of over 20 languages, of which nine are low-resource. Leveraging this new resource, we evaluate modern large language models (LLMs) against traditional MT models. Our findings reveal that LLMs consistently outperform traditional MT models, with Gemini 2.5 Flash achieving a +4.79 ChrF point improvement over NLLB-54B on our low-resource test set. Further, we investigate how LLM context utilisation affects accuracy, finding that the benefits of document-level translation are most pronounced in specialised domains like health. We release the OpenWHO corpus to encourage further research into low-resource MT in the health domain.
Authors: Kamel Kamel, Keshav Sood, Hridoy Sankar Dutta, Sunil Aryal
Abstract: Voice authentication has undergone significant changes from traditional systems that relied on handcrafted acoustic features to deep learning models that can extract robust speaker embeddings. This advancement has expanded its applications across finance, smart devices, law enforcement, and beyond. However, as adoption has grown, so have the threats. This survey presents a comprehensive review of the modern threat landscape targeting Voice Authentication Systems (VAS) and Anti-Spoofing Countermeasures (CMs), including data poisoning, adversarial, deepfake, and adversarial spoofing attacks. We chronologically trace the development of voice authentication and examine how vulnerabilities have evolved in tandem with technological advancements. For each category of attack, we summarize methodologies, highlight commonly used datasets, compare performance and limitations, and organize existing literature using widely accepted taxonomies. By highlighting emerging risks and open challenges, this survey aims to support the development of more secure and resilient voice authentication systems.
Authors: Wenfeng Feng, Penghong Zhao, Guochao Jiang, Chuzhan Hao, Yuewei Zhang, Hao Wang, Guohua Liu
Abstract: Critic-free reinforcement learning methods, particularly group policies, have attracted considerable attention for their efficiency in complex tasks. However, these methods rely heavily on multiple sampling and comparisons within the policy to estimate advantage, which may cause the policy to fall into local optimum and increase computational cost. To address these issues, we propose PVPO, an efficient reinforcement learning method enhanced by an advantage reference anchor and data pre-sampling. Specifically, we use the reference model to rollout in advance and employ the calculated reward score as a reference anchor. Our approach effectively corrects the cumulative bias introduced by intra-group comparisons and significantly reduces reliance on the number of rollouts during training. Meanwhile, the reference model can assess sample difficulty during data pre-sampling, enabling effective selection of high-gain data to improve training efficiency. Moreover, PVPO is orthogonal to other advanced critic-free RL algorithms, making it compatible with and complementary to these methods. Experiments conducted on nine datasets across two domains demonstrate that PVPO achieves State-Of-The-Art (SOTA) performance. Our approach not only demonstrates robust generalization across multiple tasks, but also exhibits scalable performance across models of varying scales.
Authors: Lennart Clasmeier, Jan-Gerrit Habekost, Connor G\"ade, Philipp Allgeuer, Stefan Wermter
Abstract: We propose a novel diffusion-based action model for robotic motion planning. Commonly, established numerical planning approaches are used to solve general motion planning problems, but have significant runtime requirements. By leveraging the power of deep learning, we are able to achieve good results in a much smaller runtime by learning from a dataset generated by these planners. While our initial model uses point cloud embeddings in the input to predict keypoint-based joint sequences in its output, we observed in our ablation study that it remained challenging to condition the network on the point cloud embeddings. We identified some biases in our dataset and refined it, which improved the model's performance. Our model, even without the use of the point cloud encodings, outperforms numerical models by an order of magnitude regarding the runtime, while reaching a success rate of up to 90% of collision free solutions on the test set.
Authors: Ayush Gupta, Ramneet Kaur, Anirban Roy, Adam D. Cobb, Rama Chellappa, Susmit Jha
Abstract: We propose a novel inference-time out-of-domain (OOD) detection algorithm for specialized large language models (LLMs). Despite achieving state-of-the-art performance on in-domain tasks through fine-tuning, specialized LLMs remain vulnerable to incorrect or unreliable outputs when presented with OOD inputs, posing risks in critical applications. Our method leverages the Inductive Conformal Anomaly Detection (ICAD) framework, using a new non-conformity measure based on the model's dropout tolerance. Motivated by recent findings on polysemanticity and redundancy in LLMs, we hypothesize that in-domain inputs exhibit higher dropout tolerance than OOD inputs. We aggregate dropout tolerance across multiple layers via a valid ensemble approach, improving detection while maintaining theoretical false alarm bounds from ICAD. Experiments with medical-specialized LLMs show that our approach detects OOD inputs better than baseline methods, with AUROC improvements of $2\%$ to $37\%$ when treating OOD datapoints as positives and in-domain test datapoints as negatives.
Authors: Matteo Bortoletto, Constantin Ruhdorfer, Andreas Bulling
Abstract: Most existing Theory of Mind (ToM) benchmarks for foundation models rely on variations of the Sally-Anne test, offering only a very limited perspective on ToM and neglecting the complexity of human social interactions. To address this gap, we propose ToM-SSI: a new benchmark specifically designed to test ToM capabilities in environments rich with social interactions and spatial dynamics. While current ToM benchmarks are limited to text-only or dyadic interactions, ToM-SSI is multimodal and includes group interactions of up to four agents that communicate and move in situated environments. This unique design allows us to study, for the first time, mixed cooperative-obstructive settings and reasoning about multiple agents' mental state in parallel, thus capturing a wider range of social cognition than existing benchmarks. Our evaluations reveal that the current models' performance is still severely limited, especially in these new tasks, highlighting critical gaps for future research.
Authors: Zhiyu Cao, Peifeng Li, Qiaoming Zhu
Abstract: Most previous work on Conversational Query Rewriting employs an end-to-end rewriting paradigm. However, this approach is hindered by the issue of multiple fuzzy expressions within the query, which complicates the simultaneous identification and rewriting of multiple positions. To address this issue, we propose a novel framework ICR (Iterative Clarification and Rewriting), an iterative rewriting scheme that pivots on clarification questions. Within this framework, the model alternates between generating clarification questions and rewritten queries. The experimental results show that our ICR can continuously improve retrieval performance in the clarification-rewriting iterative process, thereby achieving state-of-the-art performance on two popular datasets.
Authors: Justus Huebotter, Pablo Lanillos, Marcel van Gerven, Serge Thill
Abstract: Despite recent progress in training spiking neural networks (SNNs) for classification, their application to continuous motor control remains limited. Here, we demonstrate that fully spiking architectures can be trained end-to-end to control robotic arms with multiple degrees of freedom in continuous environments. Our predictive-control framework combines Leaky Integrate-and-Fire dynamics with surrogate gradients, jointly optimizing a forward model for dynamics prediction and a policy network for goal-directed action. We evaluate this approach on both a planar 2D reaching task and a simulated 6-DOF Franka Emika Panda robot. Results show that SNNs can achieve stable training and accurate torque control, establishing their viability for high-dimensional motor tasks. An extensive ablation study highlights the role of initialization, learnable time constants, and regularization in shaping training dynamics. We conclude that while stable and effective control can be achieved, recurrent spiking networks remain highly sensitive to hyperparameter settings, underscoring the importance of principled design choices.
Authors: Minh N. H. Nguyen, Anh Nguyen Tran, Dung Truong Dinh, Nam Van Vo
Abstract: Code-switching (CS) presents a significant challenge for general Auto-Speech Recognition (ASR) systems. Existing methods often fail to capture the subtle phonological shifts inherent in CS scenarios. The challenge is particularly difficult for language pairs like Vietnamese and English, where both distinct phonological features and the ambiguity arising from similar sound recognition are present. In this paper, we propose a novel architecture for Vietnamese-English CS ASR, a Two-Stage Phoneme-Centric model (TSPC). The TSPC employs a phoneme-centric approach, built upon an extended Vietnamese phoneme set as an intermediate representation to facilitate mixed-lingual modeling. Experimental results demonstrate that TSPC consistently outperforms existing baselines, including PhoWhisper-base, in Vietnamese-English CS ASR, achieving a significantly lower word error rate of 20.8\% with reduced training resources. Furthermore, the phonetic-based two-stage architecture enables phoneme adaptation and language conversion to enhance ASR performance in complex CS Vietnamese-English ASR scenarios.
Authors: Jiaming Cui, Shuai Zhou, Feng Shen
Abstract: Automated defect detection from UAV imagery of transmission lines is a challenging task due to the small size, ambiguity, and complex backgrounds of defects. This paper proposes TinyDef-DETR, a DETR-based framework designed to achieve accurate and efficient detection of transmission line defects from UAV-acquired images. The model integrates four major components: an edge-enhanced ResNet backbone to strengthen boundary-sensitive representations, a stride-free space-to-depth module to enable detail-preserving downsampling, a cross-stage dual-domain multi-scale attention mechanism to jointly model global context and local cues, and a Focaler-Wise-SIoU regression loss to improve the localization of small and difficult targets. Together, these designs effectively mitigate the limitations of conventional detectors. Extensive experiments on both public and real-world datasets demonstrate that TinyDef-DETR achieves superior detection performance and strong generalization capability, while maintaining modest computational overhead. The accuracy and efficiency of TinyDef-DETR make it a suitable method for UAV-based transmission line defect detection, particularly in scenarios involving small and ambiguous targets.
Authors: Yuming Li, Yikai Wang, Yuying Zhu, Zhongyu Zhao, Ming Lu, Qi She, Shanghang Zhang
Abstract: Recent progress in aligning image and video generative models with Group Relative Policy Optimization (GRPO) has improved human preference alignment, but existing variants remain inefficient due to sequential rollouts and large numbers of sampling steps, unreliable credit assignment: sparse terminal rewards are uniformly propagated across timesteps, failing to capture the varying criticality of decisions during denoising. In this paper, we present BranchGRPO, a method that restructures the rollout process into a branching tree, where shared prefixes amortize computation and pruning removes low-value paths and redundant depths. BranchGRPO introduces three contributions: (1) a branching scheme that amortizes rollout cost through shared prefixes while preserving exploration diversity; (2) a reward fusion and depth-wise advantage estimator that transforms sparse terminal rewards into dense step-level signals; and (3) pruning strategies that cut gradient computation but leave forward rollouts and exploration unaffected. On HPDv2.1 image alignment, BranchGRPO improves alignment scores by up to \textbf{16\%} over DanceGRPO, while reducing per-iteration training time by nearly \textbf{55\%}. A hybrid variant, BranchGRPO-Mix, further accelerates training to 4.7x faster than DanceGRPO without degrading alignment. On WanX video generation, it further achieves higher Video-Align scores with sharper and temporally consistent frames compared to DanceGRPO. Codes are available at \href{https://fredreic1849.github.io/BranchGRPO-Webpage/}{BranchGRPO}.
Authors: Jinrui Yang, Xudong Han, Timothy Baldwin
Abstract: We introduce EuroParlVote, a novel benchmark for evaluating large language models (LLMs) in politically sensitive contexts. It links European Parliament debate speeches to roll-call vote outcomes and includes rich demographic metadata for each Member of the European Parliament (MEP), such as gender, age, country, and political group. Using EuroParlVote, we evaluate state-of-the-art LLMs on two tasks -- gender classification and vote prediction -- revealing consistent patterns of bias. We find that LLMs frequently misclassify female MEPs as male and demonstrate reduced accuracy when simulating votes for female speakers. Politically, LLMs tend to favor centrist groups while underperforming on both far-left and far-right ones. Proprietary models like GPT-4o outperform open-weight alternatives in terms of both robustness and fairness. We release the EuroParlVote dataset, code, and demo to support future research on fairness and accountability in NLP within political contexts.
Authors: Rapha\"el Weuts (KU Leuven, Belgium), Johannes Bleher (University of Hohenheim, Germany), Hannah Bleher (University of Bonn, Germany), Rozanne Tuesday Flores (Bukidnon State University, Philippines), Guo Xuanyang (Southwest University of Political Science and Law, China), Pawe{\l} Pujszo (College of Europe, Natolin, Poland), Zsolt Alm\'asi (P\'azm\'any P\'eter Catholic University, Hungary)
Abstract: As artificial intelligence (AI) systems permeate critical sectors, the need for professionals who can address ethical, legal and governance challenges has become urgent. Current AI ethics education remains fragmented, often siloed by discipline and disconnected from practice. This paper synthesizes literature and regulatory developments to propose a modular, interdisciplinary curriculum that integrates technical foundations with ethics, law and policy. We highlight recurring operational failures in AI - bias, misspecified objectives, generalization errors, misuse and governance breakdowns - and link them to pedagogical strategies for teaching AI governance. Drawing on perspectives from the EU, China and international frameworks, we outline a semester plan that emphasizes integrated ethics, stakeholder engagement and experiential learning. The curriculum aims to prepare students to diagnose risks, navigate regulation and engage diverse stakeholders, fostering adaptive and ethically grounded professionals for responsible AI governance.
Authors: Haoyu Dong, Pengkun Zhang, Mingzhe Lu, Yanzhen Shen, Guolin Ke
Abstract: Large language models (LLMs) possess broad world knowledge and strong general-purpose reasoning ability, yet they struggle to learn from many in-context examples on standard machine learning (ML) tasks, that is, to leverage many-shot demonstrations purely via in-context learning (ICL) without gradient descent. We introduce MachineLearningLM, a portable continued-pretraining framework that equips a general-purpose LLM with robust in-context ML capability while preserving its general knowledge and reasoning for broader chat workflows. Our pretraining procedure synthesizes ML tasks from millions of structural causal models (SCMs), spanning shot counts up to 1,024. We begin with a random-forest teacher, distilling tree-based decision strategies into the LLM to strengthen robustness in numerical modeling. All tasks are serialized with a token-efficient prompt, enabling 3x to 6x more examples per context window and delivering up to 50x amortized throughput via batch inference. Despite a modest setup (Qwen-2.5-7B-Instruct with LoRA rank 8), MachineLearningLM outperforms strong LLM baselines (e.g., GPT-5-mini) by an average of about 15% on out-of-distribution tabular classification across finance, physics, biology, and healthcare domains. It exhibits a striking many-shot scaling law: accuracy increases monotonically as in-context demonstrations grow from 8 to 1,024. Without any task-specific training, it attains random-forest-level accuracy across hundreds of shots. General chat capabilities, including knowledge and reasoning, are preserved: it achieves 75.4% on MMLU.
Authors: Yao Liang, Dongcheng Zhao, Feifei Zhao, Guobin Shen, Yuwei Wang, Dongqi Liang, Yi Zeng
Abstract: The alignment of large language models (LLMs) with human values is critical for their safe and effective deployment across diverse user populations. However, existing benchmarks often neglect cultural and demographic diversity, leading to limited understanding of how value alignment generalizes globally. In this work, we introduce MVPBench, a novel benchmark that systematically evaluates LLMs' alignment with multi-dimensional human value preferences across 75 countries. MVPBench contains 24,020 high-quality instances annotated with fine-grained value labels, personalized questions, and rich demographic metadata, making it the most comprehensive resource of its kind to date. Using MVPBench, we conduct an in-depth analysis of several state-of-the-art LLMs, revealing substantial disparities in alignment performance across geographic and demographic lines. We further demonstrate that lightweight fine-tuning methods, such as Low-Rank Adaptation (LoRA) and Direct Preference Optimization (DPO), can significantly enhance value alignment in both in-domain and out-of-domain settings. Our findings underscore the necessity for population-aware alignment evaluation and provide actionable insights for building culturally adaptive and value-sensitive LLMs. MVPBench serves as a practical foundation for future research on global alignment, personalized value modeling, and equitable AI development.
Authors: Andrew Bell, Yan Kit Choi, Steffen E Petersen, Andrew King, Muhummad Sohaib Nazir, Alistair A Young
Abstract: Automatic quantification of intramyocardial motion and strain from tagging MRI remains an important but challenging task. We propose a method using implicit neural representations (INRs), conditioned on learned latent codes, to predict continuous left ventricular (LV) displacement -- without requiring inference-time optimisation. Evaluated on 452 UK Biobank test cases, our method achieved the best tracking accuracy (2.14 mm RMSE) and the lowest combined error in global circumferential (2.86%) and radial (6.42%) strain compared to three deep learning baselines. In addition, our method is $\sim$380$\times$ faster than the most accurate baseline. These results highlight the suitability of INR-based models for accurate and scalable analysis of myocardial strain in large CMR datasets.
Authors: Mohammed Tiouti, Mohamed Bal-Ghaoui
Abstract: Effective model and hyperparameter selection remains a major challenge in deep learning, often requiring extensive expertise and computation. While AutoML and large language models (LLMs) promise automation, current LLM-based approaches rely on trial and error and expensive APIs, which provide limited interpretability and generalizability. We propose MetaLLMiX, a zero-shot hyperparameter optimization framework combining meta-learning, explainable AI, and efficient LLM reasoning. By leveraging historical experiment outcomes with SHAP explanations, MetaLLMiX recommends optimal hyperparameters and pretrained models without additional trials. We further employ an LLM-as-judge evaluation to control output format, accuracy, and completeness. Experiments on eight medical imaging datasets using nine open-source lightweight LLMs show that MetaLLMiX achieves competitive or superior performance to traditional HPO methods while drastically reducing computational cost. Our local deployment outperforms prior API-based approaches, achieving optimal results on 5 of 8 tasks, response time reductions of 99.6-99.9%, and the fastest training times on 6 datasets (2.4-15.7x faster), maintaining accuracy within 1-5% of best-performing baselines.
Authors: Ruiqi Wang, Wenjun Li, Jing Ren, Tongyu Song, Xiong Wang, Sheng Wang, Shizhong Xu
Abstract: The deployment of large-scale LoRaWAN networks requires jointly optimizing conflicting metrics like Packet Delivery Ratio (PDR) and Energy Efficiency (EE) by dynamically allocating transmission parameters, including Carrier Frequency, Spreading Factor, and Transmission Power. Existing methods often oversimplify this challenge, focusing on a single metric or lacking the adaptability needed for dynamic channel environments, leading to suboptimal performance. To address this, we propose two online learning-based resource allocation frameworks that intelligently navigate the PDR-EE trade-off. Our foundational proposal, D-LoRa, is a fully distributed framework that models the problem as a Combinatorial Multi-Armed Bandit. By decomposing the joint parameter selection and employing specialized, disaggregated reward functions, D-LoRa dramatically reduces learning complexity and enables nodes to autonomously adapt to network dynamics. To further enhance performance in LoRaWAN networks, we introduce CD-LoRa, a hybrid framework that integrates a lightweight, centralized initialization phase to perform a one-time, quasi-optimal channel assignment and action space pruning, thereby accelerating subsequent distributed learning. Extensive simulations and real-world field experiments demonstrate the superiority of our frameworks, showing that D-LoRa excels in non-stationary environments while CD-LoRa achieves the fastest convergence in stationary conditions. In physical deployments, our methods outperform state-of-the-art baselines, improving PDR by up to 10.8% and EE by 26.1%, confirming their practical effectiveness for scalable and efficient LoRaWAN networks.
Authors: Jonathan A. Karr Jr, Ben Darden, Nicholas Pell, Ryan M. Fryer, Kayla Ambrose, Evan Hall, Ramzi K. Bualuan, Nitesh V. Chawla
Abstract: The National Running Club Database (NRCD) aggregates 15,397 race results of 5,585 athletes from the 2023 and 2024 cross country seasons. This paper introduces the NRCD dataset, which provides insights into individual athlete progressions, enabling data-driven decision-making. Analysis reveals that runners' improvement per calendar day for women, racing 6,000m, and men, racing 8,000m, is more pronounced in athletes with slower initial race times and those who race more frequently. Additionally, we factor in course conditions, including weather and elevation gain, to standardize improvement. While the NRCD shows a gender imbalance, 3,484 men vs. 2,101 women, the racing frequency between genders is comparable. This publication makes the NRCD dataset accessible to the research community, addressing a previous challenge where smaller datasets, often limited to 500 entries, had to be manually scraped from the internet. Focusing on club athletes rather than elite professionals offers a unique lens into the performance of real-world runners who balance competition with academics and other commitments. These results serve as a valuable resource for runners, coaches, and teams, bridging the gap between raw data and applied sports science.
Authors: Xiaohui Rao, Hanlin Wu, Zhenguang G. Cai
Abstract: As AI companions become capable of human-like communication, including telling jokes, understanding how people cognitively and emotionally respond to AI humor becomes increasingly important. This study used electroencephalography (EEG) to compare how people process humor from AI versus human sources. Behavioral analysis revealed that participants rated AI and human humor as comparably funny. However, neurophysiological data showed that AI humor elicited a smaller N400 effect, suggesting reduced cognitive effort during the processing of incongruity. This was accompanied by a larger Late Positive Potential (LPP), indicating a greater degree of surprise and emotional response. This enhanced LPP likely stems from the violation of low initial expectations regarding AI's comedic capabilities. Furthermore, a key temporal dynamic emerged: human humor showed habituation effects, marked by an increasing N400 and a decreasing LPP over time. In contrast, AI humor demonstrated increasing processing efficiency and emotional reward, with a decreasing N400 and an increasing LPP. This trajectory reveals how the brain can dynamically update its predictive model of AI capabilities. This process of cumulative reinforcement challenges "algorithm aversion" in humor, as it demonstrates how cognitive adaptation to AI's language patterns can lead to an intensified emotional reward. Additionally, participants' social attitudes toward AI modulated these neural responses, with higher perceived AI trustworthiness correlating with enhanced emotional engagement. These findings indicate that the brain responds to AI humor with surprisingly positive and intense reactions, highlighting humor's potential for fostering genuine engagement in human-AI social interaction.
Authors: Koji Hashimoto, Koichi Kyo, Masaki Murata, Gakuto Ogiwara, Norihiro Tanahashi
Abstract: We develop a flexible framework based on physics-informed neural networks (PINNs) for solving boundary value problems involving minimal surfaces in curved spacetimes, with a particular emphasis on singularities and moving boundaries. By encoding the underlying physical laws into the loss function and designing network architectures that incorporate the singular behavior and dynamic boundaries, our approach enables robust and accurate solutions to both ordinary and partial differential equations with complex boundary conditions. We demonstrate the versatility of this framework through applications to minimal surface problems in anti-de Sitter (AdS) spacetime, including examples relevant to the AdS/CFT correspondence (e.g. Wilson loops and gluon scattering amplitudes) popularly used in the context of string theory in theoretical physics. Our methods efficiently handle singularities at boundaries, and also support both "soft" (loss-based) and "hard" (formulation-based) imposition of boundary conditions, including cases where the position of a boundary is promoted to a trainable parameter. The techniques developed here are not limited to high-energy theoretical physics but are broadly applicable to boundary value problems encountered in mathematics, engineering, and the natural sciences, wherever singularities and moving boundaries play a critical role.
Authors: Simin Chen, Jinjun Peng, Yixin He, Junfeng Yang, Baishakhi Ray
Abstract: Deep learning (DL) compilers are core infrastructure in modern DL systems, offering flexibility and scalability beyond vendor-specific libraries. This work uncovers a fundamental vulnerability in their design: can an official, unmodified compiler alter a model's semantics during compilation and introduce hidden backdoors? We study both adversarial and natural settings. In the adversarial case, we craft benign models where triggers have no effect pre-compilation but become effective backdoors after compilation. Tested on six models, three commercial compilers, and two hardware platforms, our attack yields 100% success on triggered inputs while preserving normal accuracy and remaining undetected by state-of-the-art detectors. The attack generalizes across compilers, hardware, and floating-point settings. In the natural setting, we analyze the top 100 HuggingFace models (including one with 220M+ downloads) and find natural triggers in 31 models. This shows that compilers can introduce risks even without adversarial manipulation. Our results reveal an overlooked threat: unmodified DL compilers can silently alter model semantics. To our knowledge, this is the first work to expose inherent security risks in DL compiler design, opening a new direction for secure and trustworthy ML.
Authors: Tae Soo Kim, Heechan Lee, Yoonjoo Lee, Joseph Seering, Juho Kim
Abstract: Practitioners increasingly rely on Large Language Models (LLMs) to evaluate generative AI outputs through "LLM-as-a-Judge" approaches. However, these methods produce holistic scores that obscure which specific elements influenced the assessments. We propose functional fragmentation, a method that dissects each output into key fragments and interprets the rhetoric functions that each fragment serves relative to evaluation criteria -- surfacing the elements of interest and revealing how they fulfill or hinder user goals. We instantiate this approach in Evalet, an interactive system that visualizes fragment-level functions across many outputs to support inspection, rating, and comparison of evaluations. A user study (N=10) found that, while practitioners struggled to validate holistic scores, our approach helped them identify 48% more evaluation misalignments. This helped them calibrate trust in LLM evaluations and rely on them to find more actionable issues in model outputs. Our work shifts LLM evaluation from quantitative scores toward qualitative, fine-grained analysis of model behavior.
Authors: Wensheng Lu, Keyu Chen, Ruizhi Qiao, Xing Sun
Abstract: Retrieval-Augmented Generation (RAG) enhances the response capabilities of language models by integrating external knowledge sources. However, document chunking as an important part of RAG system often lacks effective evaluation tools. This paper first analyzes why existing RAG evaluation benchmarks are inadequate for assessing document chunking quality, specifically due to evidence sparsity. Based on this conclusion, we propose HiCBench, which includes manually annotated multi-level document chunking points, synthesized evidence-dense quetion answer(QA) pairs, and their corresponding evidence sources. Additionally, we introduce the HiChunk framework, a multi-level document structuring framework based on fine-tuned LLMs, combined with the Auto-Merge retrieval algorithm to improve retrieval quality. Experiments demonstrate that HiCBench effectively evaluates the impact of different chunking methods across the entire RAG pipeline. Moreover, HiChunk achieves better chunking quality within reasonable time consumption, thereby enhancing the overall performance of RAG systems.
Authors: Jizhuo Chen, Diwen Liu, Jiaming Wang, Harold Soh
Abstract: GBPP is a fast learning based scorer that selects a robot base pose for grasping from a single RGB-D snapshot. The method uses a two stage curriculum: (1) a simple distance-visibility rule auto-labels a large dataset at low cost; and (2) a smaller set of high fidelity simulation trials refines the model to match true grasp outcomes. A PointNet++ style point cloud encoder with an MLP scores dense grids of candidate poses, enabling rapid online selection without full task-and-motion optimization. In simulation and on a real mobile manipulator, GBPP outperforms proximity and geometry only baselines, choosing safer and more reachable stances and degrading gracefully when wrong. The results offer a practical recipe for data efficient, geometry aware base placement: use inexpensive heuristics for coverage, then calibrate with targeted simulation.