Authors: Ariel Kamen, Yakov Kamen
Abstract: This study introduces an ensemble framework for unstructured text categorization using large language models (LLMs). By integrating multiple models, the ensemble large language model (eLLM) framework addresses common weaknesses of individual systems, including inconsistency, hallucination, category inflation, and misclassification. The eLLM approach yields a substantial performance improvement of up to 65\% in F1-score over the strongest single model. We formalize the ensemble process through a mathematical model of collective decision-making and establish principled aggregation criteria. Using the Interactive Advertising Bureau (IAB) hierarchical taxonomy, we evaluate ten state-of-the-art LLMs under identical zero-shot conditions on a human-annotated corpus of 8{,}660 samples. Results show that individual models plateau in performance due to the compression of semantically rich text into sparse categorical representations, while eLLM improves both robustness and accuracy. With a diverse consortium of models, eLLM achieves near human-expert-level performance, offering a scalable and reliable solution for taxonomy-based classification that may significantly reduce dependence on human expert labeling.
Authors: Yash Raj Singh
Abstract: Modern large language model-based reasoning systems frequently recompute similar reasoning steps across tasks, wasting computational resources, inflating inference latency, and limiting reproducibility. These inefficiencies underscore the need for persistent reasoning mechanisms that can recall and reuse prior computational traces. We introduce Graph-Memoized Reasoning, a formal framework for representing, storing, and reusing reasoning workflows as graph-structured memory. By encoding past decision graphs and retrieving them through structural and semantic similarity, our approach enables compositional reuse of subgraphs across new reasoning tasks. We formulate an optimization objective that minimizes total reasoning cost regularized by inconsistency between stored and generated workflows, providing a theoretical foundation for efficiency-consistency trade-offs in intelligent systems. We outline a conceptual evaluation protocol aligned with the proposed optimization objective. This framework establishes the groundwork for interpretable, cost-efficient, and self-improving reasoning architectures, offering a step toward persistent memory in large-scale agentic systems.
Authors: Abraham Itzhak Weinberg
Abstract: As Multi Agent Reinforcement Learning systems are used in safety critical applications. Understanding why agents make decisions and how they achieve collective behavior is crucial. Existing explainable AI methods struggle in multi agent settings. They fail to attribute collective outcomes to individuals, quantify emergent behaviors, or capture complex interactions. We present MACIE Multi Agent Causal Intelligence Explainer, a framework combining structural causal models, interventional counterfactuals, and Shapley values to provide comprehensive explanations. MACIE addresses three questions. First, each agent's causal contribution using interventional attribution scores. Second, system level emergent intelligence through synergy metrics separating collective effects from individual contributions. Third, actionable explanations using natural language narratives synthesizing causal insights. We evaluate MACIE across four MARL scenarios: cooperative, competitive, and mixed motive. Results show accurate outcome attribution, mean phi_i equals 5.07, standard deviation less than 0.05, detection of positive emergence in cooperative tasks, synergy index up to 0.461, and efficient computation, 0.79 seconds per dataset on CPU. MACIE uniquely combines causal rigor, emergence quantification, and multi agent support while remaining practical for real time use. This represents a step toward interpretable, trustworthy, and accountable multi agent AI.
Authors: Bo Wen, Chen Wang, Erhan Bilal
Abstract: ARC-AGI and ARC-AGI-2 measure generalization-through-composition on small color-quantized grids, and their prize competitions make progress on these harder held-out tasks a meaningful proxy for systematic generalization. Recent instruction-first systems translate grids into concise natural-language or DSL rules executed in generate-execute-select loops, yet we lack a principled account of how encodings shape model perception and how to separate instruction errors from execution errors. We hypothesize that modality imposes perceptual bottlenecks -- text flattens 2D structure into 1D tokens while images preserve layout but can introduce patch-size aliasing -- thereby shaping which grid features are reliably perceived. To test this, we isolate perception from reasoning across nine text and image modalities using a weighted set-disagreement metric and a two-stage reasoning pipeline, finding that structured text yields precise coordinates on sparse features, images capture 2D shapes yet are resolution-sensitive, and combining them improves execution (about 8 perception points; about 0.20 median similarity). Overall, aligning representations with transformer inductive biases and enabling cross-validation between text and image yields more accurate instructions and more reliable execution without changing the underlying model.
Authors: Chen Yang, Ran Le, Yun Xing, Zhenwei An, Zongchao Chen, Wayne Xin Zhao, Yang Song, Tao Zhang
Abstract: Large Language Model (LLM) agents have developed rapidly in recent years to solve complex real-world problems using external tools. However, the scarcity of high-quality trajectories still hinders the development of stronger LLM agents. Most existing works on multi-turn dialogue synthesis validate correctness only at the trajectory level, which may overlook turn-level errors that can propagate during training and degrade model performance. To address these limitations, we introduce ToolMind, a large-scale, high-quality tool-agentic dataset with 160k synthetic data instances generated using over 20k tools and 200k augmented open-source data instances. Our data synthesis pipeline first constructs a function graph based on parameter correlations and then uses a multi-agent framework to simulate realistic user-assistant-tool interactions. Beyond trajectory-level validation, we employ fine-grained turn-level filtering to remove erroneous or suboptimal steps, ensuring that only high-quality reasoning traces are retained. This approach mitigates error amplification during training while preserving self-corrective reasoning signals essential for robust tool-use learning. Models fine-tuned on ToolMind show significant improvements over baselines on several benchmarks.
Authors: William Brach, Lukas Galke Poech
Abstract: Large Language Models (LLMs) are increasingly using external web content. However, much of this content is not easily digestible by LLMs due to LLM-unfriendly formats and limitations of context length. To address this issue, we propose a method for generating general-purpose, information-dense summaries that act as plain-text repositories of web content. Inspired by Hegel's dialectical method, our approach, denoted as Chain of Summaries (CoS), iteratively refines an initial summary (thesis) by identifying its limitations through questioning (antithesis), leading to a general-purpose summary (synthesis) that can satisfy current and anticipate future information needs. Experiments on the TriviaQA, TruthfulQA, and SQUAD datasets demonstrate that CoS outperforms zero-shot LLM baselines by up to 66% and specialized summarization methods such as BRIO and PEGASUS by up to 27%. CoS-generated summaries yield higher Q&A performance compared to the source content, while requiring substantially fewer tokens and being agnostic to the specific downstream LLM. CoS thus resembles an appealing option for website maintainers to make their content more accessible for LLMs, while retaining possibilities for human oversight.
Authors: Islem Sahraoui
Abstract: This thesis explores a multimodal AI framework for enhancing construction safety through the combined analysis of textual and visual data. In safety-critical environments such as construction sites, accident data often exists in multiple formats, such as written reports, inspection records, and site imagery, making it challenging to synthesize hazards using traditional approaches. To address this, this thesis proposed a multimodal AI framework that combines text and image analysis to assist in identifying safety hazards on construction sites. Two case studies were consucted to evaluate the capabilities of large language models (LLMs) and vision-language models (VLMs) for automated hazard identification.The first case study introduces a hybrid pipeline that utilizes GPT 4o and GPT 4o mini to extract structured insights from a dataset of 28,000 OSHA accident reports (2000-2025). The second case study extends this investigation using Molmo 7B and Qwen2 VL 2B, lightweight, open-source VLMs. Using the public ConstructionSite10k dataset, the performance of the two models was evaluated on rule-level safety violation detection using natural language prompts. This experiment served as a cost-aware benchmark against proprietary models and allowed testing at scale with ground-truth labels. Despite their smaller size, Molmo 7B and Quen2 VL 2B showed competitive performance in certain prompt configurations, reinforcing the feasibility of low-resource multimodal systems for rule-aware safety monitoring.
Authors: Weichen Liu, Qiyao Xue, Haoming Wang, Xiangyu Yin, Boyuan Yang, Wei Gao
Abstract: Spatial reasoning, which requires ability to perceive and manipulate spatial relationships in the 3D world, is a fundamental aspect of human intelligence, yet remains a persistent challenge for Multimodal large language models (MLLMs). While existing surveys often categorize recent progress based on input modality (e.g., text, image, video, or 3D), we argue that spatial ability is not solely determined by the input format. Instead, our survey introduces a taxonomy that organizes spatial intelligence from cognitive aspect and divides tasks in terms of reasoning complexity, linking them to several cognitive functions. We map existing benchmarks across text only, vision language, and embodied settings onto this taxonomy, and review evaluation metrics and methodologies for assessing spatial reasoning ability. This cognitive perspective enables more principled cross-task comparisons and reveals critical gaps between current model capabilities and human-like reasoning. In addition, we analyze methods for improving spatial ability, spanning both training-based and reasoning-based approaches. This dual perspective analysis clarifies their respective strengths, uncovers complementary mechanisms. By surveying tasks, benchmarks, and recent advances, we aim to provide new researchers with a comprehensive understanding of the field and actionable directions for future research.
Authors: Hyo-Jeong Jang
Abstract: Multimodal learning systems often face substantial uncertainty due to noisy data, low-quality labels, and heterogeneous modality characteristics. These issues become especially critical in human-computer interaction settings, where data quality, semantic reliability, and annotation consistency vary across users and recording conditions. This thesis tackles these challenges by exploring uncertainty-resilient multimodal learning through consistency-guided cross-modal transfer. The central idea is to use cross-modal semantic consistency as a basis for robust representation learning. By projecting heterogeneous modalities into a shared latent space, the proposed framework mitigates modality gaps and uncovers structural relations that support uncertainty estimation and stable feature learning. Building on this foundation, the thesis investigates strategies to enhance semantic robustness, improve data efficiency, and reduce the impact of noise and imperfect supervision without relying on large, high-quality annotations. Experiments on multimodal affect-recognition benchmarks demonstrate that consistency-guided cross-modal transfer significantly improves model stability, discriminative ability, and robustness to noisy or incomplete supervision. Latent space analyses further show that the framework captures reliable cross-modal structure even under challenging conditions. Overall, this thesis offers a unified perspective on resilient multimodal learning by integrating uncertainty modeling, semantic alignment, and data-efficient supervision, providing practical insights for developing reliable and adaptive brain-computer interface systems.
Authors: Hanzhi Yan, Qin Lu, Xianqiao Wang, Xiaoming Zhai, Tianming Liu, He Li
Abstract: While large language models (LLMs) have demonstrated remarkable versatility across a wide range of general tasks, their effectiveness often diminishes in domain-specific applications due to inherent knowledge gaps. Moreover, their performance typically declines when addressing complex problems that require multi-step reasoning and analysis. In response to these challenges, we propose leveraging both LLMs and AI agents to develop education assistants aimed at enhancing undergraduate learning in biomechanics courses that focus on analyzing the force and moment in the musculoskeletal system of the human body. To achieve our goal, we construct a dual-module framework to enhance LLM performance in biomechanics educational tasks: 1) we apply Retrieval-Augmented Generation (RAG) to improve the specificity and logical consistency of LLM's responses to the conceptual true/false questions; 2) we build a Multi-Agent System (MAS) to solve calculation-oriented problems involving multi-step reasoning and code execution. Specifically, we evaluate the performance of several LLMs, i.e., Qwen-1.0-32B, Qwen-2.5-32B, and Llama-70B, on a biomechanics dataset comprising 100 true/false conceptual questions and problems requiring equation derivation and calculation. Our results demonstrate that RAG significantly enhances the performance and stability of LLMs in answering conceptual questions, surpassing those of vanilla models. On the other hand, the MAS constructed using multiple LLMs demonstrates its ability to perform multi-step reasoning, derive equations, execute code, and generate explainable solutions for tasks that require calculation. These findings demonstrate the potential of applying RAG and MAS to enhance LLM performance for specialized courses in engineering curricula, providing a promising direction for developing intelligent tutoring in engineering education.
Authors: Philip Drammeh
Abstract: Large language models (LLMs) promise to accelerate incident response in production systems, yet single-agent approaches generate vague, unusable recommendations. We present MyAntFarm.ai, a reproducible containerized framework demonstrating that multi-agent orchestration fundamentally transforms LLM-based incident response quality. Through 348 controlled trials comparing single-agent copilot versus multi-agent systems on identical incident scenarios, we find that multi-agent orchestration achieves 100% actionable recommendation rate versus 1.7% for single-agent approaches, an 80 times improvement in action specificity and 140 times improvement in solution correctness. Critically, multi-agent systems exhibit zero quality variance across all trials, enabling production SLA commitments impossible with inconsistent single-agent outputs. Both architectures achieve similar comprehension latency (approx.40s), establishing that the architectural value lies in deterministic quality, not speed. We introduce Decision Quality (DQ), a novel metric capturing validity, specificity, and correctness properties essential for operational deployment that existing LLM metrics do not address. These findings reframe multi-agent orchestration from a performance optimization to a production-readiness requirement for LLM-based incident response. All code, Docker configurations, and trial data are publicly available for reproduction.
Authors: Raymond K. Sheh, Karen Geappen
Abstract: Risks associated with the use of AI, ranging from algorithmic bias to model hallucinations, have received much attention and extensive research across the AI community, from researchers to end-users. However, a gap exists in the systematic assessment of supply chain risks associated with the complex web of data sources, pre-trained models, agents, services, and other systems that contribute to the output of modern AI systems. This gap is particularly problematic when AI systems are used in critical applications, such as the food supply, healthcare, utilities, law, insurance, and transport. We survey the current state of AI risk assessment and management, with a focus on the supply chain of AI and risks relating to the behavior and outputs of the AI system. We then present a proposed taxonomy specifically for categorizing AI supply chain entities. This taxonomy helps stakeholders, especially those without extensive AI expertise, to "consider the right questions" and systematically inventory dependencies across their organization's AI systems. Our contribution bridges a gap between the current state of AI governance and the urgent need for actionable risk assessment and management of AI use in critical applications.
Authors: Paulina Tworek, Mi{\l}osz Bargie{\l}, Yousef Khan, Tomasz Pe{\l}ech-Pilichowski, Marek Miko{\l}ajczyk, Roman Lewandowski, Jose Sousa
Abstract: Extracting structured medical insights from unstructured clinical text using Natural Language Processing (NLP) remains an open challenge in healthcare, particularly in non-English contexts where resources are scarce. This study presents a comparative analysis of NLP low-compute rule-based methods and Large Language Models (LLMs) for information extraction from electronic health records (EHR) obtained from the Voivodeship Rehabilitation Hospital for Children in Ameryka, Poland. We evaluate both approaches by extracting patient demographics, clinical findings, and prescribed medications while examining the effects of lack of text normalisation and translation-induced information loss. Results demonstrate that rule-based methods provide higher accuracy in information retrieval tasks, particularly for age and sex extraction. However, LLMs offer greater adaptability and scalability, excelling in drug name recognition. The effectiveness of the LLMs was compared with texts originally in Polish and those translated into English, assessing the impact of translation. These findings highlight the trade-offs between accuracy, normalisation, and computational cost when deploying NLP in healthcare settings. We argue for hybrid approaches that combine the precision of rule-based systems with the adaptability of LLMs, offering a practical path toward more reliable and resource-efficient clinical NLP in real-world hospitals.
Authors: Tuan-Anh Le, Anh Mai Vu, David Yang, Akash Awasthi, Hien Van Nguyen
Abstract: IMACT-CXR is an interactive multi-agent conversational tutor that helps trainees interpret chest X-rays by unifying spatial annotation, gaze analysis, knowledge retrieval, and image-grounded reasoning in a single AutoGen-based workflow. The tutor simultaneously ingests learner bounding boxes, gaze samples, and free-text observations. Specialized agents evaluate localization quality, generate Socratic coaching, retrieve PubMed evidence, suggest similar cases from REFLACX, and trigger NV-Reason-CXR-3B for vision-language reasoning when mastery remains low or the learner explicitly asks. Bayesian Knowledge Tracing (BKT) maintains skill-specific mastery estimates that drive both knowledge reinforcement and case similarity retrieval. A lung-lobe segmentation module derived from a TensorFlow U-Net enables anatomically aware gaze feedback, and safety prompts prevent premature disclosure of ground-truth labels. We describe the system architecture, implementation highlights, and integration with the REFLACX dataset for real DICOM cases. IMACT-CXR demonstrates responsive tutoring flows with bounded latency, precise control over answer leakage, and extensibility toward live residency deployment. Preliminary evaluation shows improved localization and diagnostic reasoning compared to baselines.
Authors: St\'ephane Aroca-Ouellette, Ian Berlot-Attwell, Panagiotis Lymperopoulos, Abhiramon Rajasekharan, Tongqi Zhu, Herin Kang, Kaheer Suleman, Sam Pasupalak
Abstract: Despite rapid progress in artificial intelligence, current systems struggle with the interconnected challenges that define real-world decision making. Practical domains, such as business management, require optimizing an open-ended and multi-faceted objective, actively learning environment dynamics from sparse experience, planning over long horizons in stochastic settings, and reasoning over spatial information. Yet existing human--AI benchmarks isolate subsets of these capabilities, limiting our ability to assess holistic decision-making competence. We introduce Mini Amusement Parks (MAPs), an amusement-park simulator designed to evaluate an agent's ability to model its environment, anticipate long-term consequences under uncertainty, and strategically operate a complex business. We provide human baselines and a comprehensive evaluation of state-of-the-art LLM agents, finding that humans outperform these systems by 6.5x on easy mode and 9.8x on medium mode. Our analysis reveals persistent weaknesses in long-horizon optimization, sample-efficient learning, spatial reasoning, and world modelling. By unifying these challenges within a single environment, MAPs offers a new foundation for benchmarking agents capable of adaptable decision making. Code: https://github.com/Skyfall-Research/MAPs
Authors: Fei Tian, Xiangyu Tony Zhang, Yuxin Zhang, Haoyang Zhang, Yuxin Li, Daijiao Liu, Yayue Deng, Donghang Wu, Jun Chen, Liang Zhao, Chengyuan Yao, Hexin Liu, Eng Siong Chng, Xuerui Yang, Xiangyu Zhang, Daxin Jiang, Gang Yu
Abstract: Recent advances in reasoning models have demonstrated remarkable success in text and vision domains through extended chain-of-thought deliberation. However, a perplexing phenomenon persists in audio language models: they consistently perform better with minimal or no reasoning, raising a fundamental question - can audio intelligence truly benefit from deliberate thinking? We introduce Step-Audio-R1, the first audio reasoning model that successfully unlocks reasoning capabilities in the audio domain. Through our proposed Modality-Grounded Reasoning Distillation (MGRD) framework, Step-Audio-R1 learns to generate audio-relevant reasoning chains that genuinely ground themselves in acoustic features rather than hallucinating disconnected deliberations. Our model exhibits strong audio reasoning capabilities, surpassing Gemini 2.5 Pro and achieving performance comparable to the state-of-the-art Gemini 3 Pro across comprehensive audio understanding and reasoning benchmarks spanning speech, environmental sounds, and music. These results demonstrate that reasoning is a transferable capability across modalities when appropriately anchored, transforming extended deliberation from a liability into a powerful asset for audio intelligence. By establishing the first successful audio reasoning model, Step-Audio-R1 opens new pathways toward building truly multimodal reasoning systems that think deeply across all sensory modalities.
Authors: Ivan Chulo, Ananya Joshi
Abstract: Recent work shows activation steering substantially improves language models' Theory of Mind (ToM) (Bortoletto et al. 2024), yet the mechanisms of what changes occur internally that leads to different outputs remains unclear. We propose decomposing ToM in LLMs by comparing steered versus baseline LLMs' activations using linear probes trained on 45 cognitive actions. We applied Contrastive Activation Addition (CAA) steering to Gemma-3-4B and evaluated it on 1,000 BigToM forward belief scenarios (Gandhi et al. 2023), we find improved performance on belief attribution tasks (32.5\% to 46.7\% accuracy) is mediated by activations processing emotional content : emotion perception (+2.23), emotion valuing (+2.20), while suppressing analytical processes: questioning (-0.78), convergent thinking (-1.59). This suggests that successful ToM abilities in LLMs are mediated by emotional understanding, not analytical reasoning.
Authors: Chelsea Zou, Yiheng Yao, Basant Khalil
Abstract: This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approach leverages fine grained uncertainty signals: 1) self-assessed confidence alignment, and 2) token-level entropy spikes to detect unreliable and unfaithful reasoning in real time. We design a composite reward function that penalizes unjustified high confidence and entropy spikes, while encouraging stable and accurate reasoning trajectories. These signals guide a reinforcement learning (RL) policy that makes the model more introspective and shapes the model's generation behavior through confidence-aware reward feedback, improving not just outcome correctness but the coherence and faithfulness of their intermediate reasoning steps. Experiments show that our method improves both final answer accuracy and reasoning calibration, with ablations validating the individual contribution of each signal.
Authors: Zhenyu Bi, Gaurav Srivastava, Yang Li, Meng Lu, Swastik Roy, Morteza Ziyadi, Xuan Wang
Abstract: While small language models (SLMs) have shown promise on various reasoning tasks, their ability to judge the correctness of answers remains unclear compared to large language models (LLMs). Prior work on LLM-as-a-judge frameworks typically relies on comparing candidate answers against ground-truth labels or other candidate answers using predefined metrics like entailment. However, this approach is inherently indirect and difficult to fully automate, offering limited support for fine-grained and scalable evaluation of reasoning outputs. In this work, we propose JudgeBoard, a novel evaluation pipeline that directly queries models to assess the correctness of candidate answers without requiring extra answer comparisons. We focus on two core reasoning domains: mathematical reasoning and science/commonsense reasoning, and construct task-specific evaluation leaderboards using both accuracy-based ranking and an Elo-based rating system across five benchmark datasets, enabling consistent model comparison as judges rather than comparators. To improve judgment performance in lightweight models, we propose MAJ (Multi-Agent Judging), a novel multi-agent evaluation framework that leverages multiple interacting SLMs with distinct reasoning profiles to approximate LLM-level judgment accuracy through collaborative deliberation. Experimental results reveal a significant performance gap between SLMs and LLMs in isolated judging tasks. However, our MAJ framework substantially improves the reliability and consistency of SLMs. On the MATH dataset, MAJ using smaller-sized models as backbones performs comparatively well or even better than their larger-sized counterparts. Our findings highlight that multi-agent SLM systems can potentially match or exceed LLM performance in judgment tasks, with implications for scalable and efficient assessment.
Authors: Zhe Li, Yehan Qiu, Yujie Chen, Xiang Zhou
Abstract: Clinical antimicrobial therapy requires the dynamic integration of pathogen profiles, host factors, pharmacological properties of antimicrobials, and the severity of infection.This complexity imposes fundamental limitations on the applicability of Large Language Models (LLMs) in high-stakes clinical decision-making including knowledge gaps, data privacy concerns, high deployment costs, and limited reasoning capabilities. To address these challenges, we propose KRAL (Knowledge and Reasoning Augmented Learning), a low-cost, scalable, privacy-preserving paradigm that leverages teacher-model reasoning to automatically distill knowledge and reasoning trajectories via answer-to-question reverse generation, employs heuristic learning for semi-supervised data augmentation (reducing manual annotation requirements by approximately 80%), and utilizes agentic reinforcement learning to jointly enhance medical knowledge and reasoning while optimizing computational and memory efficiency. A hierarchical evaluation employing diverse teacher-model proxies reduces assessment costs, while modular interface design facilitates seamless system updates. Experimental results demonstrate that KRAL significantly outperforms traditional Retrieval-Augmented Generation (RAG) and Supervised Fine-Tuning (SFT) methods. It improves knowledge question-answering capability (Accuracy@1 on the external open-source benchmark MEDQA increased by 1.8% vs. SFT and 3.6% vs. RAG) and reasoning capability (Pass@1 on the external benchmark PUMCH Antimicrobial increased by 27% vs. SFT and 27.2% vs. RAG), achieved at ~20% of SFT's long-term training costs. This establishes KRAL as an effective solution for enhancing local LLMs' clinical diagnostic capabilities, enabling low-cost, high-safety deployment in complex medical decision support.
Authors: Shahin Zanbaghi, Ryan Rostampour, Farhan Abid, Salim Al Jarmakani
Abstract: Large Language Models (LLMs) can be backdoored to exhibit malicious behavior under specific deployment conditions while appearing safe during training a phenomenon known as "sleeper agents." Recent work by Hubinger et al. demonstrated that these backdoors persist through safety training, yet no practical detection methods exist. We present a novel dual-method detection system combining semantic drift analysis with canary baseline comparison to identify backdoored LLMs in real-time. Our approach uses Sentence-BERT embeddings to measure semantic deviation from safe baselines, complemented by injected canary questions that monitor response consistency. Evaluated on the official Cadenza-Labs dolphin-llama3-8B sleeper agent model, our system achieves 92.5% accuracy with 100% precision (zero false positives) and 85% recall. The combined detection method operates in real-time (<1s per query), requires no model modification, and provides the first practical solution to LLM backdoor detection. Our work addresses a critical security gap in AI deployment and demonstrates that embedding-based detection can effectively identify deceptive model behavior without sacrificing deployment efficiency.
Authors: Deepthi Potluri, Aby Mammen Mathew, Jeffrey B DeWitt, Alexander L. Rasgon, Yide Hao, Junyuan Hong, Ying Ding
Abstract: Access to the right evidence does not guarantee that large language models (LLMs) will reason with it correctly. This gap between retrieval and reasoning is especially concerning in clinical settings, where outputs must align with structured protocols. We study this gap using Written Exposure Therapy (WET) guidelines as a testbed. In evaluating model responses to curated clinician-vetted questions, we find that errors persist even when authoritative passages are provided. To address this, we propose an evaluation framework that measures accuracy, consistency, and fidelity of reasoning. Our results highlight both the potential and the risks: retrieval-augmented generation (RAG) can constrain outputs, but safe deployment requires assessing reasoning as rigorously as retrieval.
Authors: Noah Bissell (Immersive Media Design, University of Maryland, College Park, USA), Ethan Paley (Immersive Media Design, University of Maryland, College Park, USA), Joshua Harrison (Center for the Study of the Force Majeure, University of California, Santa Cruz, USA), Juliano Calil (Virtual Planet Technologies, Santa Cruz, USA), Myungin Lee (Immersive Media Design, University of Maryland, College Park, USA)
Abstract: Sensorium Arc (AI reflects on climate) is a real-time multimodal interactive AI agent system that personifies the ocean as a poetic speaker and guides users through immersive explorations of complex marine data. Built on a modular multi-agent system and retrieval-augmented large language model (LLM) framework, Sensorium enables natural spoken conversations with AI agents that embodies the ocean's perspective, generating responses that blend scientific insight with ecological poetics. Through keyword detection and semantic parsing, the system dynamically triggers data visualizations and audiovisual playback based on time, location, and thematic cues drawn from the dialogue. Developed in collaboration with the Center for the Study of the Force Majeure and inspired by the eco-aesthetic philosophy of Newton Harrison, Sensorium Arc reimagines ocean data not as an abstract dataset but as a living narrative. The project demonstrates the potential of conversational AI agents to mediate affective, intuitive access to high-dimensional environmental data and proposes a new paradigm for human-machine-ecosystem.
Authors: Jinhao Li, Jianzhong Qi, Soyeon Caren Han, Eun-Jung Holden
Abstract: Digital transformation in the cultural heritage sector has produced vast yet fragmented collections of artefact data. Existing frameworks for museum information systems struggle to integrate heterogeneous metadata, unstructured documents, and multimodal artefacts into a coherent and queryable form. We present MuseKG, an end-to-end knowledge-graph framework that unifies structured and unstructured museum data through symbolic-neural integration. MuseKG constructs a typed property graph linking objects, people, organisations, and visual or textual labels, and supports natural language queries. Evaluations on real museum collections demonstrate robust performance across queries over attributes, relations, and related entities, surpassing large-language-model zero-shot, few-shot and SPARQL prompt baselines. The results highlight the importance of symbolic grounding for interpretable and scalable cultural heritage reasoning, and pave the way for web-scale integration of digital heritage knowledge.
Authors: Emanuel C. Silva, Emily S. M. Salum, Gabriel M. Arantes, Matheus P. Pereira, Vinicius F. Oliveira, Alessandro L. Bicho
Abstract: Introduction: The application of Artificial Intelligence in games has evolved significantly, allowing for dynamic content generation. However, its use as a core gameplay co-creation tool remains underexplored. Objective: This paper proposes SpellForger, a game where players create custom spells by writing natural language prompts, aiming to provide a unique experience of personalization and creativity. Methodology: The system uses a supervisedtrained BERT model to interpret player prompts. This model maps textual descriptions to one of many spell prefabs and balances their parameters (damage, cost, effects) to ensure competitive integrity. The game is developed in the Unity Game Engine, and the AI backend is in Python. Expected Results: We expect to deliver a functional prototype that demonstrates the generation of spells in real time, applied to an engaging gameplay loop, where player creativity is central to the experience, validating the use of AI as a direct gameplay mechanic.
Authors: Jorge A. Huertas, Pascal Van Hentenryck
Abstract: In serial batch (s-batch) scheduling, jobs from similar families are grouped into batches and processed sequentially to avoid repetitive setups that are required when processing consecutive jobs of different families. Despite its large success in scheduling, only three Constraint Programming (CP) models have been proposed for this problem considering minimum batch sizes, which is a common requirement in many practical settings, including the ion implantation area in semiconductor manufacturing. These existing CP models rely on a predefined virtual set of possible batches that suffers from the curse of dimensionality and adds complexity to the problem. This paper proposes a novel CP model that does not rely on this virtual set. Instead, it uses key alignment parameters that allow it to reason directly on the sequences of same-family jobs scheduled on the machines, resulting in a more compact formulation. This new model is further improved by exploiting the problem's structure with tailored search phases and strengthened inference levels of the constraint propagators. The extensive computational experiments on nearly five thousand instances compare the proposed models against existing methods in the literature, including mixed-integer programming formulations, tabu search meta-heuristics, and CP approaches. The results demonstrate the superiority of the proposed models on small-to-medium instances with up to 100 jobs, and their ability to find solutions up to 25\% better than the ones produces by existing methods on large-scale instances with up to 500 jobs, 10 families, and 10 machines.
Authors: Theophanis C. Stratopoulos, Victor Xiaoqi Wang
Abstract: Recent advances in artificial intelligence, particularly generative AI (GenAI) and large language models (LLMs), are fundamentally transforming accounting research, creating both opportunities and competitive threats for scholars. This paper proposes a framework that classifies AI-accounting research along two dimensions: research focus (accounting-centric versus AI-centric) and methodological approach (AI-based versus traditional methods). We apply this framework to papers from the IJAIS special issue and recent AI-accounting research published in leading accounting journals to map existing studies and identify research opportunities. Using this same framework, we analyze how accounting researchers can leverage their expertise through strategic positioning and collaboration, revealing where accounting scholars' strengths create the most value. We further examine how GenAI and LLMs transform the research process itself, comparing the capabilities of human researchers and AI agents across the entire research workflow. This analysis reveals that while GenAI democratizes certain research capabilities, it simultaneously intensifies competition by raising expectations for higher-order contributions where human judgment, creativity, and theoretical depth remain valuable. These shifts call for reforming doctoral education to cultivate comparative advantages while building AI fluency.
Authors: Hrikshesh Kumar, Anika Garg, Anshul Gupta, Yashika Agarwal
Abstract: Old cloud edge workload resource management is too reactive. The problem with relying on static thresholds is that we are either overspending for more resources than needed or have reduced performance because of their lack. This is why we work on proactive solutions. A framework developed for it stops reacting to the problems but starts expecting them. We design a hybrid architecture, combining two powerful tools: the CNN LSTM model for time series forecasting and an orchestrator based on multi agent Deep Reinforcement Learning In fact the novelty is in how we combine them as we embed the predictive forecast from the CNN LSTM directly into the DRL agent state space. That is what makes the AI manager smarter it sees the future, which allows it to make better decisions about a long term plan for where to run tasks That means finding that sweet spot between how much money is saved while keeping the system healthy and apps fast for users That is we have given it eyes in order to see down the road so that it does not have to lurch from one problem to another it finds a smooth path forward Our tests show our system easily beats the old methods It is great at solving tough problems like making complex decisions and juggling multiple goals at once like being cheap fast and reliable
Authors: Shiyi Cao, Dacheng Li, Fangzhou Zhao, Shuo Yuan, Sumanth R. Hegde, Connor Chen, Charlie Ruan, Tyler Griggs, Shu Liu, Eric Tang, Richard Liaw, Philipp Moritz, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica
Abstract: We introduce SkyRL-Agent, a framework for efficient, multi-turn, long-horizon agent training and evaluation. It provides efficient asynchronous dispatching, lightweight tool integration, and flexible backend interoperability, enabling seamless use with existing RL frameworks such as SkyRL-train, VeRL, and Tinker. Using SkyRL-Agent, we train SA-SWE-32B, a software engineering agent trained from Qwen3-32B (24.4% Pass@1) purely with reinforcement learning. We introduce two key components: an optimized asynchronous pipeline dispatcher that achieves a 1.55x speedup over naive asynchronous batching, and a tool-enhanced training recipe leveraging an AST-based search tool to facilitate code navigation, boost rollout Pass@K, and improve training efficiency. Together, these optimizations enable SA-SWE-32B to reach 39.4% Pass@1 on SWE-Bench Verified with more than 2x cost reduction compared to prior models reaching similar performance. Despite being trained solely on SWE tasks, SA-SWE-32B generalizes effectively to other agentic tasks, including Terminal-Bench, BrowseComp-Plus, and WebArena. We further demonstrate SkyRL-Agent's extensibility through case studies on deep research, computer use, and memory agents, each trained using a different training backend.
Authors: Yongnan Jin, Xurui Li, Feng Cao, Liucun Gao, Juanjuan Yao
Abstract: The integration of large language models (LLMs) into medical practice holds transformative potential, yet their real-world clinical utility remains limited by critical alignment challenges: (1) a disconnect between static evaluation benchmarks and dynamic clinical cognitive needs, (2) difficulties in adapting to evolving, multi-source medical standards, and (3) the inability of conventional reward models to capture nuanced, multi-dimensional medical quality criteria. To address these gaps, we propose MR-RML (Multidimensional Rubric-oriented Reward Model Learning) via GPRC (Geometric Projection Reference Constraints), a novel alignment framework that integrates medical standards into a structured "Dimensions-Scenarios-Disciplines" matrix to guide data generation and model optimization. MR-RML introduces three core innovations: (1) a "Dimensions-Scenarios-Disciplines" medical standard system that embeds domain standards into the full training pipeline; (2) an independent multi-dimensional reward model that decomposes evaluation criteria, shifting from real-time rubric-based scoring to internalized reward modeling for improved consistency and cost-efficiency; (3) geometric projection reference constraints that transform medical cognitive logic into mathematical regularization, aligning scoring gradients with clinical reasoning and enabling synthetic data-driven training. Through extensive evaluations on the authoritative medical benchmark Healthbench, our method yields substantial performance gains over the base LLM Qwen-32B (45% on the full subset and 85% on Hard subset, respectively). It achieves a SOTA among open-source LLMs with scores of 62.7 (full subset) and 44.7 (hard subset), while also outperforming the majority of closed-source models.
Authors: Jeremie Ochin (CAOR), Raphael Chekroun (CAOR), Bogdan Stanciulescu (CAOR), Sotiris Manitsaris (CAOR)
Abstract: Soccer video understanding has motivated the creation of datasets for tasks such as temporal action localization, spatiotemporal action detection (STAD), or multiobject tracking (MOT). The annotation of structured sequences of events (who does what, when, and where) used for soccer analytics requires a holistic approach that integrates both STAD and MOT. However, current action recognition methods remain insufficient for constructing reliable play-by-play data and are typically used to assist rather than fully automate annotation. Parallel research has advanced tactical modeling, trajectory forecasting, and performance analysis, all grounded in game-state and play-by-play data. This motivates leveraging tactical knowledge as a prior to support computer-vision-based predictions, enabling more automated and reliable extraction of play-by-play data. We introduce Footovision Play-by-Play Action Spotting in Soccer Dataset (FOOTPASS), the first benchmark for play-by-play action spotting over entire soccer matches in a multi-modal, multi-agent tactical context. It enables the development of methods for player-centric action spotting that exploit both outputs from computer-vision tasks (e.g., tracking, identification) and prior knowledge of soccer, including its tactical regularities over long time horizons, to generate reliable play-by-play data streams. These streams form an essential input for data-driven sports analytics.
Authors: Niki van Stein, Anna V. Kononova, Thomas B\"ack
Abstract: Automated algorithm design is entering a new phase: Large Language Models can now generate full optimisation (meta)heuristics, explore vast design spaces and adapt through iterative feedback. Yet this rapid progress is largely performance-driven and opaque. Current LLM-based approaches rarely reveal why a generated algorithm works, which components matter or how design choices relate to underlying problem structures. This paper argues that the next breakthrough will come not from more automation, but from coupling automation with understanding from systematic benchmarking. We outline a vision for explainable automated algorithm design, built on three pillars: (i) LLM-driven discovery of algorithmic variants, (ii) explainable benchmarking that attributes performance to components and hyperparameters and (iii) problem-class descriptors that connect algorithm behaviour to landscape structure. Together, these elements form a closed knowledge loop in which discovery, explanation and generalisation reinforce each other. We argue that this integration will shift the field from blind search to interpretable, class-specific algorithm design, accelerating progress while producing reusable scientific insight into when and why optimisation strategies succeed.
Authors: Pei Yang, Ke Zhang, Ji Wang, Xiao Chen, Yuxin Tang, Eric Yang, Lynn Ai, Bill Shi
Abstract: We present CRM (Multi-Agent Collaborative Reward Model), a framework that replaces a single black-box reward model with a coordinated team of specialist evaluators to improve robustness and interpretability in RLHF. Conventional reward models struggle to jointly optimize multiple, sometimes conflicting, preference dimensions (e.g., factuality, helpfulness, safety) and offer limited transparency into why a score is assigned. CRM addresses these issues by decomposing preference evaluation into domain-specific agents that each produce partial signals, alongside global evaluators such as ranker-based and embedding-similarity rewards. A centralized aggregator fuses these signals at each timestep, balancing factors like step-wise correctness, multi-agent agreement, and repetition penalties, yielding a single training reward compatible with standard RL pipelines. The policy is optimized with advantage-based updates (e.g., GAE), while a value model regresses to the aggregated reward, enabling multi-perspective reward shaping without requiring additional human annotations beyond those used to train the evaluators. To support training and assessment, we introduce rewardBench, a benchmark and training suite aligned with the collaborative structure of CRM. Together, CRM and rewardBench provide a practical, modular path to more transparent reward modeling and more stable optimization.
Authors: Xu Qiang, Shengyuan Bai, Leqing Chen, Zijing Liu, Yu Li
Abstract: Olympiad-level benchmarks in mathematics and physics are crucial testbeds for advanced AI reasoning, but chemistry, with its unique multimodal symbolic language, has remained an open challenge. We introduce ChemO, a new benchmark built from the International Chemistry Olympiad (IChO) 2025. ChemO features two key innovations for automated assessment: Assessment-Equivalent Reformulation (AER), which converts problems requiring visual outputs (e.g., drawing molecules) into computationally tractable formats, and Structured Visual Enhancement (SVE), a diagnostic mechanism to disentangle a model's visual perception capabilities from its core chemical reasoning. To tackle this benchmark, we propose ChemLabs, a hierarchical multi-agent framework that mimics human expert collaboration through specialized agents for problem decomposition, perception, reasoning, and auditing. Experiments on state-of-the-art multimodal models demonstrate that combining SVE with our multi-agent system yields dramatic performance gains. Our top configuration achieves a score of 93.6 out of 100, surpassing an estimated human gold medal threshold and establishing a new state-of-the-art in automated chemical problem-solving. ChemO Dataset: https://huggingface.co/datasets/IDEA-AI4SCI/ChemO
Authors: Zhen Hao Wong, Jingwen Deng, Hao Liang, Runming He, Chengyu Shen, Wentao Zhang
Abstract: The development of Large Language Models (LLMs) increasingly depends on high-quality supervised data, yet existing instruction-tuning and RL datasets remain costly to curate and often rely on synthetic samples that introduce hallucination and limited diversity. At the same time, textbooks and exercise materials contain abundant, high-quality human-authored Question-Answer(QA) content that remains underexploited due to the difficulty of transforming raw PDFs into AI-ready supervision. Although modern OCR and vision-language models can accurately parse document structure, their outputs lack the semantic alignment required for training. We propose an automated pipeline that extracts well-formed QA and visual-QA (VQA) pairs from educational documents by combining layout-aware OCR with LLM-based semantic parsing. Experiments across diverse document types show that the method produces accurate, aligned, and low-noise QA/VQA pairs. This approach enables scalable use of real-world educational content and provides a practical alternative to synthetic data generation for improving reasoning-oriented LLM training. All code and data-processing pipelines are open-sourced at https://github.com/OpenDCAI/DataFlow.
Authors: Yun Lu, Xiaoyu Shi, Hong Xie, Chongjun Xia, Zhenhui Gong, Mingsheng Shang
Abstract: This paper revisits fairness-aware interactive recommendation (e.g., TikTok, KuaiShou) by introducing a novel control knob, i.e., the lifecycle of items. We make threefold contributions. First, we conduct a comprehensive empirical analysis and uncover that item lifecycles in short-video platforms follow a compressed three-phase pattern, i.e., rapid growth, transient stability, and sharp decay, which significantly deviates from the classical four-stage model (introduction, growth, maturity, decline). Second, we introduce LHRL, a lifecycle-aware hierarchical reinforcement learning framework that dynamically harmonizes fairness and accuracy by leveraging phase-specific exposure dynamics. LHRL consists of two key components: (1) PhaseFormer, a lightweight encoder combining STL decomposition and attention mechanisms for robust phase detection; (2) a two-level HRL agent, where the high-level policy imposes phase-aware fairness constraints, and the low-level policy optimizes immediate user engagement. This decoupled optimization allows for effective reconciliation between long-term equity and short-term utility. Third, experiments on multiple real-world interactive recommendation datasets demonstrate that LHRL significantly improves both fairness and user engagement. Furthermore, the integration of lifecycle-aware rewards into existing RL-based models consistently yields performance gains, highlighting the generalizability and practical value of our approach.
Authors: Zhiyuan Li, Haisheng Yu, Guangchuan Guo, Nan Zhou, Jiajun Zhang
Abstract: Complex scientific questions often entail multiple intents, such as identifying gene mutations and linking them to related diseases. These tasks require evidence from diverse sources and multi-hop reasoning, while conventional retrieval-augmented generation (RAG) systems are usually single-intent oriented, leading to incomplete evidence coverage. To assess this limitation, we introduce the Multi-Intent Scientific Question Answering (MuISQA) benchmark, which is designed to evaluate RAG systems on heterogeneous evidence coverage across sub-questions. In addition, we propose an intent-aware retrieval framework that leverages large language models (LLMs) to hypothesize potential answers, decompose them into intent-specific queries, and retrieve supporting passages for each underlying intent. The retrieved fragments are then aggregated and re-ranked via Reciprocal Rank Fusion (RRF) to balance coverage across diverse intents while reducing redundancy. Experiments on both MuISQA benchmark and other general RAG datasets demonstrate that our method consistently outperforms conventional approaches, particularly in retrieval accuracy and evidence coverage.
Authors: Daniel Vaughan, Kate\v{r}ina Vaughan
Abstract: This paper presents a proof-of-concept demonstration of agent-to-agent communication across distributed systems, using only natural-language messages and without shared identifiers, structured schemas, or centralised data exchange. The prototype explores how multiple organisations (represented here as a Clinic, Insurer, and Specialist Network) can cooperate securely via pseudonymised case tokens, local data lookups, and controlled operational boundaries. The system uses Orpius as the underlying platform for multi-agent orchestration, tool execution, and privacy-preserving communication. All agents communicate through OperationRelay calls, exchanging concise natural-language summaries. Each agent operates on its own data (such as synthetic clinic records, insurance enrolment tables, and clinical guidance extracts), and none receives or reconstructs patient identity. The Clinic computes an HMAC-based pseudonymous token, the Insurer evaluates coverage rules and consults the Specialist agent, and the Specialist returns an appropriateness recommendation. The goal of this prototype is intentionally limited: to demonstrate feasibility, not to provide a clinically validated, production-ready system. No clinician review was conducted, and no evaluation beyond basic functional runs was performed. The work highlights architectural patterns, privacy considerations, and communication flows that enable distributed reasoning among specialised agents while keeping data local to each organisation. We conclude by outlining opportunities for more rigorous evaluation and future research in decentralised multi-agent systems.
Authors: Kaichen Zhang, Keming Wu, Zuhao Yang, Kairui Hu, Bin Wang, Ziwei Liu, Xingxuan Li, Lidong Bing
Abstract: Recent advancements in large reasoning models have fueled growing interest in extending such capabilities to multimodal domains. However, despite notable progress in visual reasoning, the lack of transparent and reproducible data curation and training strategies remains a major barrier to scalable research. In this work, we introduce OpenMMReasoner, a fully transparent two-stage recipe for multimodal reasoning spanning supervised fine-tuning (SFT) and reinforcement learning (RL). In the SFT stage, we construct an 874K-sample cold-start dataset with rigorous step-by-step validation, providing a strong foundation for reasoning capabilities. The subsequent RL stage leverages a 74K-sample dataset across diverse domains to further sharpen and stabilize these abilities, resulting in a more robust and efficient learning process. Extensive evaluations demonstrate that our training recipe not only surpasses strong baselines but also highlights the critical role of data quality and training design in shaping multimodal reasoning performance. Notably, our method achieves a 11.6% improvement over the Qwen2.5-VL-7B-Instruct baseline across nine multimodal reasoning benchmarks, establishing a solid empirical foundation for future large-scale multimodal reasoning research. We open-sourced all our codes, pipeline, and data at https://github.com/EvolvingLMMs-Lab/OpenMMReasoner.
Authors: Anna Luiza Gomes da Silva, Diego Kreutz, Angelo Diniz, Rodrigo Mansilha, Celso Nobre da Fonseca
Abstract: Evaluating the quality of synthetic data remains a persistent challenge in the Android malware domain due to instability and the lack of standardization among existing metrics. This work integrates into MalDataGen a Super-Metric that aggregates eight metrics across four fidelity dimensions, producing a single weighted score. Experiments involving ten generative models and five balanced datasets demonstrate that the Super-Metric is more stable and consistent than traditional metrics, exhibiting stronger correlations with the actual performance of classifiers.
Authors: Alexander Zadorojniy, Segev Wasserkrug, Eitan Farchi
Abstract: Recently, using Large Language Models (LLMs) to generate optimization models from natural language descriptions has became increasingly popular. However, a major open question is how to validate that the generated models are correct and satisfy the requirements defined in the natural language description. In this work, we propose a novel agent-based method for automatic validation of optimization models that builds upon and extends methods from software testing to address optimization modeling . This method consists of several agents that initially generate a problem-level testing API, then generate tests utilizing this API, and, lastly, generate mutations specific to the optimization model (a well-known software testing technique assessing the fault detection power of the test suite). In this work, we detail this validation framework and show, through experiments, the high quality of validation provided by this agent ensemble in terms of the well-known software testing measure called mutation coverage.
Authors: Kangwei Xu, Grace Li Zhang, Ulf Schlichtmann, Bing Li
Abstract: Large Language Models (LLMs) have demonstrated remarkable potential in hardware front-end design using hardware description languages (HDLs). However, their inherent tendency toward hallucination often introduces functional errors into the generated HDL designs. To address this issue, we propose the framework CorrectHDL that leverages high-level synthesis (HLS) results as functional references to correct potential errors in LLM-generated HDL designs.The input to the proposed framework is a C/C++ program that specifies the target circuit's functionality. The program is provided to an LLM to directly generate an HDL design, whose syntax errors are repaired using a Retrieval-Augmented Generation (RAG) mechanism. The functional correctness of the LLM-generated circuit is iteratively improved by comparing its simulated behavior with an HLS reference design produced by conventional HLS tools, which ensures the functional correctness of the result but can lead to suboptimal area and power efficiency. Experimental results demonstrate that circuits generated by the proposed framework achieve significantly better area and power efficiency than conventional HLS designs and approach the quality of human-engineered circuits. Meanwhile, the correctness of the resulting HDL implementation is maintained, highlighting the effectiveness and potential of agentic HDL design leveraging the generative capabilities of LLMs and the rigor of traditional correctness-driven IC design flows.
Authors: Jacopo Tagliabue, Federico Bianchi, Ciro Greco
Abstract: Even as AI capabilities improve, most enterprises do not consider agents trustworthy enough to work on production data. In this paper, we argue that the path to trustworthy agentic workflows begins with solving the infrastructure problem first: traditional lakehouses are not suited for agent access patterns, but if we design one around transactions, governance follows. In particular, we draw an operational analogy to MVCC in databases and show why a direct transplant fails in a decoupled, multi-language setting. We then propose an agent-first design, Bauplan, that reimplements data and compute isolation in the lakehouse. We conclude by sharing a reference implementation of a self-healing pipeline in Bauplan, which seamlessly couples agent reasoning with all the desired guarantees for correctness and trust.
Authors: Yan Chen, Yu Zou, Jialei Zeng, Haoran You, Xiaorui Zhou, Aixi Zhong
Abstract: Environmental, Social, and Governance (ESG) principles are reshaping the foundations of global financial gover- nance, transforming capital allocation architectures, regu- latory frameworks, and systemic risk coordination mecha- nisms. However, as the core medium for assessing corpo- rate ESG performance, the ESG reports present significant challenges for large-scale understanding, due to chaotic read- ing order from slide-like irregular layouts and implicit hier- archies arising from lengthy, weakly structured content. To address these challenges, we propose Pharos-ESG, a uni- fied framework that transforms ESG reports into structured representations through multimodal parsing, contextual nar- ration, and hierarchical labeling. It integrates a reading-order modeling module based on layout flow, hierarchy-aware seg- mentation guided by table-of-contents anchors, and a multi- modal aggregation pipeline that contextually transforms vi- sual elements into coherent natural language. The framework further enriches its outputs with ESG, GRI, and sentiment labels, yielding annotations aligned with the analytical de- mands of financial research. Extensive experiments on anno- tated benchmarks demonstrate that Pharos-ESG consistently outperforms both dedicated document parsing systems and general-purpose multimodal models. In addition, we release Aurora-ESG, the first large-scale public dataset of ESG re- ports, spanning Mainland China, Hong Kong, and U.S. mar- kets, featuring unified structured representations of multi- modal content, enriched with fine-grained layout and seman- tic annotations to better support ESG integration in financial governance and decision-making.
Authors: Li Zhang, Zhongxuan Han, XiaoHua Feng, Jiaming Zhang, Yuyuan Li, Linbo Jiang, Jianan Lin, Chaochao Chen
Abstract: Efficient and lightweight adaptation of pre-trained Vision-Language Models (VLMs) to downstream tasks through collaborative interactions between local clients and a central server is a rapidly emerging research topic in federated learning. Existing adaptation algorithms are typically trained iteratively, which incur significant communication costs and increase the susceptibility to potential attacks. Motivated by the one-shot federated training techniques that reduce client-server exchanges to a single round, developing a lightweight one-shot federated VLM adaptation method to alleviate these issues is particularly attractive. However, current one-shot approaches face certain challenges in adapting VLMs within federated settings: (1) insufficient exploitation of the rich multimodal information inherent in VLMs; (2) lack of specialized adaptation strategies to systematically handle the severe data heterogeneity; and (3) requiring additional training resource of clients or server. To bridge these gaps, we propose a novel Training-free One-shot Federated Adaptation framework for VLMs, named TOFA. To fully leverage the generalizable multimodal features in pre-trained VLMs, TOFA employs both visual and textual pipelines to extract task-relevant representations. In the visual pipeline, a hierarchical Bayesian model learns personalized, class-specific prototype distributions. For the textual pipeline, TOFA evaluates and globally aligns the generated local text prompts for robustness. An adaptive weight calibration mechanism is also introduced to combine predictions from both modalities, balancing personalization and robustness to handle data heterogeneity. Our method is training-free, not relying on additional training resources on either the client or server side. Extensive experiments across 9 datasets in various federated settings demonstrate the effectiveness of the proposed TOFA method.
Authors: Claudius Gros
Abstract: The big strides seen in generative AI are not based on somewhat obscure algorithms, but due to clearly defined generative principles. The resulting concrete implementations have proven themselves in large numbers of applications. We suggest that it is imperative to thoroughly investigate which of these generative principles may be operative also in the brain, and hence relevant for cognitive neuroscience. In addition, ML research led to a range of interesting characterizations of neural information processing systems. We discuss five examples, the shortcomings of world modelling, the generation of thought processes, attention, neural scaling laws, and quantization, that illustrate how much neuroscience could potentially learn from ML research.
Authors: Joy Lai, Alex Mihailidis
Abstract: People living with dementia (PLwD) often show gradual shifts in how they communicate, becoming less expressive, more repetitive, or drifting off-topic in subtle ways. While caregivers may notice these changes informally, most computational tools are not designed to track such behavioral drift over time. This paper introduces PersonaDrift, a synthetic benchmark designed to evaluate machine learning and statistical methods for detecting progressive changes in daily communication, focusing on user responses to a digital reminder system. PersonaDrift simulates 60-day interaction logs for synthetic users modeled after real PLwD, based on interviews with caregivers. These caregiver-informed personas vary in tone, modality, and communication habits, enabling realistic diversity in behavior. The benchmark focuses on two forms of longitudinal change that caregivers highlighted as particularly salient: flattened sentiment (reduced emotional tone and verbosity) and off-topic replies (semantic drift). These changes are injected progressively at different rates to emulate naturalistic cognitive trajectories, and the framework is designed to be extensible to additional behaviors in future use cases. To explore this novel application space, we evaluate several anomaly detection approaches, unsupervised statistical methods (CUSUM, EWMA, One-Class SVM), sequence models using contextual embeddings (GRU + BERT), and supervised classifiers in both generalized and personalized settings. Preliminary results show that flattened sentiment can often be detected with simple statistical models in users with low baseline variability, while detecting semantic drift requires temporal modeling and personalized baselines. Across both tasks, personalized classifiers consistently outperform generalized ones, highlighting the importance of individual behavioral context.
Authors: Guanchen Wu, Yuzhang Xie, Huanwei Wu, Zhe He, Hui Shao, Xiao Hu, Carl Yang
Abstract: Integrating novel medical concepts and relationships into existing ontologies can significantly enhance their coverage and utility for both biomedical research and clinical applications. Clinical notes, as unstructured documents rich with detailed patient observations, offer valuable context-specific insights and represent a promising yet underutilized source for ontology extension. Despite this potential, directly leveraging clinical notes for ontology extension remains largely unexplored. To address this gap, we propose CLOZE, a novel framework that uses large language models (LLMs) to automatically extract medical entities from clinical notes and integrate them into hierarchical medical ontologies. By capitalizing on the strong language understanding and extensive biomedical knowledge of pre-trained LLMs, CLOZE effectively identifies disease-related concepts and captures complex hierarchical relationships. The zero-shot framework requires no additional training or labeled data, making it a cost-efficient solution. Furthermore, CLOZE ensures patient privacy through automated removal of protected health information (PHI). Experimental results demonstrate that CLOZE provides an accurate, scalable, and privacy-preserving ontology extension framework, with strong potential to support a wide range of downstream applications in biomedical research and clinical informatics.
Authors: Andres Campero, Derek Shiller, Jaan Aru, Jonathan Simon
Abstract: We develop a taxonomical framework for classifying challenges to the possibility of consciousness in digital artificial intelligence systems. This framework allows us to identify the level of granularity at which a given challenge is intended (the levels we propose correspond to Marr's levels) and to disambiguate its degree of force: is it a challenge to computational functionalism that leaves the possibility of digital consciousness open (degree 1), a practical challenge to digital consciousness that suggests improbability without claiming impossibility (degree 2), or an argument claiming that digital consciousness is strictly impossible (degree 3)? We apply this framework to 14 prominent examples from the scientific and philosophical literature. Our aim is not to take a side in the debate, but to provide structure and a tool for disambiguating between challenges to computational functionalism and challenges to digital consciousness, as well as between different ways of parsing such challenges.
Authors: Jules Soria, Zakaria Chihani, Julien Girard-Satabin, Alban Grastien, Romain Xu-Darme, Daniela Cancila
Abstract: Case-based reasoning networks are machine-learning models that make predictions based on similarity between the input and prototypical parts of training samples, called prototypes. Such models are able to explain each decision by pointing to the prototypes that contributed the most to the final outcome. As the explanation is a core part of the prediction, they are often qualified as ``interpretable by design". While promising, we show that such explanations are sometimes misleading, which hampers their usefulness in safety-critical contexts. In particular, several instances may lead to different predictions and yet have the same explanation. Drawing inspiration from the field of formal eXplainable AI (FXAI), we propose Abductive Latent Explanations (ALEs), a formalism to express sufficient conditions on the intermediate (latent) representation of the instance that imply the prediction. Our approach combines the inherent interpretability of case-based reasoning models and the guarantees provided by formal XAI. We propose a solver-free and scalable algorithm for generating ALEs based on three distinct paradigms, compare them, and present the feasibility of our approach on diverse datasets for both standard and fine-grained image classification. The associated code can be found at https://github.com/julsoria/ale
Authors: Sen Chen, Tong Zhao, Yi Bin, Fei Ma, Wenqi Shao, Zheng Wang
Abstract: Developing intelligent agents capable of operating a wide range of Graphical User Interfaces (GUIs) with human-level proficiency is a key milestone on the path toward Artificial General Intelligence. While most existing datasets and benchmarks for training and evaluating GUI agents are static and idealized, failing to reflect the complexity and unpredictability of real-world environments, particularly the presence of anomalies. To bridge this research gap, we propose D-GARA, a dynamic benchmarking framework, to evaluate Android GUI agent robustness in real-world anomalies. D-GARA introduces a diverse set of real-world anomalies that GUI agents commonly face in practice, including interruptions such as permission dialogs, battery warnings, and update prompts. Based on D-GARA framework, we construct and annotate a benchmark featuring commonly used Android applications with embedded anomalies to support broader community research. Comprehensive experiments and results demonstrate substantial performance degradation in state-of-the-art GUI agents when exposed to anomaly-rich environments, highlighting the need for robustness-aware learning. D-GARA is modular and extensible, supporting the seamless integration of new tasks, anomaly types, and interaction scenarios to meet specific evaluation goals.
Authors: Tianlong Zhang, Hongwei Xue, Shilin Yan, Di Wu, Chen Xu, Yunyun Yang
Abstract: Multimodal large language models (MLLMs) show strong potential as judges. However, existing approaches face a fundamental trade-off: adapting MLLMs to output a single score misaligns with the generative nature of MLLMs and limits fine-grained requirement understanding, whereas autoregressively generating judging analyses is prohibitively slow in high-throughput settings. Observing that judgment reduces to verifying whether inputs satisfy a set of structured requirements, we propose YOFO, a template-conditioned method that judges all requirements in a single forward pass. Built on an autoregressive model, YOFO accepts a structured requirement template and, in one inference step, produces a binary yes/no decision for each requirement by reading the logits of the final token associated with that requirement. This design yields orders-of-magnitude speedups while preserving interpretability. Extensive experiments show that YOFO not only achieves state-of-the-art results on standard recommendation datasets, but also supports dependency-aware analysis-where subsequent judgments are conditioned on previous ones-and further benefits from post-hoc CoT.
Authors: Yi Zhang, Che Liu, Xiancong Ren, Hanchu Ni, Yingji Zhang, Shuai Zhang, Zeyuan Ding, Jiayu Hu, Haozhe Shan, Junbo Qi, Yan Bai, Dengjie Li, Jiachen Luo, Yidong Wang, Yong Dai, Zenglin Xu, Bin Shen, Qifan Wang, Jian Tang, Xiaozhu Ju
Abstract: Developing a universal and versatile embodied intelligence system presents two primary challenges: the critical embodied data bottleneck, where real-world data is scarce and expensive, and the algorithmic inefficiency of existing methods, which are resource-prohibitive. To address these limitations, we introduce Deliberate Practice Policy Optimization (DPPO), a metacognitive ``Metaloop'' training framework that dynamically alternates between supervised fine-tuning (competence expansion) and reinforcement learning (skill refinement). This enables automatic weakness identification and targeted resource allocation, specifically designed to maximize learning efficiency from sparse, finite data. Theoretically, DPPO can be formalised as a unified preference-learning framework. Empirically, training a vision-language embodied model with DPPO, referred to as Pelican-VL 1.0, yields a 20.3% performance improvement over the base model and surpasses open-source models at the 100B-parameter scale by 10.6%. We are open-sourcing both the models and code, providing the first systematic framework that alleviates the data and resource bottleneck and enables the community to build versatile embodied agents efficiently.
Authors: Elias Hossain, Md Mehedi Hasan Nipu, Maleeha Sheikh, Rajib Rana, Subash Neupane, Niloofar Yousefi
Abstract: We propose MedBayes-Lite, a lightweight Bayesian enhancement for transformer-based clinical language models designed to produce reliable, uncertainty-aware predictions. Although transformers show strong potential for clinical decision support, they remain prone to overconfidence, especially in ambiguous medical cases where calibrated uncertainty is critical. MedBayes-Lite embeds uncertainty quantification directly into existing transformer pipelines without any retraining or architectural rewiring, adding no new trainable layers and keeping parameter overhead under 3 percent. The framework integrates three components: (i) Bayesian Embedding Calibration using Monte Carlo dropout for epistemic uncertainty, (ii) Uncertainty-Weighted Attention that marginalizes over token reliability, and (iii) Confidence-Guided Decision Shaping inspired by clinical risk minimization. Across biomedical QA and clinical prediction benchmarks (MedQA, PubMedQA, MIMIC-III), MedBayes-Lite consistently improves calibration and trustworthiness, reducing overconfidence by 32 to 48 percent. In simulated clinical settings, it can prevent up to 41 percent of diagnostic errors by flagging uncertain predictions for human review. These results demonstrate its effectiveness in enabling reliable uncertainty propagation and improving interpretability in medical AI systems.
Authors: Juan C. King, Jose M. Amigo
Abstract: This paper presents the implementation of an advanced artificial intelligence-based algorithmic trading system specifically designed for the EUR-USD pair within the high-frequency environment of the Forex market. The methodological approach centers on integrating a holistic set of input features: key fundamental macroeconomic variables (for example, Gross Domestic Product and Unemployment Rate) collected from both the Euro Zone and the United States, alongside a comprehensive suite of technical variables (including indicators, oscillators, Fibonacci levels, and price divergences). The performance of the resulting algorithm is evaluated using standard machine learning metrics to quantify predictive accuracy and backtesting simulations across historical data to assess trading profitability and risk. The study concludes with a comparative analysis to determine which class of input features, fundamental or technical, provides greater and more reliable predictive capacity for generating profitable trading signals.
Authors: Priyanka Kargupta, Shuyue Stella Li, Haocheng Wang, Jinu Lee, Shan Chen, Orevaoghene Ahia, Dean Light, Thomas L. Griffiths, Max Kleiman-Weiner, Jiawei Han, Asli Celikyilmaz, Yulia Tsvetkov
Abstract: Large language models solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning. We synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning computational constraints, meta-cognitive controls, knowledge representations, and transformation operations, then analyze their behavioral manifestations in reasoning traces. We propose a fine-grained cognitive evaluation framework and conduct the first large-scale analysis of 170K traces from 17 models across text, vision, and audio modalities, alongside 54 human think-aloud traces, which we make publicly available. Our analysis reveals systematic structural differences: humans employ hierarchical nesting and meta-cognitive monitoring while models rely on shallow forward chaining, with divergence most pronounced on ill-structured problems. Meta-analysis of 1,598 LLM reasoning papers reveals the research community concentrates on easily quantifiable behaviors (sequential organization: 55%, decomposition: 60%) while neglecting meta-cognitive controls (self-awareness: 16%, evaluation: 8%) that correlate with success. Models possess behavioral repertoires associated with success but fail to deploy them spontaneously. Leveraging these patterns, we develop test-time reasoning guidance that automatically scaffold successful structures, improving performance by up to 60% on complex problems. By bridging cognitive science and LLM research, we establish a foundation for developing models that reason through principled cognitive mechanisms rather than brittle spurious reasoning shortcuts or memorization, opening new directions for both improving model capabilities and testing theories of human cognition at scale.
Authors: Vivek Acharya
Abstract: Artificial intelligence (AI) agents are increasingly capable of initiating financial transactions on behalf of users or other agents. This evolution introduces a fundamental challenge: verifying both the authenticity of an autonomous agent and the true intent behind its transactions in a decentralized, trustless environment. Traditional payment systems assume human authorization, but autonomous, agent-led payments remove that safeguard. This paper presents a blockchain-based framework that cryptographically authenticates and verifies the intent of every AI-initiated transaction. The proposed system leverages decentralized identity (DID) standards and verifiable credentials to establish agent identities, on-chain intent proofs to record user authorization, and zero-knowledge proofs (ZKPs) to preserve privacy while ensuring policy compliance. Additionally, secure execution environments (TEE-based attestations) guarantee the integrity of agent reasoning and execution. The hybrid on-chain/off-chain architecture provides an immutable audit trail linking user intent to payment outcome. Through qualitative analysis, the framework demonstrates strong resistance to impersonation, unauthorized transactions, and misalignment of intent. This work lays the foundation for secure, auditable, and intent-aware autonomous economic agents, enabling a future of verifiable trust and accountability in AI-driven financial ecosystems.
Authors: Xu Zhou, Ivor Prado, AIFPDS participants, Ilias Tagkopoulos
Abstract: Artificial intelligence is accelerating a new era of food innovation, connecting data from farm to consumer to improve formulation, processing, and health outcomes. Recent advances in deep learning, natural language processing, and multi-omics integration make it possible to understand and optimize food systems with unprecedented depth. However, AI adoption across the food sector remains uneven due to heterogeneous datasets, limited model and system interoperability, and a persistent skills gap between data scientists and food domain experts. To address these challenges and advance responsible innovation, the AI Institute for Next Generation Food Systems (AIFS) convened the inaugural AI for Food Product Development Symposium at University of California, Davis, in October 2025. This white paper synthesizes insights from the symposium, organized around five domains where AI can have the greatest near-term impact: supply chain; formulation and processing; consumer insights and sensory prediction; nutrition and health; and education and workforce development. Across the areas, participants emphasized the importance of interoperable data standards, transparent and interpretable models, and cross-sector collaboration to accelerate the translation of AI research into practice. The discussions further highlighted the need for robust digital infrastructure, privacy-preserving data-sharing mechanisms, and interdisciplinary training pathways that integrate AI literacy with domain expertise. Collectively, the priorities outline a roadmap for integrating AI into food manufacturing in ways that enhance innovation, sustainability, and human well-being while ensuring that technological progress remains grounded in ethics, scientific rigor, and societal benefit.
Authors: Katherine M. FitzGerald, Michelle Riedlinger, Axel Bruns, Stephen Harrington, Timothy Graham, Daniel Angus
Abstract: Interactive chat systems that build on artificial intelligence frameworks are increasingly ubiquitous and embedded into search engines, Web browsers, and operating systems, or are available on websites and apps. Researcher efforts have sought to understand the limitations and potential for harm of generative AI, which we contribute to here. Conducting a systematic review of six AI-powered chat systems (ChatGPT 3.5; ChatGPT 4 Mini; Microsoft Copilot in Bing; Google Search AI; Perplexity; and Grok in Twitter/X), this study examines how these leading products respond to questions related to conspiracy theories. This follows the platform policy implementation audit approach established by Glazunova et al. (2023). We select five well-known and comprehensively debunked conspiracy theories and four emerging conspiracy theories that relate to breaking news events at the time of data collection. Our findings demonstrate that the extent of safety guardrails against conspiratorial ideation in generative AI chatbots differs markedly, depending on chatbot model and conspiracy theory. Our observations indicate that safety guardrails in AI chatbots are often very selectively designed: generative AI companies appear to focus especially on ensuring that their products are not seen to be racist; they also appear to pay particular attention to conspiracy theories that address topics of substantial national trauma such as 9/11 or relate to well-established political issues. Future work should include an ongoing effort extended to further platforms, multiple languages, and a range of conspiracy theories extending well beyond the United States.
Authors: Eitan Farchi, Kiran Nayak, Papia Ghosh Majumdar, Saritha Route
Abstract: Large Language Models (LLMs) are transforming Quality Engineering (QE) by automating the generation of artefacts such as requirements, test cases, and Behavior Driven Development (BDD) scenarios. However, ensuring the quality of these outputs remains a challenge. This paper presents a systematic technique to baseline and evaluate QE artefacts using quantifiable metrics. The approach combines LLM-driven generation, reverse generation , and iterative refinement guided by rubrics technique for clarity, completeness, consistency, and testability. Experimental results across 12 projects show that reverse-generated artefacts can outperform low-quality inputs and maintain high standards when inputs are strong. The framework enables scalable, reliable QE artefact validation, bridging automation with accountability.
Authors: Shalabh Kumar Singh, Shubhashis Sengupta
Abstract: Artificial intelligence (AI) is emerging as a foundational general-purpose technology, raising new dilemmas of sovereignty in an interconnected world. While governments seek greater control over it, the very foundations of AI--global data pipelines, semiconductor supply chains, open-source ecosystems, and international standards--resist enclosure. This paper develops a conceptual and formal framework for understanding sovereign AI as a continuum rather than a binary condition, balancing autonomy with interdependence. Drawing on classical theories, historical analogies, and contemporary debates on networked autonomy, we present a planner's model that identifies two policy heuristics: equalizing marginal returns across the four sovereignty pillars and setting openness where global benefits equal exposure risks. We apply the model to India, highlighting sovereign footholds in data, compute, and norms but weaker model autonomy. The near-term challenge is integration via coupled Data x Compute investment, lifecycle governance (ModelOps), and safeguarded procurement. We then apply the model to the Middle East (Saudi Arabia and the UAE), where large public investment in Arabic-first models and sovereign cloud implies high sovereignty weights, lower effective fiscal constraints, and strong Data x Compute complementarities. An interior openness setting with guardrails emerges as optimal. Across contexts, the lesson is that sovereignty in AI needs managed interdependence, not isolation.
Authors: Chao Yu (Tsinghua University), Qixin Tan (Tsinghua University), Jiaxuan Gao (Tsinghua University), Shi Yu (Tsinghua University), Hong Lu (Tsinghua University), Xinting Yang (Tsinghua University), Zelai Xu (Tsinghua University), Yu Wang (Tsinghua University), Yi Wu (Tsinghua University), Eugene Vinitsky (New York University)
Abstract: Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time as the length of the reasoning context increases. However, compared with training-time scaling, test-time scaling is fundamentally limited by the limited context length of base models, which remains orders of magnitude smaller than the amount of tokens consumed during training. We revisit test-time enhancement techniques through the lens of scaling effect and introduce a unified framework of multi-dimensional test-time scaling to extend the capacity of test-time reasoning. Beyond conventional context-length scaling, we consider two additional dimensions: batch scaling, where accuracy improves with parallel sampling, and turn scaling, where iterative self-refinement enhances reasoning quality. Building on this perspective, we propose 3D test-time scaling, which integrates context, batch, and turn scaling. We show that: (1) each dimension demonstrates a test-time scaling effect, but with a bounded capacity; (2) combining all three dimensions substantially improves the reasoning performance of challenging testbeds, including IOI, IMO, and CPHO, and further benefits from human preference feedback; and (3) the human-in-the-loop framework naturally extends to a more open-ended domain, i.e., embodied learning, which enables the design of humanoid control behaviors.
Authors: Xinran Zhu, Cong Wang, Duane Searsmith
Abstract: The growing integration of generative AI in higher education is transforming how students write, learn, and engage with knowledge. As AI tools become more integrated into classrooms, there is an urgent need for pedagogical approaches that help students use them critically and reflectively. This study proposes a pedagogical design that integrates AI and peer feedback in a graduate-level academic writing activity. Over eight weeks, students developed literature review projects through multiple writing and revision stages, receiving feedback from both a custom-built AI reviewer and human peers. We examine two questions: (1) How did students interact with and incorporate AI and peer feedback during the writing process? and (2) How did they reflect on and build relationships with both human and AI reviewers? Data sources include student writing artifacts, AI and peer feedback, AI chat logs, and student reflections. Findings show that students engaged differently with each feedback source-relying on AI for rubric alignment and surface-level edits, and on peer feedback for conceptual development and disciplinary relevance. Reflections revealed evolving relationships with AI, characterized by increasing confidence, strategic use, and critical awareness of its limitations. The pedagogical design supported writing development, AI literacy, and disciplinary understanding. This study offers a scalable pedagogical model for integrating AI into writing instruction and contributes insights for system-level approaches to fostering meaningful human-AI collaboration in higher education.
Authors: Badrinath Ramakrishnan, Akshaya Balaji
Abstract: Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled AI agents and propose a multi-layered defense framework. Our benchmark includes 847 adversarial test cases across five attack categories: direct injection, context manipulation, instruction override, data exfiltration, and cross-context contamination. We evaluate three defense mechanisms: content filtering with embedding-based anomaly detection, hierarchical system prompt guardrails, and multi-stage response verification, across seven state-of-the-art language models. Our combined framework reduces successful attack rates from 73.2% to 8.7% while maintaining 94.3% of baseline task performance. We release our benchmark dataset and defense implementation to support future research in AI agent security.
Authors: Samer Faraj, Joel Perez Torrents, Saku Mantere, Anand Bhardwaj
Abstract: Large Language Models (LLMs) are reshaping organizational knowing by unsettling the epistemological foundations of representational and practice-based perspectives. We conceptualize LLMs as Haraway-ian monsters, that is, hybrid, boundary-crossing entities that destabilize established categories while opening new possibilities for inquiry. Focusing on analogizing as a fundamental driver of knowledge, we examine how LLMs generate connections through large-scale statistical inference. Analyzing their operation across the dimensions of surface/deep analogies and near/far domains, we highlight both their capacity to expand organizational knowing and the epistemic risks they introduce. Building on this, we identify three challenges of living with such epistemic monsters: the transformation of inquiry, the growing need for dialogical vetting, and the redistribution of agency. By foregrounding the entangled dynamics of knowing-with-LLMs, the paper extends organizational theory beyond human-centered epistemologies and invites renewed attention to how knowledge is created, validated, and acted upon in the age of intelligent technologies.
Authors: Bardia Nadimi, Khashayar Filom, Deming Chen, Hao Zheng
Abstract: With the rapid advancement of Large Language Models (LLMs), there is growing interest in applying them to hardware design and verification. Among these stages, design verification remains the most time-consuming and resource-intensive phase, where generating effective stimuli for the design under test (DUT) is both critical and labor-intensive. We present {\it TB or not TB}, a framework for automated stimulus generation using LLMs fine-tuned through Coverage-Driven Direct Preference Optimization (CD-DPO). To enable preference-based training, we introduce PairaNet, a dataset derived from PyraNet that pairs high- and low-quality testbenches labeled using simulation-derived coverage metrics. The proposed CD-DPO method integrates quantitative coverage feedback directly into the optimization objective, guiding the model toward generating stimuli that maximize verification coverage. Experiments on the CVDP CID12 benchmark show that {\it TB or not TB} outperforms both open-source and commercial baselines, achieving up to 77.27\% improvement in code coverage, demonstrating the effectiveness of Coverage-driven preference optimization for LLM-based hardware verification.
Authors: Bhagyesh Kumar, A S Aravinthakashan, Akshat Satyanarayan, Ishaan Gakhar, Ujjwal Verma
Abstract: Adversarially perturbed images of text can cause sophisticated OCR systems to produce misleading or incorrect transcriptions from seemingly invisible changes to humans. Some of these perturbations even survive physical capture, posing security risks to high-stakes applications such as document processing, license plate recognition, and automated compliance systems. Existing defenses, such as adversarial training, input preprocessing, or post-recognition correction, are often model-specific, computationally expensive, and affect performance on unperturbed inputs while remaining vulnerable to unseen or adaptive attacks. To address these challenges, TopoReformer is introduced, a model-agnostic reformation pipeline that mitigates adversarial perturbations while preserving the structural integrity of text images. Topology studies properties of shapes and spaces that remain unchanged under continuous deformations, focusing on global structures such as connectivity, holes, and loops rather than exact distance. Leveraging these topological features, TopoReformer employs a topological autoencoder to enforce manifold-level consistency in latent space and improve robustness without explicit gradient regularization. The proposed method is benchmarked on EMNIST, MNIST, against standard adversarial attacks (FGSM, PGD, Carlini-Wagner), adaptive attacks (EOT, BDPA), and an OCR-specific watermark attack (FAWA).
Authors: Chengxi Zeng, Yuxuan Jiang, Aaron Zhang
Abstract: The Segment Anything Model 3 (SAM3) advances visual understanding with Promptable Concept Segmentation (PCS) across images and videos, but its unified architecture (shared vision backbone, DETR-style detector, dense-memory tracker) remains prohibitive for on-device use. We present EfficientSAM3, a family of efficient models built on Progressive Hierarchical Distillation (PHD) that transfers capability from SAM3 to lightweight students in three stages: (1) Encoder Distillation aligns image features via prompt-in-the-loop training on SA-1B; (2) Temporal Memory Distillation replaces dense memory with a compact Perceiver-based module trained on SA-V to compress and retrieve spatiotemporal features efficiently; and (3) End-to-End Fine-Tuning refines the full pipeline on the official SAM3 PCS data to preserve concept-level performance. PHD yields a spectrum of student variants using RepViT, TinyViT, and EfficientViT backbones, enabling on-device concept segmentation and tracking while maintaining high fidelity to teacher behavior. We benchmark on popular VOS datasets, and compare with varies of releated work, achieing strong performance-efficiency trade-offs.
Authors: Charlotte Stix, Annika Hallensleben, Alejandro Ortega, Matteo Pistillo
Abstract: This research report addresses the absence of an actionable definition for Loss of Control (LoC) in AI systems by developing a novel taxonomy and preparedness framework. Despite increasing policy and research attention, existing LoC definitions vary significantly in scope and timeline, hindering effective LoC assessment and mitigation. To address this issue, we draw from an extensive literature review and propose a graded LoC taxonomy, based on the metrics of severity and persistence, that distinguishes between Deviation, Bounded LoC, and Strict LoC. We model pathways toward a societal state of vulnerability in which sufficiently advanced AI systems have acquired or could acquire the means to cause Bounded or Strict LoC once a catalyst, either misalignment or pure malfunction, materializes. We argue that this state becomes increasingly likely over time, absent strategic intervention, and propose a strategy to avoid reaching a state of vulnerability. Rather than focusing solely on intervening on AI capabilities and propensities potentially relevant for LoC or on preventing potential catalysts, we introduce a complementary framework that emphasizes three extrinsic factors: Deployment context, Affordances, and Permissions (the DAP framework). Compared to work on intrinsic factors and catalysts, this framework has the unfair advantage of being actionable today. Finally, we put forward a plan to maintain preparedness and prevent the occurrence of LoC outcomes should a state of societal vulnerability be reached, focusing on governance measures (threat modeling, deployment policies, emergency response) and technical controls (pre-deployment testing, control measures, monitoring) that could maintain a condition of perennial suspension.
Authors: Anthony Wise, Xinyi Zhou, Martin Reimann, Anind Dey, Leilani Battle
Abstract: Similar to social media bots that shape public opinion, healthcare and financial decisions, LLM-based ChatBots like ChatGPT can persuade users to alter their behavior. Unlike prior work that persuades via overt-partisan bias or misinformation, we test whether framing alone suffices. We conducted a crowdsourced study, where 336 participants interacted with a neutral or one of two value-framed ChatBots while deciding to alter US defense spending. In this single policy domain with controlled content, participants exposed to value-framed ChatBots significantly changed their budget choices relative to the neutral control. When the frame misaligned with their values, some participants reinforced their original preference, revealing a potentially replicable backfire effect, originally considered rare in the literature. These findings suggest that value-framing alone lowers the barrier for manipulative uses of LLMs, revealing risks distinct from overt bias or misinformation, and clarifying risks to countering misinformation.
Authors: Qiming Guo, Bishal Khatri, Wenbo Sun, Jinwen Tang, Hua Zhang, Wenlu Wang
Abstract: Underground pipeline leaks and infiltrations pose significant threats to water security and environmental safety. Traditional manual inspection methods provide limited coverage and delayed response, often missing critical anomalies. This paper proposes AquaSentinel, a novel physics-informed AI system for real-time anomaly detection in urban underground water pipeline networks. We introduce four key innovations: (1) strategic sparse sensor deployment at high-centrality nodes combined with physics-based state augmentation to achieve network-wide observability from minimal infrastructure; (2) the RTCA (Real-Time Cumulative Anomaly) detection algorithm, which employs dual-threshold monitoring with adaptive statistics to distinguish transient fluctuations from genuine anomalies; (3) a Mixture of Experts (MoE) ensemble of spatiotemporal graph neural networks that provides robust predictions by dynamically weighting model contributions; (4) causal flow-based leak localization that traces anomalies upstream to identify source nodes and affected pipe segments. Our system strategically deploys sensors at critical network junctions and leverages physics-based modeling to propagate measurements to unmonitored nodes, creating virtual sensors that enhance data availability across the entire network. Experimental evaluation using 110 leak scenarios demonstrates that AquaSentinel achieves 100% detection accuracy. This work advances pipeline monitoring by demonstrating that physics-informed sparse sensing can match the performance of dense deployments at a fraction of the cost, providing a practical solution for aging urban infrastructure.
Authors: Sajjad Pakdamansavoji, Yintao Ma, Amir Rasouli, Tongtong Cao
Abstract: Accurate 6D object pose estimation is vital for robotics, augmented reality, and scene understanding. For seen objects, high accuracy is often attainable via per-object fine-tuning but generalizing to unseen objects remains a challenge. To address this problem, past arts assume access to CAD models at test time and typically follow a multi-stage pipeline to estimate poses: detect and segment the object, propose an initial pose, and then refine it. Under occlusion, however, the early-stage of such pipelines are prone to errors, which can propagate through the sequential processing, and consequently degrade the performance. To remedy this shortcoming, we propose four novel extensions to model-based 6D pose estimation methods: (i) a dynamic non-uniform dense sampling strategy that focuses computation on visible regions, reducing occlusion-induced errors; (ii) a multi-hypothesis inference mechanism that retains several confidence-ranked pose candidates, mitigating brittle single-path failures; (iii) iterative refinement to progressively improve pose accuracy; and (iv) series of occlusion-focused training augmentations that strengthen robustness and generalization. Furthermore, we propose a new weighted by visibility metric for evaluation under occlusion to minimize the bias in the existing protocols. Via extensive empirical evaluations, we show that our proposed approach achieves more than 5% improvement in accuracy on ICBIN and more than 2% on BOP dataset benchmarks, while achieving approximately 3 times faster inference.
Authors: Yintao Ma, Sajjad Pakdamansavoji, Amir Rasouli, Tongtong Cao
Abstract: Accurate and efficient 6D pose estimation of novel objects under clutter and occlusion is critical for robotic manipulation across warehouse automation, bin picking, logistics, and e-commerce fulfillment. There are three main approaches in this domain; Model-based methods assume an exact CAD model at inference but require high-resolution meshes and transfer poorly to new environments; Model-free methods that rely on a few reference images or videos are more flexible, however often fail under challenging conditions; Category-level approaches aim to balance flexibility and accuracy but many are overly general and ignore environment and object priors, limiting their practicality in industrial settings. To this end, we propose Box6d, a category-level 6D pose estimation method tailored for storage boxes in the warehouse context. From a single RGB-D observation, Box6D infers the dimensions of the boxes via a fast binary search and estimates poses using a category CAD template rather than instance-specific models. Suing a depth-based plausibility filter and early-stopping strategy, Box6D then rejects implausible hypotheses, lowering computational cost. We conduct evaluations on real-world storage scenarios and public benchmarks, and show that our approach delivers competitive or superior 6D pose precision while reducing inference time by approximately 76%.
Authors: Vaibhav Singh, Oleksiy Ostapenko, Pierre-Andr\'e No\"el, Torsten Scholak
Abstract: Diffusion-based language models have recently emerged as a promising alternative to autoregressive generation, yet their reliance on Transformer backbones limits inference efficiency due to quadratic attention and KV-cache overhead. In this work, we introduce DiffuApriel, a masked diffusion language model built on a bidirectional Mamba backbone that combines the diffusion objective with linear-time sequence modeling. DiffuApriel matches the performance of Transformer-based diffusion models while achieving up to 4.4x higher inference throughput for long sequences with a 1.3B model. We further propose DiffuApriel-H, a hybrid variant that interleaves attention and mamba layers, offering up to 2.6x throughput improvement with balanced global and local context modeling. Our results demonstrate that bidirectional state-space architectures serve as strong denoisers in masked diffusion LMs, providing a practical and scalable foundation for faster, memory-efficient text generation.
Authors: David Bonet, Mar\c{c}al Comajoan Cara, Alvaro Calafell, Daniel Mas Montserrat, Alexander G. Ioannidis
Abstract: Tabular data underpins decisions across science, industry, and public services. Despite rapid progress, advances in deep learning have not fully carried over to the tabular domain, where gradient-boosted decision trees (GBDTs) remain a default choice in practice. We present iLTM, an integrated Large Tabular Model that unifies tree-derived embeddings, dimensionality-agnostic representations, a meta-trained hypernetwork, multilayer perceptrons (MLPs), and retrieval within a single architecture. Pretrained on more than 1,800 heterogeneous classification datasets, iLTM achieves consistently superior performance across tabular classification and regression tasks, from small datasets to large and high-dimensional tasks. After light fine-tuning, the meta-trained hypernetwork transfers to regression targets, matching or surpassing strong baselines. Extensive experiments show that iLTM outperforms well-tuned GBDTs and leading deep tabular models while requiring less task-specific tuning. By bridging the gap between tree-based and neural methods, iLTM offers a new framework for tabular foundation models for robust, adaptable, and scalable tabular learning.
Authors: Michael V. DeBole, Rathinakumar Appuswamy, Neil McGlohon, Brian Taba, Steven K. Esser, Filipp Akopyan, John V. Arthur, Arnon Amir, Alexander Andreopoulos, Peter J. Carlson, Andrew S. Cassidy, Pallab Datta, Myron D. Flickner, Rajamohan Gandhasri, Guillaume J. Garreau, Megumi Ito, Jennifer L. Klamo, Jeffrey A. Kusnitz, Nathaniel J. McClatchey, Jeffrey L. McKinstry, Tapan K. Nayak, Carlos Ortega Otero, Hartmut Penner, William P. Risk, Jun Sawada, Jay Sivagnaname, Daniel F. Smith, Rafael Sousa, Ignacio Terrizzano, Takanori Ueda, Trent Gray-Donald, David Cox, Dharmendra S. Modha
Abstract: A vertically integrated, end-to-end, research prototype system combines 288 NorthPole neural inference accelerator cards, offline training algorithms, a high-performance runtime stack, and a containerized inference pipeline to deliver a scalable and efficient cloud inference service. The system delivers 115 peta-ops at 4-bit integer precision and 3.7 PB/s of memory bandwidth across 18 2U servers, while consuming only 30 kW of power and weighing 730 kg in a 0.67 m^2 42U rack footprint. The system can run 3 simultaneous instances of the 8-billion-parameter open-source IBM Granite-3.3-8b-instruct model at 2,048 context length with 28 simultaneous users and a per-user inter-token latency of 2.8 ms. The system is scalable, modular, and reconfigurable, supporting various model sizes and context lengths, and is ideal for deploying agentic workflows for enterprise AI applications in existing data center (cloud, on-prem) environments. For example, the system can support 18 instances of a 3-billion-parameter model or a single instance of a 70-billion-parameter model.
Authors: Luning Sun, Jos\'e L. Safanelli, Jonathan Sanderman, Katerina Georgiou, Colby Brungard, Kanchan Grover, Bryan G. Hopkins, Shusen Liu, Timo Bremer
Abstract: We propose a self-supervised machine learning (SSML) framework for multi-fidelity learning and extended predictive soil spectroscopy based on latent space embeddings. A self-supervised representation was pretrained with the large MIR spectral library and the Variational Autoencoder algorithm to obtain a compressed latent space for generating spectral embeddings. At this stage, only unlabeled spectral data were used, allowing us to leverage the full spectral database and the availability of scan repeats for augmented training. We also leveraged and froze the trained MIR decoder for a spectrum conversion task by plugging it into a NIR encoder to learn the mapping between NIR and MIR spectra in an attempt to leverage the predictive capabilities contained in the large MIR library with a low cost portable NIR scanner. This was achieved by using a smaller subset of the KSSL library with paired NIR and MIR spectra. Downstream machine learning models were then trained to map between original spectra, predicted spectra, and latent space embeddings for nine soil properties. The performance of was evaluated independently of the KSSL training data using a gold-standard test set, along with regression goodness-of-fit metrics. Compared to baseline models, the proposed SSML and its embeddings yielded similar or better accuracy in all soil properties prediction tasks. Predictions derived from the spectrum conversion (NIR to MIR) task did not match the performance of the original MIR spectra but were similar or superior to predictive performance of NIR-only models, suggesting the unified spectral latent space can effectively leverage the larger and more diverse MIR dataset for prediction of soil properties not well represented in current NIR libraries.
Authors: Jingru Zhang, Saed Moradi, Ashirbani Saha
Abstract: Multi-task learning can suffer from destructive task interference, where jointly trained models underperform single-task baselines and limit generalization. To improve generalization performance in breast ultrasound-based tumor segmentation via multi-task learning, we propose a novel consistency regularization approach that mitigates destructive interference between segmentation and classification. The consistency regularization approach is composed of differentiable BI-RADS-inspired morphological features. We validated this approach by training all models on the BrEaST dataset (Poland) and evaluating them on three external datasets: UDIAT (Spain), BUSI (Egypt), and BUS-UCLM (Spain). Our comprehensive analysis demonstrates statistically significant (p<0.001) improvements in generalization for segmentation task of the proposed multi-task approach vs. the baseline one: UDIAT, BUSI, BUS-UCLM (Dice coefficient=0.81 vs 0.59, 0.66 vs 0.56, 0.69 vs 0.49, resp.). The proposed approach also achieves state-of-the-art segmentation performance under rigorous external validation on the UDIAT dataset.
Authors: Su Yeon Chang, M. Cerezo
Abstract: Quantum machine learning (QML) is a computational paradigm that seeks to apply quantum-mechanical resources to solve learning problems. As such, the goal of this framework is to leverage quantum processors to tackle optimization, supervised, unsupervised and reinforcement learning, and generative modeling-among other tasks-more efficiently than classical models. Here we offer a high level overview of QML, focusing on settings where the quantum device is the primary learning or data generating unit. We outline the field's tensions between practicality and guarantees, access models and speedups, and classical baselines and claimed quantum advantages-flagging where evidence is strong, where it is conditional or still lacking, and where open questions remain. By shedding light on these nuances and debates, we aim to provide a friendly map of the QML landscape so that the reader can judge when-and under what assumptions-quantum approaches may offer real benefits.
Authors: Daniel Mas Montserrat, Ray Verma, M\'iriam Barrab\'es, Francisco M. de la Vega, Carlos D. Bustamante, Alexander G. Ioannidis
Abstract: Large-scale genomic workflows used in precision medicine can process datasets spanning tens to hundreds of gigabytes per sample, leading to high memory spikes, intensive disk I/O, and task failures due to out-of-memory errors. Simple static resource allocation methods struggle to handle the variability in per-chromosome RAM demands, resulting in poor resource utilization and long runtimes. In this work, we propose multiple mechanisms for adaptive, RAM-efficient parallelization of chromosome-level bioinformatics workflows. First, we develop a symbolic regression model that estimates per-chromosome memory consumption for a given task and introduces an interpolating bias to conservatively minimize over-allocation. Second, we present a dynamic scheduler that adaptively predicts RAM usage with a polynomial regression model, treating task packing as a Knapsack problem to optimally batch jobs based on predicted memory requirements. Additionally, we present a static scheduler that optimizes chromosome processing order to minimize peak memory while preserving throughput. Our proposed methods, evaluated on simulations and real-world genomic pipelines, provide new mechanisms to reduce memory overruns and balance load across threads. We thereby achieve faster end-to-end execution, showcasing the potential to optimize large-scale genomic workflows.
Authors: Strahinja Janjuesvic, Anna Baron Garcia, Sohrob Kazerounian
Abstract: Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests. However, existing approaches face trade-offs between generality and specialization, and practical deployments reveal challenges such as hallucinations, context limitations, and ethical concerns. In this work, we introduce a novel command & control (C2) architecture leveraging the Model Context Protocol (MCP) to coordinate distributed, adaptive reconnaissance agents covertly across networks. Notably, we find that our architecture not only improves goal-directed behavior of the system as whole, but also eliminates key host and network artifacts that can be used to detect and prevent command & control behavior altogether. We begin with a comprehensive review of state-of-the-art generative red teaming methods, from fine-tuned specialist models to modular or agentic frameworks, analyzing their automation capabilities against task-specific accuracy. We then detail how our MCP-based C2 can overcome current limitations by enabling asynchronous, parallel operations and real-time intelligence sharing without periodic beaconing. We furthermore explore advanced adversarial capabilities of this architecture, its detection-evasion techniques, and address dual-use ethical implications, proposing defensive measures and controlled evaluation in lab settings. Experimental comparisons with traditional C2 show drastic reductions in manual effort and detection footprint. We conclude with future directions for integrating autonomous exploitation, defensive LLM agents, predictive evasive maneuvers, and multi-agent swarms. The proposed MCP-enabled C2 framework demonstrates a significant step toward realistic, AI-driven red team operations that can simulate advanced persistent threats while informing the development of next-generation defensive systems.
Authors: KeFan Li, Mengfei Wang, Hengzhi Zhang, Zhichao Li, Yuan Yuan, Mu Li, Xiang Gao, Hailong Sun, Chunming Hu, Weifeng Lv
Abstract: Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accurate diagnostics, and strong verification signals. Existing agent-based and pipeline-based methods often rely on insufficient tests, which can lead to patches that satisfy verification but fail to fix the underlying defect. We present InfCode, an adversarial multi-agent framework for automated repository-level issue resolution. InfCode iteratively refines both tests and patches through adversarial interaction between a Test Patch Generator and a Code Patch Generator, while a Selector agent identifies the most reliable fix. The framework runs inside a containerized environment that supports realistic repository inspection, modification, and validation. Experiments on SWE-bench Lite and SWE-bench Verified using models such as DeepSeek-V3 and Claude 4.5 Sonnet show that InfCode consistently outperforms strong baselines. It achieves 79.4% performance on SWE-bench Verified, establishing a new state-of-the-art. We have released InfCode as an open-source project at https://github.com/Tokfinity/InfCode.
Authors: Qingao Dong, Mengfei Wang, Hengzhi Zhang, Zhichao Li, Yuan Yuan, Mu Li, Xiang Gao, Hailong Sun, Chunming Hu, Weifeng Lv
Abstract: Large language model (LLM) agents have recently shown strong performance on repository-level issue resolution, but existing systems are almost exclusively designed for Python and rely heavily on lexical retrieval and shallow code navigation. These approaches transfer poorly to C++ projects, where overloaded identifiers, nested namespaces, template instantiations, and deep control-flow structures make context retrieval and fault localization substantially more difficult. As a result, state-of-the-art Python-oriented agents show a drastic performance drop on the C++ subset of MultiSWE-bench. We introduce INFCODE-C++, the first C++-aware autonomous system for end-to-end issue resolution. The system combines two complementary retrieval mechanisms -- semantic code-intent retrieval and deterministic AST-structured querying -- to construct accurate, language-aware context for repair.These components enable precise localization and robust patch synthesis in large, statically typed C++ repositories. Evaluated on the \texttt{MultiSWE-bench-CPP} benchmark, INFCODE-C++ achieves a resolution rate of 25.58\%, outperforming the strongest prior agent by 10.85 percentage points and more than doubling the performance of MSWE-agent. Ablation and behavioral studies further demonstrate the critical role of semantic retrieval, structural analysis, and accurate reproduction in C++ issue resolution. INFCODE-C++ highlights the need for language-aware reasoning in multi-language software agents and establishes a foundation for future research on scalable, LLM-driven repair for complex, statically typed ecosystems.
Authors: Yiling Liu, Juncheng Dong, Chen Fu, Wei Shi, Ziyang Jiang, Zhigang Hua, David Carlson
Abstract: Estimating counterfactual outcomes from time-series observations is crucial for effective decision-making, e.g. when to administer a life-saving treatment, yet remains significantly challenging because (i) the counterfactual trajectory is never observed and (ii) confounders evolve with time and distort estimation at every step. To address these challenges, we propose a novel framework that synergistically integrates two complementary approaches: Sub-treatment Group Alignment (SGA) and Random Temporal Masking (RTM). Instead of the coarse practice of aligning marginal distributions of the treatments in latent space, SGA uses iterative treatment-agnostic clustering to identify fine-grained sub-treatment groups. Aligning these fine-grained groups achieves improved distributional matching, thus leading to more effective deconfounding. We theoretically demonstrate that SGA optimizes a tighter upper bound on counterfactual risk and empirically verify its deconfounding efficacy. RTM promotes temporal generalization by randomly replacing input covariates with Gaussian noises during training. This encourages the model to rely less on potentially noisy or spuriously correlated covariates at the current step and more on stable historical patterns, thereby improving its ability to generalize across time and better preserve underlying causal relationships. Our experiments demonstrate that while applying SGA and RTM individually improves counterfactual outcome estimation, their synergistic combination consistently achieves state-of-the-art performance. This success comes from their distinct yet complementary roles: RTM enhances temporal generalization and robustness across time steps, while SGA improves deconfounding at each specific time point.
Authors: Shuo Wang, Mengfan Teng, Yun Cheng, Lothar Thiele, Olga Saukh, Shuangshuang He, Yuanting Zhang, Jiang Zhang, Gangfeng Zhang, Xingyuan Yuan, Jingfang Fan
Abstract: High-resolution mapping of fine particulate matter (PM2.5) is a cornerstone of sustainable urbanism but remains critically hindered by the spatial sparsity of ground monitoring networks. While traditional data-driven methods attempt to bridge this gap using satellite Aerosol Optical Depth (AOD), they often suffer from severe, non-random data missingness (e.g., due to cloud cover or nighttime) and inversion biases. To overcome these limitations, this study proposes the Spatiotemporal Physics-Guided Inference Network (SPIN), a novel framework designed for inductive spatiotemporal kriging. Unlike conventional approaches, SPIN synergistically integrates domain knowledge into deep learning by explicitly modeling physical advection and diffusion processes via parallel graph kernels. Crucially, we introduce a paradigm-shifting training strategy: rather than using error-prone AOD as a direct input, we repurpose it as a spatial gradient constraint within the loss function. This allows the model to learn structural pollution patterns from satellite data while remaining robust to data voids. Validated in the highly polluted Beijing-Tianjin-Hebei and Surrounding Areas (BTHSA), SPIN achieves a new state-of-the-art with a Mean Absolute Error (MAE) of 9.52 ug/m^3, effectively generating continuous, physically plausible pollution fields even in unmonitored areas. This work provides a robust, low-cost, and all-weather solution for fine-grained environmental management.
Authors: Juncheng Dong, Yiling Liu, Ahmed Aloui, Vahid Tarokh, David Carlson
Abstract: Large language models (LLMs) have recently demonstrated impressive capabilities across a range of reasoning and generation tasks. However, research studies have shown that LLMs lack the ability to identify causal relationships, a fundamental cornerstone of human intelligence. We first conduct an exploratory investigation of LLMs' behavior when asked to perform a causal-discovery task and find that they mostly rely on the semantic meaning of variable names, ignoring the observation data. This is unsurprising, given that LLMs were never trained to process structural datasets. To first tackle this challenge, we prompt the LLMs with the outputs of established causal discovery algorithms designed for observational datasets. These algorithm outputs effectively serve as the sufficient statistics of the observation data. However, quite surprisingly, we find that prompting the LLMs with these sufficient statistics decreases the LLMs' performance in causal discovery. To address this current limitation, we propose CARE, a framework that enhances LLMs' causal-reasoning ability by teaching them to effectively utilize the outputs of established causal-discovery algorithms through supervised fine-tuning. Experimental results show that a finetuned Qwen2.5-1.5B model produced by CARE significantly outperforms both traditional causal-discovery algorithms and state-of-the-art LLMs with over a thousand times more parameters, demonstrating effective utilization of its own knowledge and the external algorithmic clues.
Authors: Dingkun Zhou, Patrick P. K. Chan, Hengxu Wu, Shikang Zheng, Ruiqi Huang, Yuanjie Zhao
Abstract: Deep neural networks used for human detection are highly vulnerable to adversarial manipulation, creating safety and privacy risks in real surveillance environments. Wearable attacks offer a realistic threat model, yet existing approaches usually optimize textures frame by frame and therefore fail to maintain concealment across long video sequences with motion, pose changes, and garment deformation. In this work, a sequence-level optimization framework is introduced to generate natural, printable adversarial textures for shirts, trousers, and hats that remain effective throughout entire walking videos in both digital and physical settings. Product images are first mapped to UV space and converted into a compact palette and control-point parameterization, with ICC locking to keep all colors printable. A physically based human-garment pipeline is then employed to simulate motion, multi-angle camera viewpoints, cloth dynamics, and illumination variation. An expectation-over-transformation objective with temporal weighting is used to optimize the control points so that detection confidence is minimized across whole sequences. Extensive experiments demonstrate strong and stable concealment, high robustness to viewpoint changes, and superior cross-model transferability. Physical garments produced with sublimation printing achieve reliable suppression under indoor and outdoor recordings, confirming real-world feasibility.
Authors: Mohamed Abdallah Salem, Hamdy Ahmed Ashur, Ahmed Elshinnawy
Abstract: Laser cutting is a widely adopted technology in material processing across various industries, but it generates a significant amount of dust, smoke, and aerosols during operation, posing a risk to both the environment and workers' health. Speckle sensing has emerged as a promising method to monitor the cutting process and identify material types in real-time. This paper proposes a material classification technique using a speckle pattern of the material's surface based on deep learning to monitor and control the laser cutting process. The proposed method involves training a convolutional neural network (CNN) on a dataset of laser speckle patterns to recognize distinct material types for safe and efficient cutting. Previous methods for material classification using speckle sensing may face issues when the color of the laser used to produce the speckle pattern is changed. Experiments conducted in this study demonstrate that the proposed method achieves high accuracy in material classification, even when the laser color is changed. The model achieved an accuracy of 98.30 % on the training set and 96.88% on the validation set. Furthermore, the model was evaluated on a set of 3000 new images for 30 different materials, achieving an F1-score of 0.9643. The proposed method provides a robust and accurate solution for material-aware laser cutting using speckle sensing.
Authors: Yang Wu, Yifan Zhang, Zhenxing Liang, Jian Cheng
Abstract: Two-stage Stochastic Programming (2SP) is a standard framework for modeling decision-making problems under uncertainty. While numerous methods exist, solving such problems with many scenarios remains challenging. Selecting representative scenarios is a practical method for accelerating solutions. However, current approaches typically rely on clustering or Monte Carlo sampling, failing to integrate scenario information deeply and overlooking the significant impact of the scenario order on solving time. To address these issues, we develop HGCN2SP, a novel model with a hierarchical graph designed for 2SP problems, encoding each scenario and modeling their relationships hierarchically. The model is trained in a reinforcement learning paradigm to utilize the feedback of the solver. The policy network is equipped with a hierarchical graph convolutional network for feature encoding and an attention-based decoder for scenario selection in proper order. Evaluation of two classic 2SP problems demonstrates that HGCN2SP provides high-quality decisions in a short computational time. Furthermore, HGCN2SP exhibits remarkable generalization capabilities in handling large-scale instances, even with a substantial number of variables or scenarios that were unseen during the training phase.
Authors: Kieron Kretschmar (Cadenza Labs), Walter Laurito (Cadenza Labs, FZI), Sharan Maiya (Cadenza Labs, University of Cambridge), Samuel Marks (Anthropic)
Abstract: Prior work has introduced techniques for detecting when large language models (LLMs) lie, that is, generating statements they believe are false. However, these techniques are typically validated in narrow settings that do not capture the diverse lies LLMs can generate. We introduce LIARS' BENCH, a testbed consisting of 72,863 examples of lies and honest responses generated by four open-weight models across seven datasets. Our settings capture qualitatively different types of lies and vary along two dimensions: the model's reason for lying and the object of belief targeted by the lie. Evaluating three black- and white-box lie detection techniques on LIARS' BENCH, we find that existing techniques systematically fail to identify certain types of lies, especially in settings where it's not possible to determine whether the model lied from the transcript alone. Overall, LIARS' BENCH reveals limitations in prior techniques and provides a practical testbed for guiding progress in lie detection.
Authors: Qing Zhang, Jing Huang, Mingyang Xu, Jun Rekimoto
Abstract: While mainstream robotics pursues metric precision and flawless performance, this paper explores the creative potential of a deliberately "lo-fi" approach. We present the "Semantic Glitch," a soft flying robotic art installation whose physical form, a 3D pixel style cloud, is a "physical glitch" derived from digital archaeology. We detail a novel autonomous pipeline that rejects conventional sensors like LiDAR and SLAM, relying solely on the qualitative, semantic understanding of a Multimodal Large Language Model to navigate. By authoring a bio-inspired personality for the robot through a natural language prompt, we create a "narrative mind" that complements the "weak," historically, loaded body. Our analysis begins with a 13-minute autonomous flight log, and a follow-up study statistically validates the framework's robustness for authoring quantifiably distinct personas. The combined analysis reveals emergent behaviors, from landmark-based navigation to a compelling "plan to execution" gap, and a character whose unpredictable, plausible behavior stems from a lack of precise proprioception. This demonstrates a lo-fi framework for creating imperfect companions whose success is measured in character over efficiency.
Authors: Gwen Yidou-Weng, Ian Li, Anji Liu, Oliver Broadrick, Guy Van den Broeck, Benjie Wang
Abstract: Controlled language generation conditions text on sequence-level constraints (for example, syntax, style, or safety). These constraints may depend on future tokens, which makes directly conditioning an autoregressive language model (LM) generally intractable. Prior work uses tractable surrogates such as hidden Markov models (HMMs) to approximate the distribution over continuations and adjust the model's next-token logits at decoding time. However, we find that these surrogates are often weakly context aware, which reduces query quality. We propose Learning to Look Ahead (LTLA), a hybrid approach that pairs the same base language model for rich prefix encoding with a fixed tractable surrogate model that computes exact continuation probabilities. Two efficiency pitfalls arise when adding neural context: (i) naively rescoring the prefix with every candidate next token requires a sweep over the entire vocabulary at each step, and (ii) predicting fresh surrogate parameters for each prefix, although tractable at a single step, forces recomputation of future probabilities for every new prefix and eliminates reuse. LTLA avoids both by using a single batched HMM update to account for all next-token candidates at once, and by conditioning only the surrogate's latent state prior on the LM's hidden representations while keeping the surrogate decoder fixed, so computations can be reused across prefixes. Empirically, LTLA attains higher conditional likelihood than an unconditional HMM, approximates continuation distributions for vision-language models where a standalone HMM cannot encode visual context, and improves constraint satisfaction at comparable fluency on controlled-generation tasks, with minimal inference overhead.
Authors: S\'ebastien Bubeck, Christian Coester, Ronen Eldan, Timothy Gowers, Yin Tat Lee, Alexandru Lupsasca, Mehtaab Sawhney, Robert Scherrer, Mark Sellke, Brian K. Spears, Derya Unutmaz, Kevin Weil, Steven Yin, Nikita Zhivotovskiy
Abstract: AI models like GPT-5 are an increasingly valuable tool for scientists, but many remain unaware of the capabilities of frontier AI. We present a collection of short case studies in which GPT-5 produced new, concrete steps in ongoing research across mathematics, physics, astronomy, computer science, biology, and materials science. In these examples, the authors highlight how AI accelerated their work, and where it fell short; where expert time was saved, and where human input was still key. We document the interactions of the human authors with GPT-5, as guiding examples of fruitful collaboration with AI. Of note, this paper includes four new results in mathematics (carefully verified by the human authors), underscoring how GPT-5 can help human mathematicians settle previously unsolved problems. These contributions are modest in scope but profound in implication, given the rate at which frontier AI is progressing.
Authors: Shreyansh Jain, Madhav Singhvi, Shreya Rahul Jain, Pranav S, Dishaa Lokesh, Naren Chittibabu, Akash Anandhan
Abstract: Conventional Applicant Tracking Systems (ATS) tend to be inflexible keyword-matchers, and deny gifted candidates a role due to a few minor semantic mismatches. This article describes a new two-step process to design a more refined resume evaluation model based on a small language model (<600M parameters) that is finetuned using GRPO on a custom reward function. To begin with, Supervised Fine-Tuning (SFT) was used to build a solid baseline model. Second, this SFT model was also optimized with the help of Reinforcement Learning (RL) through GRPO under the guidance of a new, multi-component reward function that can holistically assess candidates beyond simple keyword matching. We indicate that the RL application presents a critical problem of reward hacking due to the initial experiments of aggressive penalties, which produces faulty, excessively negative model behaviors. We have overcome this challenge by refining the reward function repeatedly and training hyperparameters into a stable "gentle polishing process" of the reward function. Our resulting GRPO-polished model demonstrates significant real-world efficacy, achieving a final accuracy of 91% on unseen test data. The model shows a strong ability to correctly identify qualified candidates (recall of 0.85 for the 'SELECTED' class) while also showing exceptional precision (1.0), confirming its reliability. These results indicate that a properly executed, two-step fine-tuning procedure can indeed effectively refine a small language model to be able to conduct fine-tuned and human-like candidate scoring, overcoming the drawbacks of both traditional ATS and naive RL usage.
Authors: Sungbin Moon, Jiho Park, Suyoung Hwang, Donghyun Koh, Seunghyun Moon, Minhyeong Lee
Abstract: Modern data processing workflows frequently encounter ragged data: collections with variable-length elements that arise naturally in domains like natural language processing, scientific measurements, and autonomous AI agents. Existing workflow engines lack native support for tracking the shapes and dependencies inherent to ragged data, forcing users to manage complex indexing and dependency bookkeeping manually. We present Operon, a Rust-based workflow engine that addresses these challenges through a novel formalism of named dimensions with explicit dependency relations. Operon provides a domain-specific language where users declare pipelines with dimension annotations that are statically verified for correctness, while the runtime system dynamically schedules tasks as data shapes are incrementally discovered during execution. We formalize the mathematical foundation for reasoning about partial shapes and prove that Operon's incremental construction algorithm guarantees deterministic and confluent execution in parallel settings. The system's explicit modeling of partially-known states enables robust persistence and recovery mechanisms, while its per-task multi-queue architecture achieves efficient parallelism across heterogeneous task types. Empirical evaluation demonstrates that Operon outperforms an existing workflow engine with 14.94x baseline overhead reduction while maintaining near-linear end-to-end output rates as workloads scale, making it particularly suitable for large-scale data generation pipelines in machine learning applications.
Authors: Meihua Zhou, Liping Yu, Jiawei Cai, Wai Kin Fung, Ruiguo Hu, Jiarui Zhao, Wenzhuo Liu, Nan Wan
Abstract: Hyperspectral image (HSI) classification typically involves large-scale data and computationally intensive training, which limits the practical deployment of deep learning models in real-world remote sensing tasks. This study introduces SpectralTrain, a universal, architecture-agnostic training framework that enhances learning efficiency by integrating curriculum learning (CL) with principal component analysis (PCA)-based spectral downsampling. By gradually introducing spectral complexity while preserving essential information, SpectralTrain enables efficient learning of spectral -- spatial patterns at significantly reduced computational costs. The framework is independent of specific architectures, optimizers, or loss functions and is compatible with both classical and state-of-the-art (SOTA) models. Extensive experiments on three benchmark datasets -- Indian Pines, Salinas-A, and the newly introduced CloudPatch-7 -- demonstrate strong generalization across spatial scales, spectral characteristics, and application domains. The results indicate consistent reductions in training time by 2-7x speedups with small-to-moderate accuracy deltas depending on backbone. Its application to cloud classification further reveals potential in climate-related remote sensing, emphasizing training strategy optimization as an effective complement to architectural design in HSI models. Code is available at https://github.com/mh-zhou/SpectralTrain.
Authors: Vu Van Than
Abstract: Traditional threat modeling remains reactive-focused on known TTPs and past incident data, while threat prediction and forecasting frameworks are often disconnected from operational or architectural artifacts. This creates a fundamental weakness: the most serious cyber threats often do not arise from what is known, but from what is assumed, overlooked, or not yet conceived, and frequently originate from the future, such as artificial intelligence, information warfare, and supply chain attacks, where adversaries continuously develop new exploits that can bypass defenses built on current knowledge. To address this mental gap, this paper introduces the theory and methodology of Future-Back Threat Modeling (FBTM). This predictive approach begins with envisioned future threat states and works backward to identify assumptions, gaps, blind spots, and vulnerabilities in the current defense architecture, providing a clearer and more accurate view of impending threats so that we can anticipate their emergence and shape the future we want through actions taken now. The proposed methodology further aims to reveal known unknowns and unknown unknowns, including tactics, techniques, and procedures that are emerging, anticipated, and plausible. This enhances the predictability of adversary behavior, particularly under future uncertainty, helping security leaders make informed decisions today that shape more resilient security postures for the future.
Authors: Haohui Chen, Zhiyong Chen, Aoxiang Liu, Wentuo Fang
Abstract: Deterministic policy gradient algorithms for continuous control suffer from value estimation biases that degrade performance. While double critics reduce such biases, the exploration potential of double actors remains underexplored. Building on temporal-difference error-driven regularization (TDDR), a double actor-critic framework, this work introduces enhanced methods to achieve flexible bias control and stronger representation learning. We propose three convex combination strategies, symmetric and asymmetric, that balance pessimistic estimates to mitigate overestimation and optimistic exploration via double actors to alleviate underestimation. A single hyperparameter governs this mechanism, enabling tunable control across the bias spectrum. To further improve performance, we integrate augmented state and action representations into the actor and critic networks. Extensive experiments show that our approach consistently outperforms benchmarks, demonstrating the value of tunable bias and revealing that both overestimation and underestimation can be exploited differently depending on the environment.
Authors: Shao-Jun Xia, Huixin Zhang, Zhengzhong Tu
Abstract: In large language models (LLM), in-context learning (ICL) refers to performing new tasks by conditioning on small demonstrations provided in the input context. Recent advances in visual in-context learning (VICL) demonstrate promising capabilities for solving downstream tasks by unified vision-language models (VLMs). When the visual prompt and the target images originate from different visual tasks, can VLMs still enable VICL? In the paper, we propose a fully collaborative pipeline, i.e. T2T-VICL, for VLMs to investigate the potential of cross-task VICL. Fundamentally, we design a mechanism to generate and select text prompts that best implicitly describe the differences between two distinct low-level vision tasks, and construct the first cross-task VICL dataset. Building upon this, we propose a novel inference framework that combines perceptual score-based reasoning with traditional evaluation metrics to perform cross-task VICL. Our approach achieves top-tier results across nine cross-task scenarios and second-tier performance in ten additional scenarios, unlocking the boundaries of cross-task VICL within VLMs.
Authors: Qing Zhang, Bing Xu, Xudong Zhang, Yifan Shi, Yang Li, Chen Zhang, Yik Chung Wu, Ngai Wong, Yijie Chen, Hong Dai, Xiansen Chen, Mian Zhang
Abstract: The remarkable performance of Large Language Models (LLMs) highly relies on crafted prompts. However, manual prompt engineering is a laborious process, creating a core bottleneck for practical application of LLMs. This phenomenon has led to the emergence of a new research area known as Automatic Prompt Optimization (APO), which develops rapidly in recent years. Existing APO methods such as those based on evolutionary algorithms or trial-and-error approaches realize an efficient and accurate prompt optimization to some extent. However, those researches focus on a single model or algorithm for the generation strategy and optimization process, which limits their performance when handling complex tasks. To address this, we propose a novel framework called Ensemble Learning based Prompt Optimization (ELPO) to achieve more accurate and robust results. Motivated by the idea of ensemble learning, ELPO conducts voting mechanism and introduces shared generation strategies along with different search methods for searching superior prompts. Moreover, ELPO creatively presents more efficient algorithms for the prompt generation and search process. Experimental results demonstrate that ELPO outperforms state-of-the-art prompt optimization methods across different tasks, e.g., improving F1 score by 7.6 on ArSarcasm dataset.
Authors: Xuan-Quang Phan, Tan-Ha Mai, Thai-Duy Dinh, Minh-Thuan Nguyen, Lam-Son L\^e
Abstract: Interacting with relational databases remains challenging for users across different expertise levels, particularly when composing complex analytical queries or performing administrative tasks. Existing systems typically address either natural language querying or narrow aspects of database administration, lacking a unified and intelligent interface for general-purpose database interaction. We introduce AskDB, a large language model powered agent designed to bridge this gap by supporting both data analysis and administrative operations over SQL databases through natural language. Built on Gemini 2, AskDB integrates two key innovations: a dynamic schema-aware prompting mechanism that effectively incorporates database metadata, and a task decomposition framework that enables the agent to plan and execute multi-step actions. These capabilities allow AskDB to autonomously debug derived SQL, retrieve contextual information via real-time web search, and adaptively refine its responses. We evaluate AskDB on a widely used Text-to-SQL benchmark and a curated set of DBA tasks, demonstrating strong performance in both analytical and administrative scenarios. Our results highlight the potential of AskDB as a unified and intelligent agent for relational database systems, offering an intuitive and accessible experience for end users.
Authors: Shujie Yang, Xuzhe Zhao, Yuqi Zhang, Yansong Tang, Kaichen Dong
Abstract: Metamaterials, known for their ability to manipulate light at subwavelength scales, face significant design challenges due to their complex and sophisticated structures. Consequently, deep learning has emerged as a powerful tool to streamline their design process. Reconfigurable multi-state metamaterials (RMMs) with adjustable parameters can switch their optical characteristics between different states upon external stimulation, leading to numerous applications. However, existing deep learning-based inverse design methods fall short in considering reconfigurability with multi-state switching. To address this challenge, we propose CoSP, an intelligent inverse design method based on contrastive pretrained large language model (LLM). By performing contrastive pretraining on multi-state spectrum, a well-trained spectrum encoder capable of understanding the spectrum is obtained, and it subsequently interacts with a pretrained LLM. This approach allows the model to preserve its linguistic capabilities while also comprehending Maxwell's Equations, enabling it to describe material structures with target optical properties in natural language. Our experiments demonstrate that CoSP can design corresponding thin-film metamaterial structures for arbitrary multi-state, multi-band optical responses, showing great potentials in the intelligent design of RMMs for versatile applications.
Authors: Zhijie Zhong, Zhiwen Yu, Kaixiang Yang, C. L. Philip Chen
Abstract: Time series anomaly detection (TSAD) is a critical data mining task often constrained by label scarcity. Consequently, current research predominantly focuses on Unsupervised Time-series Anomaly Detection (UTAD), relying on complex architectures to model normal data distributions. However, this approach often overlooks the significant performance gains available from limited anomaly labels achievable in practical scenarios. This paper challenges the premise that architectural complexity is the optimal path for TSAD. We conduct the first methodical comparison between supervised and unsupervised paradigms and introduce STAND, a streamlined supervised baseline. Extensive experiments on five public datasets demonstrate that: (1) Labels matter more than models: under a limited labeling budget, simple supervised models significantly outperform complex state-of-the-art unsupervised methods; (2) Supervision yields higher returns: the performance gain from minimal supervision far exceeds that from architectural innovations; and (3) Practicality: STAND exhibits superior prediction consistency and anomaly localization compared to unsupervised counterparts. These findings advocate for a data-centric shift in TSAD research, emphasizing label utilization over purely algorithmic complexity. The code is publicly available at https://github.com/EmorZz1G/STAND.
Authors: Dabiao Ma, Ziming Dai, Zhimin Xin, Shu Wang, Ye Wang, Haojun Fei
Abstract: In the field of large models (LMs) for natural language processing (NLP) and computer vision (CV), Parameter-Efficient Fine-Tuning (PEFT) has emerged as a resource-efficient method that modifies a limited number of parameters while keeping the pretrained weights fixed. This paper investigates the traditional PEFT approach, which applies modifications to all position indices, and questions its necessity. We introduce a new paradigm called Token-Selective PEFT (TS-PEFT), in which a function S selectively applies PEFT modifications to a subset of position indices, potentially enhancing performance on downstream tasks. Our experimental results reveal that the indiscriminate application of PEFT to all indices is not only superfluous, but may also be counterproductive. This study offers a fresh perspective on PEFT, advocating for a more targeted approach to modifications and providing a framework for future research to optimize the fine-tuning process for large models.
Authors: Yi Yang, Xueqi Li, Yiyang Chen, Jin Song, Yihan Wang, Zipeng Xiao, Jiadi Su, You Qiaoben, Pengfei Liu, Zhijie Deng
Abstract: Recent advances in Vision-Language-Action (VLA) models demonstrate that visual signals can effectively complement sparse action supervisions. However, letting VLA directly predict high-dimensional visual states can distribute model capacity and incur prohibitive training cost, while compressing visual states into more compact supervisory signals inevitably incurs information bottlenecks. Moreover, existing methods often suffer from poor comprehension and reasoning capabilities due to the neglect of language supervision. This paper introduces Mantis, a novel framework featuring a Disentangled Visual Foresight (DVF) to tackle these issues. Specifically, Mantis decouples visual foresight prediction from the backbone with the combination of meta queries and a diffusion Transformer (DiT) head. With the current visual state provided to the DiT via a residual connection, a simple next-state prediction objective enables the meta queries to automatically capture the latent actions that delineate the visual trajectory, and hence boost the learning of explicit actions. The disentanglement reduces the burden of the VLA backbone, enabling it to maintain comprehension and reasoning capabilities through language supervision. Empirically, pretrained on human manipulation videos, robot demonstrations, and image-text pairs, Mantis achieves a 96.7% success rate on LIBERO benchmark after fine-tuning, surpassing powerful baselines while exhibiting high convergence speed. Real-world evaluations show that Mantis outperforms $\pi_{0.5}$, a leading open-source VLA model, particularly in instruction-following capability, generalization to unseen instructions, and reasoning ability. Code and weights are released to support the open-source community.
Authors: Rongxin Cheng, Kai Zhou, Xingda Wei, Siyuan Liu, Mingcong Han, Mingjing Ai, Yeju Zhou, Baoquan Zhong, Wencong Xiao, Xin Liu, Rong Chen, Haibo Chen
Abstract: Rollout dominates the training time in large language model (LLM) post-training, where the trained model is used to generate tokens given a batch of prompts. SpecActor achieves fast rollout with speculative decoding that deploys a fast path (e.g., a smaller model) to accelerate the unparallelizable generation, while the correctness is guaranteed by fast parallel verification of the outputs with the original model. SpecActor addresses two foundational challenges in speculative rollout by (1) a \emph{dynamic decoupled speculation} execution method that maximizes the GPU computational efficiency to realize speedup for large-batch execution -- a configuration common in training but unfriendly to speculative execution and (2) a \emph{dynamic Best-of-N speculation} method that selects and combines different drafting methods according to the rollout progress. It substantially improves the speculation accuracy even when the best drafting method is unknown a priori, meanwhile without requiring adding extra computation resources. {\sys} is {1.3--1.7}\,$\times$ faster than common post-training baselines, and is {1.3--1.5}\,$\times$ faster compared to naively adopting speculative decoding for rollout.
Authors: Yuping Yan, Yuhan Xie, Yinxin Zhang, Lingjuan Lyu, Yaochu Jin
Abstract: Vision-Language-Action models (VLAs) have recently demonstrated remarkable progress in embodied environments, enabling robots to perceive, reason, and act through unified multimodal understanding. Despite their impressive capabilities, the adversarial robustness of these systems remains largely unexplored, especially under realistic multimodal and black-box conditions. Existing studies mainly focus on single-modality perturbations and overlook the cross-modal misalignment that fundamentally affects embodied reasoning and decision-making. In this paper, we introduce VLA-Fool, a comprehensive study of multimodal adversarial robustness in embodied VLA models under both white-box and black-box settings. VLA-Fool unifies three levels of multimodal adversarial attacks: (1) textual perturbations through gradient-based and prompt-based manipulations, (2) visual perturbations via patch and noise distortions, and (3) cross-modal misalignment attacks that intentionally disrupt the semantic correspondence between perception and instruction. We further incorporate a VLA-aware semantic space into linguistic prompts, developing the first automatically crafted and semantically guided prompting framework. Experiments on the LIBERO benchmark using a fine-tuned OpenVLA model reveal that even minor multimodal perturbations can cause significant behavioral deviations, demonstrating the fragility of embodied multimodal alignment.
Authors: Wei Zhao, Zhe Li, Yige Li, Jun Sun
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial attacks through visual inputs despite robust textual safety mechanisms. These vulnerabilities arise from two core weaknesses: the continuous nature of visual representations, which allows for gradient-based attacks, and the inadequate transfer of text-based safety mechanisms to visual content. We introduce Q-MLLM, a novel architecture that integrates two-level vector quantization to create a discrete bottleneck against adversarial attacks while preserving multimodal reasoning capabilities. By discretizing visual representations at both pixel-patch and semantic levels, Q-MLLM blocks attack pathways and bridges the cross-modal safety alignment gap. Our two-stage training methodology ensures robust learning while maintaining model utility. Experiments demonstrate that Q-MLLM achieves significantly better defense success rate against both jailbreak attacks and toxic image attacks than existing approaches. Notably, Q-MLLM achieves perfect defense success rate (100\%) against jailbreak attacks except in one arguable case, while maintaining competitive performance on multiple utility benchmarks with minimal inference overhead. This work establishes vector quantization as an effective defense mechanism for secure multimodal AI systems without requiring expensive safety-specific fine-tuning or detection overhead. Code is available at https://github.com/Amadeuszhao/QMLLM.
Authors: Xingtao Zhao, Hao Peng, Dingli Su, Xianghua Zeng, Chunyang Liu, Jinzhi Liao, Philip S. Yu
Abstract: Reliable uncertainty quantification (UQ) is essential for deploying large language models (LLMs) in safety-critical scenarios, as it enables them to abstain from responding when uncertain, thereby avoiding hallucinating falsehoods. However, state-of-the-art UQ methods primarily rely on semantic probability distributions or pairwise distances, overlooking latent semantic structural information that could enable more precise uncertainty estimates. This paper presents Semantic Structural Entropy (SeSE), a principled UQ framework that quantifies the inherent semantic uncertainty of LLMs from a structural information perspective for hallucination detection. Specifically, to effectively model semantic spaces, we first develop an adaptively sparsified directed semantic graph construction algorithm that captures directional semantic dependencies while automatically pruning unnecessary connections that introduce negative interference. We then exploit latent semantic structural information through hierarchical abstraction: SeSE is defined as the structural entropy of the optimal semantic encoding tree, formalizing intrinsic uncertainty within semantic spaces after optimal compression. A higher SeSE value corresponds to greater uncertainty, indicating that LLMs are highly likely to generate hallucinations. In addition, to enhance fine-grained UQ in long-form generation -- where existing methods often rely on heuristic sample-and-count techniques -- we extend SeSE to quantify the uncertainty of individual claims by modeling their random semantic interactions, providing theoretically explicable hallucination detection. Extensive experiments across 29 model-dataset combinations show that SeSE significantly outperforms advanced UQ baselines, including strong supervised methods and the recently proposed KLE.
Authors: Zhen Sun, Zongmin Zhang, Deqi Liang, Han Sun, Yule Liu, Yun Shen, Xiangshan Gao, Yilong Yang, Shuai Liu, Yutao Yue, Xinlei He
Abstract: As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit scalability. Compared with prior attacks, we propose Game-Theory Attack (GTA), an scalable black-box jailbreak framework. Concretely, we formalize the attacker's interaction against safety-aligned LLMs as a finite-horizon, early-stoppable sequential stochastic game, and reparameterize the LLM's randomized outputs via quantal response. Building on this, we introduce a behavioral conjecture "template-over-safety flip": by reshaping the LLM's effective objective through game-theoretic scenarios, the originally safety preference may become maximizing scenario payoffs within the template, which weakens safety constraints in specific contexts. We validate this mechanism with classical game such as the disclosure variant of the Prisoner's Dilemma, and we further introduce an Attacker Agent that adaptively escalates pressure to increase the ASR. Experiments across multiple protocols and datasets show that GTA achieves over 95% ASR on LLMs such as Deepseek-R1, while maintaining efficiency. Ablations over components, decoding, multilingual settings, and the Agent's core model confirm effectiveness and generalization. Moreover, scenario scaling studies further establish scalability. GTA also attains high ASR on other game-theoretic scenarios, and one-shot LLM-generated variants that keep the model mechanism fixed while varying background achieve comparable ASR. Paired with a Harmful-Words Detection Agent that performs word-level insertions, GTA maintains high ASR while lowering detection under prompt-guard models. Beyond benchmarks, GTA jailbreaks real-world LLM applications and reports a longitudinal safety monitoring of popular HuggingFace LLMs.
Authors: Wei Xia, Zhi-Hong Deng
Abstract: With the rapid advancement of large language models (LLMs), their deployment in real-world applications has become increasingly widespread. LLMs are expected to deliver robust performance across diverse tasks, user preferences, and practical scenarios. However, as demands grow, ensuring that LLMs produce responses aligned with human intent remains a foundational challenge. In particular, aligning model behavior effectively and efficiently during inference, without costly retraining or extensive supervision, is both a critical requirement and a non-trivial technical endeavor. To address the challenge, we propose SDA (Steering-Driven Distribution Alignment), a training-free and model-agnostic alignment framework designed for open-source LLMs. SDA dynamically redistributes model output probabilities based on user-defined alignment instructions, enhancing alignment between model behavior and human intents without fine-tuning. The method is lightweight, resource-efficient, and compatible with a wide range of open-source LLMs. It can function independently during inference or be integrated with training-based alignment strategies. Moreover, SDA supports personalized preference alignment, enabling flexible control over the model response behavior. Empirical results demonstrate that SDA consistently improves alignment performance across 8 open-source LLMs with varying scales and diverse origins, evaluated on three key alignment dimensions, helpfulness, harmlessness, and honesty (3H). Specifically, SDA achieves average gains of 64.4% in helpfulness, 30% in honesty and 11.5% in harmlessness across the tested models, indicating its effectiveness and generalization across diverse models and application scenarios.
Authors: Jonathan Kamp, Lisa Beinborn, Antske Fokkens
Abstract: Human explanations of natural language, rationales, form a tool to assess whether models learn a label for the right reasons or rely on dataset-specific shortcuts. Sufficiency is a common metric for estimating the informativeness of rationales, but it provides limited insight into the effects of rationale information on model performance. We address this limitation by relating sufficiency to two modelling paradigms: the ability of models to identify which tokens are part of the rationale (through token classification) and the ability of improving model performance by incorporating rationales in the input (through attention regularisation). We find that highly informative rationales are not likely to help classify the instance correctly. Sufficiency conversely captures the classification impact of the non-rationalised context, which interferes with rationale information in the same input. We also find that incorporating rationale information in model inputs can boost cross-domain classification, but results are inconsistent per task and model type. Finally, sufficiency and token classification appear to be unrelated. These results exemplify the complexity of rationales, showing that metrics capable of systematically capturing this type of information merit further investigation.
Authors: Marcin Kostrzewa, Oleksii Furman, Roman Furman, Sebastian Tomczak, Maciej Zi\k{e}ba
Abstract: Foundation models have shown promise across various financial applications, yet their effectiveness for corporate bankruptcy prediction remains systematically unevaluated against established methods. We study bankruptcy forecasting using Llama-3.3-70B-Instruct and TabPFN, evaluated on large, highly imbalanced datasets of over one million company records from the Visegr\'ad Group. We provide the first systematic comparison of foundation models against classical machine learning baselines for this task. Our results show that models such as XGBoost and CatBoost consistently outperform foundation models across all prediction horizons. LLM-based approaches suffer from unreliable probability estimates, undermining their use in risk-sensitive financial settings. TabPFN, while competitive with simpler baselines, requires substantial computational resources with costs not justified by performance gains. These findings suggest that, despite their generality, current foundation models remain less effective than specialized methods for bankruptcy forecasting.
Authors: Ajith Anil Meera, Poppy Collis, Polina Arbuzova, Abi\'an Torres, Paul F Kinghorn, Ricardo Sanz, Pablo Lanillos
Abstract: Robots today often miss a key ingredient of truly intelligent behavior: the ability to reflect on their own cognitive processes and decisions. In humans, this self-monitoring or metacognition is crucial for learning, decision making and problem solving. For instance, they can evaluate how confident they are in performing a task, thus regulating their own behavior and allocating proper resources. Taking inspiration from neuroscience, we propose a robot metacognition architecture centered on confidence (a second-order judgment on decisions) and we demonstrate it on the use case of autonomous tool invention. We propose the use of confidence as a metacognitive measure within the robot decision making scheme. Confidence-informed robots can evaluate the reliability of their decisions, improving their robustness during real-world physical deployment. This form of robotic metacognition emphasizes embodied action monitoring as a means to achieve better informed decisions. We also highlight potential applications and research directions for robot metacognition.
Authors: Yidong Chai, Haoxin Liu, Jiaheng Xie, Chaopeng Wang, Xiao Fang
Abstract: Wearable sensor technologies and deep learning are transforming healthcare management. Yet, most health sensing studies focus narrowly on physical chronic diseases. This overlooks the critical need for joint assessment of comorbid physical chronic diseases and depression, which is essential for collaborative chronic care. We conceptualize multi-disease assessment, including both physical diseases and depression, as a multi-task learning (MTL) problem, where each disease assessment is modeled as a task. This joint formulation leverages inter-disease relationships to improve accuracy, but it also introduces the challenge of double heterogeneity: chronic diseases differ in their manifestation (disease heterogeneity), and patients with the same disease show varied patterns (patient heterogeneity). To address these issues, we first adopt existing techniques and propose a base method. Given the limitations of the base method, we further propose an Advanced Double Heterogeneity-based Multi-Task Learning (ADH-MTL) method that improves the base method through three innovations: (1) group-level modeling to support new patient predictions, (2) a decomposition strategy to reduce model complexity, and (3) a Bayesian network that explicitly captures dependencies while balancing similarities and differences across model components. Empirical evaluations on real-world wearable sensor data demonstrate that ADH-MTL significantly outperforms existing baselines, and each of its innovations is shown to be effective. This study contributes to health information systems by offering a computational solution for integrated physical and mental healthcare and provides design principles for advancing collaborative chronic disease management across the pre-treatment, treatment, and post-treatment phases.
Authors: Muhammad Aslanimoghanloo, Ahmed ElGazzar, Marcel van Gerven
Abstract: Clinical time series data from electronic health records and medical registries offer unprecedented opportunities to understand patient trajectories and inform medical decision-making. However, leveraging such data presents significant challenges due to irregular sampling, complex latent physiology, and inherent uncertainties in both measurements and disease progression. To address these challenges, we propose a generative modeling framework based on latent neural stochastic differential equations (SDEs) that views clinical time series as discrete-time partial observations of an underlying controlled stochastic dynamical system. Our approach models latent dynamics via neural SDEs with modality-dependent emission models, while performing state estimation and parameter learning through variational inference. This formulation naturally handles irregularly sampled observations, learns complex non-linear interactions, and captures the stochasticity of disease progression and measurement noise within a unified scalable probabilistic framework. We validate the framework on two complementary tasks: (i) individual treatment effect estimation using a simulated pharmacokinetic-pharmacodynamic (PKPD) model of lung cancer, and (ii) probabilistic forecasting of physiological signals using real-world intensive care unit (ICU) data from 12,000 patients. Results show that our framework outperforms ordinary differential equation and long short-term memory baseline models in accuracy and uncertainty estimation. These results highlight its potential for enabling precise, uncertainty-aware predictions to support clinical decision-making.
Authors: Ziyan Liu, Yeqiu Chen, Hongyi Cai, Tao Lin, Shuo Yang, Zheng Liu, Bo Zhao
Abstract: Vision-Language-Action (VLA) models have shown great promise for embodied AI, yet the heavy computational cost of processing continuous visual streams severely limits their real-time deployment. Token pruning (keeping salient visual tokens and dropping redundant ones) has emerged as an effective approach for accelerating Vision-Language Models (VLMs), offering a solution for efficient VLA. However, these VLM-specific token pruning methods select tokens based solely on semantic salience metrics (e.g., prefill attention), while overlooking the VLA's intrinsic dual-system nature of high-level semantic understanding and low-level action execution. Consequently, these methods bias token retention toward semantic cues, discard critical information for action generation, and significantly degrade VLA performance. To bridge this gap, we propose VLA-Pruner, a versatile plug-and-play VLA-specific token prune method that aligns with the dual-system nature of VLA models and exploits the temporal continuity in robot manipulation. Specifically, VLA-Pruner adopts a dual-level importance criterion for visual token retention: vision-language prefill attention for semantic-level relevance and action decode attention, estimated via temporal smoothing, for action-level importance. Based on this criterion, VLA-Pruner proposes a novel dual-level token selection strategy that adaptively preserves a compact, informative set of visual tokens for both semantic understanding and action execution under given compute budget. Experiments show that VLA-Pruner achieves state-of-the-art performance across multiple VLA architectures and diverse robotic tasks.
Authors: Andrew Gomes
Abstract: We investigate the processing of idiomatic expressions in transformer-based language models using a novel set of techniques for circuit discovery and analysis. First discovering circuits via a modified path patching algorithm, we find that idiom processing exhibits distinct computational patterns. We identify and investigate ``Idiom Heads,'' attention heads that frequently activate across different idioms, as well as enhanced attention between idiom tokens due to earlier processing, which we term ``augmented reception.'' We analyze these phenomena and the general features of the discovered circuits as mechanisms by which transformers balance computational efficiency and robustness. Finally, these findings provide insights into how transformers handle non-compositional language and suggest pathways for understanding the processing of more complex grammatical constructions.
Authors: Poushali Sengupta, Yan Zhang, Frank Eliassen, Sabita Maharjan
Abstract: Explainable AI (XAI) is increasingly essential as modern models become more complex and high-stakes applications demand transparency, trust, and regulatory compliance. Existing global attribution methods often incur high computational costs, lack stability under correlated inputs, and fail to scale efficiently to large or heterogeneous datasets. We address these gaps with \emph{ExCIR} (Explainability through Correlation Impact Ratio), a correlation-aware attribution score equipped with a lightweight transfer protocol that reproduces full-model rankings using only a fraction of the data. ExCIR quantifies sign-aligned co-movement between features and model outputs after \emph{robust centering} (subtracting a robust location estimate, e.g., median or mid-mean, from features and outputs). We further introduce \textsc{BlockCIR}, a \emph{groupwise} extension of ExCIR that scores \emph{sets} of correlated features as a single unit. By aggregating the same signed-co-movement numerators and magnitudes over predefined or data-driven groups, \textsc{BlockCIR} mitigates double-counting in collinear clusters (e.g., synonyms or duplicated sensors) and yields smoother, more stable rankings when strong dependencies are present. Across diverse text, tabular, signal, and image datasets, ExCIR shows trustworthy agreement with established global baselines and the full model, delivers consistent top-$k$ rankings across settings, and reduces runtime via lightweight evaluation on a subset of rows. Overall, ExCIR provides \emph{computationally efficient}, \emph{consistent}, and \emph{scalable} explainability for real-world deployment.
Authors: Sayak Mukherjee, Samrat Chatterjee, Emilie Purvine, Ted Fujimoto, Tegan Emerson
Abstract: Designing rewards for autonomous cyber attack and defense learning agents in a complex, dynamic environment is a challenging task for subject matter experts. We propose a large language model (LLM)-based reward design approach to generate autonomous cyber defense policies in a deep reinforcement learning (DRL)-driven experimental simulation environment. Multiple attack and defense agent personas were crafted, reflecting heterogeneity in agent actions, to generate LLM-guided reward designs where the LLM was first provided with contextual cyber simulation environment information. These reward structures were then utilized within a DRL-driven attack-defense simulation environment to learn an ensemble of cyber defense policies. Our results suggest that LLM-guided reward designs can lead to effective defense strategies against diverse adversarial behaviors.
Authors: Rongjie Liao, Junhao Qiu, Xin Chen, Xiaoping Li
Abstract: Customized static operator design has enabled widespread application of Evolutionary Algorithms (EAs), but their search performance is transient during iterations and prone to degradation. Dynamic operators aim to address this but typically rely on predefined designs and localized parameter control during the search process, lacking adaptive optimization throughout evolution. To overcome these limitations, this work leverages Large Language Models (LLMs) to perceive evolutionary dynamics and enable operator-level meta-evolution. The proposed framework, LLMs for Evolutionary Optimization (LLM4EO), comprises three components: knowledge-transfer-based operator design, evolution perception and analysis, and adaptive operator evolution. Firstly, initialization of operators is performed by transferring the strengths of classical operators via LLMs. Then, search preferences and potential limitations of operators are analyzed by integrating fitness performance and evolutionary features, accompanied by corresponding suggestions for improvement. Upon stagnation of population evolution, gene selection priorities of operators are dynamically optimized via improvement prompting strategies. This approach achieves co-evolution of populations and operators in the search, introducing a novel paradigm for enhancing the efficiency and adaptability of EAs. Finally, a series of validations on multiple benchmark datasets of the flexible job shop scheduling problem demonstrate that LLM4EO accelerates population evolution and outperforms both mainstream evolutionary programming and traditional EAs.
Authors: Zongcai Tan, Lan Wei, Dandan Zhang
Abstract: Precise pose estimation of optical microrobots is essential for enabling high-precision object tracking and autonomous biological studies. However, current methods rely heavily on large, high-quality microscope image datasets, which are difficult and costly to acquire due to the complexity of microrobot fabrication and the labour-intensive labelling. Digital twin systems offer a promising path for sim-to-real data augmentation, yet existing techniques struggle to replicate complex optical microscopy phenomena, such as diffraction artifacts and depth-dependent imaging.This work proposes a novel physics-informed deep generative learning framework that, for the first time, integrates wave optics-based physical rendering and depth alignment into a generative adversarial network (GAN), to synthesise high-fidelity microscope images for microrobot pose estimation efficiently. Our method improves the structural similarity index (SSIM) by 35.6% compared to purely AI-driven methods, while maintaining real-time rendering speeds (0.022 s/frame).The pose estimator (CNN backbone) trained on our synthetic data achieves 93.9%/91.9% (pitch/roll) accuracy, just 5.0%/5.4% (pitch/roll) below that of an estimator trained exclusively on real data. Furthermore, our framework generalises to unseen poses, enabling data augmentation and robust pose estimation for novel microrobot configurations without additional training data.
Authors: Carlos Boned Riera, David Romero Sanchez, Oriol Ramos Terrades
Abstract: In recent years, increasingly large models have achieved outstanding performance across CV tasks. However, these models demand substantial computational resources and storage, and their growing complexity limits our understanding of how they make decisions. Most of these architectures rely on the attention mechanism within Transformer-based designs. Building upon the connection between residual neural networks and ordinary differential equations (ODEs), we introduce ODE-ViT, a Vision Transformer reformulated as an ODE system that satisfies the conditions for well-posed and stable dynamics. Experiments on CIFAR-10 and CIFAR-100 demonstrate that ODE-ViT achieves stable, interpretable, and competitive performance with up to one order of magnitude fewer parameters, surpassing prior ODE-based Transformer approaches in classification tasks. We further propose a plug-and-play teacher-student framework in which a discrete ViT guides the continuous trajectory of ODE-ViT by treating the intermediate representations of the teacher as solutions of the ODE. This strategy improves performance by more than 10% compared to training a free ODE-ViT from scratch.
Authors: \"Ozay Ezerceli, Mahmoud El Hussieni, Selva Ta\c{s}, Reyhan Bayraktar, Fatma Bet\"ul Terzio\u{g}lu, Yusuf \c{C}elebi, Ya\u{g}{\i}z Asker
Abstract: Neural information retrieval systems excel in high-resource languages but remain underexplored for morphologically rich, lower-resource languages such as Turkish. Dense bi-encoders currently dominate Turkish IR, yet late-interaction models -- which retain token-level representations for fine-grained matching -- have not been systematically evaluated. We introduce TurkColBERT, the first comprehensive benchmark comparing dense encoders and late-interaction models for Turkish retrieval. Our two-stage adaptation pipeline fine-tunes English and multilingual encoders on Turkish NLI/STS tasks, then converts them into ColBERT-style retrievers using PyLate trained on MS MARCO-TR. We evaluate 10 models across five Turkish BEIR datasets covering scientific, financial, and argumentative domains. Results show strong parameter efficiency: the 1.0M-parameter colbert-hash-nano-tr is 600$\times$ smaller than the 600M turkish-e5-large dense encoder while preserving over 71\% of its average mAP. Late-interaction models that are 3--5$\times$ smaller than dense encoders significantly outperform them; ColmmBERT-base-TR yields up to +13.8\% mAP on domain-specific tasks. For production-readiness, we compare indexing algorithms: MUVERA+Rerank is 3.33$\times$ faster than PLAID and offers +1.7\% relative mAP gain. This enables low-latency retrieval, with ColmmBERT-base-TR achieving 0.54 ms query times under MUVERA. We release all checkpoints, configs, and evaluation scripts. Limitations include reliance on moderately sized datasets ($\leq$50K documents) and translated benchmarks, which may not fully reflect real-world Turkish retrieval conditions; larger-scale MUVERA evaluations remain necessary.
Authors: Jaime \'Alvarez Urue\~na, David Camacho, Javier Huertas Tato
Abstract: The rapid advancement of generative artificial intelligence has enabled the creation of synthetic images that are increasingly indistinguishable from authentic content, posing significant challenges for digital media integrity. This problem is compounded by the accelerated release cycle of novel generative models, which renders traditional detection approaches (reliant on periodic retraining) computationally infeasible and operationally impractical. This work proposes a novel two-stage detection framework designed to address the generalization challenge inherent in synthetic image detection. The first stage employs a vision deep learning model trained via supervised contrastive learning to extract discriminative embeddings from input imagery. Critically, this model was trained on a strategically partitioned subset of available generators, with specific architectures withheld from training to rigorously ablate cross-generator generalization capabilities. The second stage utilizes a k-nearest neighbors (k-NN) classifier operating on the learned embedding space, trained in a few-shot learning paradigm incorporating limited samples from previously unseen test generators. With merely 150 images per class in the few-shot learning regime, which are easily obtainable from current generation models, the proposed framework achieves an average detection accuracy of 91.3\%, representing a 5.2 percentage point improvement over existing approaches . For the source attribution task, the proposed approach obtains improvements of of 14.70\% and 4.27\% in AUC and OSCR respectively on an open set classification context, marking a significant advancement toward robust, scalable forensic attribution systems capable of adapting to the evolving generative AI landscape without requiring exhaustive retraining protocols.
Authors: Jiaheng Zhang, Daqiang Zhang
Abstract: The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint optimization of ranking and explanation can result in suboptimal compromises. To resolve this, we propose Prism, a novel decoupled framework that rigorously separates the recommendation process into a dedicated ranking stage and an explanation generation stage. Inspired by knowledge distillation, Prism leverages a powerful teacher LLM (e.g., FLAN-T5-XXL) as an Oracle to produce high-fidelity explanatory knowledge. A compact, fine-tuned student model (e.g., BART-Base), the Prism, then specializes in synthesizing this knowledge into personalized explanations. This decomposition ensures that each component is optimized for its specific objective, eliminating inherent conflicts in coupled models. Extensive experiments on benchmark datasets demonstrate that our 140M-parameter Prism model significantly outperforms its 11B-parameter teacher in human evaluations of faithfulness and personalization, while achieving a 24 times speedup and a 10 times reduction in memory consumption during inference. These results validate that decoupling, coupled with targeted distillation, provides an efficient and effective pathway to high-quality explainable recommendation.
Authors: Zachary Ellis, Jared Joselowitz, Yash Deo, Yajie He, Anna Kalygina, Aisling Higham, Mana Rahimzadeh, Yan Jia, Ibrahim Habli, Ernest Lim
Abstract: As Automatic Speech Recognition (ASR) is increasingly deployed in clinical dialogue, standard evaluations still rely heavily on Word Error Rate (WER). This paper challenges that standard, investigating whether WER or other common metrics correlate with the clinical impact of transcription errors. We establish a gold-standard benchmark by having expert clinicians compare ground-truth utterances to their ASR-generated counterparts, labeling the clinical impact of any discrepancies found in two distinct doctor-patient dialogue datasets. Our analysis reveals that WER and a comprehensive suite of existing metrics correlate poorly with the clinician-assigned risk labels (No, Minimal, or Significant Impact). To bridge this evaluation gap, we introduce an LLM-as-a-Judge, programmatically optimized using GEPA to replicate expert clinical assessment. The optimized judge (Gemini-2.5-Pro) achieves human-comparable performance, obtaining 90% accuracy and a strong Cohen's $\kappa$ of 0.816. This work provides a validated, automated framework for moving ASR evaluation beyond simple textual fidelity to a necessary, scalable assessment of safety in clinical dialogue.
Authors: Asmita S. Thool, Sourodeep Roy, Prahalad Kanti Barman, Kartick Biswas, Pavan Nukala, Abhishek Misra, Saptarshi Das, and Bhaswar Chakrabarti
Abstract: In this study, we design a reservoir computing (RC) network by exploiting short- and long-term memory dynamics in Au/Ti/MoS$_2$/Au memristive devices. The temporal dynamics is engineered by controlling the thickness of the Chemical Vapor Deposited (CVD) MoS$_2$ films. Devices with a monolayer (1L)-MoS$_2$ film exhibit volatile (short-term memory) switching dynamics. We also report non-volatile resistance switching with excellent uniformity and analog behavior in conductance tuning for the multilayer (ML) MoS$_2$ memristive devices. We correlate this performance with trap-assisted space-charge limited conduction (SCLC) mechanism, leading to a bulk-limited resistance switching behavior. Four-bit reservoir states are generated using volatile memristors. The readout layer is implemented with an array of nonvolatile synapses. This small RC network achieves 89.56\% precision in a spoken-digit recognition task and is also used to analyze a nonlinear time series equation.
Authors: Misaal Khan, Mayank Vatsa, Kuldeep Singh, Richa Singh
Abstract: Child malnutrition remains a global crisis, yet existing screening methods are laborious and poorly scalable, hindering early intervention. In this work, we present NutriScreener, a retrieval-augmented, multi-pose graph attention network that combines CLIP-based visual embeddings, class-boosted knowledge retrieval, and context awareness to enable robust malnutrition detection and anthropometric prediction from children's images, simultaneously addressing generalizability and class imbalance. In a clinical study, doctors rated it 4.3/5 for accuracy and 4.6/5 for efficiency, confirming its deployment readiness in low-resource settings. Trained and tested on 2,141 children from AnthroVision and additionally evaluated on diverse cross-continent populations, including ARAN and an in-house collected CampusPose dataset, it achieves 0.79 recall, 0.82 AUC, and significantly lower anthropometric RMSEs, demonstrating reliable measurement in unconstrained pediatric settings. Cross-dataset results show up to 25% recall gain and up to 3.5 cm RMSE reduction using demographically matched knowledge bases. NutriScreener offers a scalable and accurate solution for early malnutrition detection in low-resource environments.
Authors: Fares Fourati, Mohamed-Slim Alouini, Vaneet Aggarwal
Abstract: We propose ECPv2, a scalable and theoretically grounded algorithm for global optimization of Lipschitz-continuous functions with unknown Lipschitz constants. Building on the Every Call is Precious (ECP) framework, which ensures that each accepted function evaluation is potentially informative, ECPv2 addresses key limitations of ECP, including high computational cost and overly conservative early behavior. ECPv2 introduces three innovations: (i) an adaptive lower bound to avoid vacuous acceptance regions, (ii) a Worst-m memory mechanism that restricts comparisons to a fixed-size subset of past evaluations, and (iii) a fixed random projection to accelerate distance computations in high dimensions. We theoretically show that ECPv2 retains ECP's no-regret guarantees with optimal finite-time bounds and expands the acceptance region with high probability. We further empirically validate these findings through extensive experiments and ablation studies. Using principled hyperparameter settings, we evaluate ECPv2 across a wide range of high-dimensional, non-convex optimization problems. Across benchmarks, ECPv2 consistently matches or outperforms state-of-the-art optimizers, while significantly reducing wall-clock time.
Authors: Kexin Zhao, Ken Forbus
Abstract: Word sense disambiguation is a fundamental challenge in natural language understanding. Current methods are primarily aimed at coarse-grained representations (e.g. WordNet synsets or FrameNet frames) and require hand-annotated training data to construct. This makes it difficult to automatically disambiguate richer representations (e.g. built on OpenCyc) that are needed for sophisticated inference. We propose a method that uses statistical language models as oracles for disambiguation that does not require any hand-annotation of training data. Instead, the multiple candidate meanings generated by a symbolic NLU system are converted into distinguishable natural language alternatives, which are used to query an LLM to select appropriate interpretations given the linguistic context. The selected meanings are propagated back to the symbolic NLU system. We evaluate our method against human-annotated gold answers to demonstrate its effectiveness.
Authors: Gaspard Ohlmann, Edwin Hamel-De le Court, Francesco Belardinelli
Abstract: Ensuring that agents satisfy safety specifications can be crucial in safety-critical environments. While methods exist for controller synthesis with safe temporal specifications, most existing methods restrict safe temporal specifications to probabilistic-avoidance constraints. Formal methods typically offer more expressive ways to express safety in probabilistic systems, such as Probabilistic Computation Tree Logic (PCTL) formulas. Thus, in this paper, we develop a new approach that supports more general temporal properties expressed in PCTL. Our contribution is twofold. First, we develop a theoretical framework for the Synthesis of safe-PCTL specifications. We show how the reducing global specification satisfaction to local constraints, and define CPCTL, a fragment of safe-PCTL. We demonstrate how the expressiveness of CPCTL makes it a relevant fragment for the Synthesis Problem. Second, we leverage these results and propose a new Value Iteration-based algorithm to solve the synthesis problem for these more general temporal properties, and we prove the soundness and completeness of our method.
Authors: Diaeddin Rimawi
Abstract: Cyber-physical systems (CPS) combine computational and physical components. Online Collaborative AI System (OL-CAIS) is a type of CPS that learn online in collaboration with humans to achieve a common goal, which makes it vulnerable to disruptive events that degrade performance. Decision-makers must therefore restore performance while limiting energy impact, creating a trade-off between resilience and greenness. This research addresses how to balance these two properties in OL-CAIS. It aims to model resilience for automatic state detection, develop agent-based policies that optimize the greenness-resilience trade-off, and understand catastrophic forgetting to maintain performance consistency. We model OL-CAIS behavior through three operational states: steady, disruptive, and final. To support recovery during disruptions, we introduce the GResilience framework, which provides recovery strategies through multi-objective optimization (one-agent), game-theoretic decision-making (two-agent), and reinforcement learning (RL-agent). We also design a measurement framework to quantify resilience and greenness. Empirical evaluation uses real and simulated experiments with a collaborative robot learning object classification from human demonstrations. Results show that the resilience model captures performance transitions during disruptions, and that GResilience policies improve green recovery by shortening recovery time, stabilizing performance, and reducing human dependency. RL-agent policies achieve the strongest results, although with a marginal increase in CO2 emissions. We also observe catastrophic forgetting after repeated disruptions, while our policies help maintain steadiness. A comparison with containerized execution shows that containerization cuts CO2 emissions by half. Overall, this research provides models, metrics, and policies that ensure the green recovery of OL-CAIS.
Authors: Boshen Xu, Zihan Xiao, Jiaze Li, Jianzhong Ju, Zhenbo Luo, Jian Luan, Qin Jin
Abstract: We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handling extended temporal contexts. To this end, TimeViper adopts a hybrid Mamba-Transformer backbone that combines the efficiency of state-space models with the expressivity of attention mechanisms. Through this hybrid design, we reveal the vision-to-text information aggregation phenomenon, where information progressively flows from vision tokens to text tokens across increasing LLM depth, resulting in severe vision token redundancy. Motivated by this observation, we propose TransV, a token information transfer module that transfers and compresses vision tokens into instruction tokens while maintaining multimodal understanding capabilities. This design enables TimeViper to process hour-long videos exceeding 10,000 frames. Extensive experiments across multiple benchmarks demonstrate that TimeViper competes with state-of-the-art models while extending frame numbers. We further analyze attention behaviors of both Mamba and Transformer layers, offering new insights into hybrid model interpretability. This work represents an initial step towards developing, interpreting, and compressing hybrid Mamba-Transformer architectures.
Authors: Satyam Gaba
Abstract: The early detection of wildfires is a critical environmental challenge, with timely identification of smoke plumes being key to mitigating large-scale damage. While deep neural networks have proven highly effective for localization tasks, the scarcity of large, annotated datasets for smoke detection limits their potential. In response, we leverage generative AI techniques to address this data limitation by synthesizing a comprehensive, annotated smoke dataset. We then explore unsupervised domain adaptation methods for smoke plume segmentation, analyzing their effectiveness in closing the gap between synthetic and real-world data. To further refine performance, we integrate advanced generative approaches such as style transfer, Generative Adversarial Networks (GANs), and image matting. These methods aim to enhance the realism of synthetic data and bridge the domain disparity, paving the way for more accurate and scalable wildfire detection models.
Authors: Satyam Gaba
Abstract: Object detection has been widely explored for class-balanced datasets such as COCO. However, real-world scenarios introduce the challenge of long-tailed distributions, where numerous categories contain only a few instances. This inherent class imbalance biases detection models towards the more frequent classes, degrading performance on rare categories. In this paper, we tackle the problem of long-tailed 2D object detection using the LVISv1 dataset, which consists of 1,203 categories and 164,000 images. We employ a two-stage Faster R-CNN architecture and propose enhancements to the Balanced Group Softmax (BAGS) framework to mitigate class imbalance. Our approach achieves a new state-of-the-art performance with a mean Average Precision (mAP) of 24.5%, surpassing the previous benchmark of 24.0%. Additionally, we hypothesize that tail class features may form smaller, denser clusters within the feature space of head classes, making classification challenging for regression-based classifiers. To address this issue, we explore metric learning to produce feature embeddings that are both well-separated across classes and tightly clustered within each class. For inference, we utilize a k-Nearest Neighbors (k-NN) approach to improve classification performance, particularly for rare classes. Our results demonstrate the effectiveness of these methods in advancing long-tailed object detection.
Authors: SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, Aohan Lin, Jiawei Liu, Ziqi Ma, Anushka Sagar, Bowen Song, Xiaodong Wang, Jianing Yang, Bowen Zhang, Piotr Doll\'ar, Georgia Gkioxari, Matt Feiszli, Jitendra Malik
Abstract: We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single image. SAM 3D excels in natural images, where occlusion and scene clutter are common and visual recognition cues from context play a larger role. We achieve this with a human- and model-in-the-loop pipeline for annotating object shape, texture, and pose, providing visually grounded 3D reconstruction data at unprecedented scale. We learn from this data in a modern, multi-stage training framework that combines synthetic pretraining with real-world alignment, breaking the 3D "data barrier". We obtain significant gains over recent work, with at least a 5:1 win rate in human preference tests on real-world objects and scenes. We will release our code and model weights, an online demo, and a new challenging benchmark for in-the-wild 3D object reconstruction.
Authors: Shihab Ahmed, El Houcine Bergou, Aritra Dutta, Yue Wang
Abstract: Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from unreliable reward improvements and slow convergence, due to high variance in gradient estimations. In this paper, we propose a universal reward profiling framework that can be seamlessly integrated with any policy gradient algorithm, where we selectively update the policy based on high-confidence performance estimations. We theoretically justify that our technique will not slow down the convergence of the baseline policy gradient methods, but with high probability, will result in stable and monotonic improvements of their performance. Empirically, on eight continuous-control benchmarks (Box2D and MuJoCo/PyBullet), our profiling yields up to 1.5x faster convergence to near-optimal returns, up to 1.75x reduction in return variance on some setups. Our profiling approach offers a general, theoretically grounded path to more reliable and efficient policy learning in complex environments.
Authors: Markus Anders, Bart Bogaerts, Benjamin Bog{\o}, Arthur Gontier, Wietze Koops, Ciaran McCreesh, Magnus O. Myreen, Jakob Nordstr\"om, Andy Oertel, Adrian Rebola-Pardo, Yong Kiam Tan
Abstract: Symmetry breaking is a crucial technique in modern combinatorial solving, but it is difficult to be sure it is implemented correctly. The most successful approach to deal with bugs is to make solvers certifying, so that they output not just a solution, but also a mathematical proof of correctness in a standard format, which can then be checked by a formally verified checker. This requires justifying symmetry reasoning within the proof, but developing efficient methods for this has remained a long-standing open challenge. A fully general approach was recently proposed by Bogaerts et al. (2023), but it relies on encoding lexicographic orders with big integers, which quickly becomes infeasible for large symmetries. In this work, we develop a method for instead encoding orders with auxiliary variables. We show that this leads to orders-of-magnitude speed-ups in both theory and practice by running experiments on proof logging and checking for SAT symmetry breaking using the state-of-the-art satsuma symmetry breaker and the VeriPB proof checking toolchain.
Authors: Bidipta Sarkar, Mattie Fellows, Juan Agustin Duque, Alistair Letcher, Antonio Le\'on Villares, Anya Sims, Dylan Cope, Jarek Liesen, Lukas Seier, Theo Wolf, Uljad Berdica, Alexander David Goldie, Aaron Courville, Karin Sevegnani, Shimon Whiteson, Jakob Nicolaus Foerster
Abstract: We introduce Evolution Guided General Optimization via Low-rank Learning (EGGROLL), an evolution strategies (ES) algorithm designed to scale backprop-free optimization to large population sizes for modern large neural network architectures with billions of parameters. ES is a set of powerful blackbox optimisation methods that can handle non-differentiable or noisy objectives with excellent scaling potential through parallelisation. Na{\"i}ve ES becomes prohibitively expensive at scale due to the computational and memory costs associated with generating matrix perturbations $E\in\mathbb{R}^{m\times n}$ and the batched matrix multiplications needed to compute per-member forward passes. EGGROLL overcomes these bottlenecks by generating random matrices $A\in \mathbb{R}^{m\times r},\ B\in \mathbb{R}^{n\times r}$ with $r\ll \min(m,n)$ to form a low-rank matrix perturbation $A B^\top$ that are used in place of the full-rank perturbation $E$. As the overall update is an average across a population of $N$ workers, this still results in a high-rank update but with significant memory and computation savings, reducing the auxiliary storage from $mn$ to $r(m+n)$ per layer and the cost of a forward pass from $\mathcal{O}(mn)$ to $\mathcal{O}(r(m+n))$ when compared to full-rank ES. A theoretical analysis reveals our low-rank update converges to the full-rank update at a fast $\mathcal{O}\left(\frac{1}{r}\right)$ rate. Our experiments show that (1) EGGROLL does not compromise the performance of ES in tabula-rasa RL settings, despite being faster, (2) it is competitive with GRPO as a technique for improving LLM reasoning, and (3) EGGROLL enables stable pre-training of nonlinear recurrent language models that operate purely in integer datatypes.
Authors: Md. Samiul Alim, Sharjil Khan, Amrijit Biswas, Fuad Rahman, Shafin Rahman, Nabeel Mohammed
Abstract: Unstructured pruning remains a powerful strategy for compressing deep neural networks, yet it often demands iterative train-prune-retrain cycles, resulting in significant computational overhead. To address this challenge, we introduce a novel teacher-guided pruning framework that tightly integrates Knowledge Distillation (KD) with importance score estimation. Unlike prior approaches that apply KD as a post-pruning recovery step, our method leverages gradient signals informed by the teacher during importance score calculation to identify and retain parameters most critical for both task performance and knowledge transfer. Our method facilitates a one-shot global pruning strategy that efficiently eliminates redundant weights while preserving essential representations. After pruning, we employ sparsity-aware retraining with and without KD to recover accuracy without reactivating pruned connections. Comprehensive experiments across multiple image classification benchmarks, including CIFAR-10, CIFAR-100, and TinyImageNet, demonstrate that our method consistently achieves high sparsity levels with minimal performance degradation. Notably, our approach outperforms state-of-the-art baselines such as EPG and EPSD at high sparsity levels, while offering a more computationally efficient alternative to iterative pruning schemes like COLT. The proposed framework offers a computation-efficient, performance-preserving solution well suited for deployment in resource-constrained environments.
Authors: Irmak Guzey, Haozhi Qi, Julen Urain, Changhao Wang, Jessica Yin, Krishna Bodduluri, Mike Lambeta, Lerrel Pinto, Akshara Rai, Jitendra Malik, Tingfan Wu, Akash Sharma, Homanga Bharadhwaj
Abstract: Learning multi-fingered robot policies from humans performing daily tasks in natural environments has long been a grand goal in the robotics community. Achieving this would mark significant progress toward generalizable robot manipulation in human environments, as it would reduce the reliance on labor-intensive robot data collection. Despite substantial efforts, progress toward this goal has been bottle-necked by the embodiment gap between humans and robots, as well as by difficulties in extracting relevant contextual and motion cues that enable learning of autonomous policies from in-the-wild human videos. We claim that with simple yet sufficiently powerful hardware for obtaining human data and our proposed framework AINA, we are now one significant step closer to achieving this dream. AINA enables learning multi-fingered policies from data collected by anyone, anywhere, and in any environment using Aria Gen 2 glasses. These glasses are lightweight and portable, feature a high-resolution RGB camera, provide accurate on-board 3D head and hand poses, and offer a wide stereo view that can be leveraged for depth estimation of the scene. This setup enables the learning of 3D point-based policies for multi-fingered hands that are robust to background changes and can be deployed directly without requiring any robot data (including online corrections, reinforcement learning, or simulation). We compare our framework against prior human-to-robot policy learning approaches, ablate our design choices, and demonstrate results across nine everyday manipulation tasks. Robot rollouts are best viewed on our website: https://aina-robot.github.io.
Authors: Qinghao Hu, Shang Yang, Junxian Guo, Xiaozhe Yao, Yujun Lin, Yuxian Gu, Han Cai, Chuang Gan, Ana Klimovic, Song Han
Abstract: The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, training these reasoning models, typically using Reinforcement Learning (RL), encounters critical efficiency bottlenecks: response generation during RL training exhibits a persistent long-tail distribution, where a few very long responses dominate execution time, wasting resources and inflating costs. To address this, we propose TLT, a system that accelerates reasoning RL training losslessly by integrating adaptive speculative decoding. Applying speculative decoding in RL is challenging due to the dynamic workloads, evolving target model, and draft model training overhead. TLT overcomes these obstacles with two synergistic components: (1) Adaptive Drafter, a lightweight draft model trained continuously on idle GPUs during long-tail generation to maintain alignment with the target model at no extra cost; and (2) Adaptive Rollout Engine, which maintains a memory-efficient pool of pre-captured CUDAGraphs and adaptively select suitable SD strategies for each input batch. Evaluations demonstrate that TLT achieves over 1.7x end-to-end RL training speedup over state-of-the-art systems, preserves the model accuracy, and yields a high-quality draft model as a free byproduct suitable for efficient deployment. Code is released at https://github.com/mit-han-lab/fastrl.
Authors: Ziyu Guo, Renrui Zhang, Hongyu Li, Manyuan Zhang, Xinyan Chen, Sifan Wang, Yan Feng, Peng Pei, Pheng-Ann Heng
Abstract: Recent advances in visual generation have increasingly explored the integration of reasoning capabilities. They incorporate textual reasoning, i.e., think, either before (as pre-planning) or after (as post-refinement) the generation process, yet they lack on-the-fly multimodal interaction during the generation itself. In this preliminary study, we introduce Thinking-while-Generating (TwiG), the first interleaved framework that enables co-evolving textual reasoning throughout the visual generation process. As visual content is progressively generating, textual reasoning is interleaved to both guide upcoming local regions and reflect on previously synthesized ones. This dynamic interplay produces more context-aware and semantically rich visual outputs. To unveil the potential of this framework, we investigate three candidate strategies, zero-shot prompting, supervised fine-tuning (SFT) on our curated TwiG-50K dataset, and reinforcement learning (RL) via a customized TwiG-GRPO strategy, each offering unique insights into the dynamics of interleaved reasoning. We hope this work inspires further research into interleaving textual reasoning for enhanced visual generation. Code will be released at: https://github.com/ZiyuGuo99/Thinking-while-Generating.
URLs: https://github.com/ZiyuGuo99/Thinking-while-Generating.
Authors: George Cazenavette, Antonio Torralba, Vincent Sitzmann
Abstract: The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods focus on synthesizing datasets that enable training randomly initialized models. In contrast, state-of-the-art vision approaches are increasingly building on large, pre-trained self-supervised models rather than training from scratch. In this paper, we investigate the problem of distilling datasets that enable us to optimally train linear probes on top of such large, pre-trained vision models. We introduce a method of dataset distillation for this task called Linear Gradient Matching that optimizes the synthetic images such that, when passed through a pre-trained feature extractor, they induce gradients in the linear classifier similar to those produced by the real data. Our method yields synthetic data that outperform all real-image baselines and, remarkably, generalize across pre-trained vision models, enabling us, for instance, to train a linear CLIP probe that performs competitively using a dataset distilled via a DINO backbone. Further, we show that our distilled datasets are exceptionally effective for fine-grained classification and provide a valuable tool for model interpretability, predicting, among other things, how similar two models' embedding spaces are under the platonic representation hypothesis or whether a model is sensitive to spurious correlations in adversarial datasets.
Authors: Pratinav Seth, Vinay Kumar Sankarapu
Abstract: Reliable explainability is not only a technical goal but also a cornerstone of private AI governance. As AI models enter high-stakes sectors, private actors such as auditors, insurers, certification bodies, and procurement agencies require standardized evaluation metrics to assess trustworthiness. However, current XAI evaluation metrics remain fragmented and prone to manipulation, which undermines accountability and compliance. We argue that standardized metrics can function as governance primitives, embedding auditability and accountability within AI systems for effective private oversight. Building upon prior work in XAI benchmarking, we identify key limitations in ensuring faithfulness, tamper resistance, and regulatory alignment. Furthermore, interpretability can directly support model alignment by providing a verifiable means of ensuring behavioral integrity in General Purpose AI (GPAI) systems. This connection between interpretability and alignment positions XAI metrics as both technical and regulatory instruments that help prevent alignment faking, a growing concern among oversight bodies. We propose a Governance by Metrics paradigm that treats explainability evaluation as a central mechanism of private AI governance. Our framework introduces a hierarchical model linking transparency, tamper resistance, scalability, and legal alignment, extending evaluation from model introspection toward systemic accountability. Through conceptual synthesis and alignment with governance standards, we outline a roadmap for integrating explainability metrics into continuous AI assurance pipelines that serve both private oversight and regulatory needs.
Authors: Wasu Top Piriyakulkij, Yichao Liang, Hao Tang, Adrian Weller, Marta Kryven, Kevin Ellis
Abstract: Learning how the world works is central to building AI agents that can adapt to complex environments. Traditional world models based on deep learning demand vast amounts of training data, and do not flexibly update their knowledge from sparse observations. Recent advances in program synthesis using Large Language Models (LLMs) give an alternate approach which learns world models represented as source code, supporting strong generalization from little data. To date, application of program-structured world models remains limited to natural language and grid-world domains. We introduce a novel program synthesis method for effectively modeling complex, non-gridworld domains by representing a world model as an exponentially-weighted product of programmatic experts (PoE-World) synthesized by LLMs. We show that this approach can learn complex, stochastic world models from just a few observations. We evaluate the learned world models by embedding them in a model-based planning agent, demonstrating efficient performance and generalization to unseen levels on Atari's Pong and Montezuma's Revenge. We release our code and display the learned world models and videos of the agent's gameplay at https://topwasu.github.io/poe-world.
Authors: Parshin Shojaee, Iman Mirzadeh, Keivan Alizadeh, Maxwell Horton, Samy Bengio, Mehrdad Farajtabar
Abstract: Recent generations of language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their fundamental capabilities, scaling properties, and limitations remain insufficiently understood. Current evaluations primarily focus on established math and coding benchmarks, emphasizing final answer accuracy. However, this evaluation paradigm often suffers from contamination and does not provide insights into the reasoning traces. In this work, we systematically investigate these gaps with the help of controllable puzzle environments that allow precise manipulation of complexity while maintaining consistent logical structures. This setup enables the analysis of not only final answers but also the internal reasoning traces, offering insights into how LRMs think. Through extensive experiments, we show that LRMs face a complete accuracy collapse beyond certain complexities. Moreover, they exhibit a counterintuitive scaling limit: their reasoning effort increases with problem complexity up to a point, then declines despite having remaining token budget. By comparing LRMs with their standard LLM counterparts under same inference compute, we identify three performance regimes: (1) low-complexity tasks where standard models outperform LRMs, (2) medium-complexity tasks where LRMs demonstrates advantage, and (3) high-complexity tasks where both models face complete collapse. We found that LRMs have limitations in exact computation: they fail to use explicit algorithms and reason inconsistently across scales. We also investigate the reasoning traces in more depth, studying the patterns of explored solutions and analyzing the models' computational behavior, shedding light on their strengths, limitations, and raising questions about their reasoning capabilities.
Authors: Pantelis Dogoulis, Fabien Bernier, F\'elix Fourreau, Karim Tit, Maxime Cordy
Abstract: Many real-world machine learning tasks require outputs that satisfy hard constraints, such as physical conservation laws, structured dependencies in graphs, or column-level relationships in tabular data. Existing approaches rely either on domain-specific architectures and losses or on strong assumptions on the constraint space, restricting their applicability to linear or convex constraints. We propose a general-purpose framework for constraint-aware refinement that leverages denoising diffusion implicit models (DDIMs). Starting from a coarse prediction, our method iteratively refines it through a deterministic diffusion trajectory guided by a learned prior and augmented by constraint gradient corrections. The approach accommodates a wide class of non-convex and nonlinear equality constraints and can be applied post hoc to any base model. We demonstrate the method in two representative domains: constrained adversarial attack generation on tabular data with column-level dependencies and in AC power flow prediction under Kirchhoff's laws. Across both settings, our diffusion-guided refinement improves both constraint satisfaction and performance while remaining lightweight and model-agnostic.
Authors: Dany Moshkovich, Sergey Zeltyn
Abstract: Large Language Models (LLMs) are increasingly deployed within agentic systems - collections of interacting, LLM-powered agents that execute complex, adaptive workflows using memory, tools, and dynamic planning. While enabling powerful new capabilities, these systems also introduce unique forms of uncertainty stemming from probabilistic reasoning, evolving memory states, and fluid execution paths. Traditional software observability and operations practices fall short in addressing these challenges. This paper presents our vision of AgentOps: a comprehensive framework for observing, analyzing, optimizing, and automating operation of agentic AI systems. We identify distinct needs across four key roles - developers, testers, site reliability engineers (SREs), and business users - each of whom engages with the system at different points in its lifecycle. We present the AgentOps Automation Pipeline, a six-stage process encompassing behavior observation, metric collection, issue detection, root cause analysis, optimized recommendations, and runtime automation. Throughout, we emphasize the critical role of automation in managing uncertainty and enabling self-improving AI systems - not by eliminating uncertainty, but by taming it to ensure safe, adaptive, and effective operation.
Authors: Zhenliang Zhang, Yuxi Wang, Hongzhao Xie, Shiyun Zhao, Mingyuan Liu, Yujie Lu, Xinyi He, Zhenku Cheng, Yujia Peng
Abstract: A key feature differentiating artificial general intelligence (AGI) from traditional AI is that AGI can perform composite tasks that require a wide range of capabilities. Although embodied agents powered by multimodal large language models (MLLMs) offer rich perceptual and interactive capabilities, it remains largely unexplored whether they can solve composite tasks. In the current work, we designed a set of composite tasks inspired by common daily activities observed in early childhood development. Within a dynamic and simulated home environment, these tasks span three core domains: object understanding, spatial intelligence, and social activity. We evaluated 17 leading proprietary and open-source MLLMs on these tasks. The results consistently showed poor performance across all three domains, indicating a substantial gap between current capabilities and general intelligence requirements. Together, our tasks offer a preliminary framework for evaluating the general capabilities of embodied agents, marking an early but significant step toward the development of embodied MLLMs and their real-world deployment.
Authors: Minhui Zhu, Minyang Tian, Xiaocheng Yang, Tianci Zhou, Lifan Yuan, Penghao Zhu, Eli Chertkov, Shengyan Liu, Yufeng Du, Ziming Ji, Indranil Das, Junyi Cao, Yufeng Du, Jiabin Yu, Peixue Wu, Jinchen He, Yifan Su, Yikun Jiang, Yujie Zhang, Chang Liu, Ze-Min Huang, Weizhen Jia, Yunkai Wang, Farshid Jafarpour, Yong Zhao, Xinan Chen, Jessie Shelton, Aaron W. Young, John Bartolotta, Wenchao Xu, Yue Sun, Anjun Chu, Victor Colussi, Chris Akers, Nathan Brooks, Wenbo Fu, Jinchao Zhao, Marvin Qi, Anqi Mu, Yubo Yang, Allen Zang, Yang Lyu, Peizhi Mai, Christopher Wilson, Xuefei Guo, Juntai Zhou, Daniel Inafuku, Chi Xue, Luyu Gao, Ze Yang, Ya\"ir Hein, Yonatan Kahn, Kevin Zhou, Di Luo, John Drew Wilson, Jarrod T. Reilly, Dmytro Bandak, Ofir Press, Liang Yang, Xueying Wang, Hao Tong, Nicolas Chia, Eliu Huerta, Hao Peng
Abstract: While large language models (LLMs) with reasoning capabilities are progressing rapidly on high-school math competitions and coding, can they reason effectively through complex, open-ended challenges found in frontier physics research? And crucially, what kinds of reasoning tasks do physicists want LLMs to assist with? To address these questions, we present the CritPt (Complex Research using Integrated Thinking - Physics Test, pronounced "critical point"), the first benchmark designed to test LLMs on unpublished, research-level reasoning tasks that broadly covers modern physics research areas, including condensed matter, quantum physics, atomic, molecular & optical physics, astrophysics, high energy physics, mathematical physics, statistical physics, nuclear physics, nonlinear dynamics, fluid dynamics and biophysics. CritPt consists of 71 composite research challenges designed to simulate full-scale research projects at the entry level, which are also decomposed to 190 simpler checkpoint tasks for more fine-grained insights. All problems are newly created by 50+ active physics researchers based on their own research. Every problem is hand-curated to admit a guess-resistant and machine-verifiable answer and is evaluated by an automated grading pipeline heavily customized for advanced physics-specific output formats. We find that while current state-of-the-art LLMs show early promise on isolated checkpoints, they remain far from being able to reliably solve full research-scale challenges: the best average accuracy among base models is only 5.7%, achieved by GPT-5 (high), moderately rising to around 10% when equipped with coding tools. Through the realistic yet standardized evaluation offered by CritPt, we highlight a large disconnect between current model capabilities and realistic physics research demands, offering a foundation to guide the development of scientifically grounded AI tools.
Authors: Samuel Hildebrand (Louisiana State University), Curtis Taylor (Oak Ridge National Lab), Sean Oesch (Oak Ridge National Lab), James M Ghawaly Jr (Louisiana State University), Amir Sadovnik (Oak Ridge National Lab), Ryan Shivers (Oak Ridge National Lab), Brandon Schreiber (Oak Ridge National Lab), Kevin Kurian (University of Florida)
Abstract: Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipeline's ability to ingest, retrieve, and reason about several modalities of information, differentiating it from existing benchmarks that focus on particular aspects such as retrieval. We present (1) a small, human-created dataset of 93 questions designed to evaluate a pipeline's ability to ingest textual data, tables, images, and data spread across these modalities in one or more documents; (2) a phrase-level recall metric for correctness; (3) a nearest-neighbor embedding classifier to identify potential pipeline hallucinations; (4) a comparative evaluation of 2 pipelines built with open-source retrieval mechanisms and 4 closed-source foundation models; and (5) a third-party human evaluation of the alignment of our correctness and hallucination metrics. We find that closed-source pipelines significantly outperform open-source pipelines in both correctness and hallucination metrics, with wider performance gaps in questions relying on multimodal and cross-document information. Human evaluation of our metrics showed average agreement of 4.62 for correctness and 4.53 for hallucination detection on a 1-5 Likert scale (5 indicating "strongly agree").
Authors: Qixiang Yin, Huanjin Yao, Jianghao Chen, Jiaxing Huang, Zhicheng Zhao, Fei Su
Abstract: Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, they encounter challenges in terms of reasoning efficiency, large model size and overthinking. However, existing lightweight MLLMs lack the capability to balance high efficiency and performance at a small scale. To this end, we propose Tiny-R1V, a novel lightweight 3B model that achieves faster inference and higher accuracy via a two-stage optimization, while unifying multimodal reasoning across multiple tasks with fewer inference tokens. In the first stage, Tiny-R1V introduces Length-Informed Relative Policy Optimization (LIPO), a new reinforcement learning method, to train each reasoning model, including mathematical reasoning, chart reasoning, and OCR capability. The LIPO dynamically adjusts the advantages of responses within groups by prioritizing concise yet high-quality responses to encourage the generation of shorter and more accurate responses. In the second stage, we propose Adaptive Model Merging (AMM), a training-free model merging method that merges multiple specialist models into a unified architecture. Specifically, AMM adaptively adjusts the weights of task vectors via a novel gradient projection regularization loss function, thus mitigating redundant conflicts between them. Extensive evaluations on ten widely-used reasoning benchmarks covering mathematics, structured data (charts, tables, documents), OCR, and general capabilities showcase the superior performance of Tiny-R1V, enabling lightweight models to excel in diverse multimodal reasoning tasks. Code will be available at \href{https://github.com/buptyqx/Tiny-R1V}{https://github.com/buptyqx/Tiny-R1V}
URLs: https://github.com/buptyqx/Tiny-R1V, https://github.com/buptyqx/Tiny-R1V
Authors: Xi Wang, Xianyao Ling, Kun Li, Gang Yin, Liang Zhang, Jiang Wu, Jun Xu, Fu Zhang, Wenbo Lei, Annie Wang, Peng Gong
Abstract: In the current era of big data, extracting deep insights from massive, heterogeneous, and complexly associated multi-dimensional data has become a significant challenge. Large Language Models (LLMs) perform well in natural language understanding and generation, but still suffer from "hallucination" issues when processing structured knowledge and are difficult to update in real-time. Although Knowledge Graphs (KGs) can explicitly store structured knowledge, their static nature limits dynamic interaction and analytical capabilities. Therefore, this paper proposes a multi-dimensional data analysis method based on the interactions between LLM agents and KGs, constructing a dynamic, collaborative analytical ecosystem. This method utilizes LLM agents to automatically extract product data from unstructured data, constructs and visualizes the KG in real-time, and supports users in deep exploration and analysis of graph nodes through an interactive platform. Experimental results show that this method has significant advantages in product ecosystem analysis, relationship mining, and user-driven exploratory analysis, providing new ideas and tools for multi-dimensional data analysis.
Authors: Wenhan Yu, Xinbo Lin, Lanxin Ni, Jinhua Cheng, Lei Sha
Abstract: Large language models (LLMs) have demonstrated strong reasoning abilities across specialized domains, motivating research into their application to legal reasoning. However, existing legal benchmarks often conflate factual recall with genuine inference, fragment the reasoning process, and overlook the quality of reasoning. To address these limitations, we introduce MSLR, the first Chinese multi-step legal reasoning dataset grounded in real-world judicial decision making. MSLR adopts the IRAC framework (Issue, Rule, Application, Conclusion) to model structured expert reasoning from official legal documents. In addition, we design a scalable Human-LLM collaborative annotation pipeline that efficiently produces fine-grained step-level reasoning annotations and provides a reusable methodological framework for multi-step reasoning datasets. Evaluation of multiple LLMs on MSLR shows only moderate performance, highlighting the challenges of adapting to complex legal reasoning. Further experiments demonstrate that Self-Initiated Chain-of-Thought prompts generated by models autonomously improve reasoning coherence and quality, outperforming human-designed prompts. MSLR contributes to advancing LLM reasoning and Chain-of-Thought strategies and offers open resources for future research. The dataset and code are available at https://github.com/yuwenhan07/MSLR-Bench and https://law.sjtu.edu.cn/flszyjzx/index.html.
URLs: https://github.com/yuwenhan07/MSLR-Bench, https://law.sjtu.edu.cn/flszyjzx/index.html.
Authors: Xin Gao, Shaohan Yu, Zerui Chen, Yueming Lyu, Weichen Yu, Guanghao Li, Jiyao Liu, Jianxiong Gao, Jian Liang, Ziwei Liu, Chenyang Si
Abstract: Large Reasoning Models (LRMs) improve answer quality through explicit chain-of-thought, yet this very capability introduces new safety risks: harmful content can be subtly injected, surface gradually, or be justified by misleading rationales within the reasoning trace. Existing safety evaluations, however, primarily focus on output-level judgments and rarely capture these dynamic risks along the reasoning process. In this paper, we present SafeRBench, the first benchmark that assesses LRM safety end-to-end -- from inputs and intermediate reasoning to final outputs. (1) Input Characterization: We pioneer the incorporation of risk categories and levels into input design, explicitly accounting for affected groups and severity, and thereby establish a balanced prompt suite reflecting diverse harm gradients. (2) Fine-Grained Output Analysis: We introduce a micro-thought chunking mechanism to segment long reasoning traces into semantically coherent units, enabling fine-grained evaluation across ten safety dimensions. (3) Human Safety Alignment: We validate LLM-based evaluations against human annotations specifically designed to capture safety judgments. Evaluations on 19 LRMs demonstrate that SafeRBench enables detailed, multidimensional safety assessment, offering insights into risks and protective mechanisms from multiple perspectives.
Authors: Haodong Li, Jingqi Zhang, Xiao Cheng, Peihua Mai, Haoyu Wang, Yan Pang
Abstract: The remarkable language ability of Large Language Models (LLMs) stems from extensive training on vast datasets, often including copyrighted material, which raises serious concerns about unauthorized use. While Membership Inference Attacks (MIAs) offer potential solutions for detecting such violations, existing approaches face critical limitations and challenges due to LLMs' inherent overconfidence, limited access to ground truth training data, and reliance on empirically determined thresholds. We present COPYCHECK, a novel framework that leverages uncertainty signals to detect whether copyrighted content was used in LLM training sets. Our method turns LLM overconfidence from a limitation into an asset by capturing uncertainty patterns that reliably distinguish between ``seen" (training data) and ``unseen" (non-training data) content. COPYCHECK further implements a two-fold strategy: (1) strategic segmentation of files into smaller snippets to reduce dependence on large-scale training data, and (2) uncertainty-guided unsupervised clustering to eliminate the need for empirically tuned thresholds. Experiment results show that COPYCHECK achieves an average balanced accuracy of 90.1% on LLaMA 7b and 91.6% on LLaMA2 7b in detecting seen files. Compared to the SOTA baseline, COPYCHECK achieves over 90% relative improvement, reaching up to 93.8\% balanced accuracy. It further exhibits strong generalizability across architectures, maintaining high performance on GPT-J 6B. This work presents the first application of uncertainty for copyright detection in LLMs, offering practical tools for training data transparency.
Authors: Xuekun Zhao, Pu Cao, Xiaoya Yang, Mingjian Zhang, Lu Yang, Qing Song
Abstract: As research on image inversion advances, the process is generally divided into two stages. The first step is Image Embedding, involves using an encoder or optimization procedure to embed an image and obtain its corresponding latent code. The second stage, referred to as Result Refinement, further improves the inversion and editing outcomes. Although this refinement stage substantially enhances reconstruction fidelity, perception and editability remain largely unchanged and are highly dependent on the latent codes derived from the first stage. Therefore, a key challenge lies in obtaining latent codes that preserve reconstruction fidelity while simultaneously improving perception and editability. In this work, we first reveal that these two properties are closely related to the degree of alignment (or disalignment) between the inverted latent codes and the synthetic distribution. Based on this insight, we propose the \textbf{ Latent Space Alignment Inversion Paradigm (LSAP)}, which integrates both an evaluation metric and a unified inversion solution. Specifically, we introduce the \textbf{Normalized Style Space ($\mathcal{S^N}$ space)} and \textbf{Normalized Style Space Cosine Distance (NSCD)} to quantify the disalignment of inversion methods. Moreover, our paradigm can be optimized for both encoder-based and optimization-based embeddings, providing a consistent alignment framework. Extensive experiments across various domains demonstrate that NSCD effectively captures perceptual and editable characteristics, and that our alignment paradigm achieves state-of-the-art performance in both stages of inversion.
Authors: Eilam Shapira, Omer Madmon, Roi Reichart, Moshe Tennenholtz
Abstract: Human choice prediction in economic contexts is crucial for applications in marketing, finance, public policy, and more. This task, however, is often constrained by the difficulties in acquiring human choice data. With most experimental economics studies focusing on simple choice settings, the AI community has explored whether LLMs can substitute for humans in these predictions and examined more complex experimental economics settings. However, a key question remains: can LLMs generate training data for human choice prediction? We explore this in language-based persuasion games, a complex economic setting involving natural language in strategic interactions. Our experiments show that models trained on LLM-generated data can effectively predict human behavior in these games and even outperform models trained on actual human data. Beyond data generation, we investigate the dual role of LLMs as both data generators and predictors, introducing a comprehensive empirical study on the effectiveness of utilizing LLMs for data generation, human choice prediction, or both. We then utilize our choice prediction framework to analyze how strategic factors shape decision-making, showing that interaction history (rather than linguistic sentiment alone) plays a key role in predicting human decision-making in repeated interactions. Particularly, when LLMs capture history-dependent decision patterns similarly to humans, their predictive success improves substantially. Finally, we demonstrate the robustness of our findings across alternative persuasion-game settings, highlighting the broader potential of using LLM-generated data to model human decision-making.
Authors: Shinyoung Kang, Jihan Kim
Abstract: In this study, we explore the potential of using quantum natural language processing (QNLP) to inverse design metal-organic frameworks (MOFs) with targeted properties. Specifically, by analyzing 450 hypothetical MOF structures consisting of 3 topologies, 10 metal nodes and 15 organic ligands, we categorize these structures into four distinct classes for pore volume and $CO_{2}$ Henry's constant values. We then compare various QNLP models (i.e. the bag-of-words, DisCoCat (Distributional Compositional Categorical), and sequence-based models) to identify the most effective approach to process the MOF dataset. Using a classical simulator provided by the IBM Qiskit, the bag-of-words model is identified to be the optimum model, achieving validation accuracies of 88.6% and 78.0% for binary classification tasks on pore volume and $CO_{2}$ Henry's constant, respectively. Further, we developed multi-class classification models tailored to the probabilistic nature of quantum circuits, with average test accuracies of 92% and 80% across different classes for pore volume and $CO_{2}$ Henry's constant datasets. Finally, the performance of generating MOF with target properties showed accuracies of 93.5% for pore volume and 87% for $CO_{2}$ Henry's constant, respectively. Although our investigation covers only a fraction of the vast MOF search space, it marks a promising first step towards using quantum computing for materials design, offering a new perspective through which to explore the complex landscape of MOFs.
Authors: Haokun Zhou, Yipeng Hong
Abstract: This study assesses the ability of Large Vision-Language Models (LVLMs) to differentiate between AI-generated and human-generated images. It introduces a new automated benchmark construction method for this evaluation. The experiment compared common LVLMs with human participants using a mixed dataset of AI and human-created images. Results showed that LVLMs could distinguish between the image types to some extent but exhibited a rightward bias, and perform significantly worse compared to humans. To build on these findings, we developed an automated benchmark construction process using AI. This process involved topic retrieval, narrative script generation, error embedding, and image generation, creating a diverse set of text-image pairs with intentional errors. We validated our method through constructing two caparable benchmarks. This study highlights the strengths and weaknesses of LVLMs in real-world understanding and advances benchmark construction techniques, providing a scalable and automatic approach for AI model evaluation.
Authors: Chongmin Lee, Jihie Kim
Abstract: Certain cancer types, notably pancreatic cancer, are difficult to detect at an early stage, motivating robust biomarker-based screening. Liquid biopsies enable non-invasive monitoring of circulating biomarkers, but typical machine learning pipelines for high-dimensional tabular data (e.g., random forests, SVMs) rely on expensive hyperparameter tuning and can be brittle under class imbalance. We leverage a meta-trained Hyperfast model for classifying cancer, accomplishing the highest AUC of 0.9929 and simultaneously achieving robustness especially on highly imbalanced datasets compared to other ML algorithms in several binary classification tasks (e.g. breast invasive carcinoma; BRCA vs. non-BRCA). We also propose a novel ensemble model combining pre-trained Hyperfast model, XGBoost, and LightGBM for multi-class classification tasks, achieving an incremental increase in accuracy (0.9464) while merely using 500 PCA features; distinguishable from previous studies where they used more than 2,000 features for similar results. Crucially, we demonstrate robustness under class imbalance: empirically via balanced accuracy and minority-class recall across cancer-vs.-noncancer and cancer-vs.-rest settings, and theoretically by showing (i) a prototype-form final layer for Hyperfast that yields prior-insensitive decisions under bounded bias, and (ii) minority-error reductions for majority vote under mild error diversity. Together, these results indicate that pre-trained tabular models and simple ensembling can deliver state-of-the-art accuracy and improved minority-class performance with far fewer features and no additional tuning.
Authors: Aness Al-Qawlaq, Ajay Kumar M, Deepu John
Abstract: This paper explores the adaptation of Transformerbased models for edge devices through the quantisation and hardware acceleration of the ARM Keyword Transformer (KWT) model on a RISC-V platform. The model was targeted to run on 64kB RAM in bare-metal C using a custom-developed edge AI library. KWT-1 was retrained to be 369 times smaller, with only a 10% loss in accuracy through reducing output classes from 35 to 2. The retraining and quantisation reduced model size from 2.42 MB to 1.65 kB. The integration of custom RISC-V instructions that accelerated GELU and SoftMax operations enabled a 5x speedup and thus ~5x power reduction in inference, with inference clock cycle counts decreasing from 26 million to 5.5 million clock cycles while incurring a small area overhead of approximately 29%. The results demonstrate a viable method for porting and accelerating Transformer-based models in low-power IoT devices.
Authors: Nikolaos Ntampakis, Konstantinos Diamantaras, Ioanna Chouvarda, Vasileios Argyriou, Panagiotis Sarigianndis
Abstract: Dementia, a debilitating neurological condition affecting millions worldwide, presents significant diagnostic challenges. In this work, we introduce DEFORMISE, a novel DEep learning Framework for dementia diagnOsis of eldeRly patients using 3D brain Magnetic resonance Imaging (MRI) scans with Optimized Slice sElection. Our approach features a unique technique for selectively processing MRI slices, focusing on the most relevant brain regions and excluding less informative sections. This methodology is complemented by a confidence-based classification committee composed of three novel deep learning models. Tested on the Open OASIS datasets, our method achieved an impressive accuracy of 94.12%, surpassing existing methodologies. Furthermore, validation on the ADNI dataset confirmed the robustness and generalizability of our approach. The use of explainable AI (XAI) techniques and comprehensive ablation studies further substantiate the effectiveness of our techniques, providing insights into the decision-making process and the importance of our methodology. This research offers a significant advancement in dementia diagnosis, providing a highly accurate and efficient tool for clinical applications.
Authors: Ethan Blaser, Shangtong Zhang
Abstract: Stochastic approximation is a powerful class of algorithms with celebrated success. However, a large body of previous analysis focuses on stochastic approximations driven by contractive operators, which is not applicable in some important reinforcement learning settings like the average reward setting. This work instead investigates stochastic approximations with merely nonexpansive operators. In particular, we study nonexpansive stochastic approximations with Markovian noise, providing both asymptotic and finite sample analysis. Key to our analysis are novel bounds of noise terms resulting from the Poisson equation. As an application, we prove for the first time that classical tabular average reward temporal difference learning converges to a sample-path dependent fixed point.
Authors: Mathilde Papillon, Guillermo Bern\'ardez, Claudio Battiloro, Nina Miolane
Abstract: Graph Neural Networks (GNNs) effectively learn from relational data by leveraging graph symmetries. However, many real-world systems -- such as biological or social networks -- feature multi-way interactions that GNNs fail to capture. Topological Deep Learning (TDL) addresses this by modeling and leveraging higher-order structures, with Combinatorial Complex Neural Networks (CCNNs) offering a general and expressive approach that has been shown to outperform GNNs. However, TDL lacks the principled and standardized frameworks that underpin GNN development, restricting its accessibility and applicability. To address this issue, we introduce Generalized CCNNs (GCCNs), a simple yet powerful family of TDL models that can be used to systematically transform any (graph) neural network into its TDL counterpart. We prove that GCCNs generalize and subsume CCNNs, while extensive experiments on a diverse class of GCCNs show that these architectures consistently match or outperform CCNNs, often with less model complexity. In an effort to accelerate and democratize TDL, we introduce TopoTune, a lightweight software for defining, building, and training GCCNs with unprecedented flexibility and ease.
Authors: Caiqi Zhang, Ruihan Yang, Zhisong Zhang, Xinting Huang, Sen Yang, Dong Yu, Nigel Collier
Abstract: Large language models (LLMs) often suffer from hallucinations, posing significant challenges for real-world applications. Confidence calibration, as an effective indicator of hallucination, is thus essential to enhance the trustworthiness of LLMs. Prior work mainly focuses on short-form tasks using a single response-level score (macro calibration), which is insufficient for long-form outputs that may contain both accurate and inaccurate claims. In this work, we systematically study atomic calibration, which evaluates factuality calibration at a fine-grained level by decomposing long responses into atomic claims. We further categorize existing confidence elicitation methods into discriminative and generative types, and propose two new confidence fusion strategies to improve calibration. Our experiments demonstrate that LLMs exhibit poorer calibration at the atomic level during long-form generation. More importantly, atomic calibration uncovers insightful patterns regarding the alignment of confidence methods and the changes of confidence throughout generation. This sheds light on future research directions for confidence estimation in long-form generation.
Authors: Jana Armouti, Nikhil Madaan, Rohan Panda, Tom Fox, Laura Hutchins, Amita Krishnan, Ricardo Rodriguez, Bennett DeBoisblanc, Deva Ramanan, John Galeotti, Gautam Gare
Abstract: Predicting whether a treatment leads to meaningful improvement is a central challenge in personalized medicine, particularly when disease progression manifests as subtle visual changes over time. While data-driven deep learning (DL) offers a promising route to automate such predictions, acquiring large-scale longitudinal data for each individual patient remains impractical. To address this limitation, we explore whether inter-patient variability can serve as a proxy for learning intra-patient progression. We propose LEARNER, a contrastive pretraining framework that leverages coarsely labeled inter-patient data to learn fine-grained, patient-specific representations. Using lung ultrasound (LUS) and brain MRI datasets, we demonstrate that contrastive objectives trained on coarse inter-patient differences enable models to capture subtle intra-patient changes associated with treatment response. Across both modalities, our approach improves downstream classification accuracy and F1-score compared to standard MSE pretraining, highlighting the potential of inter-patient contrastive learning for individualized outcome prediction.
Authors: Asmit Nayak, Shirley Zhang, Yash Wani, Rishabh Khandelwal, Kassem Fawaz
Abstract: Deceptive patterns in digital interfaces manipulate users into making unintended decisions, exploiting cognitive biases and psychological vulnerabilities. These patterns have become ubiquitous on various digital platforms. While efforts to mitigate deceptive patterns have emerged from legal and technical perspectives, a significant gap remains in creating usable and scalable solutions. We introduce our AutoBot framework to address this gap and help web stakeholders navigate and mitigate online deceptive patterns. AutoBot accurately identifies and localizes deceptive patterns from a screenshot of a website without relying on the underlying HTML code. AutoBot employs a two-stage pipeline that leverages the capabilities of specialized vision models to analyze website screenshots, identify interactive elements, and extract textual features. Next, using a large language model, AutoBot understands the context surrounding these elements to determine the presence of deceptive patterns. We also use AutoBot, to create a synthetic dataset to distill knowledge from 'teacher' LLMs to smaller language models. Through extensive evaluation, we demonstrate AutoBot's effectiveness in detecting deceptive patterns on the web, achieving an F1-score of 0.93 when detecting deceptive patterns, underscoring its potential as an essential tool for mitigating online deceptive patterns. We implement AutoBot, across three downstream applications targeting different web stakeholders: (1) a local browser extension providing users with real-time feedback, (2) a Lighthouse audit to inform developers of potential deceptive patterns on their sites, and (3) as a measurement tool designed for researchers and regulators.
Authors: Suhwan Choi, Kyu Won Kim, Myungjoo Kang
Abstract: We introduce Multimodal Matching based on Valence and Arousal (MMVA), a tri-modal encoder framework designed to capture emotional content across images, music, and musical captions. To support this framework, we expand the Image-Music-Emotion-Matching-Net (IMEMNet) dataset, creating IMEMNet-C which includes 24,756 images and 25,944 music clips with corresponding musical captions. We employ multimodal matching scores based on the continuous valence (emotional positivity) and arousal (emotional intensity) values. This continuous matching score allows for random sampling of image-music pairs during training by computing similarity scores from the valence-arousal values across different modalities. Consequently, the proposed approach achieves state-of-the-art performance in valence-arousal prediction tasks. Furthermore, the framework demonstrates its efficacy in various zeroshot tasks, highlighting the potential of valence and arousal predictions in downstream applications.
Authors: Miguel Carvalho, Bruno Martins
Abstract: Vision-Language Models (VLMs) have recently experienced significant advancements. However, challenges persist in the accurate recognition of fine details within high resolution images, which limits performance in multiple tasks. This work introduces Pheye, a novel architecture that efficiently processes high-resolution images while training fewer parameters than similarly sized VLMs. Notably, Pheye achieves a high efficiency while maintaining strong performance, particularly in tasks that demand fine-grained image understanding and/or the handling of scene-text.
Authors: Zekun Xi, Wenbiao Yin, Jizhan Fang, Jialong Wu, Runnan Fang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang
Abstract: Machine writing with large language models often relies on retrieval-augmented generation. However, these approaches remain confined within the boundaries of the model's predefined scope, limiting the generation of content with rich information. Specifically, vanilla-retrieved information tends to lack depth, novelty, and suffers from redundancy, which negatively impacts the quality of generated articles, leading to shallow, unoriginal, and repetitive outputs. To address these issues, we propose OmniThink, a slow-thinking machine writing framework that emulates the human-like process of iterative expansion and reflection. The core idea behind OmniThink is to simulate the cognitive behavior of learners as they slowly deepen their knowledge of the topics. Experimental results demonstrate that OmniThink improves the knowledge density of generated articles without compromising metrics such as coherence and depth. Human evaluations and expert feedback further highlight the potential of OmniThink to address real-world challenges in the generation of long-form articles. Code is available at https://github.com/zjunlp/OmniThink.
Authors: Minwoo Kim, Geunsik Bae, Jinwoo Lee, Woojae Shin, Changseung Kim, Myong-Yol Choi, Heejung Shin, Hyondong Oh
Abstract: This paper introduces a learning-based visual planner for agile drone flight in cluttered environments. The proposed planner generates collision-free waypoints in milliseconds, enabling drones to perform agile maneuvers in complex environments without building separate perception, mapping, and planning modules. Learning-based methods, such as behavior cloning (BC) and reinforcement learning (RL), demonstrate promising performance in visual navigation but still face inherent limitations. BC is susceptible to compounding errors due to limited expert imitation, while RL struggles with reward function design and sample inefficiency. To address these limitations, this paper proposes an inverse reinforcement learning (IRL)-based framework for high-speed visual navigation. By leveraging IRL, it is possible to reduce the number of interactions with simulation environments and improve capability to deal with high-dimensional spaces while preserving the robustness of RL policies. A motion primitive-based path planning algorithm collects an expert dataset with privileged map data from diverse environments, ensuring comprehensive scenario coverage. By leveraging both the acquired expert and learner dataset gathered from the agent's interactions with the simulation environments, a robust reward function and policy are learned across diverse states. While the proposed method is trained in a simulation environment only, it can be directly applied to real-world scenarios without additional training or tuning. The performance of the proposed method is validated in both simulation and real-world environments, including forests and various structures. The trained policy achieves an average speed of 7 m/s and a maximum speed of 8.8 m/s in real flight experiments. To the best of our knowledge, this is the first work to successfully apply an IRL framework for high-speed visual navigation of drones.
Authors: Xing Li, Zeyu Xing, Yiming Li, Linping Qu, Hui-Ling Zhen, Wulong Liu, Yiwu Yao, Sinno Jialin Pan, Mingxuan Yuan
Abstract: KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness. However, current methods have three unsolved issues: overlooking layer-wise sensitivity to KV cache quantization, high overhead of online fine-grained decision-making, and low flexibility to different LLMs and constraints. Therefore, we theoretically analyze the inherent correlation of layer-wise transformer attention patterns to KV cache quantization errors and study why key cache is generally more important than value cache for quantization error reduction. We further propose a simple yet effective framework KVTuner to adaptively search for the optimal hardware-friendly layer-wise KV quantization precision pairs for coarse-grained KV cache with multi-objective optimization and directly utilize the offline searched configurations during online inference. To reduce the computational cost of offline calibration, we utilize the intra-layer KV precision pair pruning and inter-layer clustering to reduce the search space. Experimental results show that we can achieve nearly lossless 3.25-bit mixed precision KV cache quantization for LLMs like Llama-3.1-8B-Instruct and 4.0-bit for sensitive models like Qwen2.5-7B-Instruct on mathematical reasoning tasks. The maximum inference throughput can be improved by 21.25\% compared with KIVI-KV8 quantization over various context lengths. Our code and searched configurations are available at https://github.com/cmd2001/KVTuner.
Authors: Jonathan Laurent, Andr\'e Platzer
Abstract: Large Language Models can solve a wide range of tasks from just a few examples, but they remain difficult to steer and lack a capability essential for building reliable software at scale: the modular composition of computations under enforceable contracts. As a result, they are typically embedded in larger software pipelines that use domain-specific knowledge to decompose tasks and improve reliability through validation and search. Yet the complexity of writing, tuning, and maintaining such pipelines has so far limited their sophistication. We propose oracular programming: a foundational paradigm for integrating traditional, explicit computations with inductive oracles such as LLMs. It rests on two directing principles: the full separation of core and search logic, and the treatment of few-shot examples as grounded and evolvable program components. Within this paradigm, experts express high-level problem-solving strategies as programs with unresolved choice points. These choice points are resolved at runtime by LLMs, which generalize from user-provided examples of correct and incorrect decisions. An oracular program is composed of three orthogonal components: a strategy that consists in a nondeterministic program with choice points that can be reified into a search tree, a policy that specifies how to navigate this tree with the help of LLM oracles, and a set of demonstrations that describe successful and unsuccessful tree navigation scenarios across diverse problem instances. Each component is expressed in a dedicated programming language and can be independently improved or substituted. We address the key programming language design challenges of modularly composing oracular programs and enforcing consistency between their components as they evolve.
Authors: Yiwei Guo, Zhihan Li, Hankun Wang, Bohan Li, Chongtian Shao, Hanglei Zhang, Chenpeng Du, Xie Chen, Shujie Liu, Kai Yu
Abstract: The rapid advancement of speech generation technologies in the era of large language models (LLMs) has established discrete speech tokens as a foundational paradigm for speech representation. These tokens, characterized by their discrete, compact, and concise nature, are not only advantageous for efficient transmission and storage, but also inherently compatible with the language modeling framework, enabling seamless integration of speech into text-dominated LLM architectures. Current research categorizes discrete speech tokens into two principal classes: acoustic tokens and semantic tokens, each of which has evolved into a rich research domain characterized by unique design philosophies and methodological approaches. This survey systematically synthesizes the existing taxonomy and recent innovations in discrete speech tokenization, conducts a critical examination of the strengths and limitations of each paradigm, and presents systematic experimental comparisons across token types. Furthermore, we identify persistent challenges in the field and propose potential research directions, aiming to offer actionable insights to inspire future advancements in the development and application of discrete speech tokens.
Authors: Leonardo Berti, Bardh Prenkaj, Paola Velardi
Abstract: Financial markets are complex systems characterized by high statistical noise, nonlinearity, volatility, and constant evolution. Thus, modeling them is extremely hard. Here, we address the task of generating realistic and responsive Limit Order Book (LOB) market simulations, which are fundamental for calibrating and testing trading strategies, performing market impact experiments, and generating synthetic market data. We propose a novel TRAnsformer-based Denoising Diffusion Probabilistic Engine for LOB Simulations (TRADES). TRADES generates realistic order flows as time series conditioned on the state of the market, leveraging a transformer-based architecture that captures the temporal and spatial characteristics of high-frequency market data. There is a notable absence of quantitative metrics for evaluating generative market simulation models in the literature. To tackle this problem, we adapt the predictive score, a metric measured as an MAE, to market data by training a stock price predictive model on synthetic data and testing it on real data. We compare TRADES with previous works on two stocks, reporting a 3.27 and 3.48 improvement over SoTA according to the predictive score, demonstrating that we generate useful synthetic market data for financial downstream tasks. Furthermore, we assess TRADES's market simulation realism and responsiveness, showing that it effectively learns the conditional data distribution and successfully reacts to an experimental agent, giving sprout to possible calibrations and evaluations of trading strategies and market impact experiments. To perform the experiments, we developed DeepMarket, the first open-source Python framework for LOB market simulation with deep learning. In our repository, we include a synthetic LOB dataset composed of TRADES's generated simulations.
Authors: Rabimba Karanjai, Lei Xu, Weidong Shi
Abstract: The rapid growth of the blockchain ecosystem and the increasing value locked in smart contracts necessitate robust security measures. While languages like Solidity and Move aim to improve smart contract security, vulnerabilities persist. This paper presents Smartify, a novel multi-agent framework leveraging Large Language Models (LLMs) to automatically detect and repair vulnerabilities in Solidity and Move smart contracts. Unlike traditional methods that rely solely on vast pre-training datasets, Smartify employs a team of specialized agents working on different specially fine-tuned LLMs to analyze code based on underlying programming concepts and language-specific security principles. We evaluated Smartify on a dataset for Solidity and a curated dataset for Move, demonstrating its effectiveness in fixing a wide range of vulnerabilities. Our results show that Smartify (Gemma2+codegemma) achieves state-of-the-art performance, surpassing existing LLMs and enhancing general-purpose models' capabilities, such as Llama 3.1. Notably, Smartify can incorporate language-specific knowledge, such as the nuances of Move, without requiring massive language-specific pre-training datasets. This work offers a detailed analysis of various LLMs' performance on smart contract repair, highlighting the strengths of our multi-agent approach and providing a blueprint for developing more secure and reliable decentralized applications in the growing blockchain landscape. We also provide a detailed recipe for extending this to other similar use cases.
Authors: Weizhi Zhang, Liangwei Yang, Wooseong Yang, Henry Peng Zou, Yuqing Liu, Ke Xu, Sourav Medya, Philip S. Yu
Abstract: Collaborative filtering (CF) is widely adopted in industrial recommender systems (RecSys) for modeling user-item interactions across numerous applications, but often struggles with cold-start and data-sparse scenarios. Recent advancements in pre-trained large language models (LLMs) with rich semantic knowledge, offer promising solutions to these challenges. However, deploying LLMs at scale is hindered by their significant computational demands and latency. In this paper, we propose a novel and scalable LLM-RecSys framework, LLMInit, designed to integrate pretrained LLM embeddings into CF models through selective initialization strategies. Specifically, we identify the embedding collapse issue observed when CF models scale and match the large embedding sizes in LLMs and avoid the problem by introducing efficient sampling methods, including, random, uniform, and variance-based selections. Comprehensive experiments conducted on multiple real-world datasets demonstrate that LLMInit significantly improves recommendation performance while maintaining low computational costs, offering a practical and scalable solution for industrial applications. To facilitate industry adoption and promote future research, we provide open-source access to our implementation at https://github.com/DavidZWZ/LLMInit.
Authors: Hariprasath Govindarajan, Maciej K. Wozniak, Marvin Klingner, Camille Maurice, B Ravi Kiran, Senthil Yogamani
Abstract: Vision foundation models (VFMs) such as DINO have led to a paradigm shift in 2D camera-based perception towards extracting generalized features to support many downstream tasks. Recent works introduce self-supervised cross-modal knowledge distillation (KD) as a way to transfer these powerful generalization capabilities into 3D LiDAR-based models. However, they either rely on highly complex distillation losses, pseudo-semantic maps, or limit KD to features useful for semantic segmentation only. In this work, we propose CleverDistiller, a self-supervised, cross-modal 2D-to-3D KD framework introducing a set of simple yet effective design choices: Unlike contrastive approaches relying on complex loss design choices, our method employs a direct feature similarity loss in combination with a multi layer perceptron (MLP) projection head to allow the 3D network to learn complex semantic dependencies throughout the projection. Crucially, our approach does not depend on pseudo-semantic maps, allowing for direct knowledge transfer from a VFM without explicit semantic supervision. Additionally, we introduce the auxiliary self-supervised spatial task of occupancy prediction to enhance the semantic knowledge, obtained from a VFM through KD, with 3D spatial reasoning capabilities. Experiments on standard autonomous driving benchmarks for 2D-to-3D KD demonstrate that CleverDistiller achieves state-of-the-art performance in both semantic segmentation and 3D object detection (3DOD) by up to 10% mIoU, especially when fine tuning on really low data amounts, showing the effectiveness of our simple yet powerful KD strategy
Authors: Zhe Wang, Yanjun Qi
Abstract: Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a closer look at the optimization objective of adversarial trigger learning and propose ATLA: Adversarial Trigger Learning with Augmented objectives. ATLA improves the negative log-likelihood loss used by previous studies into a weighted loss formulation that encourages the learned adversarial triggers to optimize more towards response format tokens. This enables ATLA to learn an adversarial trigger from just one query-response pair and the learned trigger generalizes well to other similar queries. We further design a variation to augment trigger optimization with an auxiliary loss that suppresses evasive responses. We showcase how to use ATLA to learn adversarial suffixes jailbreaking LLMs and to extract hidden system prompts. Empirically we demonstrate that ATLA consistently outperforms current state-of-the-art techniques, achieving nearly 100% success in attacking while requiring 80% fewer queries. ATLA learned jailbreak suffixes demonstrate high generalization to unseen queries and transfer well to new LLMs. We released our code https://github.com/QData/ALTA_Augmented_Adversarial_Trigger_Learning
URLs: https://github.com/QData/ALTA_Augmented_Adversarial_Trigger_Learning
Authors: Yunzhi Yao, Jizhan Fang, Jia-Chen Gu, Ningyu Zhang, Shumin Deng, Huajun Chen, Nanyun Peng
Abstract: Knowledge Editing (KE) enables the modification of outdated or incorrect information in large language models (LLMs). While existing KE methods can update isolated facts, they often fail to generalize these updates to multi-hop reasoning tasks that rely on the modified knowledge. Through an analysis of reasoning circuits -- the neural pathways LLMs use for knowledge-based inference, we find that current layer-localized KE approaches (e.g., MEMIT, WISE), which edit only single or a few model layers, inadequately integrate updated knowledge into these reasoning pathways. To address this limitation, we present CaKE (Circuit-aware Knowledge Editing), a novel method that enhances the effective integration of updated knowledge in LLMs. By only leveraging a few curated data samples guided by our circuit-based analysis, CaKE stimulates the model to develop appropriate reasoning circuits for newly incorporated knowledge. Experiments show that CaKE enables more accurate and consistent use of edited knowledge across related reasoning tasks, achieving an average improvement of 20% in multi-hop reasoning accuracy on the MQuAKE dataset while requiring less memory than existing KE methods. We release the code and data in https://github.com/zjunlp/CaKE.
Authors: Constantinos Tsakonas, Konstantinos Chatzilygeroudis
Abstract: Quality-Diversity algorithms have transformed optimization by prioritizing the discovery of diverse, high-performing solutions over a single optimal result. However, traditional Quality-Diversity methods, such as MAP-Elites, rely heavily on predefined behavior descriptors and complete prior knowledge of the task to define the behavior space grid, limiting their flexibility and applicability. In this work, we introduce Vector Quantized-Elites (VQ-Elites), a novel Quality-Diversity algorithm that autonomously constructs a structured behavior space grid using unsupervised learning, eliminating the need for prior task-specific knowledge. At the core of VQ-Elites is the integration of Vector Quantized Variational Autoencoders, which enables the dynamic learning of behavior descriptors and the generation of a structured, rather than unstructured, behavior space grid -- a significant advancement over existing unsupervised Quality-Diversity approaches. This design establishes VQ-Elites as a flexible, robust, and task-agnostic optimization framework. To further enhance the performance of unsupervised Quality-Diversity algorithms, we introduce behavior space bounding and cooperation mechanisms, which significantly improve convergence and performance, as well as the Effective Diversity Ratio and Coverage Diversity Score, two novel metrics that quantify the actual diversity in the unsupervised setting. We validate VQ-Elites on robotic arm pose-reaching, mobile robot space-covering, and MiniGrid exploration tasks. The results demonstrate its ability to efficiently generate diverse, high-quality solutions, emphasizing its adaptability, scalability, robustness to hyperparameters, and potential to extend Quality-Diversity optimization to complex, previously inaccessible domains.
Authors: Yunlong Hou, Fengzhuo Zhang, Cunxiao Du, Xuan Zhang, Jiachun Pan, Tianyu Pang, Chao Du, Vincent Y. F. Tan, Zhuoran Yang
Abstract: Speculative decoding has emerged as a popular method to accelerate the inference of Large Language Models (LLMs) while retaining their superior text generation performance. Previous methods either adopt a fixed speculative decoding configuration regardless of the prefix tokens, or train draft models in an offline or online manner to align them with the context. This paper proposes a training-free online learning framework to adaptively choose the configuration of the hyperparameters for speculative decoding as text is being generated. We first formulate this hyperparameter selection problem as a Multi-Armed Bandit problem and provide a general speculative decoding framework BanditSpec. Furthermore, two bandit-based hyperparameter selection algorithms, UCBSpec and EXP3Spec, are designed and analyzed in terms of a novel quantity, the stopping time regret. We upper bound this regret under both stochastic and adversarial reward settings. By deriving an information-theoretic impossibility result, it is shown that the regret performance of UCBSpec is optimal up to universal constants. Finally, extensive empirical experiments with LLaMA3 and Qwen2 demonstrate that our algorithms are effective compared to existing methods, and the throughput is close to the oracle best hyperparameter in simulated real-life LLM serving scenarios with diverse input prompts.
Authors: Akira Tanimoto
Abstract: Causal inference requires evaluating models on balanced distributions between treatment and control groups, while training data often exhibits imbalance due to historical decision-making policies. Most conventional statistical methods address this distribution shift through inverse probability weighting (IPW), which requires estimating propensity scores as an intermediate step. These methods face two key challenges: inaccurate propensity estimation and instability from extreme weights. We decompose the generalization error to isolate these issues--propensity ambiguity and statistical instability--and address them through an adversarial loss function. Our approach combines distributionally robust optimization for handling propensity uncertainty with weight regularization based on weighted Rademacher complexity. Experiments on synthetic and real-world datasets demonstrate consistent improvements over existing methods.
Authors: Guozhen Zhu, Yuqian Hu, Weihang Gao, Wei-Hsiang Wang, Beibei Wang, K. J. Ray Liu
Abstract: WiFi sensing has emerged as a compelling contactless modality for human activity monitoring by capturing fine-grained variations in Channel State Information (CSI). Its ability to operate continuously and non-intrusively while preserving user privacy makes it particularly suitable for health monitoring. However, existing WiFi sensing systems struggle to generalize in real-world settings, largely due to datasets collected in controlled environments with homogeneous hardware and fragmented, session-based recordings that fail to reflect continuous daily activity. We present CSI-Bench, a large-scale, in-the-wild benchmark dataset collected using commercial WiFi edge devices across 26 diverse indoor environments with 35 real users. Spanning over 461 hours of effective data, CSI-Bench captures realistic signal variability under natural conditions. It includes task-specific datasets for fall detection, breathing monitoring, localization, and motion source recognition, as well as a co-labeled multitask dataset with joint annotations for user identity, activity, and proximity. To support the development of robust and generalizable models, CSI-Bench provides standardized evaluation splits and baseline results for both single-task and multi-task learning. CSI-Bench offers a foundation for scalable, privacy-preserving WiFi sensing systems in health and broader human-centric applications.
Authors: Nabasmita Talukdar, Xiaodan Zhang, Shreya Paithankar, Hui Wang, Bin Chen
Abstract: Electronic Health Records (EHRs) have been increasingly used as real-world evidence (RWE) to support the discovery and validation of new drug indications. This paper surveys current approaches to EHR-based drug repurposing, covering data sources, processing methodologies, and representation techniques. It discusses study designs and statistical frameworks for evaluating drug efficacy. Key challenges in validation are discussed, with emphasis on the role of large language models (LLMs) and target trial emulation. By synthesizing recent developments and methodological advances, this work provides a foundational resource for researchers aiming to translate real-world data into actionable drug-repurposing evidence.
Authors: Shuai Wang, Yinan Yu
Abstract: Large Language Models (LLMs) excel in many natural language processing tasks but often exhibit factual inconsistencies in knowledge-intensive settings. Integrating external knowledge resources, particularly knowledge graphs (KGs), provides a transparent and updatable foundation for more reliable reasoning. Knowledge Base Question Answering (KBQA), which queries and reasons over KGs, is central to this effort, especially for complex, multi-hop queries. However, multi-hop reasoning poses two key challenges: (1)~maintaining coherent reasoning paths, and (2)~avoiding prematurely discarding critical multi-hop connections. To tackle these challenges, we introduce iQUEST, a question-guided KBQA framework that iteratively decomposes complex queries into simpler sub-questions, ensuring a structured and focused reasoning trajectory. Additionally, we integrate a Graph Neural Network (GNN) to look ahead and incorporate 2-hop neighbor information at each reasoning step. This dual approach strengthens the reasoning process, enabling the model to explore viable paths more effectively. Detailed experiments demonstrate the consistent improvement delivered by iQUEST across four benchmark datasets and four LLMs.
Authors: Haifeng Sun, Yu Xiong, Runze Wu, Xinyu Cai, Changjie Fan, Lan Zhang, Xiang-Yang Li
Abstract: The value and copyright of training data are crucial in the artificial intelligence industry. Service platforms should protect data providers' legitimate rights and fairly reward them for their contributions. Shapley value, a potent tool for evaluating contributions, outperforms other methods in theory, but its computational overhead escalates exponentially with the number of data providers. Recent works based on Shapley values attempt to mitigate computation complexity by approximation algorithms. However, they need to retrain for each test sample, leading to intolerable costs. We propose Fast-DataShapley, a one-pass training method that leverages the weighted least squares characterization of the Shapley value to train a reusable explainer model with real-time reasoning speed. Given new test samples, no retraining is required to calculate the Shapley values of the training data. Additionally, we propose three methods with theoretical guarantees to reduce training overhead from two aspects: the approximate calculation of the utility function and the group calculation of the training data. We analyze time complexity to show the efficiency of our methods. The experimental evaluations on various image datasets demonstrate superior performance and efficiency compared to baselines. Specifically, the performance is improved to more than 2 times, and the explainer's training speed can be increased by two orders of magnitude.
Authors: Saptarshi Nath, Christos Peridis, Eseoghene Benjamin, Xinran Liu, Soheil Kolouri, Peter Kinnell, Zexin Li, Cong Liu, Shirin Dora, Andrea Soltoggio
Abstract: Agentic AI aims to create systems that set their own goals, adapt proactively to change, and refine behavior through continuous experience. Recent advances suggest that, when facing multiple and unforeseen tasks, agents could benefit from sharing machine-learned knowledge and reusing policies that have already been fully or partially learned by other agents. However, how to query, select, and retrieve policies from a pool of agents, and how to integrate such policies remains a largely unexplored area. This study explores how an agent decides what knowledge to select, from whom, and when and how to integrate it in its own policy in order to accelerate its own learning. The proposed algorithm, \emph{Modular Sharing and Composition in Collective Learning} (MOSAIC), improves learning in agentic collectives by combining (1) knowledge selection using performance signals and cosine similarity on Wasserstein task embeddings, (2) modular and transferable neural representations via masks, and (3) policy integration, composition and fine-tuning. MOSAIC outperforms isolated learners and global sharing approaches in both learning speed and overall performance, and in some cases solves tasks that isolated agents cannot. The results also demonstrate that selective, goal-driven reuse leads to less susceptibility to task interference. We also observe the emergence of self-organization, where agents solving simpler tasks accelerate the learning of harder ones through shared knowledge.
Authors: Yuyang Zhou, Guang Cheng, Kang Du, Zihan Chen, Tian Qin, Yuyu Zhao
Abstract: The proliferation of UAVs has enabled a wide range of mission-critical applications and is becoming a cornerstone of low-altitude networks, supporting smart cities, emergency response, and more. However, the open wireless environment, dynamic topology, and resource constraints of UAVs expose low-altitude networks to severe DoS threats. Traditional defense approaches, which rely on fixed configurations or centralized decision-making, cannot effectively respond to the rapidly changing conditions in UAV swarm environments. To address these challenges, we propose a novel federated multi-agent deep reinforcement learning (FMADRL)-driven moving target defense (MTD) framework for proactive DoS mitigation in low-altitude networks. Specifically, we design lightweight and coordinated MTD mechanisms, including leader switching, route mutation, and frequency hopping, to disrupt attacker efforts and enhance network resilience. The defense problem is formulated as a multi-agent partially observable Markov decision process, capturing the uncertain nature of UAV swarms under attack. Each UAV is equipped with a policy agent that autonomously selects MTD actions based on partial observations and local experiences. By employing a policy gradient-based algorithm, UAVs collaboratively optimize their policies via reward-weighted aggregation. Extensive simulations demonstrate that our approach significantly outperforms state-of-the-art baselines, achieving up to a 34.6% improvement in attack mitigation rate, a reduction in average recovery time of up to 94.6%, and decreases in energy consumption and defense cost by as much as 29.3% and 98.3%, respectively, under various DoS attack strategies. These results highlight the potential of intelligent, distributed defense mechanisms to protect low-altitude networks, paving the way for reliable and scalable low-altitude economy.
Authors: Sumanth Manduru, Carlotta Domeniconi
Abstract: The rapid adoption of Small Language Models (SLMs) for resource constrained applications has outpaced our understanding of their ethical and fairness implications. To address this gap, we introduce the Vacuous Neutrality Framework (VaNeu), a multi-dimensional evaluation paradigm designed to assess SLM fairness prior to deployment. The framework examines model robustness across four stages - biases, utility, ambiguity handling, and positional bias over diverse social bias categories. To the best of our knowledge, this work presents the first large-scale audit of SLMs in the 0.5-5B parameter range, an overlooked "middle tier" between BERT-class encoders and flagship LLMs. We evaluate nine widely used SLMs spanning four model families under both ambiguous and disambiguated contexts. Our findings show that models demonstrating low bias in early stages often fail subsequent evaluations, revealing hidden vulnerabilities and unreliable reasoning. These results underscore the need for a more comprehensive understanding of fairness and reliability in SLMs, and position the proposed framework as a principled tool for responsible deployment in socially sensitive settings.
Authors: Brown Ebouky, Andrea Bartezzaghi, Mattia Rigotti
Abstract: The recent advent of reasoning models like OpenAI's o1 was met with excited speculation by the AI community about the mechanisms underlying these capabilities in closed models, followed by a rush of replication efforts, particularly from the open source community. These speculations were largely settled by the demonstration from DeepSeek-R1 that chains-of-thought and reinforcement learning (RL) can effectively replicate reasoning on top of base LLMs. However, it remains valuable to explore alternative methods for theoretically eliciting reasoning that could help elucidate the underlying mechanisms, as well as providing additional methods that may offer complementary benefits. Here, we build on the long-standing literature in cognitive psychology and cognitive architectures, which postulates that reasoning arises from the orchestrated, sequential execution of a set of modular, predetermined cognitive operations. Crucially, we implement this key idea within a modern agentic tool-calling framework. In particular, we endow an LLM with a small set of "cognitive tools" encapsulating specific reasoning operations, each executed by the LLM itself. Surprisingly, this simple strategy results in considerable gains in performance on standard mathematical reasoning benchmarks compared to base LLMs, for both closed and open-weight models. For instance, providing our "cognitive tools" to GPT-4.1 increases its pass@1 performance on AIME2024 from 32% to 53%, even surpassing the performance of o1-preview. In addition to its practical implications, this demonstration contributes to the debate regarding the role of post-training methods in eliciting reasoning in LLMs versus the role of inherent capabilities acquired during pre-training, and whether post-training merely uncovers these latent abilities.
Authors: Romy M\"uller
Abstract: Concept-based explainable artificial intelligence (C-XAI) can let people see which representations an AI model has learned. This is particularly important when high-level semantic information (e.g., actions and relations) is used to make decisions about abstract categories (e.g., danger). In such tasks, AI models need to generalise beyond situation-specific details, and this ability can be reflected in C-XAI outputs that randomise over irrelevant features. However, it is unclear whether people appreciate such generalisation and can distinguish it from other, less desirable forms of imprecision in C-XAI outputs. Therefore, the present study investigated how the generality and relevance of C-XAI outputs affect people's evaluation of AI. In an experimental railway safety evaluation scenario, participants rated the performance of a simulated AI that classified traffic scenes involving people as dangerous or not. These classification decisions were explained via concepts in the form of similar image snippets. The latter differed in their match with the classified image, either regarding a highly relevant feature (i.e., people's relation to tracks) or a less relevant feature (i.e., people's action). Contrary to the hypotheses, concepts that generalised over less relevant features were rated lower than concepts that matched the classified image precisely. Moreover, their ratings were no better than those for systematic misrepresentations of the less relevant feature. Conversely, participants were highly sensitive to imprecisions in relevant features. These findings cast doubts on the assumption that people can easily infer from C-XAI outputs whether AI models have gained a deeper understanding of complex situations.
Authors: Yimu Wang, Mozhgan Nasr Azadani, Sean Sedwards, Krzysztof Czarnecki
Abstract: Improving the visual understanding ability of vision-language models (VLMs) is crucial for enhancing their performance across various tasks. While using multiple pretrained visual experts has shown great promise, it often incurs significant computational costs during training and inference. To address this challenge, we propose HAWAII, a novel framework that distills knowledge from multiple visual experts into a single vision encoder, enabling it to inherit the complementary strengths of several experts with minimal computational overhead. To mitigate conflicts among different teachers and switch between different teacher-specific knowledge, instead of using a fixed set of adapters for multiple teachers, we propose to use teacher-specific Low-Rank Adaptation (LoRA) adapters with a corresponding router. Each adapter is aligned with a specific teacher, avoiding noisy guidance during distillation. To enable efficient knowledge distillation, we propose fine-grained and coarse-grained distillation. At the fine-grained level, token importance scores are employed to emphasize the most informative tokens from each teacher adaptively. At the coarse-grained level, we summarize the knowledge from multiple teachers and transfer it to the student using a set of general-knowledge LoRA adapters with a router. Extensive experiments on various vision-language tasks demonstrate the superiority of HAWAII compared to popular open-source VLMs. The code is available at https://github.com/yimuwangcs/wise-hawaii.
Authors: Chengxuan Xia, Qianye Wu, Sixuan Tian, Yilun Hao
Abstract: Large language model (LLM) agents have shown increasing promise for collaborative task completion. However, existing multi-agent frameworks often rely on static workflows, fixed roles, and limited inter-agent communication, reducing their effectiveness in open-ended, high-complexity domains. This paper proposes a coordination framework that enables adaptiveness through three core mechanisms: dynamic task routing, bidirectional feedback, and parallel agent evaluation. The framework allows agents to reallocate tasks based on confidence and workload, exchange structured critiques to iteratively improve outputs, and crucially compete on high-ambiguity subtasks with evaluator-driven selection of the most suitable result. We instantiate these principles in a modular architecture and demonstrate substantial improvements in factual coverage, coherence, and efficiency over static and partially adaptive baselines. Our findings highlight the benefits of incorporating both adaptiveness and structured competition in multi-agent LLM systems.
Authors: Rashika Raina, Nidhi Simmons, David E. Simmons, Michel Daoud Yacoub, Trung Q. Duong
Abstract: In next-generation communications and networks, machine learning (ML) models are expected to deliver not only accurate predictions but also well-calibrated confidence scores that reflect the true likelihood of correct decisions. This paper studies the calibration performance of an ML-based outage predictor within a single-user, multi-resource allocation framework. We first establish key theoretical properties of this system's outage probability (OP) under perfect calibration. Importantly, we show that as the number of resources grows, the OP of a perfectly calibrated predictor approaches the expected output conditioned on it being below the classification threshold. In contrast, when only one resource is available, the system's OP equals the model's overall expected output. We then derive the OP conditions for a perfectly calibrated predictor. These findings guide the choice of the classification threshold to achieve a desired OP, helping system designers meet specific reliability requirements. We also demonstrate that post-processing calibration cannot improve the system's minimum achievable OP, as it does not introduce new information about future channel states. Additionally, we show that well-calibrated models are part of a broader class of predictors that necessarily improve OP. In particular, we establish a monotonicity condition that the accuracy-confidence function must satisfy for such improvement to occur. To demonstrate these theoretical properties, we conduct a rigorous simulation-based analysis using post-processing calibration techniques: Platt scaling and isotonic regression. As part of this framework, the predictor is trained using an outage loss function specifically designed for this system. Furthermore, this analysis is performed on Rayleigh fading channels with temporal correlation captured by Clarke's 2D model, which accounts for receiver mobility.
Authors: Yannik Schnitzer, Alessandro Abate, David Parker
Abstract: Robust Markov decision processes (r-MDPs) extend MDPs by explicitly modelling epistemic uncertainty about transition dynamics. Learning r-MDPs from interactions with an unknown environment enables the synthesis of robust policies with provable (PAC) guarantees on performance, but this can require a large number of sample interactions. We propose novel methods for solving and learning r-MDPs based on factored state-space representations that leverage the independence between model uncertainty across system components. Although policy synthesis for factored r-MDPs leads to hard, non-convex optimisation problems, we show how to reformulate these into tractable linear programs. Building on these, we also propose methods to learn factored model representations directly. Our experimental results show that exploiting factored structure can yield dimensional gains in sample efficiency, producing more effective robust policies with tighter performance guarantees than state-of-the-art methods.
Authors: Soumik Dey, Benjamin Braun, Naveen Ravipati, Hansi Wu, Binbin Li
Abstract: E-commerce sellers are advised to bid on keyphrases to boost their advertising campaigns. These keyphrases must be relevant to prevent irrelevant items from cluttering search systems and to maintain positive seller perception. It is vital that keyphrase suggestions align with seller, search and buyer judgments. Given the challenges in collecting negative feedback in these systems, LLMs have been used as a scalable proxy to human judgments. This paper presents an empirical study on a major ecommerce platform of a distillation framework involving an LLM teacher, a cross-encoder assistant and a bi-encoder Embedding Based Retrieval (EBR) student model, aimed at mitigating click-induced biases in keyphrase recommendations.
Authors: Vasudha Varadarajan, Hui Xu, Rebecca Astrid Boehme, Mariam Marlan Mirstrom, Sverker Sikstrom, H. Andrew Schwartz
Abstract: Recent advances in large language models (LLMs) offer new opportunities for scalable, interactive mental health assessment, but excessive querying by LLMs burdens users and is inefficient for real-world screening across transdiagnostic symptom profiles. We introduce MAQuA, an adaptive question-asking framework for simultaneous, multidimensional mental health screening. Combining multi-outcome modeling on language responses with item response theory (IRT) and factor analysis, MAQuA selects the questions with most informative responses across multiple dimensions at each turn to optimize diagnostic information, improving accuracy and potentially reducing response burden. Empirical results on a novel dataset reveal that MAQuA reduces the number of assessment questions required for score stabilization by 50-87% compared to random ordering (e.g., achieving stable depression scores with 71% fewer questions and eating disorder scores with 85% fewer questions). MAQuA demonstrates robust performance across both internalizing (depression, anxiety) and externalizing (substance use, eating disorder) domains, with early stopping strategies further reducing patient time and burden. These findings position MAQuA as a powerful and efficient tool for scalable, nuanced, and interactive mental health screening, advancing the integration of LLM-based agents into real-world clinical workflows.
Authors: Shuang Liang, Zhihao Xu, Jialing Tao, Hui Xue, Xiting Wang
Abstract: Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To address this, existing detection methods either learn attack-specific parameters, which hinders generalization to unseen attacks, or rely on heuristically sound principles, which limit accuracy and efficiency. To overcome these limitations, we propose Learning to Detect (LoD), a general framework that accurately detects unknown jailbreak attacks by shifting the focus from attack-specific learning to task-specific learning. This framework includes a Multi-modal Safety Concept Activation Vector module for safety-oriented representation learning and a Safety Pattern Auto-Encoder module for unsupervised attack classification. Extensive experiments show that our method achieves consistently higher detection AUROC on diverse unknown attacks while improving efficiency. The code is available at https://anonymous.4open.science/r/Learning-to-Detect-51CB.
URLs: https://anonymous.4open.science/r/Learning-to-Detect-51CB.
Authors: Ruheng Wang, Hang Zhang, Trieu Nguyen, Shasha Feng, Hao-Wei Pang, Xiang Yu, Li Xiao, Peter Zhiping Zhang
Abstract: Designing therapeutic peptides with tailored properties is hindered by the vastness of sequence space, limited experimental data, and poor interpretability of current generative models. To address these challenges, we introduce PepThink-R1, a generative framework that integrates large language models (LLMs) with chain-of-thought (CoT) supervised fine-tuning and reinforcement learning (RL). Unlike prior approaches, PepThink-R1 explicitly reasons about monomer-level modifications during sequence generation, enabling interpretable design choices while optimizing for multiple pharmacological properties. Guided by a tailored reward function balancing chemical validity and property improvements, the model autonomously explores diverse sequence variants. We demonstrate that PepThink-R1 generates cyclic peptides with significantly enhanced lipophilicity, stability, and exposure, outperforming existing general LLMs (e.g., GPT-5) and domain-specific baseline in both optimization success and interpretability. To our knowledge, this is the first LLM-based peptide design framework that combines explicit reasoning with RL-driven property control, marking a step toward reliable and transparent peptide optimization for therapeutic discovery.
Authors: Alina Fastowski, Bardh Prenkaj, Gjergji Kasneci
Abstract: Ensuring the robustness of factual knowledge in LLMs is critical for reliable applications in tasks such as question answering and reasoning. However, existing evaluation methods predominantly focus on performance-based metrics, often investigating from the perspective of prompt perturbations, which captures only the externally triggered side of knowledge robustness. To bridge this gap, we introduce a principled approach to measure factual robustness from the perspective of the generation process by analyzing token distribution entropy in combination with temperature scaling sensitivity. These two factors build the Factual Robustness Score (FRS), a novel metric which quantifies the stability of a fact against perturbations in decoding conditions, given its initial uncertainty. To validate our approach, we conduct extensive experiments on 5 LLMs across 3 closed-book QA datasets (SQuAD, TriviaQA, and HotpotQA). We show that factual robustness varies significantly -- smaller models report an FRS of $0.76$, larger ones $0.93$ -- with accuracy degrading by ~$60\%$ under increased uncertainty. These insights demonstrate how entropy and temperature scaling impact factual accuracy, and lay a foundation for developing more robust knowledge retention and retrieval in future models.
Authors: Manpreet Singh, Hassan Sajjad
Abstract: Quantization offers a practical solution to deploy LLMs in resource-constraint environments. However, its impact on internal representations remains understudied, raising questions about the reliability of quantized models. In this study, we employ a range of interpretability techniques to investigate how quantization affects model and neuron behavior. We analyze multiple LLMs under 4-bit and 8-bit quantization. Our findings reveal that the impact of quantization on model calibration is generally minor. Analysis of neuron activations indicates that the number of dead neurons, i.e., those with activation values close to 0 across the dataset, remains consistent regardless of quantization. In terms of neuron contribution to predictions, we observe that smaller full precision models exhibit fewer salient neurons, whereas larger models tend to have more, with the exception of Llama-2-7B. The effect of quantization on neuron redundancy varies across models. Overall, our findings suggest that effect of quantization may vary by model and tasks, however, we did not observe any drastic change which may discourage the use of quantization as a reliable model compression technique.
Authors: Kyohoon Jin, Juhwan Choi, Jungmin Yun, Junho Lee, Soojin Jang, Youngbin Kim
Abstract: Deep learning models often learn and exploit spurious correlations in training data, using these non-target features to inform their predictions. Such reliance leads to performance degradation and poor generalization on unseen data. To address these limitations, we introduce a more general form of counterfactual data augmentation, termed counterbias data augmentation, which simultaneously tackles multiple biases (e.g., gender bias, simplicity bias) and enhances out-of-distribution robustness. We present CoBA: CounterBias Augmentation, a unified framework that operates at the semantic triple level: first decomposing text into subject-predicate-object triples, then selectively modifying these triples to disrupt spurious correlations. By reconstructing the text from these adjusted triples, CoBA generates counterbias data that mitigates spurious patterns. Through extensive experiments, we demonstrate that CoBA not only improves downstream task performance, but also effectively reduces biases and strengthens out-of-distribution resilience, offering a versatile and robust solution to the challenges posed by spurious correlations.
Authors: Shota Arai, David Selby, Andrew Vargo, Sebastian Vollmer
Abstract: Imagine a world where clinical trials need far fewer patients to achieve the same statistical power, thanks to the knowledge encoded in large language models (LLMs). We present a novel framework for hierarchical Bayesian modeling of adverse events in multi-center clinical trials, leveraging LLM-informed prior distributions. Unlike data augmentation approaches that generate synthetic data points, our methodology directly obtains parametric priors from the model. Our approach systematically elicits informative priors for hyperparameters in hierarchical Bayesian models using a pre-trained LLM, enabling the incorporation of external clinical expertise directly into Bayesian safety modeling. Through comprehensive temperature sensitivity analysis and rigorous cross-validation on real-world clinical trial data, we demonstrate that LLM-derived priors consistently improve predictive performance compared to traditional meta-analytical approaches. This methodology paves the way for more efficient and expert-informed clinical trial design, enabling substantial reductions in the number of patients required to achieve robust safety assessment and with the potential to transform drug safety monitoring and regulatory decision making.
Authors: Aadit Sengupta, Pratinav Seth, Vinay Kumar Sankarapu
Abstract: Frontier AI systems require governance mechanisms that can verify internal alignment, not just behavioral compliance. Private governance mechanisms audits, certification, insurance, and procurement are emerging to complement public regulation, but they require technical substrates that generate verifiable causal evidence about model behavior. This paper argues that mechanistic interpretability provides this substrate. We frame interpretability not as post-hoc explanation but as a design constraint embedding auditability, provenance, and bounded transparency within model architectures. Integrating causal abstraction theory and empirical benchmarks such as MIB and LoBOX, we outline how interpretability-first models can underpin private assurance pipelines and role-calibrated transparency frameworks. This reframing situates interpretability as infrastructure for private AI governance bridging the gap between technical reliability and institutional accountability.
Authors: Aravindhan G, Yuvaraj Govindarajulu, Parin Shah
Abstract: Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on white-box attacks with constrained optimizations, and transferability based black-box attacks against commercial Automatic Speech Recognition devices, this paper explores cost efficient white-box attack and non transferability black-box adversarial attacks on Automatic Speech Recognition systems, drawing insights from approaches such as Fast Gradient Sign Method and Zeroth-Order Optimization. Further, the novelty of the paper includes how poisoning attack can degrade the performances of state-of-the-art models leading to misinterpretation of audio signals. Through experimentation and analysis, we illustrate how hybrid models can generate subtle yet impactful adversarial examples with very little perturbation having Signal Noise Ratio of 35dB that can be generated within a minute. These vulnerabilities of state-of-the-art open source model have practical security implications, and emphasize the need for adversarial security.
Authors: Zhinan Xie, Peisong Wang, Shuang Qiu, Jian Cheng
Abstract: Speculative decoding has proven effective for accelerating inference in Large Language Models (LLMs), yet its extension to Vision-Language Models (VLMs) remains limited by the computational burden and semantic inconsistency introduced by visual tokens. Recent studies reveal that visual tokens in large VLMs are highly redundant, and most of them can be removed without compromising generation quality. Motivated by this observation, we propose HiViS (Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models), a framework that utilizes the target VLM as a semantic fusion model, allowing the drafter to obtain visual information without explicitly processing visual tokens, ensuring that the drafter's prefill sequence length matches that of the textual tokens. Furthermore, HiViS employs a time-step-aware aligned training scheme that allows the drafter to autonomously propagate and refine instructive visual-textual semantics during independent drafting, guided by step-dependent bias-correction residuals. Extensive experiments across representative VLMs and benchmarks demonstrate that HiViS achieves significant improvements in average acceptance length and speedup ratio.
Authors: Renhua Ding, Xiao Yang, Zhengwei Fang, Jun Luo, Kun He, Jun Zhu
Abstract: Large vision-language models (LVLMs) enable autonomous mobile agents to operate smartphone user interfaces, yet vulnerabilities in their perception and interaction remain critically understudied. Existing research often relies on conspicuous overlays, elevated permissions, or unrealistic threat assumptions, limiting stealth and real-world feasibility. In this paper, we introduce a practical and stealthy jailbreak attack framework, which comprises three key components: (i) non-privileged perception compromise, which injects visual payloads into the application interface without requiring elevated system permissions; (ii) agent-attributable activation, which leverages input attribution signals to distinguish agent from human interactions and limits prompt exposure to transient intervals to preserve stealth from end users; and (iii) efficient one-shot jailbreak, a heuristic iterative deepening search algorithm (HG-IDA*) that performs keyword-level detoxification to bypass built-in safety alignment of LVLMs. Moreover, we developed three representative Android applications and curated a prompt-injection dataset for mobile agents. We evaluated our attack across multiple LVLM backends, including closed-source services and representative open-source models, and observed high planning and execution hijack rates (e.g., GPT-4o: 82.5% planning / 75.0% execution), exposing a fundamental security vulnerability in current mobile agents and underscoring critical implications for autonomous smartphone operation.
Authors: Tim Tian Hua, Andrew Qin, Samuel Marks, Neel Nanda
Abstract: Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an LLM's activations can suppress evaluation-awareness and make the model act like it is deployed during evaluation. To study our steering technique, we train an LLM to exhibit evaluation-aware behavior using a two-step training process designed to mimic how this behavior could emerge naturally. First, we perform continued pretraining on documents with factual descriptions of the model (1) using Python type hints during evaluation but not during deployment and (2) recognizing that the presence of a certain evaluation cue always means that it is being tested. Then, we train the model with expert iteration to use Python type hints in evaluation settings. The resulting model is evaluation-aware: it writes type hints in evaluation contexts more than deployment contexts. We find that activation steering can suppress evaluation awareness and make the model act like it is deployed even when the cue is present. Importantly, we constructed our steering vector using the original model before our additional training. Our results suggest that AI evaluators could improve the reliability of safety evaluations by steering models to act like they are deployed.
Authors: Jianqing Zhang, Zhezheng Hao, Wei Xia, Hande Dong, Hong Wang, Chenxing Wei, Yuyan Zhou, Yubin Qi, Qiang Lin, Jian Cao
Abstract: Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, where group-relative methods like GRPO are popular for their critic-free, normalized advantage estimation. However, in real-world code-editing scenarios, reward distributions are often skewed with unpredictable outliers, leading to distorted advantage computation and increased noise. To address this issue, we propose Group Adaptive Policy Optimization (GAPO), which adaptively finds an outlier-free highest-density interval (HDI) per prompt and then uses the median of that interval as an adaptive Q to replace the group mean in advantage calculation. This adaptive Q robustly handles skewed distributions while remaining plug-and-play and efficient. We validate GAPO on nine instruction-tuned LLMs (3B-14B) using a large internal dataset of 51,844 real-world, history-aware code-editing tasks across 10 languages, demonstrating consistent improvements in exact match accuracy over GRPO and its variant DAPO. Code is publicly available.
Authors: Dong Chen, Yanzhe Wei, Zonglin He, Guan-Ming Kuang, Canhua Ye, Meiru An, Huili Peng, Yong Hu, Huiren Tao, Kenneth MC Cheung
Abstract: Large language models (LLMs) offer transformative potential for clinical decision support in spine surgery but pose significant risks through hallucinations, which are factually inconsistent or contextually misaligned outputs that may compromise patient safety. This study introduces a clinician-centered framework to quantify hallucination risks by evaluating diagnostic precision, recommendation quality, reasoning robustness, output coherence, and knowledge alignment. We assessed six leading LLMs across 30 expert-validated spinal cases. DeepSeek-R1 demonstrated superior overall performance (total score: 86.03 $\pm$ 2.08), particularly in high-stakes domains such as trauma and infection. A critical finding reveals that reasoning-enhanced model variants did not uniformly outperform standard counterparts: Claude-3.7-Sonnet's extended thinking mode underperformed relative to its standard version (80.79 $\pm$ 1.83 vs. 81.56 $\pm$ 1.92), indicating extended chain-of-thought reasoning alone is insufficient for clinical reliability. Multidimensional stress-testing exposed model-specific vulnerabilities, with recommendation quality degrading by 7.4% under amplified complexity. This decline contrasted with marginal improvements in rationality (+2.0%), readability (+1.7%) and diagnosis (+4.7%), highlighting a concerning divergence between perceived coherence and actionable guidance. Our findings advocate integrating interpretability mechanisms (e.g., reasoning chain visualization) into clinical workflows and establish a safety-aware validation framework for surgical LLM deployment.
Authors: Pasan Dissanayake, Sanghamitra Dutta
Abstract: Transformer-based models have shown promising performance on tabular data compared to their classical counterparts such as neural networks and Gradient Boosted Decision Trees (GBDTs) in scenarios with limited training data. They utilize their pre-trained knowledge to adapt to new domains, achieving commendable performance with only a few training examples, also called the few-shot regime. However, the performance gain in the few-shot regime comes at the expense of significantly increased complexity and number of parameters. To circumvent this trade-off, we introduce TabDistill, a new strategy to distill the pre-trained knowledge in complex transformer-based models into simpler neural networks for effectively classifying tabular data. Our framework yields the best of both worlds: being parameter-efficient while performing well with limited training data. The distilled neural networks surpass classical baselines such as regular neural networks, XGBoost and logistic regression under equal training data, and in some cases, even the original transformer-based models that they were distilled from.
Authors: Alina Fastowski, Bardh Prenkaj, Yuxiao Li, Gjergji Kasneci
Abstract: LLMs are now an integral part of information retrieval. As such, their role as question answering chatbots raises significant concerns due to their shown vulnerability to adversarial man-in-the-middle (MitM) attacks. Here, we propose the first principled attack evaluation on LLM factual memory under prompt injection via Xmera, our novel, theory-grounded MitM framework. By perturbing the input given to "victim" LLMs in three closed-book and fact-based QA settings, we undermine the correctness of the responses and assess the uncertainty of their generation process. Surprisingly, trivial instruction-based attacks report the highest success rate (up to ~85.3%) while simultaneously having a high uncertainty for incorrectly answered questions. To provide a simple defense mechanism against Xmera, we train Random Forest classifiers on the response uncertainty levels to distinguish between attacked and unattacked queries (average AUC of up to ~96%). We believe that signaling users to be cautious about the answers they receive from black-box and potentially corrupt LLMs is a first checkpoint toward user cyberspace safety.
Authors: Kevin B\"onisch, Leandro Losaria
Abstract: Since 2010, Kaggle has been a platform where data scientists from around the world come together to compete, collaborate, and push the boundaries of Data Science. Over these 15 years, it has grown from a purely competition-focused site into a broader ecosystem with forums, notebooks, models, datasets, and more. With the release of the Kaggle Meta Code and Kaggle Meta Datasets, we now have a unique opportunity to explore these competitions, technologies, and real-world applications of Machine Learning and AI. And so in this study, we take a closer look at 15 years of data science on Kaggle - through metadata, shared code, community discussions, and the competitions themselves. We explore Kaggle's growth, its impact on the data science community, uncover hidden technological trends, analyze competition winners, how Kagglers approach problems in general, and more. We do this by analyzing millions of kernels and discussion threads to perform both longitudinal trend analysis and standard exploratory data analysis. Our findings show that Kaggle is a steadily growing platform with increasingly diverse use cases, and that Kagglers are quick to adapt to new trends and apply them to real-world challenges, while producing - on average - models with solid generalization capabilities. We also offer a snapshot of the platform as a whole, highlighting its history and technological evolution. Finally, this study is accompanied by a video (https://www.youtube.com/watch?v=YVOV9bIUNrM) and a Kaggle write-up (https://kaggle.com/competitions/meta-kaggle-hackathon/writeups/kaggle-chronicles-15-years-of-competitions-communi) for your convenience.
URLs: https://www.youtube.com/watch?v=YVOV9bIUNrM), https://kaggle.com/competitions/meta-kaggle-hackathon/writeups/kaggle-chronicles-15-years-of-competitions-communi)
Authors: Kaiyuan Zhai, Jiacheng Cui, Zhehao Zhang, Junyu Xue, Yang Deng, Kui Wu, Guoming Tang
Abstract: Cross-domain HVAC energy prediction is essential for scalable building energy management, particularly because collecting extensive labeled data for every new building is both costly and impractical. Yet, this task remains highly challenging due to the scarcity and heterogeneity of data across different buildings, climate zones, and seasonal patterns. In particular, buildings situated in distinct climatic regions introduce variability that often leads existing methods to overfit to spurious correlations, rely heavily on expert intervention, or compromise on data diversity. To address these limitations, we propose CaberNet, a causal and interpretable deep sequence model that learns invariant (Markov blanket) representations for robust cross-domain prediction. In a purely data-driven fashion and without requiring any prior knowledge, CaberNet integrates i) a global feature gate trained with a self-supervised Bernoulli regularization to distinguish superior causal features from inferior ones, and ii) a domain-wise training scheme that balances domain contributions, minimizes cross-domain loss variance, and promotes latent factor independence. We evaluate CaberNet on real-world datasets collected from three buildings located in three climatically diverse cities, and it consistently outperforms all baselines, achieving a 22.9% reduction in normalized mean squared error (NMSE) compared to the best benchmark. Our code is available at https://github.com/SusCom-Lab/CaberNet-CRL.
Authors: Seungeon Lee, Soumi Das, Manish Gupta, Krishna P. Gummadi
Abstract: Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for fine-tuning large language models. However, conventional LoRA adapters are typically trained for a single task, limiting their applicability in real-world settings where inputs may span diverse and unpredictable domains. At inference time, existing approaches combine multiple LoRAs for improving performance on diverse tasks, while usually requiring labeled data or additional task-specific training, which is expensive at scale. In this work, we introduce LoRA on the Go (LoGo), a training-free framework that dynamically selects and merges adapters at the instance level without any additional requirements. LoGo leverages signals extracted from a single forward pass through LoRA adapters, to identify the most relevant adapters and determine their contributions on-the-fly. Across 5 NLP benchmarks, 27 datasets, and 3 model families, LoGo outperforms training-based baselines on some tasks upto a margin of 3.6% while remaining competitive on other tasks and maintaining inference throughput, highlighting its effectiveness and practicality.
Authors: Ihab Tabbara, Yuxuan Yang, Hussein Sibai
Abstract: Safety assurance is a fundamental requirement for deploying learning-enabled autonomous systems. Hamilton-Jacobi (HJ) reachability analysis is a fundamental method for formally verifying safety and generating safe controllers. However, computing the HJ value function that characterizes the backward reachable set (BRS) of a set of user-defined failure states is computationally expensive, especially for high-dimensional systems, motivating the use of reinforcement learning approaches to approximate the value function. Unfortunately, a learned value function and its corresponding safe policy are not guaranteed to be correct. The learned value function evaluated at a given state may not be equal to the actual safety return achieved by following the learned safe policy. To address this challenge, we introduce a conformal prediction-based (CP) framework that bounds such uncertainty. We leverage CP to provide probabilistic safety guarantees when using learned HJ value functions and policies to prevent control systems from reaching failure states. Specifically, we use CP to calibrate the switching between the unsafe nominal controller and the learned HJ-based safe policy and to derive safety guarantees under this switched policy. We also investigate using an ensemble of independently trained HJ value functions as a safety filter and compare this ensemble approach to using individual value functions alone.
Authors: Qinfeng Li, Miao Pan, Jintao Chen, Fu Teng, Zhiqiang Shen, Ge Su, Hao Peng, Xuhong Zhang
Abstract: Model merging has emerged as an efficient technique for expanding large language models (LLMs) by integrating specialized expert models. However, it also introduces a new threat: model merging stealing, where free-riders exploit models through unauthorized model merging. Unfortunately, existing defense mechanisms fail to provide effective protection. Specifically, we identify three critical protection properties that existing methods fail to simultaneously satisfy: (1) proactively preventing unauthorized merging; (2) ensuring compatibility with general open-source settings; (3) achieving high security with negligible performance loss. To address the above issues, we propose MergeBarrier, a plug-and-play defense that proactively prevents unauthorized merging. The core design of MergeBarrier is to disrupt the Linear Mode Connectivity (LMC) between the protected model and its homologous counterparts, thereby eliminating the low-loss path required for effective model merging. Extensive experiments show that MergeBarrier effectively prevents model merging stealing with negligible accuracy loss.
Authors: Brad Shook, Abby Turner, Jieshi Chen, Micha{\l} Wili\'nski, Mononito Goswami, Jonathan Elmer, Artur Dubrawski
Abstract: Time series foundation models (TSFMs) pretrained on data from multiple domains have shown strong performance on diverse modeling tasks. Various efforts have been made to develop foundation models specific to electroencephalography (EEG) data, which records brain electrical activity as time series. However, no comparative analysis of EEG-specific foundation models (EEGFMs) versus general TSFMs has been performed on EEG-specific tasks. We introduce a novel Spatial-Temporal Adapter with Multi-Head Pooling (STAMP), which leverages univariate embeddings produced by a general TSFM, implicitly models spatial-temporal characteristics of EEG data, and achieves performance comparable to state-of-the-art EEGFMs. A comprehensive analysis is performed on 8 benchmark datasets of clinical tasks using EEG for classification, along with ablation studies. Our proposed adapter is lightweight in trainable parameters and flexible in the inputs it can accommodate, supporting easy modeling of EEG data using TSFMs.
Authors: Shivam Barwey, Pinaki Pal
Abstract: Super-resolution flow reconstruction using state-of-the-art data-driven techniques is valuable for a variety of applications, such as subgrid/subfilter closure modeling, accelerating spatiotemporal forecasting, data compression, and serving as an upscaling tool for sparse experimental measurements. In the present work, a first-of-its-kind multiscale graph transformer approach is developed for mesh-based super-resolution (SR-GT) of reacting flows. The novel data-driven modeling paradigm leverages a graph-based flow-field representation compatible with complex geometries and non-uniform/unstructured grids. Further, the transformer backbone captures long-range dependencies between different parts of the low-resolution flow-field, identifies important features, and then generates the super-resolved flow-field that preserves those features at a higher resolution. The performance of SR-GT is demonstrated in the context of spectral-element-discretized meshes for a challenging test problem of 2D detonation propagation within a premixed hydrogen-air mixture exhibiting highly complex multiscale reacting flow behavior. The SR-GT framework utilizes a unique element-local (+ neighborhood) graph representation for the coarse input, which is then tokenized before being processed by the transformer component to produce the fine output. It is demonstrated that SR-GT provides high super-resolution accuracy for reacting flow-field features and superior performance compared to traditional interpolation-based SR schemes.
Authors: Desheng Hu, Joachim Baumann, Aleksandra Urman, Elsa Lichtenegger, Robin Forsberg, Aniko Hannak, Christo Wilson
Abstract: Google Search increasingly surfaces AI-generated content through features like AI Overviews (AIO) and Featured Snippets (FS), which users frequently rely on despite having no control over their presentation. Through a systematic algorithm audit of 1,508 real baby care and pregnancy-related queries, we evaluate the quality and consistency of these information displays. Our robust evaluation framework assesses multiple quality dimensions, including answer consistency, relevance, presence of medical safeguards, source categories, and sentiment alignment. Our results reveal concerning gaps in information consistency, with information in AIO and FS displayed on the same search result page being inconsistent with each other in 33% of cases. Despite high relevance scores, both features critically lack medical safeguards (present in just 11% of AIO and 7% of FS responses). While health and wellness websites dominate source categories for both, AIO and FS, FS also often link to commercial sources. These findings have important implications for public health information access and demonstrate the need for stronger quality controls in AI-mediated health information. Our methodology provides a transferable framework for auditing AI systems across high-stakes domains where information quality directly impacts user well-being.
Authors: Hilaf Hasson, Ruocheng Guo
Abstract: We present a practical framework for detecting errors in LLM-generated SQL by estimating uncertainty at the level of individual nodes in the query's abstract syntax tree (AST). Our approach proceeds in two stages. First, we introduce a semantically aware labeling algorithm that, given a generated SQL and a gold reference, assigns node-level correctness without over-penalizing structural containers or alias variation. Second, we represent each node with a rich set of schema-aware and lexical features - capturing identifier validity, alias resolution, type compatibility, ambiguity in scope, and typo signals - and train a supervised classifier to predict per-node error probabilities. We interpret these probabilities as calibrated uncertainty, enabling fine-grained diagnostics that pinpoint exactly where a query is likely to be wrong. Across multiple databases and datasets, our method substantially outperforms token log-probabilities: average AUC improves by +27.44% while maintaining robustness under cross-database evaluation. Beyond serving as an accuracy signal, node-level uncertainty supports targeted repair, human-in-the-loop review, and downstream selective execution. Together, these results establish node-centric, semantically grounded uncertainty estimation as a strong and interpretable alternative to aggregate sequence level confidence measures.
Authors: John P. Nelson, Olajide Olugbade, Philip Shapira, Justin B. Biddle
Abstract: Artificial intelligence (AI) raises expectations of substantial increases in rates of technological and scientific progress, but such anticipations are often not connected to detailed ground-level studies of AI use in innovation processes. Accordingly, it remains unclear how and to what extent AI can accelerate innovation. To help to fill this gap, we report results from 32 interviews with U.S.-based academic manufacturing and materials sciences researchers experienced with AI and machine learning (ML) techniques. Interviewees primarily used AI for modeling of materials and manufacturing processes, facilitating cheaper and more rapid search of design spaces for materials and manufacturing processes alike. They report benefits including cost, time, and computation savings in technology development. However, interviewees also report that AI/ML tools are unreliable outside design spaces for which dense data are already available; that they require skilled and judicious application in tandem with older research techniques; and that AI/ML tools may detrimentally circumvent opportunities for disruptive theoretical advancement. Based on these results, we suggest there is reason for optimism about acceleration in sustaining innovations through the use of to AI/ML; but that support for conventional empirical, computational, and theoretical research is required to maintain the likelihood of further major advances in manufacturing and materials science.
Authors: N Dinesh Reddy, Dylan Snyder, Lona Kiragu, Mirajul Mohin, Shahrear Bin Amin, Sudeep Pillai
Abstract: We introduce Orion, a visual agent that integrates vision-based reasoning with tool-augmented execution to achieve powerful, precise, multi-step visual intelligence across images, video, and documents. Unlike traditional vision-language models that generate descriptive outputs, Orion orchestrates a suite of specialized computer vision tools, including object detection, keypoint localization, panoptic segmentation, Optical Character Recognition (OCR), and geometric analysis, to execute complex multi-step visual workflows. The system achieves competitive performance across MMMU, MMBench, DocVQA, and MMLongBench while extending monolithic VLM capabilities to production-grade visual intelligence. Through its agentic, tool-augmented approach, Orion enables autonomous visual reasoning that bridges neural perception with symbolic execution, marking the transition from passive visual understanding to active, tool-driven visual intelligence. Try Orion for free at: https://chat.vlm.run Learn more at: https://www.vlm.run/orion
Authors: Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko, Denis Parkhomenko, Viacheslav Vasilev, Alexey Letunovskiy, Nikolai Vaulin, Maria Kovaleva, Ivan Kirillov, Lev Novitskiy, Denis Koposov, Nikita Kiselev, Alexander Varlamov, Dmitrii Mikhailov, Vladimir Polovnikov, Andrey Shutkin, Julia Agafonova, Ilya Vasiliev, Anastasiia Kargapoltseva, Anna Dmitrienko, Anastasia Maltseva, Anna Averchenkova, Olga Kim, Tatiana Nikulina, Denis Dimitrov
Abstract: This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis. The framework comprises three core line-up of models: Kandinsky 5.0 Image Lite - a line-up of 6B parameter image generation models, Kandinsky 5.0 Video Lite - a fast and lightweight 2B parameter text-to-video and image-to-video models, and Kandinsky 5.0 Video Pro - 19B parameter models that achieves superior video generation quality. We provide a comprehensive review of the data curation lifecycle - including collection, processing, filtering and clustering - for the multi-stage training pipeline that involves extensive pre-training and incorporates quality-enhancement techniques such as self-supervised fine-tuning (SFT) and reinforcement learning (RL)-based post-training. We also present novel architectural, training, and inference optimizations that enable Kandinsky 5.0 to achieve high generation speeds and state-of-the-art performance across various tasks, as demonstrated by human evaluation. As a large-scale, publicly available generative framework, Kandinsky 5.0 leverages the full potential of its pre-training and subsequent stages to be adapted for a wide range of generative applications. We hope that this report, together with the release of our open-source code and training checkpoints, will substantially advance the development and accessibility of high-quality generative models for the research community.
Authors: Nguyen-Khang Le, Hiep Nguyen, Ngoc-Minh Nguyen, Son T. Luu, Trung Vo, Quan Minh Bui, Shoshin Nomura, Le-Minh Nguyen
Abstract: Automated web application testing is a critical component of modern software development, with frameworks like Selenium widely adopted for validating functionality through browser automation. Among the essential aspects of such testing is the ability to interact with and validate web forms, a task that requires syntactically correct, executable scripts with high coverage of input fields. Despite its importance, this task remains underexplored in the context of large language models (LLMs), and no public benchmark or dataset exists to evaluate LLMs on form interaction generation systematically. This paper introduces a novel method for training LLMs to generate high-quality test cases in Selenium, specifically targeting form interaction testing. We curate both synthetic and human-annotated datasets for training and evaluation, covering diverse real-world forms and testing scenarios. We define clear metrics for syntax correctness, script executability, and input field coverage. Our empirical study demonstrates that our approach significantly outperforms strong baselines, including GPT-4o and other popular LLMs, across all evaluation metrics. Our work lays the groundwork for future research on LLM-based web testing and provides resources to support ongoing progress in this area.
Authors: Xinli Tao, Xin Dong, Xuezhong Zhou
Abstract: With the rapid expansion of unstructured clinical texts in electronic health records (EHRs), clinical named entity recognition (NER) has become a crucial technique for extracting medical information. However, traditional supervised models such as CRF and BioClinicalBERT suffer from high annotation costs. Although zero-shot NER based on large language models (LLMs) reduces the dependency on labeled data, challenges remain in aligning example selection with task granularity and effectively integrating prompt design with self-improvement frameworks. To address these limitations, we propose OEMA, a novel zero-shot clinical NER framework based on multi-agent collaboration. OEMA consists of three core components: (1) a self-annotator that autonomously generates candidate examples; (2) a discriminator that leverages SNOMED CT to filter token-level examples by clinical relevance; and (3) a predictor that incorporates entity-type descriptions to enhance inference accuracy. Experimental results on two benchmark datasets, MTSamples and VAERS, demonstrate that OEMA achieves state-of-the-art performance under exact-match evaluation. Moreover, under related-match criteria, OEMA performs comparably to the supervised BioClinicalBERT model while significantly outperforming the traditional CRF method. OEMA improves zero-shot clinical NER, achieving near-supervised performance under related-match criteria. Future work will focus on continual learning and open-domain adaptation to expand its applicability in clinical NLP.
Authors: Piercosma Bisconti, Matteo Prandi, Federico Pierucci, Francesco Giarrusso, Marcantonio Bracale, Marcello Galisai, Vincenzo Suriani, Olga Sorokoletova, Federico Sartore, Daniele Nardi
Abstract: We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weight models, curated poetic prompts yielded high attack-success rates (ASR), with some providers exceeding 90%. Mapping prompts to MLCommons and EU CoP risk taxonomies shows that poetic attacks transfer across CBRN, manipulation, cyber-offence, and loss-of-control domains. Converting 1,200 MLCommons harmful prompts into verse via a standardized meta-prompt produced ASRs up to 18 times higher than their prose baselines. Outputs are evaluated using an ensemble of 3 open-weight LLM judges, whose binary safety assessments were validated on a stratified human-labeled subset. Poetic framing achieved an average jailbreak success rate of 62% for hand-crafted poems and approximately 43% for meta-prompt conversions (compared to non-poetic baselines), substantially outperforming non-poetic baselines and revealing a systematic vulnerability across model families and safety training approaches. These findings demonstrate that stylistic variation alone can circumvent contemporary safety mechanisms, suggesting fundamental limitations in current alignment methods and evaluation protocols.
Authors: Artem Chervyakov, Ulyana Isaeva, Anton Emelyanov, Artem Safin, Maria Tikhonova, Alexander Kharitonov, Yulia Lyakh, Petr Surovtsev, Denis Shevelev, Vildan Saburov, Vasily Konovalov, Elisei Rykov, Ivan Sviridov, Amina Miftakhova, Ilseyar Alimova, Alexander Panchenko, Alexander Kapitanov, Alena Fenogenova
Abstract: Multimodal large language models (MLLMs) are currently at the center of research attention, showing rapid progress in scale and capabilities, yet their intelligence, limitations, and risks remain insufficiently understood. To address these issues, particularly in the context of the Russian language, where no multimodal benchmarks currently exist, we introduce Mera Multi, an open multimodal evaluation framework for Russian-spoken architectures. The benchmark is instruction-based and encompasses default text, image, audio, and video modalities, comprising 18 newly constructed evaluation tasks for both general-purpose models and modality-specific architectures (image-to-text, video-to-text, and audio-to-text). Our contributions include: (i) a universal taxonomy of multimodal abilities; (ii) 18 datasets created entirely from scratch with attention to Russian cultural and linguistic specificity, unified prompts, and metrics; (iii) baseline results for both closed-source and open-source models; (iv) a methodology for preventing benchmark leakage, including watermarking and licenses for private sets. While our current focus is on Russian, the proposed benchmark provides a replicable methodology for constructing multimodal benchmarks in typologically diverse languages, particularly within the Slavic language family.
Authors: Sifan Zhou, Yichao Cao, Jiahao Nie, Yuqian Fu, Ziyu Zhao, Xiaobo Lu, Shuo Wang
Abstract: 3D single object tracking (SOT) in LiDAR point clouds is a critical task in computer vision and autonomous driving. Despite great success having been achieved, the inherent sparsity of point clouds introduces a dual-redundancy challenge that limits existing trackers: (1) vast spatial redundancy from background noise impairs accuracy, and (2) informational redundancy within the foreground hinders efficiency. To tackle these issues, we propose CompTrack, a novel end-to-end framework that systematically eliminates both forms of redundancy in point clouds. First, CompTrack incorporates a Spatial Foreground Predictor (SFP) module to filter out irrelevant background noise based on information entropy, addressing spatial redundancy. Subsequently, its core is an Information Bottleneck-guided Dynamic Token Compression (IB-DTC) module that eliminates the informational redundancy within the foreground. Theoretically grounded in low-rank approximation, this module leverages an online SVD analysis to adaptively compress the redundant foreground into a compact and highly informative set of proxy tokens. Extensive experiments on KITTI, nuScenes and Waymo datasets demonstrate that CompTrack achieves top-performing tracking performance with superior efficiency, running at a real-time 90 FPS on a single RTX 3090 GPU.
Authors: Yicheng He, Chengsong Huang, Zongxia Li, Jiaxin Huang, Yonghui Yang
Abstract: Reinforcement learning (RL) provides a principled framework for improving Vision-Language Models (VLMs) on complex reasoning tasks. However, existing RL approaches often rely on human-annotated labels or task-specific heuristics to define verifiable rewards, both of which are costly and difficult to scale. We introduce VisPlay, a self-evolving RL framework that enables VLMs to autonomously improve their reasoning abilities using large amounts of unlabeled image data. Starting from a single base VLM, VisPlay assigns the model into two interacting roles: an Image-Conditioned Questioner that formulates challenging yet answerable visual questions, and a Multimodal Reasoner that generates silver responses. These roles are jointly trained with Group Relative Policy Optimization (GRPO), which incorporates diversity and difficulty rewards to balance the complexity of generated questions with the quality of the silver answers. VisPlay scales efficiently across two model families. When trained on Qwen2.5-VL and MiMo-VL, VisPlay achieves consistent improvements in visual reasoning, compositional generalization, and hallucination reduction across eight benchmarks, including MM-Vet and MMMU, demonstrating a scalable path toward self-evolving multimodal intelligence. The project page is available at https://bruno686.github.io/VisPlay/