Authors: Sahil Rajesh Dhayalkar
Abstract: Transformer-based language models display impressive reasoning-like behavior, yet remain brittle on tasks that require stable symbolic manipulation. This paper develops a unified perspective on these phenomena by interpreting self-attention and residual streams as implementing an approximate Vector Symbolic Architecture (VSA). In this view, queries and keys define role spaces, values encode fillers, attention weights perform soft unbinding, and residual connections realize superposition of many bound structures. We use this algebraic lens to relate transformer internals to chain-of-thought traces, program-based reasoning, and memory-augmented tool use, and to explain characteristic failure modes such as variable confusion and inconsistency across logically related prompts. Building on this perspective, we propose VSA-inspired architectural biases, including explicit binding/unbinding heads and hyperdimensional memory layers, and training objectives that promote role-filler separation and robust superposition. Finally, we outline metrics for measuring "VSA-likeness" and logical compositionality, and pose theoretical and architectural open problems. Overall, the paper argues that viewing attention as soft vector-symbolic computation offers a principled route toward more interpretable and logically reliable reasoning systems.
Authors: Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Jiaoyan Chen, Steffen Staab, Yuan He, Evgeny Kharlamov
Abstract: Large language models (LLMs) achieve strong results on knowledge graph question answering (KGQA), but most benchmarks assume complete knowledge graphs (KGs) where direct supporting triples exist. This reduces evaluation to shallow retrieval and overlooks the reality of incomplete KGs, where many facts are missing and answers must be inferred from existing facts. We bridge this gap by proposing a methodology for constructing benchmarks under KG incompleteness, which removes direct supporting triples while ensuring that alternative reasoning paths required to infer the answer remain. Experiments on benchmarks constructed using our methodology show that existing methods suffer consistent performance degradation under incompleteness, highlighting their limited reasoning ability. To overcome this limitation, we present the Adaptive Graph Reasoning Agent (GR-Agent). It first constructs an interactive environment from the KG, and then formalizes KGQA as agent environment interaction within this environment. GR-Agent operates over an action space comprising graph reasoning tools and maintains a memory of potential supporting reasoning evidence, including relevant relations and reasoning paths. Extensive experiments demonstrate that GR-Agent outperforms non-training baselines and performs comparably to training-based methods under both complete and incomplete settings.
Authors: Roman Nekrasov, Stefano Fossati, Indika Kumara, Damian Andrew Tamburri, Willem-Jan van den Heuvel
Abstract: Large Language Models (LLMs) currently exhibit low success rates in generating correct and intent-aligned Infrastructure as Code (IaC). This research investigated methods to improve LLM-based IaC generation, specifically for Terraform, by systematically injecting structured configuration knowledge. To facilitate this, an existing IaC-Eval benchmark was significantly enhanced with cloud emulation and automated error analysis. Additionally, a novel error taxonomy for LLM-assisted IaC code generation was developed. A series of knowledge injection techniques was implemented and evaluated, progressing from Naive Retrieval-Augmented Generation (RAG) to more sophisticated Graph RAG approaches. These included semantic enrichment of graph components and modeling inter-resource dependencies. Experimental results demonstrated that while baseline LLM performance was poor (27.1% overall success), injecting structured configuration knowledge increased technical validation success to 75.3% and overall success to 62.6%. Despite these gains in technical correctness, intent alignment plateaued, revealing a "Correctness-Congruence Gap" where LLMs can become proficient "coders" but remain limited "architects" in fulfilling nuanced user intent.
Authors: Nadine Angela Cantonjos, Arpita Biswas
Abstract: Agricultural regions in rural areas face damage from climate-related risks, including droughts, heavy rainfall, and shifting weather patterns. Prior research calls for adaptive risk-management solutions and decision-making strategies. To this end, artificial intelligence (AI), particularly agentic AI, offers a promising path forward. Agentic AI systems consist of autonomous, specialized agents capable of solving complex, dynamic tasks. While past systems have relied on single-agent models or have used multi-agent frameworks only for static functions, there is a growing need for architectures that support dynamic collaborative reasoning and context-aware outputs. To bridge this gap, we present AgroAskAI, a multi-agent reasoning system for climate adaptation decision support in agriculture, with a focus on vulnerable rural communities. AgroAskAI features a modular, role-specialized architecture that uses a chain-of-responsibility approach to coordinate autonomous agents, integrating real-time tools and datasets. The system has built-in governance mechanisms that mitigate hallucination and enable internal feedback for coherent, locally relevant strategies. The system also supports multilingual interactions, making it accessible to non-English-speaking farmers. Experiments on common agricultural queries related to climate adaptation show that, with additional tools and prompt refinement, AgroAskAI delivers more actionable, grounded, and inclusive outputs. Our experimental results highlight the potential of agentic AI for sustainable and accountable decision support in climate adaptation for agriculture.
Authors: Xidan Song, Weiqi Wang, Ruifeng Cao, Qingya Hu
Abstract: The evaluation of Large Language Models (LLMs) in complex reasoning domains typically relies on performance alignment with ground-truth oracles. In the domain of chess, this standard manifests as accuracy benchmarks against strong engines like Stockfish. However, high scalar accuracy does not necessarily imply robust conceptual understanding. This paper argues that standard accuracy metrics fail to distinguish between genuine geometric reasoning and the superficial memorization of canonical board states. To address this gap, we propose a Geometric Stability Framework, a novel evaluation methodology that rigorously tests model consistency under invariant transformations-including board rotation, mirror symmetry, color inversion, and format conversion. We applied this framework to a comparative analysis of six state-of-the-art LLMs including GPT-5.1, Claude Sonnet 4.5, and Kimi K2 Turbo, utilizing a dataset of approximately 3,000 positions. Our results reveal a significant Accuracy-Stability Paradox. While models such as GPT-5.1 achieve near-optimal accuracy on standard positions, they exhibit catastrophic degradation under geometric perturbation, specifically in rotation tasks where error rates surge by over 600%. This disparity suggests a reliance on pattern matching over abstract spatial logic. Conversely, Claude Sonnet 4.5 and Kimi K2 Turbo demonstrate superior dual robustness, maintaining high consistency across all transformation axes. Furthermore, we analyze the trade-off between helpfulness and safety, identifying Gemini 2.5 Flash as the leader in illegal state rejection (96.0%). We conclude that geometric stability provides an orthogonal and essential metric for AI evaluation, offering a necessary proxy for disentangling reasoning capabilities from data contamination and overfitting in large-scale models.
Authors: Jihao Huang, Xi Xia, Zhiyuan Li, Tianle Liu, Jingke Wang, Junbo Chen, Tengju Ye
Abstract: End-to-end paradigms have demonstrated great potential for autonomous driving. Additionally, most existing methods are built upon Transformer architectures. However, transformers incur a quadratic attention cost, limiting their ability to model long spatial and temporal sequences-particularly on resource-constrained edge platforms. As autonomous driving inherently demands efficient temporal modeling, this challenge severely limits their deployment and real-time performance. Recently, linear attention mechanisms have gained increasing attention due to their superior spatiotemporal complexity. However, existing linear attention architectures are limited to self-attention, lacking support for cross-modal and cross-temporal interactions-both crucial for autonomous driving. In this work, we propose LADY, the first fully linear attention-based generative model for end-to-end autonomous driving. LADY enables fusion of long-range temporal context at inference with constant computational and memory costs, regardless of the history length of camera and LiDAR features. Additionally, we introduce a lightweight linear cross-attention mechanism that enables effective cross-modal information exchange. Experiments on the NAVSIM and Bench2Drive benchmarks demonstrate that LADY achieves state-of-the-art performance with constant-time and memory complexity, offering improved planning performance and significantly reduced computational cost. Additionally, the model has been deployed and validated on edge devices, demonstrating its practicality in resource-limited scenarios.
Authors: Wenwen Xie, Geng Sun, Ruichen Zhang, Xuejie Liu, Yinqiu Liu, Jiacheng Wang, Dusit Niyato, Ping Zhang
Abstract: Integrated sensing and communication (ISAC) has emerged as a key development direction in the sixth-generation (6G) era, which provides essential support for the collaborative sensing and communication of future intelligent networks. However, as wireless environments become increasingly dynamic and complex, ISAC systems require more intelligent processing and more autonomous operation to maintain efficiency and adaptability. Meanwhile, agentic artificial intelligence (AI) offers a feasible solution to address these challenges by enabling continuous perception-reasoning-action loops in dynamic environments to support intelligent, autonomous, and efficient operation for ISAC systems. As such, we delve into the application value and prospects of agentic AI in ISAC systems in this work. Firstly, we provide a comprehensive review of agentic AI and ISAC systems to demonstrate their key characteristics. Secondly, we show several common optimization approaches for ISAC systems and highlight the significant advantages of generative artificial intelligence (GenAI)-based agentic AI. Thirdly, we propose a novel agentic ISAC framework and prensent a case study to verify its superiority in optimizing ISAC performance. Finally, we clarify future research directions for agentic AI-based ISAC systems.
Authors: Jinwu Hu, Dongjin Yang, Langyu Bian, Zhiquan Wen, Yufeng Wang, Yaofo Chen, Bin Xiao, Yuanqing Li, Mingkui Tan
Abstract: Large language models (LLMs) have demonstrated impressive performance across various language tasks. However, existing LLM reasoning strategies mainly rely on the LLM itself with fast or slow mode (like o1 thinking) and thus struggle to balance reasoning efficiency and accuracy across queries of varying difficulties. In this paper, we propose Cognitive-Inspired Elastic Reasoning (CogER), a framework inspired by human hierarchical reasoning that dynamically selects the most suitable reasoning strategy for each query. Specifically, CogER first assesses the complexity of incoming queries and assigns them to one of several predefined levels, each corresponding to a tailored processing strategy, thereby addressing the challenge of unobservable query difficulty. To achieve automatic strategy selection, we model the process as a Markov Decision Process and train a CogER-Agent using reinforcement learning. The agent is guided by a reward function that balances solution quality and computational cost, ensuring resource-efficient reasoning. Moreover, for queries requiring external tools, we introduce Cognitive Tool-Assisted Reasoning, which enables the LLM to autonomously invoke external tools within its chain-of-thought. Extensive experiments demonstrate that CogER outperforms state-of-the-art Test-Time scaling methods, achieving at least a 13% relative improvement in average exact match on In-Domain tasks and an 8% relative gain on Out-of-Domain tasks.
Authors: Mohsen Nafar, Michael R\"omer, Lin Xie
Abstract: Efficient exact algorithms for Discrete Optimization (DO) rely heavily on strong primal and dual bounds. Relaxed Decision Diagrams (DDs) provide a versatile mechanism for deriving such dual bounds by compactly over-approximating the solution space through node merging. However, the quality of these relaxed diagrams, i.e. the tightness of the resulting dual bounds, depends critically on the variable ordering and the merging decisions executed during compilation. While dynamic variable ordering heuristics effectively tighten bounds, they often incur computational overhead when evaluated globally across the entire variable set. To mitigate this trade-off, this work introduces a novel clustering-based framework for variable ordering. Instead of applying dynamic ordering heuristics to the full set of unfixed variables, we first partition variables into clusters. We then leverage this structural decomposition to guide the ordering process, significantly reducing the heuristic's search space. Within this framework, we investigate two distinct strategies: Cluster-to-Cluster, which processes clusters sequentially using problem-specific aggregate criteria (such as cumulative vertex weights in the Maximum Weighted Independent Set Problem (MWISP)), and Pick-and-Sort, which iteratively selects and sorts representative variables from each cluster to balance local diversity with heuristic guidance. Later on, developing some theoretical results on the growth of the size of DDs for MWISP we propose two different policies for setting the number of clusters within the proposed framework. We embed these strategies into a DD-based branch-and-bound algorithm and evaluate them on the MWISP. Across benchmark instances, the proposed methodology consistently reduces computational costs compared to standard dynamic variable ordering baseline.
Authors: Zhengchao Chen, Haoran Wang, Jing Yao, Pedram Ghamisi, Jun Zhou, Peter M. Atkinson, Bing Zhang
Abstract: The automated and intelligent processing of massive remote sensing (RS) datasets is critical in Earth observation (EO). Existing automated systems are normally task-specific, lacking a unified framework to manage diverse, end-to-end workflows--from data preprocessing to advanced interpretation--across diverse RS applications. To address this gap, this paper introduces CangLing-KnowFlow, a unified intelligent agent framework that integrates a Procedural Knowledge Base (PKB), Dynamic Workflow Adjustment, and an Evolutionary Memory Module. The PKB, comprising 1,008 expert-validated workflow cases across 162 practical RS tasks, guides planning and substantially reduces hallucinations common in general-purpose agents. During runtime failures, the Dynamic Workflow Adjustment autonomously diagnoses and replans recovery strategies, while the Evolutionary Memory Module continuously learns from these events, iteratively enhancing the agent's knowledge and performance. This synergy enables CangLing-KnowFlow to adapt, learn, and operate reliably across diverse, complex tasks. We evaluated CangLing-KnowFlow on the KnowFlow-Bench, a novel benchmark of 324 workflows inspired by real-world applications, testing its performance across 13 top Large Language Model (LLM) backbones, from open-source to commercial. Across all complex tasks, CangLing-KnowFlow surpassed the Reflexion baseline by at least 4% in Task Success Rate. As the first most comprehensive validation along this emerging field, this research demonstrates the great potential of CangLing-KnowFlow as a robust, efficient, and scalable automated solution for complex EO challenges by leveraging expert knowledge (Knowledge) into adaptive and verifiable procedures (Flow).
Authors: Toshihide Ubukata, Enhong Mu, Takuto Yamauchi, Mingyue Zhang, Jialong Li, Kenji Tei
Abstract: Controller synthesis is a formal method approach for automatically generating Labeled Transition System (LTS) controllers that satisfy specified properties. The efficiency of the synthesis process, however, is critically dependent on exploration policies. These policies often rely on fixed rules or strategies learned through reinforcement learning (RL) that consider only a limited set of current features. To address this limitation, this paper introduces GCRL, an approach that enhances RL-based methods by integrating Graph Neural Networks (GNNs). GCRL encodes the history of LTS exploration into a graph structure, allowing it to capture a broader, non-current-based context. In a comparative experiment against state-of-the-art methods, GCRL exhibited superior learning efficiency and generalization across four out of five benchmark domains, except one particular domain characterized by high symmetry and strictly local interactions.
Authors: Seok-Hyun Ga, Chun-Yen Chang
Abstract: The rapid development of Generative AI is bringing innovative changes to education and assessment. As the prevalence of students utilizing AI for assignments increases, concerns regarding academic integrity and the validity of assessments are growing. This study utilizes the Earth Science I section of the 2025 Korean College Scholastic Ability Test (CSAT) to deeply analyze the multimodal scientific reasoning capabilities and cognitive limitations of state-of-the-art Large Language Models (LLMs), including GPT-4o, Gemini 2.5 Flash, and Gemini 2.5 Pro. Three experimental conditions (full-page input, individual item input, and optimized multimodal input) were designed to evaluate model performance across different data structures. Quantitative results indicated that unstructured inputs led to significant performance degradation due to segmentation and Optical Character Recognition (OCR) failures. Even under optimized conditions, models exhibited fundamental reasoning flaws. Qualitative analysis revealed that "Perception Errors" were dominant, highlighting a "Perception-Cognition Gap" where models failed to interpret symbolic meanings in schematic diagrams despite recognizing visual data. Furthermore, models demonstrated a "Calculation-Conceptualization Discrepancy," successfully performing calculations while failing to apply the underlying scientific concepts, and "Process Hallucination," where models skipped visual verification in favor of plausible but unfounded background knowledge. Addressing the challenge of unauthorized AI use in coursework, this study provides actionable cues for designing "AI-resistant questions" that target these specific cognitive vulnerabilities. By exploiting AI's weaknesses, such as the gap between perception and cognition, educators can distinguish genuine student competency from AI-generated responses, thereby ensuring assessment fairness.
Authors: Zehua Pei, Hui-Ling Zhen, Shixiong Kai, Sinno Jialin Pan, Yunhe Wang, Mingxuan Yuan, Bei Yu
Abstract: Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts. However, a critical bottleneck remains: while agents have access to this context, their static prompts lack the mechanisms to manage it effectively, leading to recurring Corrective and Enhancement failures. To address this capability gap, we introduce \textbf{SCOPE} (Self-evolving Context Optimization via Prompt Evolution). SCOPE frames context management as an \textit{online optimization} problem, synthesizing guidelines from execution traces to automatically evolve the agent's prompt. We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles). Furthermore, we introduce Perspective-Driven Exploration to maximize strategy coverage, increasing the likelihood that the agent has the correct strategy for any given task. Experiments on the HLE benchmark show that SCOPE improves task success rates from 14.23\% to 38.64\% without human intervention. We make our code publicly available at https://github.com/JarvisPei/SCOPE.
Authors: Reinhard Moratz, Niklas Daute, James Ondieki, Markus Kattenbeck, Mario Krajina, Ioannis Giannopoulos
Abstract: This paper deals with improving the capabilities of Large Language Models (LLM) to provide route instructions for pedestrian wayfinders by means of qualitative spatial relations.
Authors: Stefan Edelkamp
Abstract: In multi-player card games such as Skat or Bridge, the early stages of the game, such as bidding, game selection, and initial card selection, are often more critical to the success of the play than refined middle- and end-game play. At the current limits of computation, such early decision-making resorts to using statistical information derived from a large corpus of human expert games. In this paper, we derive and evaluate a general bootstrapping outer-learning framework that improves prediction accuracy by expanding the database of human games with millions of self-playing AI games to generate and merge statistics. We implement perfect feature hash functions to address compacted tables, producing a self-improving card game engine, where newly inferred knowledge is continuously improved during self-learning. The case study in Skat shows that the automated approach can be used to support various decisions in the game.
Authors: Jeongseok Kim, Kangjin Kim
Abstract: Due to the restricted resources, efficient scheduling in vertiports has received much more attention in the field of Urban Air Mobility (UAM). For the scheduling problem, we utilize a Mixed Integer Linear Programming (MILP), which is often formulated in a resource-restricted project scheduling problem (RCPSP). In this paper, we show our approach to handle both dynamic operation requirements and vague rescheduling requests from humans. Particularly, we utilize a three-valued logic for interpreting ambiguous user intents and a decision tree, proposing a newly integrated system that combines Answer Set Programming (ASP) and MILP. This integrated framework optimizes schedules and supports human inputs transparently. With this system, we provide a robust structure for explainable, adaptive UAM scheduling.
Authors: Wei Du, Shubham Toshniwal, Branislav Kisacanin, Sadegh Mahdavi, Ivan Moshkov, George Armstrong, Stephen Ge, Edgar Minasyan, Feng Chen, Igor Gitman
Abstract: High-quality mathematical reasoning supervision requires diverse reasoning styles, long-form traces, and effective tool integration, capabilities that existing datasets provide only in limited form. Leveraging the multi-mode generation ability of gpt-oss-120b, we introduce Nemotron-Math, a large-scale mathematical reasoning dataset containing 7.5M solution traces across high, medium, and low reasoning modes, each available both with and without Python tool-integrated reasoning (TIR). The dataset integrates 85K curated AoPS problems with 262K community-sourced StackExchange-Math problems, combining structured competition tasks with diverse real-world mathematical queries. We conduct controlled evaluations to assess the dataset quality. Nemotron-Math consistently outperforms the original OpenMathReasoning on matched AoPS problems. Incorporating StackExchange-Math substantially improves robustness and generalization, especially on HLE-Math, while preserving accuracy on math competition benchmarks. To support efficient long-context training, we develop a sequential bucketed strategy that accelerates 128K context-length fine-tuning by 2--3$\times$ without significant accuracy loss. Overall, Nemotron-Math enables state-of-the-art performance, including 100\% maj@16 accuracy on AIME 2024 and 2025 with Python TIR.
Authors: Zhangde Song, Jieyu Lu, Yuanqi Du, Botao Yu, Thomas M. Pruyn, Yue Huang, Kehan Guo, Xiuzhe Luo, Yuanhao Qu, Yi Qu, Yinkai Wang, Haorui Wang, Jeff Guo, Jingru Gan, Parshin Shojaee, Di Luo, Andres M Bran, Gen Li, Qiyuan Zhao, Shao-Xiong Lennon Luo, Yuxuan Zhang, Xiang Zou, Wanru Zhao, Yifan F. Zhang, Wucheng Zhang, Shunan Zheng, Saiyang Zhang, Sartaaj Takrim Khan, Mahyar Rajabi-Kochi, Samantha Paradi-Maropakis, Tony Baltoiu, Fengyu Xie, Tianyang Chen, Kexin Huang, Weiliang Luo, Meijing Fang, Xin Yang, Lixue Cheng, Jiajun He, Soha Hassoun, Xiangliang Zhang, Wei Wang, Chandan K. Reddy, Chao Zhang, Zhiling Zheng, Mengdi Wang, Le Cong, Carla P. Gomes, Chang-Yu Hsieh, Aditya Nandy, Philippe Schwaller, Heather J. Kulik, Haojun Jia, Huan Sun, Seyed Mohamad Moosavi, Chenru Duan
Abstract: Large language models (LLMs) are increasingly applied to scientific research, yet prevailing science benchmarks probe decontextualized knowledge and overlook the iterative reasoning, hypothesis generation, and observation interpretation that drive scientific discovery. We introduce a scenario-grounded benchmark that evaluates LLMs across biology, chemistry, materials, and physics, where domain experts define research projects of genuine interest and decompose them into modular research scenarios from which vetted questions are sampled. The framework assesses models at two levels: (i) question-level accuracy on scenario-tied items and (ii) project-level performance, where models must propose testable hypotheses, design simulations or experiments, and interpret results. Applying this two-phase scientific discovery evaluation (SDE) framework to state-of-the-art LLMs reveals a consistent performance gap relative to general science benchmarks, diminishing return of scaling up model sizes and reasoning, and systematic weaknesses shared across top-tier models from different providers. Large performance variation in research scenarios leads to changing choices of the best performing model on scientific discovery projects evaluated, suggesting all current LLMs are distant to general scientific "superintelligence". Nevertheless, LLMs already demonstrate promise in a great variety of scientific discovery projects, including cases where constituent scenario scores are low, highlighting the role of guided exploration and serendipity in discovery. This SDE framework offers a reproducible benchmark for discovery-relevant evaluation of LLMs and charts practical paths to advance their development toward scientific discovery.
Authors: Daniel A. Herrmann, Abinav Chari, Isabelle Qian, Sree Sharvesh, B. A. Levinstein
Abstract: When should we delegate decisions to AI systems? While the value alignment literature has developed techniques for shaping AI values, less attention has been paid to how to determine, under uncertainty, when imperfect alignment is good enough to justify delegation. We argue that rational delegation requires balancing an agent's value (mis)alignment with its epistemic accuracy and its reach (the acts it has available). This paper introduces a formal, decision-theoretic framework to analyze this tradeoff precisely accounting for a principal's uncertainty about these factors. Our analysis reveals a sharp distinction between two delegation scenarios. First, universal delegation (trusting an agent with any problem) demands near-perfect value alignment and total epistemic trust, conditions rarely met in practice. Second, we show that context-specific delegation can be optimal even with significant misalignment. An agent's superior accuracy or expanded reach may grant access to better overall decision problems, making delegation rational in expectation. We develop a novel scoring framework to quantify this ex ante decision. Ultimately, our work provides a principled method for determining when an AI is aligned enough for a given context, shifting the focus from achieving perfect alignment to managing the risks and rewards of delegation under uncertainty.
Authors: Jiaqi Xu, Cuiling Lan, Xuejin Chen, Yan LU
Abstract: Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, most existing large language models (LLMs) decouple reasoning from verification: they either generate reasoning without explicit self-checking or rely on external verifiers to detect errors post hoc. The former lacks immediate feedback, while the latter increases system complexity and hinders synchronized learning. Motivated by human critical thinking, we propose Stepwise Think-Critique (STC), a unified framework that interleaves reasoning and self-critique at each step within a single model. STC is trained with a hybrid reinforcement learning objective combining reasoning rewards and critique-consistency rewards to jointly optimize reasoning quality and self-evaluation. Experiments on mathematical reasoning benchmarks show that STC demonstrates strong critic-thinking capabilities and produces more interpretable reasoning traces, representing a step toward LLMs with built-in critical thinking.
Authors: Chase Walker, Rickard Ewetz
Abstract: Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which assign credit to input features, have proven effective for explaining the decision making of computer vision models. From these, context attributions have emerged as a promising approach for explaining the behavior of autoregressive LLMs. However, current context attributions produce incomplete explanations by directly relating generated tokens to the prompt, discarding inter-generational influence in the process. To overcome these shortcomings, we introduce the Context Attribution via Graph Explanations (CAGE) framework. CAGE introduces an attribution graph: a directed graph that quantifies how each generation is influenced by both the prompt and all prior generations. The graph is constructed to preserve two properties-causality and row stochasticity. The attribution graph allows context attributions to be computed by marginalizing intermediate contributions along paths in the graph. Across multiple models, datasets, metrics, and methods, CAGE improves context attribution faithfulness, achieving average gains of up to 40%.
Authors: Shuai Liu, Yiqing Tian, Yang Chen, Mar Canet Sola
Abstract: This paper proposes a dual-engine AI architectural method designed to address the complex problem of exploring potential trajectories in the evolution of art. We present two interconnected components: AIDA (an artificial artist social network) and the Ismism Machine, a system for critical analysis. The core innovation lies in leveraging deep learning and multi-agent collaboration to enable multidimensional simulations of art historical developments and conceptual innovation patterns. The framework explores a shift from traditional unidirectional critique toward an intelligent, interactive mode of reflexive practice. We are currently applying this method in experimental studies on contemporary art concepts. This study introduces a general methodology based on AI-driven critical loops, offering new possibilities for computational analysis of art.
Authors: Vincent Huang, Dami Choi, Daniel D. Johnson, Sarah Schwettmann, Jacob Steinhardt
Abstract: Interpreting the internal activations of neural networks can produce more faithful explanations of their behavior, but is difficult due to the complex structure of activation space. Existing approaches to scalable interpretability use hand-designed agents that make and test hypotheses about how internal activations relate to external behavior. We propose to instead turn this task into an end-to-end training objective, by training interpretability assistants to accurately predict model behavior from activations through a communication bottleneck. Specifically, an encoder compresses activations to a sparse list of concepts, and a decoder reads this list and answers a natural language question about the model. We show how to pretrain this assistant on large unstructured data, then finetune it to answer questions. The resulting architecture, which we call a Predictive Concept Decoder, enjoys favorable scaling properties: the auto-interp score of the bottleneck concepts improves with data, as does the performance on downstream applications. Specifically, PCDs can detect jailbreaks, secret hints, and implanted latent concepts, and are able to accurately surface latent user attributes.
Authors: Sahibpreet Singh, Manjit Singh
Abstract: AI-powered greenwashing has emerged as an insidious challenge within corporate sustainability governance, exacerbating the opacity of environmental disclosures and subverting regulatory oversight. This study conducts a comparative legal analysis of criminal liability for AI-mediated greenwashing across India, the US, and the EU, exposing doctrinal lacunae in attributing culpability when deceptive claims originate from algorithmic systems. Existing statutes exhibit anthropocentric biases by predicating liability on demonstrable human intent, rendering them ill-equipped to address algorithmic deception. The research identifies a critical gap in jurisprudential adaptation, as prevailing fraud statutes remain antiquated vis-\`a-vis AI-generated misrepresentation. Utilising a doctrinal legal methodology, this study systematically dissects judicial precedents and statutory instruments, yielding results regarding the potential expansion of corporate criminal liability. Findings underscore the viability of strict liability models, recalibrated governance frameworks for AI accountability, and algorithmic due diligence mandates under ESG regimes. Comparative insights reveal jurisdictional disparities, with the EU Corporate Sustainability Due Diligence Directive (CSDDD) offering a potential transnational model. This study contributes to AI ethics and environmental jurisprudence by advocating for a hybrid liability framework integrating algorithmic risk assessment with legal personhood constructs, ensuring algorithmic opacity does not preclude liability enforcement.
Authors: Sonia Djebali, Quentin Gabot, Guillaume Guerard
Abstract: With the recent digital revolution, analyzing of tourists' behaviors and research fields associated with it have changed profoundly. It is now easier to examine behaviors of tourists using digital traces they leave during their travels. The studies conducted on diverse aspects of tourism focus on quantitative aspects of digital traces to reach its conclusions. In this paper, we suggest a study focused on both qualitative and quantitative aspect of digital traces to understand the dynamics governing tourist behavior, especially those concerning attractions networks.
Authors: Krunal Jesani, Dmitry Ignatov, Radu Timofte
Abstract: Neural architecture search (NAS) traditionally requires significant human expertise or automated trial-and-error to design deep learning models. We present NN-Caption, an LLM-guided neural architecture search pipeline that generates runnable image-captioning models by composing CNN encoders from LEMUR's classification backbones with sequence decoders (LSTM/GRU/Transformer) under a strict Net API. Using DeepSeek-R1-0528-Qwen3-8B as the primary generator, we present the prompt template and examples of generated architectures. We evaluate on MS COCO with BLEU-4. The LLM generated dozens of captioning models, with over half successfully trained and producing meaningful captions. We analyse the outcomes of using different numbers of input model snippets (5 vs. 10) in the prompt, finding a slight drop in success rate when providing more candidate components. We also report training dynamics (caption accuracy vs. epochs) and the highest BLEU-4 attained. Our results highlight the promise of LLM-guided NAS: the LLM not only proposes architectures but also suggests hyperparameters and training practices. We identify the challenges encountered (e.g., code hallucinations or API compliance issues) and detail how prompt rules and iterative code fixes addressed them. This work presents a pipeline that integrates prompt-based code generation with automatic evaluation, and adds dozens of novel captioning models to the open LEMUR dataset to facilitate reproducible benchmarking and downstream AutoML research.
Authors: Keqiuyin Li, Jie Lu, Hua Zuo, Guangquan Zhang
Abstract: Unsupervised multi-domain adaptation plays a key role in transfer learning by leveraging acquired rich source information from multiple source domains to solve target task from an unlabeled target domain. However, multiple source domains often contain much redundant or unrelated information which can harm transfer performance, especially when in massive-source domain settings. It is urgent to develop effective strategies for identifying and selecting the most transferable knowledge from massive source domains to address the target task. In this paper, we propose a multi-domain adaptation method named \underline{\textit{Auto}}nomous Source Knowledge \underline{\textit{S}}election (AutoS) to autonomosly select source training samples and models, enabling the prediction of target task using more relevant and transferable source information. The proposed method employs a density-driven selection strategy to choose source samples during training and to determine which source models should contribute to target prediction. Simulteneously, a pseudo-label enhancement module built on a pre-trained multimodal modal is employed to mitigate target label noise and improve self-supervision. Experiments on real-world datasets indicate the superiority of the proposed method.
Authors: Changan Liu, Xiaotian Zhou, Ahad N. Zehmakan, Zhongzhi Zhang
Abstract: The advent of online social networks has facilitated fast and wide spread of information. However, some users, especially members of minority groups, may be less likely to receive information spreading on the network, due to their disadvantaged network position. We study the optimization problem of adding new connections to a network to enhance fairness in information access among different demographic groups. We provide a concrete formulation of this problem where information access is measured in terms of resistance distance, {offering a new perspective that emphasizes global network structure and multi-path connectivity.} The problem is shown to be NP-hard. We propose a simple greedy algorithm which turns out to output accurate solutions, but its run time is cubic, which makes it undesirable for large networks. As our main technical contribution, we reduce its time complexity to linear, leveraging several novel approximation techniques. In addition to our theoretical findings, we also conduct an extensive set of experiments using both real-world and synthetic datasets. We demonstrate that our linear-time algorithm can produce accurate solutions for networks with millions of nodes.
Authors: Ryan Cartularo
Abstract: Sepsis accounts for nearly 20% of global ICU admissions, yet conventional prediction models often fail to effectively integrate heterogeneous data streams, remaining either siloed by modality or reliant on brittle early fusion. In this work, we present a rigorous architectural comparison between End-to-End Deep Fusion and Context-Aware Stacking for sepsis tasks. We initially hypothesized that a novel Quad-Modal Hierarchical Gated Attention Network -- termed SepsisFusionFormer -- would resolve complex cross-modal interactions between vitals, text, and imaging. However, experiments on MIMIC-IV revealed that SepsisFusionFormer suffered from "attention starvation" in the small antibiotic cohort ($N \approx 2,100$), resulting in overfitting (AUC 0.66). This counterintuitive result informed the design of SepsisLateFusion, a "leaner" Context-Aware Mixture-of-Experts (MoE) architecture. By treating modalities as orthogonal experts -- the "Historian" (Static), the "Monitor" (Temporal), and the "Reader" (NLP) -- and dynamically gating them via a CatBoost meta-learner, we achieved State-of-the-Art (SOTA) performance: 0.915 AUC for prediction 4 hours prior to clinical onset. By calibrating the decision threshold for clinical safety, we reduced missed cases by 48% relative to the default operating point, thus opening a true preventative window for timely intervention over reactive alerts. Furthermore, for the novel prescriptive task of multi-class antibiotic selection, we demonstrate that a Quad-Modal Ensemble achieved the highest performance (0.72 AUC). These models are integrated into SepsisSuite, a deployment-ready Python framework for clinical decision support. SepsisSuite is available for free at: https://github.com/RyanCartularo/SepsisSuite-Info
Authors: Lucas Cesar Ferreira Domingos, Russell Brinkworth, Paulo Eduardo Santos, Karl Sammut
Abstract: Remotely detecting and classifying underwater acoustic targets is critical for environmental monitoring and defence. However, the complex nature of ship-radiated and environmental underwater noise poses significant challenges to accurate signal processing. While recent advancements in machine learning have improved classification accuracy, issues such as limited dataset availability and a lack of standardised experimentation hinder generalisation and robustness. This paper introduces GSE ResNeXt, a deep learning architecture integrating learnable Gabor convolutional layers with a ResNeXt backbone enhanced by squeeze-and-excitation attention mechanisms. The Gabor filters serve as two-dimensional adaptive band-pass filters, extending the feature channel representation. Its combination with channel attention improves training stability and convergence while enhancing the model's ability to extract discriminative features. The model is evaluated on three classification tasks of increasing complexity. In particular, the impact of temporal differences between the training and testing data is explored, revealing that the distance between the vessel and sensor significantly affects performance. Results show that, GSE ResNeXt consistently outperforms baseline models like Xception, ResNet, and MobileNetV2, in terms of classification performance. Regarding stability and convergence, the addition of Gabor convolutions in the initial layers of the model represents a 28% reduction in training time. These results emphasise the importance of signal processing strategies in improving the reliability and generalisation of models under different environmental conditions, especially in data-limited underwater acoustic classification scenarios. Future developments should focus on mitigating the impact of environmental factors on input signals.
Authors: Zafaryab Haider, Md Hafizur Rahman, Shane Moeykens, Vijay Devabhaktuni, Prabuddha Chakraborty
Abstract: Hard-to-detect hardware bit flips, from either malicious circuitry or bugs, have already been shown to make transformers vulnerable in non-generative tasks. This work, for the first time, investigates how low-level, bitwise perturbations (fault injection) to the weights of a large language model (LLM) used for image captioning can influence the semantic meaning of its generated descriptions while preserving grammatical structure. While prior fault analysis methods have shown that flipping a few bits can crash classifiers or degrade accuracy, these approaches overlook the semantic and linguistic dimensions of generative systems. In image captioning models, a single flipped bit might subtly alter how visual features map to words, shifting the entire narrative an AI tells about the world. We hypothesize that such semantic drifts are not random but differentiably estimable. That is, the model's own gradients can predict which bits, if perturbed, will most strongly influence meaning while leaving syntax and fluency intact. We design a differentiable fault analysis framework, BLADE (Bit-level Fault Analysis via Differentiable Estimation), that uses gradient-based sensitivity estimation to locate semantically critical bits and then refines their selection through a caption-level semantic-fluency objective. Our goal is not merely to corrupt captions, but to understand how meaning itself is encoded, distributed, and alterable at the bit level, revealing that even imperceptible low-level changes can steer the high-level semantics of generative vision-language models. It also opens pathways for robustness testing, adversarial defense, and explainable AI, by exposing how structured bit-level faults can reshape a model's semantic output.
Authors: Feng Xiong, Zongxia Xie, Yanru Sun, Haoyu Wang, Jianhong Lin
Abstract: Effective multivariate time series forecasting often benefits from accurately modeling complex inter-variable dependencies. However, existing attention- or graph-based methods face three key issues: (a) strong temporal self-dependencies are often disrupted by irrelevant variables; (b) softmax normalization ignores and reverses negative correlations; (c) variables struggle to perceive their temporal positions. To address these, we propose \textbf{SEED}, a Spectral Entropy-guided Evaluation framework for spatial-temporal Dependency modeling. SEED introduces a Dependency Evaluator, a key innovation that leverages spectral entropy to dynamically provide a preliminary evaluation of the spatial and temporal dependencies of each variable, enabling the model to adaptively balance Channel Independence (CI) and Channel Dependence (CD) strategies. To account for temporal regularities originating from the influence of other variables rather than intrinsic dynamics, we propose Spectral Entropy-based Fuser to further refine the evaluated dependency weights, effectively separating this part. Moreover, to preserve negative correlations, we introduce a Signed Graph Constructor that enables signed edge weights, overcoming the limitations of softmax. Finally, to help variables perceive their temporal positions and thereby construct more comprehensive spatial features, we introduce the Context Spatial Extractor, which leverages local contextual windows to extract spatial features. Extensive experiments on 12 real-world datasets from various application domains demonstrate that SEED achieves state-of-the-art performance, validating its effectiveness and generality.
Authors: Zhuoran Zhang, Feng Zhang, Shangyuan Li, Yang Shi, Yuanxing Zhang, Wei Chen, Tengjiao Wang, Kam-Fai Wong
Abstract: Small language models (SLMs) are widely used in tasks that require low latency and lightweight deployment, particularly classification. As interpretability and robustness gain increasing importance, explanation-guided learning has emerged as an effective framework by introducing attribution-based supervision during training; however, deriving general and reliable attribution priors remains a significant challenge. Through an analysis of representative attribution methods in classification settings, we find that although these methods can reliably highlight class-relevant tokens, they often focus on common keywords shared by semantically similar classes. Because such classes are already difficult to distinguish under standard training, these attributions provide insufficient discriminative cues, limiting their ability to improve model differentiation. To overcome this limitation, we propose Class-Aware Attribution Prior (CAP), a novel attribution prior extraction framework that guides language models toward capturing fine-grained class distinctions and producing more salient, discriminative attribution priors. Building on this idea, we further introduce CAP Hybrid, which combines priors from CAP with those from existing attribution techniques to form a more comprehensive and balanced supervisory signal. By aligning a model's self-attribution with these enriched priors, our approach encourages the learning of diverse, decision-relevant features. Extensive experiments in full-data, few-shot, and adversarial scenarios demonstrate that our method consistently enhances both interpretability and robustness.
Authors: Dizhan Xue, Jing Cui, Shengsheng Qian, Chuanrui Hu, Changsheng Xu
Abstract: Intelligent agents powered by large language models (LLMs) have recently demonstrated impressive capabilities and gained increasing popularity on social media platforms. While LLM agents are reshaping the ecology of social media, there exists a current gap in conducting a comprehensive evaluation of their ability to comprehend media content, understand user behaviors, and make intricate decisions. To address this challenge, we introduce SoMe, a pioneering benchmark designed to evaluate social media agents equipped with various agent tools for accessing and analyzing social media data. SoMe comprises a diverse collection of 8 social media agent tasks, 9,164,284 posts, 6,591 user profiles, and 25,686 reports from various social media platforms and external websites, with 17,869 meticulously annotated task queries. Compared with the existing datasets and benchmarks for social media tasks, SoMe is the first to provide a versatile and realistic platform for LLM-based social media agents to handle diverse social media tasks. By extensive quantitative and qualitative analysis, we provide the first overview insight into the performance of mainstream agentic LLMs in realistic social media environments and identify several limitations. Our evaluation reveals that both the current closed-source and open-source LLMs cannot handle social media agent tasks satisfactorily. SoMe provides a challenging yet meaningful testbed for future social media agents. Our code and data are available at https://github.com/LivXue/SoMe
Authors: Mohamed Malhou, Ludovic Perret, Kristin Lauter
Abstract: At NeurIPS 2024, Kera et al. introduced the use of transformers for computing Groebner bases, a central object in computer algebra with numerous practical applications. In this paper, we improve this approach by applying Hierarchical Attention Transformers (HATs) to solve systems of multivariate polynomial equations via Groebner bases computation. The HAT architecture incorporates a tree-structured inductive bias that enables the modeling of hierarchical relationships present in the data and thus achieves significant computational savings compared to conventional flat attention models. We generalize to arbitrary depths and include a detailed computational cost analysis. Combined with curriculum learning, our method solves instances that are much larger than those in Kera et al. (2024 Learning to compute Groebner bases)
Authors: Francisco Giral, \'Alvaro Manzano, Ignacio G\'omez, Petros Koumoutsakos, Soledad Le Clainche
Abstract: Urban wind flow modeling and simulation play an important role in air quality assessment and sustainable city planning. A key challenge for modeling and simulation is handling the complex geometries of the urban landscape. Low order models are limited in capturing the effects of geometry, while high-fidelity Computational Fluid Dynamics (CFD) simulations are prohibitively expensive, especially across multiple geometries or wind conditions. Here, we propose a generative diffusion framework for synthesizing steady-state urban wind fields over unstructured meshes that requires only geometry information. The framework combines a hierarchical graph neural network with score-based diffusion modeling to generate accurate and diverse velocity fields without requiring temporal rollouts or dense measurements. Trained across multiple mesh slices and wind angles, the model generalizes to unseen geometries, recovers key flow structures such as wakes and recirculation zones, and offers uncertainty-aware predictions. Ablation studies confirm robustness to mesh variation and performance under different inference regimes. This work develops is the first step towards foundation models for the built environment that can help urban planners rapidly evaluate design decisions under densification and climate uncertainty.
Authors: Abraham Itzhak Weinberg
Abstract: Offline reinforcement learning enables policy learning from pre-collected datasets without environment interaction, but existing Decision Transformer (DT) architectures struggle with long-horizon credit assignment and complex state-action dependencies. We introduce the Quantum Decision Transformer (QDT), a novel architecture incorporating quantum-inspired computational mechanisms to address these challenges. Our approach integrates two core components: Quantum-Inspired Attention with entanglement operations that capture non-local feature correlations, and Quantum Feedforward Networks with multi-path processing and learnable interference for adaptive computation. Through comprehensive experiments on continuous control tasks, we demonstrate over 2,000\% performance improvement compared to standard DTs, with superior generalization across varying data qualities. Critically, our ablation studies reveal strong synergistic effects between quantum-inspired components: neither alone achieves competitive performance, yet their combination produces dramatic improvements far exceeding individual contributions. This synergy demonstrates that effective quantum-inspired architecture design requires holistic co-design of interdependent mechanisms rather than modular component adoption. Our analysis identifies three key computational advantages: enhanced credit assignment through non-local correlations, implicit ensemble behavior via parallel processing, and adaptive resource allocation through learnable interference. These findings establish quantum-inspired design principles as a promising direction for advancing transformer architectures in sequential decision-making, with implications extending beyond reinforcement learning to neural architecture design more broadly.
Authors: Klaus-Rudolf Kladny, Bernhard Sch\"olkopf, Lisa Koch, Christian F. Baumgartner, Michael Muehlebach
Abstract: Machine learning (ML) is transforming healthcare, but safe clinical decisions demand reliable uncertainty estimates that standard ML models fail to provide. Conformal prediction (CP) is a popular tool that allows users to turn heuristic uncertainty estimates into uncertainty estimates with statistical guarantees. CP works by converting predictions of a ML model, together with a calibration sample, into prediction sets that are guaranteed to contain the true label with any desired probability. An often cited advantage is that CP theory holds for calibration samples of arbitrary size, suggesting that uncertainty estimates with practically meaningful statistical guarantees can be achieved even if only small calibration sets are available. We question this promise by showing that, although the statistical guarantees hold for calibration sets of arbitrary size, the practical utility of these guarantees does highly depend on the size of the calibration set. This observation is relevant in medical domains because data is often scarce and obtaining large calibration sets is therefore infeasible. We corroborate our critique in an empirical demonstration on a medical image classification task.
Authors: Nikit Phadke
Abstract: We present a geometric framework for policy-constrained semantic interpretation that provably prevents hallucinated commitments in high-stakes domains. Semantic meaning is represented as direction on a unit sphere, evidence is modeled as sets of witness vectors, and admissible interpretations correspond to spherical convex regions. Policy constraints are introduced as explicit priors defined over the same manifold, separated from evidence geometry. Interpretation reduces to constrained optimization over admissible regions, with refusal emerging as a topologically necessary outcome under contradiction or policy exclusion. We connect this framework to information theory, Bayesian inference, and sheaf-theoretic semantics, proving that our complexity bounds are information-theoretically optimal. Empirical validation on large scale regulated financial data demonstrates zero hallucinated approvals across multiple policy regimes-the first such result at scale.
Authors: Idan Tankel, Nir Mazor, Rafi Brada, Christina LeBedis, Guy ben-Yosef
Abstract: Incidental findings in CT scans, though often benign, can have significant clinical implications and should be reported following established guidelines. Traditional manual inspection by radiologists is time-consuming and variable. This paper proposes a novel framework that leverages large language models (LLMs) and foundational vision-language models (VLMs) in a plan-and-execute agentic approach to improve the efficiency and precision of incidental findings detection, classification, and reporting for abdominal CT scans. Given medical guidelines for abdominal organs, the process of managing incidental findings is automated through a planner-executor framework. The planner, based on LLM, generates Python scripts using predefined base functions, while the executor runs these scripts to perform the necessary checks and detections, via VLMs, segmentation models, and image processing subroutines. We demonstrate the effectiveness of our approach through experiments on a CT abdominal benchmark for three organs, in a fully automatic end-to-end manner. Our results show that the proposed framework outperforms existing pure VLM-based approaches in terms of accuracy and efficiency.
Authors: Yuqun Zhang, Yuxuan Zhao, Sijia Chen
Abstract: This paper proposes PyFi, a novel framework for pyramid-like financial image understanding that enables vision language models (VLMs) to reason through question chains in a progressive, simple-to-complex manner. At the core of PyFi is PyFi-600K, a dataset comprising 600K financial question-answer pairs organized into a reasoning pyramid: questions at the base require only basic perception, while those toward the apex demand increasing levels of capability in financial visual understanding and expertise. This data is scalable because it is synthesized without human annotations, using PyFi-adv, a multi-agent adversarial mechanism under the Monte Carlo Tree Search (MCTS) paradigm, in which, for each image, a challenger agent competes with a solver agent by generating question chains that progressively probe deeper capability levels in financial visual reasoning. Leveraging this dataset, we present fine-grained, hierarchical, and comprehensive evaluations of advanced VLMs in the financial domain. Moreover, fine-tuning Qwen2.5-VL-3B and Qwen2.5-VL-7B on the pyramid-structured question chains enables these models to answer complex financial questions by decomposing them into sub-questions with gradually increasing reasoning demands, yielding average accuracy improvements of 19.52% and 8.06%, respectively, on the dataset. All resources of code, dataset and models are available at: https://github.com/AgenticFinLab/PyFi .
Authors: Guanlin Jing, Huayi Qi
Abstract: Existing agent communication frameworks face critical limitations in providing verifiable audit trails without compromising the privacy and confidentiality of agent interactions. The protection of agent communication privacy while ensuring auditability emerges as a fundamental challenge for applications requiring accurate billing, compliance verification, and accountability in regulated environments. We introduce a framework for auditing agent communications that keeps messages private while still checking they follow expected rules. It pairs zero-knowledge proofs with the existing Model Context Protocol (MCP) so messages can be verified without revealing their contents. The approach runs in lightweight networks, stays compatible with standard MCP exchanges, and adds asynchronous audit verification to confirm format and general message types without exposing specifics. The framework enables mutual audits between agents: one side can check communication content and quality while the other verifies usage metrics, all without revealing sensitive information. We formalize security goals and show that zk-MCP provides data authenticity and communication privacy, achieving efficient verification with negligible latency overhead. We fully implement the framework, including Circom-based zero-knowledge proof generation and an audit protocol integrated with MCP's bidirectional channel, and, to our knowledge, this is the first privacy-preserving audit system for agent communications that offers verifiable mutual auditing without exposing message content or compromising agent privacy.
Authors: Jing Cui, Yufei Han, Jianbin Jiao, Junge Zhang
Abstract: Backdoor attacks embed malicious behaviors into Large Language Models (LLMs), enabling adversaries to trigger harmful outputs or bypass safety controls. However, the persistence of the implanted backdoors under user-driven post-deployment continual fine-tuning has been rarely examined. Most prior works evaluate the effectiveness and generalization of implanted backdoors only at releasing and empirical evidence shows that naively injected backdoor persistence degrades after updates. In this work, we study whether and how implanted backdoors persist through a multi-stage post-deployment fine-tuning. We propose P-Trojan, a trigger-based attack algorithm that explicitly optimizes for backdoor persistence across repeated updates. By aligning poisoned gradients with those of clean tasks on token embeddings, the implanted backdoor mapping is less likely to be suppressed or forgotten during subsequent updates. Theoretical analysis shows the feasibility of such persistent backdoor attacks after continual fine-tuning. And experiments conducted on the Qwen2.5 and LLaMA3 families of LLMs, as well as diverse task sequences, demonstrate that P-Trojan achieves over 99% persistence while preserving clean-task accuracy. Our findings highlight the need for persistence-aware evaluation and stronger defenses in realistic model adaptation pipelines.
Authors: Tan Le, Van Le, Sachin Shetty
Abstract: Open Radio Access Networks (O-RAN) enhance modularity and telemetry granularity but also widen the cybersecurity attack surface across disaggregated control, user and management planes. We propose a hierarchical defense framework with three coordinated layers-anomaly detection, intrusion confirmation, and multiattack classification-each aligned with O-RAN's telemetry stack. Our approach integrates hybrid quantum computing and machine learning, leveraging amplitude- and entanglement-based feature encodings with deep and ensemble classifiers. We conduct extensive benchmarking across synthetic and real-world telemetry, evaluating encoding depth, architectural variants, and diagnostic fidelity. The framework consistently achieves near-perfect accuracy, high recall, and strong class separability. Multi-faceted evaluation across decision boundaries, probabilistic margins, and latent space geometry confirms its interpretability, robustness, and readiness for slice-aware diagnostics and scalable deployment in near-RT and non-RT RIC domains.
Authors: Adewale Akinfaderin, Shreyas Subramanian
Abstract: Financial AI systems suffer from a critical blind spot: while Retrieval-Augmented Generation (RAG) excels at finding relevant documents, language models still generate calculation errors and regulatory violations during reasoning, even with perfect retrieval. This paper introduces VERAFI (Verified Agentic Financial Intelligence), an agentic framework with neurosymbolic policy generation for verified financial intelligence. VERAFI combines state-of-the-art dense retrieval and cross-encoder reranking with financial tool-enabled agents and automated reasoning policies covering GAAP compliance, SEC requirements, and mathematical validation. Our comprehensive evaluation on FinanceBench demonstrates remarkable improvements: while traditional dense retrieval with reranking achieves only 52.4\% factual correctness, VERAFI's integrated approach reaches 94.7\%, an 81\% relative improvement. The neurosymbolic policy layer alone contributes a 4.3 percentage point gain over pure agentic processing, specifically targeting persistent mathematical and logical errors. By integrating financial domain expertise directly into the reasoning process, VERAFI offers a practical pathway toward trustworthy financial AI that meets the stringent accuracy demands of regulatory compliance, investment decisions, and risk management.
Authors: Edward Lue Chee Lip, Anthony Channg, Diana Kim, Aaron Sandoval, Kevin Zhu
Abstract: As AI capabilities advance, we increasingly rely on powerful models to decompose complex tasks $\unicode{x2013}$ but what if the decomposer itself is malicious? Factored cognition protocols decompose complex tasks into simpler child tasks: one model creates the decomposition, while other models implement the child tasks in isolation. Prior work uses trusted (weaker but reliable) models for decomposition, which limits usefulness for tasks where decomposition itself is challenging. We introduce Factor($U$,$T$), in which an untrusted (stronger but potentially malicious) model decomposes while trusted models implement child tasks. Can monitors detect malicious activity when observing only natural language task instructions, rather than complete solutions? We baseline and red team Factor($U$,$T$) in control evaluations on BigCodeBench, a dataset of Python coding tasks. Monitors distinguishing malicious from honest decompositions perform poorly (AUROC 0.52) compared to monitors evaluating complete Python solutions (AUROC 0.96). Furthermore, Factor($D$,$U$), which uses a trusted decomposer and monitors concrete child solutions, achieves excellent discrimination (AUROC 0.96) and strong safety (1.2% ASR), demonstrating that implementation-context monitoring succeeds where decomposition-only monitoring fails.
Authors: Ying Cui, Dongzhe Zheng, Ke Yu, Xiyin Zheng, Xiaorui Wang, Xinxiang Li, Yan Gu, Lin Fu, Xinyi Chen, Wenjie Mei, Xin-Gui Peng
Abstract: Clear cell renal cell carcinoma (ccRCC) exhibits extensive intratumoral heterogeneity on multiple biological scales, contributing to variable clinical outcomes and limiting the effectiveness of conventional TNM staging, which highlights the urgent need for multiscale integrative analytic frameworks. The lipid-deficient de-clear cell differentiated (DCCD) ccRCC subtype, defined by multi-omics analyses, is associated with adverse outcomes even in early-stage disease. Here, we establish a hierarchical cross-scale framework for the preoperative identification of DCCD-ccRCC. At the highest layer, cross-modal mapping transferred molecular signatures to histological and CT phenotypes, establishing a molecular-to-pathology-to-radiology supervisory bridge. Within this framework, each modality-specific model is designed to mirror the inherent hierarchical structure of tumor biology. PathoDCCD captured multi-scale microscopic features, from cellular morphology and tissue architecture to meso-regional organization. RadioDCCD integrated complementary macroscopic information by combining whole-tumor and its habitat-subregions radiomics with a 2D maximal-section heterogeneity metric. These nested models enabled integrated molecular subtype prediction and clinical risk stratification. Across five cohorts totaling 1,659 patients, PathoDCCD reliably recapitulated molecular subtypes, while RadioDCCD provided reliable preoperative prediction. The consistent predictions identified patients with the poorest clinical outcomes. This cross-scale paradigm unifies molecular biology, computational pathology, and quantitative radiology into a biologically grounded strategy for preoperative noninvasive molecular phenotyping of ccRCC.
Authors: Yixin Tan, Zhe Yu, Jun Sakuma
Abstract: Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak vulnerabilities from their pretrained sources. We investigate this question in a realistic pretrain-to-finetune threat model, where the attacker has white-box access to the pretrained LLM and only black-box access to its finetuned derivatives. Empirical analysis shows that adversarial prompts optimized on the pretrained model transfer most effectively to its finetuned variants, revealing inherited vulnerabilities from pretrained to finetuned LLMs. To further examine this inheritance, we conduct representation-level probing, which shows that transferable prompts are linearly separable within the pretrained hidden states, suggesting that universal transferability is encoded in pretrained representations. Building on this insight, we propose the Probe-Guided Projection (PGP) attack, which steers optimization toward transferability-relevant directions. Experiments across multiple LLM families and diverse finetuned tasks confirm PGP's strong transfer success, underscoring the security risks inherent in the pretrain-to-finetune paradigm.
Authors: Abdelsadeq Elfergany, Ammar Adl, Mohammed Kayed
Abstract: Recommendation systems face challenges in dynamically adapting to evolving user preferences and interactions within complex social networks. Traditional approaches often fail to account for the intricate interactions within cyber-social systems and lack the flexibility to generalize across diverse domains, highlighting the need for more adaptive and versatile solutions. In this work, we introduce a general-purpose swarm intelligence algorithm for recommendation systems, designed to adapt seamlessly to varying applications. It was inspired by social psychology principles. The framework models user preferences and community influences within a dynamic hypergraph structure. It leverages centrality-based feature extraction and Node2Vec embeddings. Preference evolution is guided by message-passing mechanisms and hierarchical graph modeling, enabling real-time adaptation to changing behaviors. Experimental evaluations demonstrated the algorithm's superior performance in various recommendation tasks, including social networks and content discovery. Key metrics such as Hit Rate (HR), Mean Reciprocal Rank (MRR), and Normalized Discounted Cumulative Gain (NDCG) consistently outperformed baseline methods across multiple datasets. The model's adaptability to dynamic environments allowed for contextually relevant and precise recommendations. The proposed algorithm represents an advancement in recommendation systems by bridging individual preferences and community influences. Its general-purpose design enables applications in diverse domains, including social graphs, personalized learning, and medical graphs. This work highlights the potential of integrating swarm intelligence with network dynamics to address complex optimization challenges in recommendation systems.
Authors: Li Lin, Siyuan Xin, Yang Cao, Xiaochun Cao
Abstract: Watermarking large language models (LLMs) is vital for preventing their misuse, including the fabrication of fake news, plagiarism, and spam. It is especially important to watermark LLM-generated code, as it often contains intellectual property.However, we found that existing methods for watermarking LLM-generated code fail to address comment removal attack.In such cases, an attacker can simply remove the comments from the generated code without affecting its functionality, significantly reducing the effectiveness of current code-watermarking techniques.On the other hand, injecting a watermark into code is challenging because, as previous works have noted, most code represents a low-entropy scenario compared to natural language. Our approach to addressing this issue involves leveraging prior knowledge to distinguish between low-entropy and high-entropy parts of the code, as indicated by a Cue List of words.We then inject the watermark guided by this Cue List, achieving higher detectability and usability than existing methods.We evaluated our proposed method on HumanEvaland compared our method with three state-of-the-art code watermarking techniques. The results demonstrate the effectiveness of our approach.
Authors: Jianshuo Dong, Yutong Zhang, Yan Liu, Zhenyu Zhong, Tao Wei, Chao Zhang, Han Qiu
Abstract: Advanced LLMs have achieved near-ceiling instruction-following accuracy on benchmarks such as IFEval. However, these impressive scores do not necessarily translate to reliable services in real-world use, where users often vary their phrasing, contextual framing, and task formulations. In this paper, we study nuance-oriented reliability: whether models exhibit consistent competence across cousin prompts that convey analogous user intents but with subtle nuances. To quantify this, we introduce a new metric, reliable@k, and develop an automated pipeline that generates high-quality cousin prompts via data augmentation. Building upon this, we construct IFEval++ for systematic evaluation. Across 20 proprietary and 26 open-source LLMs, we find that current models exhibit substantial insufficiency in nuance-oriented reliability -- their performance can drop by up to 61.8% with nuanced prompt modifications. What's more, we characterize it and explore three potential improvement recipes. Our findings highlight nuance-oriented reliability as a crucial yet underexplored next step toward more dependable and trustworthy LLM behavior. Our code and benchmark are accessible: https://github.com/jianshuod/IFEval-pp.
Authors: David Ball
Abstract: Modern AI systems lack a way to express and enforce requirements. Pre-training produces intelligence, and post-training optimizes preferences, but neither guarantees that models reliably satisfy explicit, context-dependent constraints. This missing abstraction explains why highly intelligent models routinely fail in deployment despite strong benchmark performance. We introduce Capability Engineering, the systematic practice of converting requirements into executable specifications and training models to satisfy them by default. We operationalize this practice through CAPE (Capability Achievement via Policy Execution), a protocol implementing a Specify -> Verify -> Correct -> Train loop. CAPE is grounded in two empirical findings: (1) contextual objectivity, where properties appearing subjective become objective once context is fixed (inter-annotator agreement rises from kappa = 0.42 to kappa = 0.98), and (2) verification-fidelity scaling, where verification accuracy improves with model scale (r = 0.94), unlike preference agreement which plateaus at 30 to 50 percent disagreement regardless of compute. Across 109,500 examples in six domains, CAPE reduces violation rates by 81 percent relative to DPO (standard deviation less than 0.3 percent). By replacing per-example annotation with reusable specifications, CAPE reduces costs by 5 to 20 times and shortens timelines from months to weeks. We release the CAPE protocol, PredicateGraph schema, CPL specification language, and policy packs under Apache 2.0. We also launch CapabilityBench, a public registry of model evaluations against community-contributed policies, shifting evaluation from intelligence benchmarks toward capability measurement.
Authors: Henry Gray, Tom Yotam, Octavian Udrea
Abstract: Translating algorithms from high-level languages like MATLAB to hardware description languages (HDLs) is a resource-intensive but necessary step for deployment on FPGAs and ASICs. While large language models (LLMs) offer a path to automation, their limited training on HDL code makes end-to-end transpilation brittle and prone to syntax errors. We compare two LLM-driven methods for syntax repair in a MATLAB-to-HDL pipeline: a structured, expert-designed flow that follows a fixed sequence of operations, and a more autonomous agentic approach that uses the Model Context Protocol (MCP) \cite{anthropic2024mcp} to dynamically select its own tools. We study 42 MATLAB signal-processing functions and isolate the syntax-repair stage. Across three model scales, the agentic approach is more effective at resolving initial syntax errors, unblocking a greater number of candidates to proceed through the pipeline. This upstream improvement yields measurable downstream improvements, most notably on mid-sized models, where it increases the simulation reach rate by over 20 percentage points. We hypothesize the gains come from short prompts, aggressive context management, and conditional tool use. Conditional retrieval helps at 8B and 30B; at 235B final-success gains are small and a naive RAG variant attains the highest final success. Our findings suggest that these agentic frameworks, when properly designed, are most effective at compensating for the capacity limits of small and mid-sized models.
Authors: Alessandro Casadei, Sreyoshi Bhaduri, Rohit Malshe, Pavan Mullapudi, Raj Ratan, Ankush Pole, Arkajit Rakshit
Abstract: Modern operational systems ranging from logistics and cloud infrastructure to industrial IoT, are governed by complex, interdependent processes. Understanding how interventions propagate through such systems requires causal inference methods that go beyond direct effects to quantify mediated pathways. Traditional mediation analysis, while effective in simple settings, fails to scale to the high-dimensional directed acyclic graphs (DAGs) encountered in practice, particularly when multiple treatments and mediators interact. In this paper, we propose a scalable mediation analysis framework tailored for large causal DAGs involving multiple treatments and mediators. Our approach systematically decomposes total effects into interpretable direct and indirect components. We demonstrate its practical utility through applied case studies in fulfillment center logistics, where complex dependencies and non-controllable factors often obscure root causes.
Authors: Justin Jung
Abstract: We propose discrete diffusion guidance for constraint satisfaction problems (CSPs) and demonstrate its ability to solve Sudoku puzzles without supervision.
Authors: Unai Laskurain, Aitor Aguirre-Ortuzar, Urko Zurutuza
Abstract: Federated Learning (FL) is an emerging machine learning paradigm that enables multiple parties to collaboratively train models without sharing raw data, ensuring data privacy. In Vertical FL (VFL), where each party holds different features for the same users, a key challenge is to evaluate the feature contribution of each party before any model is trained, particularly in the early stages when no model exists. To address this, the Shapley-CMI method was recently proposed as a model-free, information-theoretic approach to feature valuation using Conditional Mutual Information (CMI). However, its original formulation did not provide a practical implementation capable of computing the required permutations and intersections securely. This paper presents a novel privacy-preserving implementation of Shapley-CMI for VFL. Our system introduces a private set intersection (PSI) server that performs all necessary feature permutations and computes encrypted intersection sizes across discretized and encrypted ID groups, without the need for raw data exchange. Each party then uses these intersection results to compute Shapley-CMI values, computing the marginal utility of their features. Initial experiments confirm the correctness and privacy of the proposed system, demonstrating its viability for secure and efficient feature contribution estimation in VFL. This approach ensures data confidentiality, scales across multiple parties, and enables fair data valuation without requiring the sharing of raw data or training models.
Authors: Xixian Wu, Yang Ou, Pengchao Tian, Zian Yang, Jielei Zhang, Peiyi Li, Longwen Gao
Abstract: Vision-language models (VLMs) have demonstrated significant potential in Visual Question Answering (VQA). However, the susceptibility of VLMs to hallucinations can lead to overconfident yet incorrect answers, severely undermining answer reliability. To address this, we propose Dual-Assessment for VLM Reliability (DAVR), a novel framework that integrates Self-Reflection and Cross-Model Verification for comprehensive uncertainty estimation. The DAVR framework features a dual-pathway architecture: one pathway leverages dual selector modules to assess response reliability by fusing VLM latent features with QA embeddings, while the other deploys external reference models for factual cross-checking to mitigate hallucinations. Evaluated in the Reliable VQA Challenge at ICCV-CLVL 2025, DAVR achieves a leading $\Phi_{100}$ score of 39.64 and a 100-AUC of 97.22, securing first place and demonstrating its effectiveness in enhancing the trustworthiness of VLM responses.
Authors: Mahmut S. Gokmen, Mitchell A. Klusty, Peter T. Nelson, Allison M. Neltner, Sen-Ching Samson Cheung, Thomas M. Pearce, David A Gutman, Brittany N. Dugger, Devavrat S. Bisht, Margaret E. Flanagan, V. K. Cody Bumgardner
Abstract: Whole-slide images (WSIs) contain tissue information distributed across multiple magnification levels, yet most self-supervised methods treat these scales as independent views. This separation prevents models from learning representations that remain stable when resolution changes, a key requirement for practical neuropathology workflows. This study introduces Magnification-Aware Distillation (MAD), a self-supervised strategy that links low-magnification context with spatially aligned high-magnification detail, enabling the model to learn how coarse tissue structure relates to fine cellular patterns. The resulting foundation model, MAD-NP, is trained entirely through this cross-scale correspondence without annotations. A linear classifier trained only on 10x embeddings maintains 96.7% of its performance when applied to unseen 40x tiles, demonstrating strong resolution-invariant representation learning. Segmentation outputs remain consistent across magnifications, preserving anatomical boundaries and minimizing noise. These results highlight the feasibility of scalable, magnification-robust WSI analysis using a unified embedding space
Authors: Riccardo Oliva, Farahdiba Zarin, Alice Zampolini Faustini, Armine Vardazaryan, Andrea Rosati, Vinkle Srivastav, Nunzia Del Villano, Jacques Marescaux, Giovanni Scambia, Pietro Mascagni, Nicolas Padoy, Anna Fagotti
Abstract: Advanced Ovarian Cancer (AOC) is often diagnosed at an advanced stage with peritoneal carcinosis (PC). Fagotti score (FS) assessment at diagnostic laparoscopy (DL) guides treatment planning by estimating surgical resectability, but its subjective and operator-dependent nature limits reproducibility and widespread use. Videos of patients undergoing DL with concomitant FS assessments at a referral center were retrospectively collected and divided into a development dataset, for data annotation, AI training and evaluation, and an independent test dataset, for internal validation. In the development dataset, FS-relevant frames were manually annotated for anatomical structures and PC. Deep learning models were trained to automatically identify FS-relevant frames, segment structures and PC, and predict video-level FS and indication to surgery (ItS). AI performance was evaluated using Dice score for segmentation, F1-scores for anatomical stations (AS) and ItS prediction, and root mean square error (RMSE) for final FS estimation. In the development dataset, the segmentation model trained on 7,311 frames, achieved Dice scores of 70$\pm$3% for anatomical structures and 56$\pm$3% for PC. Video-level AS classification achieved F1-scores of 74$\pm$3% and 73$\pm$4%, FS prediction showed normalized RMSE values of 1.39$\pm$0.18 and 1.15$\pm$0.08, and ItS reached F1-scores of 80$\pm$8% and 80$\pm$2% in the development (n=101) and independent test datasets (n=50), respectively. This is the first AI model to predict the feasibility of cytoreductive surgery providing automated FS estimation from DL videos. Its reproducible and reliable performance across datasets suggests that AI can support surgeons through standardized intraoperative tumor burden assessment and clinical decision-making in AOC.
Authors: Richard Ackermann, Simeon Emanuilov
Abstract: OpenAI has recently argued that hallucinations in large language models result primarily from misaligned evaluation incentives that reward confident guessing rather than epistemic humility. On this view, hallucination is a contingent behavioral artifact, remediable through improved benchmarks and reward structures. In this paper, we challenge that interpretation. Drawing on previous work on structural hallucination and empirical experiments using a Licensing Oracle, we argue that hallucination is not an optimization failure but an architectural inevitability of the transformer model. Transformers do not represent the world; they model statistical associations among tokens. Their embedding spaces form a pseudo-ontology derived from linguistic co-occurrence rather than world-referential structure. At ontological boundary conditions - regions where training data is sparse or incoherent - the model necessarily interpolates fictional continuations in order to preserve coherence. No incentive mechanism can modify this structural dependence on pattern completion. Our empirical results demonstrate that hallucination can only be eliminated through external truth-validation and abstention modules, not through changes to incentives, prompting, or fine-tuning. The Licensing Oracle achieves perfect abstention precision across domains precisely because it supplies grounding that the transformer lacks. We conclude that hallucination is a structural property of generative architectures and that reliable AI requires hybrid systems that distinguish linguistic fluency from epistemic responsibility.
Authors: Ellie Y. Cheng, Logan Weber, Tian Jin, Michael Carbin
Abstract: The rise of large language models (LLMs) has introduced a new type of programming: natural language programming. By writing prompts that direct LLMs to perform natural language processing, code generation, reasoning, etc., users are writing code in natural language -- natural language code -- for the LLM to execute. An emerging area of research enables interoperability between natural language code and formal languages such as Python. We present a novel programming abstraction, shared program state, that removes the manual work required to enable interoperability between natural language code and program state. With shared program state, programmers can write natural code that directly writes program variables, computes with program objects, and implements control flow in the program. We present a schema for specifying natural function interfaces that extend programming systems to support natural code and leverage this schema to specify shared program state as a natural function interface. We implement shared program state in the Nightjar programming system. Nightjar enables programmers to write Python programs that contain natural code that shares the Python program state. We show that Nightjar programs achieve comparable or higher task accuracy than manually written implementations (+4-19%), while decreasing the lines of code by 39.6% on average. The tradeoff to using Nightjar is that it may incur runtime overhead (0.4-4.3x runtime of manual implementations).
Authors: Audrey Cheng, Shu Liu, Melissa Pan, Zhifei Li, Shubham Agarwal, Mert Cemri, Bowen Wang, Alexander Krentsel, Tian Xia, Jongseok Park, Shuo Yang, Jeff Chen, Lakshya Agrawal, Ashwin Naren, Shulu Li, Ruiying Ma, Aditya Desai, Jiarong Xing, Koushik Sen, Matei Zaharia, Ion Stoica
Abstract: Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate solutions. Research focused on improving systems performance is especially well-suited to this paradigm because system performance problems naturally admit such verifiers: candidates can be implemented in real systems or simulators and evaluated against predefined workloads. We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems (ADRS). Using several open-source ADRS instances (i.e., OpenEvolve, GEPA, and ShinkaEvolve), we demonstrate across ten case studies (e.g., multi-region cloud scheduling, mixture-of-experts load balancing, LLM-based SQL, transaction scheduling) that ADRS-generated solutions can match or even outperform human state-of-the-art designs. Based on these findings, we outline best practices (e.g., level of prompt specification, amount of feedback, robust evaluation) for effectively using ADRS, and we discuss future research directions and their implications. Although we do not yet have a universal recipe for applying ADRS across all of systems research, we hope our preliminary findings, together with the challenges we identify, offer meaningful guidance for future work as researcher effort shifts increasingly toward problem formulation and strategic oversight. Note: This paper is an extension of our prior work [14]. It adds extensive evaluation across multiple ADRS frameworks and provides deeper analysis and insights into best practices.
Authors: Arth Bhardwaj, Sia Godika, Yuvam Loonker
Abstract: Traditional, centralized security tools often miss adaptive, multi-vector attacks. We present the Multi-Agent LLM Cyber Defense Framework (MALCDF), a practical setup where four large language model (LLM) agents-Detection, Intelligence, Response, and Analysis-work together in real time. Agents communicate over a Secure Communication Layer (SCL) with encrypted, ontology-aligned messages, and produce audit-friendly outputs (e.g., MITRE ATT&CK mappings). For evaluation, we keep the test simple and consistent: all reported metrics come from the same 50-record live stream derived from the CICIDS2017 feature schema. CICIDS2017 is used for configuration (fields/schema) and to train a practical ML baseline. The ML-IDS baseline is a Lightweight Random Forest IDS (LRF-IDS) trained on a subset of CICIDS2017 and tested on the 50-record stream, with no overlap between training and test records. In experiments, MALCDF reaches 90.0% detection accuracy, 85.7% F1-score, and 9.1% false-positive rate, with 6.8s average per-event latency. It outperforms the lightweight ML-IDS baseline and a single-LLM setup on accuracy while keeping end-to-end outputs consistent. Overall, this hands-on build suggests that coordinating simple LLM agents with secure, ontology-aligned messaging can improve practical, real-time cyber defense.
Authors: Mahmuda Sharmin, Taihao Han, Jie Huang, Narayanan Neithalath, Gaurav Sant, Aditya Kumar
Abstract: Machine learning (ML) has been increasingly applied in concrete research to optimize performance and mixture design. However, one major challenge in applying ML to cementitious materials is the limited size and diversity of available databases. A promising solution is the development of multi-modal databases that integrate both numerical and graphical data. Conventional ML frameworks in cement research are typically restricted to a single data modality. Graph neural network (GNN) represents a new generation of neural architectures capable of learning from data structured as graphs, capturing relationships through irregular or topology-dependent connections rather than fixed spatial coordinates. While GNN is inherently designed for graphical data, they can be adapted to extract correlations from numerical datasets and potentially embed physical laws directly into their architecture, enabling explainable and physics-informed predictions. This work is among the first few studies to implement GNNs to design concrete, with a particular emphasis on establishing a clear and reproducible pathway for converting tabular data into graph representations using the k-nearest neighbor (K-NN) approach. Model hyperparameters and feature selection are systematically optimized to enhance prediction performance. The GNN shows performance comparable to the benchmark random forest, which has been demonstrated by many studies to yield reliable predictions for cementitious materials. Overall, this study provides a foundational roadmap for transitioning from traditional ML to advanced AI architectures. The proposed framework establishes a strong foundation for future multi-modal and physics-informed GNN models capable of capturing complex material behaviors and accelerating the design and optimization of cementitious materials.
Authors: Viet K. Nguyen, Mohammad I. Husain
Abstract: Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in chat mode, there is no comparative analysis in multiple models and frameworks. We conducted the first systematic penetration testing and comparative evaluation of agentic AI systems, testing five prominent models (Claude 3.5 Sonnet, Gemini 2.5 Flash, GPT-4o, Grok 2, and Nova Pro) across two agentic AI frameworks (AutoGen and CrewAI) using a seven-agent architecture that mimics the functionality of a university information management system and 13 distinct attack scenarios that span prompt injection, Server Side Request Forgery (SSRF), SQL injection, and tool misuse. Our 130 total test cases reveal significant security disparities: AutoGen demonstrates a 52.3% refusal rate versus CrewAI's 30.8%, while model performance ranges from Nova Pro's 46.2% to Claude and Grok 2's 38.5%. Most critically, Grok 2 on CrewAI rejected only 2 of 13 attacks (15.4% refusal rate), and the overall refusal rate of 41.5% across all configurations indicates that more than half of malicious prompts succeeded despite enterprise-grade safety mechanisms. We identify six distinct defensive behavior patterns including a novel "hallucinated compliance" strategy where models fabricate outputs rather than executing or refusing attacks, and provide actionable recommendations for secure agent deployment. Complete attack prompts are also included in the Appendix to enable reproducibility.
Authors: Jingwei Chen
Abstract: Self-referential learning -- training a model on data it generated itself -- promises boundless scalability but chronically suffers from model collapse: language models degenerate into repetitive text, GANs drop modes, and reinforcement-learning policies over-exploit. Although practitioners employ ad~hoc fixes such as real-data mixing, entropy bonuses, knowledge distillation, or retrieval-augmented generation, a single principle that explains both the failure mode and the success of these fixes has remained elusive. We present Entropy-Reservoir Bregman Projection (ERBP), an information-geometric framework that unifies these phenomena. We model the closed loop as a stochastic Bregman projection sequence in distribution space. Without external coupling, finite-sample noise forces the system to project onto an ever-shrinking empirical support, causing exponential entropy decay and eventual collapse. Introducing an Entropy Reservoir -- a high-entropy distribution mixed into each projection -- injects a controllable entropy flux that provably stabilises the dynamics. Our theory yields (i) a necessary condition for collapse, (ii) a sufficient condition that guarantees a non-trivial entropy floor, and (iii) closed-form rates that depend only on sample size and the strong-convexity/Lipschitz constants of the Bregman generator. Experiments on large-language-model self-training, Soft Actor-Critic in reinforcement learning, and GAN optimisation validate our predictions and show that disparate stabilisation heuristics correspond to specific reservoir choices and coupling coefficients. ERBP thus transforms a collection of folk remedies into a single, quantitative design rule: monitor and budget your entropy flux.
Authors: Massimiliano Fadda, Enrico Motta, Francesco Osborne, Diego Reforgiato Recupero, Angelo Salatino
Abstract: News sources play a central role in democratic societies by shaping political and social discourse through specific topics, viewpoints and voices. Understanding these dynamics is essential for assessing whether the media landscape offers a balanced and fair account of public debate. In earlier work, we introduced a pipeline that, given a news corpus, i) uses a hybrid human-machine approach to identify the range of viewpoints expressed about a given topic, and ii) classifies relevant claims with respect to the identified viewpoints, defined as sets of semantically and ideologically congruent claims (e.g., positions arguing that immigration positively impacts the UK economy). In this paper, we improve this pipeline by i) fine-tuning Large Language Models (LLMs) for viewpoint classification and ii) enriching claim representations with semantic descriptions of relevant actors drawn from Wikidata. We evaluate our approach against alternative solutions on a benchmark centred on the UK immigration debate. Results show that while both mechanisms independently improve classification performance, their integration yields the best results, particularly when using LLMs capable of processing long inputs.
Authors: Mohammad Abu-Shaira, Alejandro Rodriguez, Greg Speegle, Victor Sheng, Ishfaq Ahmad
Abstract: Online learning updates models incrementally with new data, avoiding large storage requirements and costly model recalculations. In this paper, we introduce "OLR-WA; OnLine Regression with Weighted Average", a novel and versatile multivariate online linear regression model. We also investigate scenarios involving drift, where the underlying patterns in the data evolve over time, conduct convergence analysis, and compare our approach with existing online regression models. The results of OLR-WA demonstrate its ability to achieve performance comparable to the batch regression, while also showcasing comparable or superior performance when compared with other state-of-the-art online models, thus establishing its effectiveness. Moreover, OLR-WA exhibits exceptional performance in terms of rapid convergence, surpassing other online models with consistently achieving high r2 values as a performance measure from the first iteration to the last iteration, even when initialized with minimal amount of data points, as little as 1% to 10% of the total data points. In addition to its ability to handle time-based (temporal drift) scenarios, remarkably, OLR-WA stands out as the only model capable of effectively managing confidence-based challenging scenarios. It achieves this by adopting a conservative approach in its updates, giving priority to older data points with higher confidence levels. In summary, OLR-WA's performance further solidifies its versatility and utility across different contexts, making it a valuable solution for online linear regression tasks.
Authors: Niklas Lauffer, Xiang Deng, Srivatsa Kundurthy, Brad Kenstler, Jeff Da
Abstract: A popular paradigm for training LM agents relies on imitation learning, fine-tuning on expert trajectories. However, we show that the off-policy nature of imitation learning for multi-turn LM agents suffers from the fundamental limitation known as covariate shift: as the student policy's behavior diverges from the expert's, it encounters states not present in the training data, reducing the effectiveness of fine-tuning. Taking inspiration from the classic DAgger algorithm, we propose a novel data generation methodology for addressing covariate shift for multi-turn LLM training. We introduce on-policy expert corrections (OECs), partially on-policy data generated by starting rollouts with a student model and then switching to an expert model part way through the trajectory. We explore the effectiveness of our data generation technique in the domain of software engineering (SWE) tasks, a multi-turn setting where LLM agents must interact with a development environment to fix software bugs. Our experiments compare OEC data against various other on-policy and imitation learning approaches on SWE agent problems and train models using a common rejection sampling (i.e., using environment reward) combined with supervised fine-tuning technique. Experiments find that OEC trajectories show a relative 14% and 13% improvement over traditional imitation learning in the 7b and 32b setting, respectively, on SWE-bench verified. Our results demonstrate the need for combining expert demonstrations with on-policy data for effective multi-turn LM agent training.
Authors: Houman Kazemzadeh, Kiarash Mokhtari Dizaji, Seyed Reza Tavakoli, Farbod Davoodi, MohammadReza KarimiNejad, Parham Abed Azad, Ali Sabzi, Armin Khosravi, Siavash Ahmadi, Mohammad Hossein Rohban, Glolamali Aminian, Tahereh Javaheri
Abstract: Objectives: To evaluate large language model (LLM) performance on pharmacy licensure-style question-answering (QA) tasks and develop an external knowledge integration method to improve their accuracy. Methods: We benchmarked eleven existing LLMs with varying parameter sizes (8 billion to 70+ billion) using a 141-question pharmacy dataset. We measured baseline accuracy for each model without modification. We then developed a three-step retrieval-augmented generation (RAG) pipeline, DrugRAG, that retrieves structured drug knowledge from validated sources and augments model prompts with evidence-based context. This pipeline operates externally to the models, requiring no changes to model architecture or parameters. Results: Baseline accuracy ranged from 46% to 92%, with GPT-5 (92%) and o3 (89%) achieving the highest scores. Models with fewer than 8 billion parameters scored below 50%. DrugRAG improved accuracy across all tested models, with gains ranging from 7 to 21 percentage points (e.g., Gemma 3 27B: 61% to 71%, Llama 3.1 8B: 46% to 67%) on the 141-item benchmark. Conclusion: We demonstrate that external structured drug knowledge integration through DrugRAG measurably improves LLM accuracy on pharmacy tasks without modifying the underlying models. This approach provides a practical pipeline for enhancing pharmacy-focused AI applications with evidence-based information.
Authors: George-Andrei Dima, Dumitru-Clementin Cercel
Abstract: Focusing on low-resource languages is an essential step toward democratizing generative AI. In this work, we contribute to reducing the multimodal NLP resource gap for Romanian. We translate the widely known Flickr30k dataset into Romanian and further extend it for visual question answering by leveraging open-source LLMs. We demonstrate the usefulness of our datasets by fine-tuning open-source VLMs on Romanian visual question answering. We select VLMs from three widely used model families: LLaMA 3.2, LLaVA 1.6, and Qwen2. For fine-tuning, we employ the parameter-efficient LoRA method. Our models show improved Romanian capabilities in visual QA, as well as on tasks they were not trained on, such as Romanian image description generation. The seven-billion-parameter Qwen2-VL-RoVQA obtains top scores on both tasks, with improvements of +6.05% and +2.61% in BERTScore F1 over its original version. Finally, the models show substantial reductions in grammatical errors compared to their original forms, indicating improvements not only in language understanding but also in Romanian fluency.
Authors: Jaume Anguera Peris, Songtao Cheng, Hanzhao Zhang, Wei Ouyang, Joakim Jald\'en
Abstract: High-content screening microscopy generates large amounts of live-cell imaging data, yet its potential remains constrained by the inability to determine when and where to image most effectively. Optimally balancing acquisition time, computational capacity, and photobleaching budgets across thousands of dynamically evolving regions of interest remains an open challenge, further complicated by limited field-of-view adjustments and sensor sensitivity. Existing approaches either rely on static sampling or heuristics that neglect the dynamic evolution of biological processes, leading to inefficiencies and missed events. Here, we introduce the restless multi-process multi-armed bandit (RMPMAB), a new decision-theoretic framework in which each experimental region is modeled not as a single process but as an ensemble of Markov chains, thereby capturing the inherent heterogeneity of biological systems such as asynchronous cell cycles and heterogeneous drug responses. Building upon this foundation, we derive closed-form expressions for transient and asymptotic behaviors of aggregated processes, and design scalable Whittle index policies with sub-linear complexity in the number of imaging regions. Through both simulations and a real biological live-cell imaging dataset, we show that our approach achieves substantial improvements in throughput under resource constraints. Notably, our algorithm outperforms Thomson Sampling, Bayesian UCB, epsilon-Greedy, and Round Robin by reducing cumulative regret by more than 37% in simulations and capturing 93% more biologically relevant events in live imaging experiments, underscoring its potential for transformative smart microscopy. Beyond improving experimental efficiency, the RMPMAB framework unifies stochastic decision theory with optimal autonomous microscopy control, offering a principled approach to accelerate discovery across multidisciplinary sciences.
Authors: Abhijeet Parida, Daniel Capell\'an-Mart\'in, Zhifan Jiang, Nishad Kulkarni, Krithika Iyer, Austin Tapp, Syed Muhammad Anwar, Mar\'ia J. Ledesma-Carbayo, Marius George Linguraru
Abstract: Gliomas are the most common malignant brain tumors in adults and are among the most lethal. Despite aggressive treatment, the median survival rate is less than 15 months. Accurate multiparametric MRI (mpMRI) tumor segmentation is critical for surgical planning, radiotherapy, and disease monitoring. While deep learning models have improved the accuracy of automated segmentation, large-scale pre-trained models generalize poorly and often underperform, producing systematic errors such as false positives, label swaps, and slice discontinuities in slices. These limitations are further compounded by unequal access to GPU resources and the growing environmental cost of large-scale model training. In this work, we propose adaptive post-processing techniques to refine the quality of glioma segmentations produced by large-scale pretrained models developed for various types of tumors. We demonstrated the techniques in multiple BraTS 2025 segmentation challenge tasks, with the ranking metric improving by 14.9 % for the sub-Saharan Africa challenge and 0.9% for the adult glioma challenge. This approach promotes a shift in brain tumor segmentation research from increasingly complex model architectures to efficient, clinically aligned post-processing strategies that are precise, computationally fair, and sustainable.
Authors: Zhenzhi Wang, Jian Wang, Ke Ma, Dahua Lin, Bing Zhou
Abstract: We introduce TalkVerse, a large-scale, open corpus for single-person, audio-driven talking video generation designed to enable fair, reproducible comparison across methods. While current state-of-the-art systems rely on closed data or compute-heavy models, TalkVerse offers 2.3 million high-resolution (720p/1080p) audio-video synchronized clips totaling 6.3k hours. These are curated from over 60k hours of video via a transparent pipeline that includes scene-cut detection, aesthetic assessment, strict audio-visual synchronization checks, and comprehensive annotations including 2D skeletons and structured visual/audio-style captions. Leveraging TalkVerse, we present a reproducible 5B DiT baseline built on Wan2.2-5B. By utilizing a video VAE with a high downsampling ratio and a sliding window mechanism with motion-frame context, our model achieves minute-long generation with low drift. It delivers comparable lip-sync and visual quality to the 14B Wan-S2V model but with 10$\times$ lower inference cost. To enhance storytelling in long videos, we integrate an MLLM director to rewrite prompts based on audio and visual cues. Furthermore, our model supports zero-shot video dubbing via controlled latent noise injection. We open-source the dataset, training recipes, and 5B checkpoints to lower barriers for research in audio-driven human video generation. Project Page: https://zhenzhiwang.github.io/talkverse/
Authors: Shaoting Feng, Yuhan Liu, Hanchen Li, Xiaokun Chen, Samuel Shen, Kuntai Du, Zhuohan Gu, Rui Zhang, Yuyang Huang, Yihua Cheng, Jiayi Yao, Qizheng Zhang, Ganesh Ananthanarayanan, Junchen Jiang
Abstract: Reusing KV cache is essential for high efficiency of Large Language Model (LLM) inference systems. With more LLM users, the KV cache footprint can easily exceed GPU memory capacity, so prior work has proposed to either evict KV cache to lower-tier storage devices, or compress KV cache so that more KV cache can be fit in the fast memory. However, prior work misses an important opportunity: jointly optimizing the eviction and compression decisions across all KV caches to minimize average generation latency without hurting quality. We propose EVICPRESS, a KV-cache management system that applies lossy compression and adaptive eviction to KV cache across multiple storage tiers. Specifically, for each KV cache of a context, EVICPRESS considers the effect of compression and eviction of the KV cache on the average generation quality and delay across all contexts as a whole. To achieve this, EVICPRESS proposes a unified utility function that quantifies the effect of quality and delay of the lossy compression or eviction. To this end, EVICPRESS's profiling module periodically updates the utility function scores on all possible eviction-compression configurations for all contexts and places KV caches using a fast heuristic to rearrange KV caches on all storage tiers, with the goal of maximizing the utility function scores on each storage tier. Compared to the baselines that evict KV cache or compress KV cache, EVICPRESS achieves higher KV-cache hit rates on fast devices, i.e., lower delay, while preserving high generation quality by applying conservative compression to contexts that are sensitive to compression errors. Evaluation on 12 datasets and 5 models demonstrates that EVICPRESS achieves up to 2.19x faster time-to-first-token (TTFT) at equivalent generation quality.
Authors: Yaniv Leviathan, Matan Kalman, Yossi Matias
Abstract: When not using reasoning, repeating the input prompt improves performance for popular models (Gemini, GPT, Claude, and Deepseek) without increasing the number of generated tokens or latency.
Authors: Yiming Cui, Xin Yao, Yuxuan Qin, Xin Li, Shijin Wang, Guoping Hu
Abstract: Multimodal scientific reasoning remains a significant challenge for large language models (LLMs), particularly in chemistry, where problem-solving relies on symbolic diagrams, molecular structures, and structured visual data. Here, we systematically evaluate 40 proprietary and open-source multimodal LLMs, including GPT-5, o3, Gemini-2.5-Pro, and Qwen2.5-VL, on a curated benchmark of Olympiad-style chemistry questions drawn from over two decades of U.S. National Chemistry Olympiad (USNCO) exams. These questions require integrated visual and textual reasoning across diverse modalities. We find that many models struggle with modality fusion, where in some cases, removing the image even improves accuracy, indicating misalignment in vision-language integration. Chain-of-Thought prompting consistently enhances both accuracy and visual grounding, as demonstrated through ablation studies and occlusion-based interpretability. Our results reveal critical limitations in the scientific reasoning abilities of current MLLMs, providing actionable strategies for developing more robust and interpretable multimodal systems in chemistry. This work provides a timely benchmark for measuring progress in domain-specific multimodal AI and underscores the need for further advances at the intersection of artificial intelligence and scientific reasoning.
Authors: Mehil B Shah, Mohammad Masudur Rahman, Foutse Khomh
Abstract: Despite their wide adoption in various domains (e.g., healthcare, finance, software engineering), Deep Learning (DL)-based applications suffer from many bugs, failures, and vulnerabilities. Reproducing these bugs is essential for their resolution, but it is extremely challenging due to the inherent nondeterminism of DL models and their tight coupling with hardware and software environments. According to recent studies, only about 3% of DL bugs can be reliably reproduced using manual approaches. To address these challenges, we present RepGen, a novel, automated, and intelligent approach for reproducing deep learning bugs. RepGen constructs a learning-enhanced context from a project, develops a comprehensive plan for bug reproduction, employs an iterative generate-validate-refine mechanism, and thus generates such code using an LLM that reproduces the bug at hand. We evaluate RepGen on 106 real-world deep learning bugs and achieve a reproduction rate of 80.19%, a 19.81% improvement over the state-of-the-art measure. A developer study involving 27 participants shows that RepGen improves the success rate of DL bug reproduction by 23.35%, reduces the time to reproduce by 56.8%, and lowers participants' cognitive load.
Authors: Maria Bulychev, Neil G. Marchant, Benjamin I. P. Rubinstein
Abstract: Recent advances in generative AI have enabled the creation of highly realistic digital content, raising concerns around authenticity, ownership, and misuse. While watermarking has become an increasingly important mechanism to trace and protect digital media, most existing image watermarking schemes operate as black boxes, producing global detection scores without offering any insight into how or where the watermark is present. This lack of transparency impacts user trust and makes it difficult to interpret the impact of tampering. In this paper, we present a post-hoc image watermarking method that combines localised embedding with region-level interpretability. Our approach embeds watermark signals in the discrete wavelet transform domain using a statistical block-wise strategy. This allows us to generate detection maps that reveal which regions of an image are likely watermarked or altered. We show that our method achieves strong robustness against common image transformations while remaining sensitive to semantic manipulations. At the same time, the watermark remains highly imperceptible. Compared to prior post-hoc methods, our approach offers more interpretable detection while retaining competitive robustness. For example, our watermarks are robust to cropping up to half the image.
Authors: Sibi Parivendan, Kashfia Sailunaz, Suresh Neethirajan
Abstract: Precision livestock farming requires objective assessment of social behavior to support herd welfare monitoring, yet most existing approaches infer interactions using static proximity thresholds that cannot distinguish affiliative from agonistic behaviors in complex barn environments. This limitation constrains the interpretability of automated social network analysis in commercial settings. We present a pose-based computational framework for interaction classification that moves beyond proximity heuristics by modeling the spatiotemporal geometry of anatomical keypoints. Rather than relying on pixel-level appearance or simple distance measures, the proposed method encodes interaction-specific motion signatures from keypoint trajectories, enabling differentiation of social interaction valence. The framework is implemented as an end-to-end computer vision pipeline integrating YOLOv11 for object detection (mAP@0.50: 96.24%), supervised individual identification (98.24% accuracy), ByteTrack for multi-object tracking (81.96% accuracy), ZebraPose for 27-point anatomical keypoint estimation, and a support vector machine classifier trained on pose-derived distance dynamics. On annotated interaction clips collected from a commercial dairy barn, the classifier achieved 77.51% accuracy in distinguishing affiliative and agonistic behaviors using pose information alone. Comparative evaluation against a proximity-only baseline shows substantial gains in behavioral discrimination, particularly for affiliative interactions. The results establish a proof-of-concept for automated, vision-based inference of social interactions suitable for constructing interaction-aware social networks, with near-real-time performance on commodity hardware.
Authors: Ruiyi Zhang, Peijia Qin, Qi Cao, Pengtao Xie
Abstract: Process Reward Models (PRMs) have become essential for improving Large Language Models (LLMs) via test-time scaling, yet their effectiveness in coding remains limited due to the lack of meaningful step decompositions in code and the noise of Monte-Carlo-generated partial labels. We propose DreamPRM-Code, a coding-focused PRM that treats functions as reasoning steps using a Chain-of-Function prompting strategy to induce modular code generation, enabling PRM training and application analogous to mathematical reasoning tasks. To address label noise, DreamPRM-Code introduces a meta-learning-based correction mechanism that leverages clean final-solution unit-test labels and performs bi-level optimization to refine intermediate labels. Applying on test-time scaling, DreamPRM-Code achieved state-of-the-art performance on LiveCodeBench with 80.9 pass@1 rate, surpassing OpenAI o4-mini.
Authors: Huaying Zhang, Atsushi Hashimoto, Tosho Hirasawa
Abstract: Skilled human interviewers can extract valuable information from experts. This raises a fundamental question: what makes some questions more effective than others? To address this, a quantitative evaluation of question-generation models is essential. Video question generation (VQG) is a topic for video question answering (VideoQA), where questions are generated for given answers. Their evaluation typically focuses on the ability to answer questions, rather than the quality of generated questions. In contrast, we focus on the question quality in eliciting unseen knowledge from human experts. For a continuous improvement of VQG models, we propose a protocol that evaluates the ability by simulating question-answering communication with experts using a question-to-answer retrieval. We obtain the retriever by constructing a novel dataset, EgoExoAsk, which comprises 27,666 QA pairs generated from Ego-Exo4D's expert commentary annotation. The EgoExoAsk training set is used to obtain the retriever, and the benchmark is constructed on the validation set with Ego-Exo4D video segments. Experimental results demonstrate our metric reasonably aligns with question generation settings: models accessing richer context are evaluated better, supporting that our protocol works as intended. The EgoExoAsk dataset is available in https://github.com/omron-sinicx/VQG4ExpertKnowledge .
Authors: Damian Hodel, Jevin D. West
Abstract: The growing use of artificial intelligence (AI) raises concerns of knowledge collapse, i.e., a reduction to the most dominant and central set of ideas. Prior work has demonstrated single-model collapse, defined as performance decay in an AI model trained on its own output. Inspired by ecology, we ask whether AI ecosystem diversity, that is, diversity among models, can mitigate such a collapse. We build on the single-model approach but focus on ecosystems of models trained on their collective output. To study the effect of diversity on model performance, we segment the training data across language models and evaluate the resulting ecosystems over ten, self-training iterations. We find that increased epistemic diversity mitigates collapse, but, interestingly, only up to an optimal level. Our results suggest that an ecosystem containing only a few diverse models fails to express the rich mixture of the full, true distribution, resulting in rapid performance decay. Yet distributing the data across too many models reduces each model's approximation capacity on the true distribution, leading to poor performance already in the first iteration step. In the context of AI monoculture, our results suggest the need to monitor diversity across AI systems and to develop policies that incentivize more domain- and community-specific models.
Authors: Chenxiao Gao, Haotian Sun, Na Li, Dale Schuurmans, Bo Dai
Abstract: In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies, value functions, and dynamics models. Although powerful approximations such as neural networks offer great expressiveness, they often present theoretical ambiguities, suffer from optimization instability and exploration difficulty, and incur substantial computational costs in practice. In this paper, we introduce the perspective of spectral representations as a solution to address these difficulties in RL. Stemming from the spectral decomposition of the transition operator, this framework yields an effective abstraction of the system dynamics for subsequent policy optimization while also providing a clear theoretical characterization. We reveal how to construct spectral representations for transition operators that possess latent variable structures or energy-based structures, which implies different learning methods to extract spectral representations from data. Notably, each of these learning methods realizes an effective RL algorithm under this framework. We also provably extend this spectral view to partially observable MDPs. Finally, we validate these algorithms on over 20 challenging tasks from the DeepMind Control Suite, where they achieve performances comparable or superior to current state-of-the-art model-free and model-based baselines.
Authors: Yunheng Wang, Yixiao Feng, Yuetong Fang, Shuning Zhang, Tan Jing, Jian Li, Xiangrui Jiang, Renjing Xu
Abstract: 3D Scene Graphs (3DSGs) constitute a powerful representation of the physical world, distinguished by their abilities to explicitly model the complex spatial, semantic, and functional relationships between entities, rendering a foundational understanding that enables agents to interact intelligently with their environment and execute versatile behaviors. Embodied navigation, as a crucial component of such capabilities, leverages the compact and expressive nature of 3DSGs to enable long-horizon reasoning and planning in complex, large-scale environments. However, prior works rely on a static-world assumption, defining traversable space solely based on static spatial layouts and thereby treating interactable obstacles as non-traversable. This fundamental limitation severely undermines their effectiveness in real-world scenarios, leading to limited reachability, low efficiency, and inferior extensibility. To address these issues, we propose HERO, a novel framework for constructing Hierarchical Traversable 3DSGs, that redefines traversability by modeling operable obstacles as pathways, capturing their physical interactivity, functional semantics, and the scene's relational hierarchy. The results show that, relative to its baseline, HERO reduces PL by 35.1% in partially obstructed environments and increases SR by 79.4% in fully obstructed ones, demonstrating substantially higher efficiency and reachability.
Authors: Hongbo Wang, MaungMaung AprilPyone, Isao Echizen
Abstract: Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal generation but inherit toxic, biased, and NSFW signals from weakly curated pretraining corpora, causing safety risks, especially under adversarial triggers that late, opaque training-free detoxification methods struggle to handle. We propose SGM, a white-box neuron-level multimodal intervention that acts like safety glasses for toxic neurons: it selectively recalibrates a small set of toxic expert neurons via expertise-weighted soft suppression, neutralizing harmful cross-modal activations without any parameter updates. We establish MM-TOXIC-QA, a multimodal toxicity evaluation framework, and compare SGM with existing detoxification techniques. Experiments on open-source MLLMs show that SGM mitigates toxicity in standard and adversarial conditions, cutting harmful rates from 48.2\% to 2.5\% while preserving fluency and multimodal reasoning. SGM is extensible, and its combined defenses, denoted as SGM*, integrate with existing detoxification methods for stronger safety performance, providing an interpretable, low-cost solution for toxicity-controlled multimodal generation.
Authors: Fanzhe Fu
Abstract: The transition of Large Language Models (LLMs) from stochastic chat interfaces to reliable software components necessitates a fundamental re-engineering of interaction paradigms. Current methodologies, predominantly heuristic-based "prompt engineering," fail to provide the deterministic guarantees required for mission-critical applications. We introduce the Meta-Prompting Protocol, a rigorous theoretical framework that formalizes the orchestration of LLMs as a programmable, self-optimizing system. Central to this protocol is the Adversarial Trinity, a tripartite topology comprising a Generator (P), an Auditor (A), and an Optimizer (O). By treating natural language instructions as differentiable variables within a semantic computation graph and utilizing textual critiques as gradients, this architecture mitigates hallucination and prevents model collapse. We demonstrate the theoretical viability of this approach using declarative programming paradigms (DSPy) and automatic textual differentiation (TextGrad), establishing a foundation for "Observable Software Engineering" in the era of probabilistic computing.
Authors: Pandega Abyan Zumarsyah, Igi Ardiyanto, Hanung Adi Nugroho
Abstract: This study develops meta-learners for few-shot weakly-supervised segmentation (FWS) to address the challenge of optic disc (OD) and optic cup (OC) segmentation for glaucoma diagnosis with limited labeled fundus images. We significantly improve existing meta-learners by introducing Omni meta-training which balances data usage and diversifies the number of shots. We also develop their efficient versions that reduce computational costs. In addition, we develop sparsification techniques that generate more customizable and representative scribbles and other sparse labels. After evaluating multiple datasets, we find that Omni and efficient versions outperform the original versions, with the best meta-learner being Efficient Omni ProtoSeg (EO-ProtoSeg). It achieves intersection over union (IoU) scores of 88.15% for OD and 71.17% for OC on the REFUGE dataset using just one sparsely labeled image, outperforming few-shot and semi-supervised methods which require more labeled images. Its best performance reaches 86.80% for OD and 71.78%for OC on DRISHTIGS, 88.21% for OD and 73.70% for OC on REFUGE, 80.39% for OD and 52.65% for OC on REFUGE. EO-ProtoSeg is comparable to unsupervised domain adaptation methods yet much lighter with less than two million parameters and does not require any retraining.
Authors: Chenxiao Zhang, Runshi Zhang, Junchen Wang
Abstract: Medical ultrasound videos are widely used for medical inspections, disease diagnosis and surgical planning. High-fidelity lesion area and target organ segmentation constitutes a key component of the computer-assisted surgery workflow. The low contrast levels and noisy backgrounds of ultrasound videos cause missegmentation of organ boundary, which may lead to small object losses and increase boundary segmentation errors. Object tracking in long videos also remains a significant research challenge. To overcome these challenges, we propose a memory bank-based wavelet filtering and fusion network, which adopts an encoder-decoder structure to effectively extract fine-grained detailed spatial features and integrate high-frequency (HF) information. Specifically, memory-based wavelet convolution is presented to simultaneously capture category, detailed information and utilize adjacent information in the encoder. Cascaded wavelet compression is used to fuse multiscale frequency-domain features and expand the receptive field within each convolutional layer. A long short-term memory bank using cross-attention and memory compression mechanisms is designed to track objects in long video. To fully utilize the boundary-sensitive HF details of feature maps, an HF-aware feature fusion module is designed via adaptive wavelet filters in the decoder. In extensive benchmark tests conducted on four ultrasound video datasets (two thyroid nodule, the thyroid gland, the heart datasets) compared with the state-of-the-art methods, our method demonstrates marked improvements in segmentation metrics. In particular, our method can more accurately segment small thyroid nodules, demonstrating its effectiveness for cases involving small ultrasound objects in long video. The code is available at https://github.com/XiAooZ/MWNet.
Authors: Zijiang Yan, Yixiang Huang, Jianhua Pei, Hina Tabassum, Luca Chiaraviglio
Abstract: The rapid growth in wireless infrastructure has increased the need to accurately estimate and forecast electromagnetic field (EMF) levels to ensure ongoing compliance, assess potential health impacts, and support efficient network planning. While existing studies rely on univariate forecasting of wideband aggregate EMF data, frequency-selective multivariate forecasting is needed to capture the inter-operator and inter-frequency variations essential for proactive network planning. To this end, this paper introduces EMFusion, a conditional multivariate diffusion-based probabilistic forecasting framework that integrates diverse contextual factors (e.g., time of day, season, and holidays) while providing explicit uncertainty estimates. The proposed architecture features a residual U-Net backbone enhanced by a cross-attention mechanism that dynamically integrates external conditions to guide the generation process. Furthermore, EMFusion integrates an imputation-based sampling strategy that treats forecasting as a structural inpainting task, ensuring temporal coherence even with irregular measurements. Unlike standard point forecasters, EMFusion generates calibrated probabilistic prediction intervals directly from the learned conditional distribution, providing explicit uncertainty quantification essential for trustworthy decision-making. Numerical experiments conducted on frequency-selective EMF datasets demonstrate that EMFusion with the contextual information of working hours outperforms the baseline models with or without conditions. The EMFusion outperforms the best baseline by 23.85% in continuous ranked probability score (CRPS), 13.93% in normalized root mean square error, and reduces prediction CRPS error by 22.47%.
Authors: Debu Sinha
Abstract: Retrieval-Augmented Generation (RAG) systems remain susceptible to hallucinations despite grounding in retrieved evidence. Current detection methods rely on semantic similarity and natural language inference (NLI), but their fundamental limitations have not been rigorously characterized. We apply conformal prediction to hallucination detection, providing finite-sample coverage guarantees that enable precise quantification of detection capabilities. Using calibration sets of approximately 600 examples, we achieve 94% coverage with 0% false positive rate on synthetic hallucinations (Natural Questions). However, on three real hallucination benchmarks spanning multiple LLMs (GPT-4, ChatGPT, GPT-3, Llama-2, Mistral), embedding-based methods - including state-of-the-art OpenAI text-embedding-3-large and cross-encoder models - exhibit unacceptable false positive rates: 100% on HaluEval, 88% on RAGTruth, and 50% on WikiBio. Crucially, GPT-4 as an LLM judge achieves only 7% FPR (95% CI: [3.4%, 13.7%]) on the same data, proving the task is solvable through reasoning. We term this the "semantic illusion": semantically plausible hallucinations preserve similarity to source documents while introducing factual errors invisible to embeddings. This limitation persists across embedding architectures, LLM generators, and task types, suggesting embedding-based detection is insufficient for production RAG deployment.
Authors: Ziyu Shang, Haoran Liu, Rongchao Zhang, Zhiqian Wei, Tongtong Feng
Abstract: Generating consistent human images with controllable pose and appearance is essential for applications in virtual try on, image editing, and digital human creation. Current methods often suffer from occlusions, garment style drift, and pose misalignment. We propose Pose-guided Multi-view Multimodal Diffusion (PMMD), a diffusion framework that synthesizes photorealistic person images conditioned on multi-view references, pose maps, and text prompts. A multimodal encoder jointly models visual views, pose features, and semantic descriptions, which reduces cross modal discrepancy and improves identity fidelity. We further design a ResCVA module to enhance local detail while preserving global structure, and a cross modal fusion module that integrates image semantics with text throughout the denoising pipeline. Experiments on the DeepFashion MultiModal dataset show that PMMD outperforms representative baselines in consistency, detail preservation, and controllability. Project page and code are available at https://github.com/ZANMANGLOOPYE/PMMD.
Authors: Richard Helder Moulton, Austin O'Brien, John D. Hastings
Abstract: Although large language models (LLMs) are increasingly used in security-critical workflows, practitioners lack quantitative guidance on which safeguards are worth deploying. This paper introduces a decision-oriented framework and reproducible methodology that together quantify residual risk, convert adversarial probe outcomes into financial risk estimates and return-on-control (RoC) metrics, and enable monetary comparison of layered defenses for LLM-based systems. A retrieval-augmented generation (RAG) service is instantiated using the DeepSeek-R1 model over a corpus containing synthetic personally identifiable information (PII), and subjected to automated attacks with Garak across five vulnerability classes: PII leakage, latent context injection, prompt injection, adversarial attack generation, and divergence. For each (vulnerability, control) pair, attack success probabilities are estimated via Laplace's Rule of Succession and combined with loss triangle distributions, calibrated from public breach-cost data, in 10,000-run Monte Carlo simulations to produce loss exceedance curves and expected losses. Three widely used mitigations, attribute-based access control (ABAC); named entity recognition (NER) redaction using Microsoft Presidio; and NeMo Guardrails, are then compared to a baseline RAG configuration. The baseline system exhibits very high attack success rates (>= 0.98 for PII, latent injection, and prompt injection), yielding a total simulated expected loss of $313k per attack scenario. ABAC collapses success probabilities for PII and prompt-related attacks to near zero and reduces the total expected loss by ~94%, achieving an RoC of 9.83. NER redaction likewise eliminates PII leakage and attains an RoC of 5.97, while NeMo Guardrails provides only marginal benefit (RoC of 0.05).
Authors: Sunwoo Kim, Soo Yong Lee, Kyungho Kim, Hyunjin Hwang, Jaemin Yoo, Kijung Shin
Abstract: Unsupervised node representation learning aims to obtain meaningful node embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information from neighboring nodes, is commonly employed to encode node features and graph topology. However, excessive reliance on graph convolution can be suboptimal-especially in non-homophilic graphs-since it may yield unduly similar embeddings for nodes that differ in their features or topological properties. As a result, adjusting the degree of graph convolution usage has been actively explored in supervised learning settings, whereas such approaches remain underexplored in unsupervised scenarios. To tackle this, we propose FUEL, which adaptively learns the adequate degree of graph convolution usage by aiming to enhance intra-class similarity and inter-class separability in the embedding space. Since classes are unknown, FUEL leverages node features to identify node clusters and treats these clusters as proxies for classes. Through extensive experiments using 15 baseline methods and 14 benchmark datasets, we demonstrate the effectiveness of FUEL in downstream tasks, achieving state-of-the-art performance across graphs with diverse levels of homophily.
Authors: Ali Ghodsi
Abstract: Sequence modeling has produced diverse architectures -- from classical recurrent neural networks to modern Transformers and state space models (SSMs) -- yet a unified theoretical understanding of expressivity and trainability trade-offs remains limited. We introduce a unified framework that represents a broad class of sequence maps via an input-dependent effective interaction operator $W_{ij}(X)$, making explicit two recurring construction patterns: (i) the Unified Factorized Framework (Explicit) (attention-style mixing), in which $W_{ij}(X)$ varies through scalar coefficients applied to shared value maps, and (ii) Structured Dynamics (Implicit) (state-space recurrences), in which $W_{ij}$ is induced by a latent dynamical system. Using this framework, we derive three theoretical results. First, we establish the Interaction Rank Gap: models in the Unified Factorized Framework, such as single-head attention, are constrained to a low-dimensional operator span and cannot represent certain structured dynamical maps. Second, we prove an Equivalence (Head-Count) Theorem showing that, within our multi-head factorized class, representing a linear SSM whose lag operators span a $k$-dimensional subspace on length-$n$ sequences requires and is achievable with $H=k$ heads. Third, we prove a Gradient Highway Result, showing that attention layers admit inputs with distance-independent gradient paths, whereas stable linear dynamics exhibit distance-dependent gradient attenuation. Together, these results formalize a fundamental trade-off between algebraic expressivity (interaction/operator span) and long-range gradient propagation, providing theoretical grounding for modern sequence architecture design.
Authors: Runze Li, Hanchen Wang, Wenjie Zhang, Binghao Li, Yu Zhang, Xuemin Lin, Ying Zhang
Abstract: Multivariate time series imputation is fundamental in applications such as healthcare, traffic forecasting, and biological modeling, where sensor failures and irregular sampling lead to pervasive missing values. However, existing Transformer- and diffusion-based models lack explicit inductive biases and frequency awareness, limiting their generalization under structured missing patterns and distribution shifts. We propose FADTI, a diffusion-based framework that injects frequency-informed feature modulation via a learnable Fourier Bias Projection (FBP) module and combines it with temporal modeling through self-attention and gated convolution. FBP supports multiple spectral bases, enabling adaptive encoding of both stationary and non-stationary patterns. This design injects frequency-domain inductive bias into the generative imputation process. Experiments on multiple benchmarks, including a newly introduced biological time series dataset, show that FADTI consistently outperforms state-of-the-art methods, particularly under high missing rates. Code is available at https://anonymous.4open.science/r/TimeSeriesImputation-52BF
URLs: https://anonymous.4open.science/r/TimeSeriesImputation-52BF
Authors: Pilyoung Kim, Yun Xie, Sujin Yang
Abstract: General-purpose conversational AI chatbots and AI companions increasingly provide young adolescents with emotionally supportive conversations, raising questions about how conversational style shapes anthropomorphism and emotional reliance. In a preregistered online experiment with 284 adolescent-parent dyads, youth aged 11-15 and their parents read two matched transcripts in which a chatbot responded to an everyday social problem using either a relational style (first-person, affiliative, commitment language) or a transparent style (explicit nonhumanness, informational tone). Adolescents more often preferred the relational than the transparent style, whereas parents were more likely to prefer transparent style than adolescents. Adolescents rated the relational chatbot as more human-like, likable, trustworthy and emotionally close, while perceiving both styles as similarly helpful. Adolescents who preferred relational style had lower family and peer relationship quality and higher stress and anxiety than those preferring transparent style or both chatbots. These findings identify conversational style as a key design lever for youth AI safety, showing that relational framing heightens anthropomorphism, trust and emotional closeness and can be especially appealing to socially and emotionally vulnerable adolescents, who may be at increased risk for emotional reliance on conversational AI.
Authors: Jiayang Wan, Ke He, Yafei Wang, Fan Liu, Wenjin Wang, Shi Jin
Abstract: Due to the significant variations in unmanned aerial vehicle (UAV) altitude and horizontal mobility, it becomes difficult for any single network to ensure continuous and reliable threedimensional coverage. Towards that end, the space-air-ground integrated network (SAGIN) has emerged as an essential architecture for enabling ubiquitous UAV connectivity. To address the pronounced disparities in coverage and signal characteristics across heterogeneous networks, this paper formulates UAV mobility management in SAGIN as a constrained multi-objective joint optimization problem. The formulation couples discrete link selection with continuous trajectory optimization. Building on this, we propose a two-level multi-agent hierarchical deep reinforcement learning (HDRL) framework that decomposes the problem into two alternately solvable subproblems. To map complex link selection decisions into a compact discrete action space, we conceive a double deep Q-network (DDQN) algorithm in the top-level, which achieves stable and high-quality policy learning through double Q-value estimation. To handle the continuous trajectory action space while satisfying quality of service (QoS) constraints, we integrate the maximum-entropy mechanism of the soft actor-critic (SAC) and employ a Lagrangian-based constrained SAC (CSAC) algorithm in the lower-level that dynamically adjusts the Lagrange multipliers to balance constraint satisfaction and policy optimization. Moreover, the proposed algorithm can be extended to multi-UAV scenarios under the centralized training and decentralized execution (CTDE) paradigm, which enables more generalizable policies. Simulation results demonstrate that the proposed scheme substantially outperforms existing benchmarks in throughput, link switching frequency and QoS satisfaction.
Authors: Yuqing Xie, Jiayu Chen, Wenhao Tang, Ya Zhang, Chao Yu, Yu Wang
Abstract: Designing effective reward functions remains a central challenge in reinforcement learning, especially in multi-objective environments. In this work, we propose Multi-Objective Reward Shaping with Exploration (MORSE), a general framework that automatically combines multiple human-designed heuristic rewards into a unified reward function. MORSE formulates the shaping process as a bi-level optimization problem: the inner loop trains a policy to maximize the current shaped reward, while the outer loop updates the reward function to optimize task performance. To encourage exploration in the reward space and avoid suboptimal local minima, MORSE introduces stochasticity into the shaping process, injecting noise guided by task performance and the prediction error of a fixed, randomly initialized neural network. Experimental results in MuJoCo and Isaac Sim environments show that MORSE effectively balances multiple objectives across various robotic tasks, achieving task performance comparable to those obtained with manually tuned reward functions.
Authors: Yi Zhou, Haohao Qu, Yunqing Liu, Shanru Lin, Le Song, Wenqi Fan
Abstract: Proteins inherently possess a consistent sequence-structure duality. The abundance of protein sequence data, which can be readily represented as discrete tokens, has driven fruitful developments in protein language models (pLMs). A key remaining challenge, however, is how to effectively integrate continuous structural knowledge into pLMs. Current methods often discretize protein structures to accommodate the language modeling framework, which inevitably results in the loss of fine-grained information and limits the performance potential of multimodal pLMs. In this paper, we argue that such concerns can be circumvented: a sequence-based pLM can be extended to incorporate the structure modality through continuous tokens, i.e., high-fidelity protein structure latents that avoid vector quantization. Specifically, we propose a hybrid diffusion protein language model, HD-Prot, which embeds a continuous-valued diffusion head atop a discrete pLM, enabling seamless operation with both discrete and continuous tokens for joint sequence-structure modeling. It captures inter-token dependencies across modalities through a unified absorbing diffusion process, and estimates per-token distributions via categorical prediction for sequences and continuous diffusion for structures. Extensive empirical results show that HD-Prot achieves competitive performance in unconditional sequence-structure co-generation, motif-scaffolding, protein structure prediction, and inverse folding tasks, performing on par with state-of-the-art multimodal pLMs despite being developed under limited computational resources. It highlights the viability of simultaneously estimating categorical and continuous distributions within a unified language model architecture, offering a promising alternative direction for multimodal pLMs.
Authors: Aaron Mueller, Andrew Lee, Shruti Joshi, Ekdeep Singh Lubana, Dhanya Sridhar, Patrik Reizinger
Abstract: A central goal of interpretability is to recover representations of causally relevant concepts from the activations of neural networks. The quality of these concept representations is typically evaluated in isolation, and under implicit independence assumptions that may not hold in practice. Thus, it is unclear whether common featurization methods - including sparse autoencoders (SAEs) and sparse probes - recover disentangled representations of these concepts. This study proposes a multi-concept evaluation setting where we control the correlations between textual concepts, such as sentiment, domain, and tense, and analyze performance under increasing correlations between them. We first evaluate the extent to which featurizers can learn disentangled representations of each concept under increasing correlational strengths. We observe a one-to-many relationship from concepts to features: features correspond to no more than one concept, but concepts are distributed across many features. Then, we perform steering experiments, measuring whether each concept is independently manipulable. Even when trained on uniform distributions of concepts, SAE features generally affect many concepts when steered, indicating that they are neither selective nor independent; nonetheless, features affect disjoint subspaces. These results suggest that correlational metrics for measuring disentanglement are generally not sufficient for establishing independence when steering, and that affecting disjoint subspaces is not sufficient for concept selectivity. These results underscore the importance of compositional evaluations in interpretability research.
Authors: Xian-Rong Zhang, Yue-Jiao Gong, Zeyuan Ma, Jun Zhang
Abstract: Data-driven evolutionary algorithms has shown surprising results in addressing expensive optimization problems through robust surrogate modeling. Though promising, existing surrogate modeling schemes may encounter limitations in complex optimization problems with many sub-objectives, which rely on repeated and tedious approximation. To address such technical gap, we propose Q-MetaSur as a plug-and-play surrogate modeling scheme capable of providing unified and generalized surrogate learning. Specifically, we consider multi-task-multi-objective optimization~(MTMOO) in offline setting. Several key designs are proposed: 1) we transform objective approximation into sequence-to-sequence modeling where MTMOO problem can be represented by tenxual tokenization. To operate under such auto-regressive modeling, we introduce a Large Language Model-based surrogate model that first encodes a MTMOO instance and then decodes objective values of unseen decision variables. To ensure stability in training the proposed model, we propose a two-stage offline training strategy that operates as a synergy of supervised tuning and RL fine-tuning, which first exploits offline dataset to fit existing knowledge and then leverages RL to enhance model's generalization performance. Extensive empirical results on the CEC2019 benchmark demonstrate that Q-MetaSur not only outperforms representative surrogate baselines in objective approximation accuracy, but also helps underlying evolutionary algorithms achieve both desired optimization convergence and improved pareto optimality.
Authors: Xuanjun Zong, Zhiqi Shen, Lei Wang, Yunshi Lan, Chao Yang
Abstract: Large language models (LLMs) are evolving into agentic systems that reason, plan, and operate external tools. The Model Context Protocol (MCP) is a key enabler of this transition, offering a standardized interface for connecting LLMs with heterogeneous tools and services. Yet MCP's openness and multi-server workflows introduce new safety risks that existing benchmarks fail to capture, as they focus on isolated attacks or lack real-world coverage. We present MCP-SafetyBench, a comprehensive benchmark built on real MCP servers that supports realistic multi-turn evaluation across five domains: browser automation, financial analysis, location navigation, repository management, and web search. It incorporates a unified taxonomy of 20 MCP attack types spanning server, host, and user sides, and includes tasks requiring multi-step reasoning and cross-server coordination under uncertainty. Using MCP-SafetyBench, we systematically evaluate leading open- and closed-source LLMs, revealing large disparities in safety performance and escalating vulnerabilities as task horizons and server interactions grow. Our results highlight the urgent need for stronger defenses and establish MCP-SafetyBench as a foundation for diagnosing and mitigating safety risks in real-world MCP deployments.
Authors: Zicong Cheng, Guo-Wei Yang, Jia Li, Zhijie Deng, Meng-Hao Guo, Shi-Min Hu
Abstract: Efficiency, as a critical practical challenge for LLM-driven agentic and reasoning systems, is increasingly constrained by the inherent latency of autoregressive (AR) decoding. Speculative decoding mitigates this cost through a draft-verify scheme, yet existing approaches rely on AR draft models (a.k.a., drafters), which introduce two fundamental issues: (1) step-wise uncertainty accumulation leads to a progressive collapse of trust between the target model and the drafter, and (2) inherently sequential decoding of AR drafters. Together, these factors cause limited speedups. In this paper, we show that a diffusion large language model (dLLM) drafters can naturally overcome these issues through its fundamentally different probabilistic modeling and efficient parallel decoding strategy. Building on this insight, we introduce DEER, an efficient speculative decoding framework that drafts with diffusion and verifies with AR models. To enable high-quality drafting, DEER employs a two-stage training pipeline to align the dLLM-based drafters with the target AR model, and further adopts single-step decoding to generate long draft segments. Experiments show DEER reaches draft acceptance lengths of up to 32 tokens, far surpassing the 10 tokens achieved by EAGLE-3. Moreover, on HumanEval with Qwen3-30B-A3B, DEER attains a 5.54x speedup, while EAGLE-3 achieves only 2.41x. Code, model, demo, etc, will be available at https://czc726.github.io/DEER/
Authors: Atte Ojanen, Johannes Anttila, Thilo H. K. Thelitz, Anna Bjork
Abstract: The rapid advancements in artificial intelligence (AI) present unique challenges for policymakers that seek to govern the technology. In this context, the Delphi method has become an established way to identify consensus and disagreement on emerging technological issues among experts in the field of futures studies and foresight. The aim of this article is twofold: first, it examines key tensions experts see in the development of AI governance in Europe, and second, it reflects on the Delphi method's capacity to inform anticipatory governance of emerging technologies like AI based on these insights. The analysis is based on the results of a two-round Policy Delphi study on the future of AI governance with European policymakers, researchers and NGOs, conducted in mid-2024. The Policy Delphi proved useful in revealing diverse perspectives on European AI governance, drawing out a consensus that future-proof AI regulation will likely depend more on practical implementation and enforcement of legislation than on its technical specifics or scope. Furthermore, the study identified a desirability-probability gap in AI governance: desirable policy directions, like greater citizen participation, were perceived as less probable and feasible. This highlights a tension between desirable regulatory oversight and the practical difficulty for regulation to keep up with technological change.
Authors: Chao Zhang, Minghan Li, Tianrui Lv, Guodong Zhou
Abstract: Large language models (LLMs) often generate hallucinations in knowledge-intensive QA due to parametric knowledge limitations. While existing methods like KG-CoT improve reliability by integrating knowledge graph (KG) paths, they suffer from rigid hop-count selection (solely question-driven) and underutilization of reasoning paths (lack of guidance). To address this, we propose RFKG-CoT: First, it replaces the rigid hop-count selector with a relation-driven adaptive hop-count selector that dynamically adjusts reasoning steps by activating KG relations (e.g., 1-hop for direct "brother" relations, 2-hop for indirect "father-son" chains), formalized via a relation mask. Second, it introduces a few-shot in-context learning path guidance mechanism with CoT (think) that constructs examples in a "question-paths-answer" format to enhance LLMs' ability to understand reasoning paths. Experiments on four KGQA benchmarks show RFKG-CoT improves accuracy by up to 14.7 pp (Llama2-7B on WebQSP) over KG-CoT. Ablations confirm the hop-count selector and the path prompt are complementary, jointly transforming KG evidence into more faithful answers.
Authors: Yash Bhaskar, Parameswari Krishnamurthy
Abstract: This paper presents the systems submitted by the Yes-MT team for the Low-Resource Indic Language Translation Shared Task at WMT 2024 (Pakray et al., 2024), focusing on translating between English and the Assamese, Mizo, Khasi, and Manipuri languages. The experiments explored various approaches, including fine-tuning pre-trained models like mT5 (Xue et al., 2020) and IndicBart (Dabre et al., 2021) in both multilingual and monolingual settings, LoRA (Hu et al., 2021) fine-tuning IndicTrans2 (Gala et al., 2023), zero-shot and few-shot prompting (Brown, 2020) with large language models (LLMs) like Llama 3 (Dubey et al., 2024) and Mixtral 8x7b (Jiang et al., 2024), LoRA supervised fine-tuning of Llama 3 (Mecklenburg et al., 2024), and training Transformer models (Vaswani, 2017) from scratch. The results were evaluated on the WMT23 Low-Resource Indic Language Translation Shared Task test data using SacreBLEU (Post, 2018) and CHRF (Popovic, 2015), highlighting the challenges of low-resource translation and the potential of LLMs for these tasks, particularly with fine-tuning.
Authors: Yupeng Zhang, Adam G. Dunn, Usman Naseem, Jinman Kim
Abstract: Medical artificial intelligence (AI) systems, particularly multimodal vision-language models (VLM), often exhibit intersectional biases where models are systematically less confident in diagnosing marginalised patient subgroups. Such bias can lead to higher rates of inaccurate and missed diagnoses due to demographically skewed data and divergent distributions of diagnostic certainty. Current fairness interventions frequently fail to address these gaps or compromise overall diagnostic performance to achieve statistical parity among the subgroups. In this study, we developed Cross-Modal Alignment Consistency (CMAC-MMD), a training framework that standardises diagnostic certainty across intersectional patient subgroups. Unlike traditional debiasing methods, this approach equalises the model's decision confidence without requiring sensitive demographic data during clinical inference. We evaluated this approach using 10,015 skin lesion images (HAM10000) with external validation on 12,000 images (BCN20000), and 10,000 fundus images for glaucoma detection (Harvard-FairVLMed), stratifying performance by intersectional age, gender, and race attributes. In the dermatology cohort, the proposed method reduced the overall intersectional missed diagnosis gap (difference in True Positive Rate, $\Delta$TPR) from 0.50 to 0.26 while improving the overall Area Under the Curve (AUC) from 0.94 to 0.97 compared to standard training. Similarly, for glaucoma screening, the method reduced $\Delta$TPR from 0.41 to 0.31, achieving a better AUC of 0.72 (vs. 0.71 baseline). This establishes a scalable framework for developing high-stakes clinical decision support systems that are both accurate and can perform equitably across diverse patient subgroups, ensuring reliable performance without increasing privacy risks.
Authors: Youssef Ghallab, Omar Iraqy, Mohamed Kandil, Mohamed Ashraf, Saadeldine Eletter, Morougue Ghazal, Ayman Khalafallah, Nagwa El-Makky
Abstract: Physiological signals such as electrocardiograms (ECG) and electroencephalograms (EEG) provide complementary insights into human health and cognition, yet multi-modal integration is challenging due to limited multi-modal labeled data, and modality-specific differences . In this work, we adapt the CBraMod encoder for large-scale self-supervised ECG pretraining, introducing a dual-masking strategy to capture intra- and inter-lead dependencies. To overcome the above challenges, we utilize a pre-trained CBraMod encoder for EEG and pre-train a symmetric ECG encoder, equipping each modality with a rich foundational representation. These representations are then fused via simple embedding concatenation, allowing the classification head to learn cross-modal interactions, together enabling effective downstream learning despite limited multi-modal supervision. Evaluated on emotion recognition, our approach achieves near state-of-the-art performance, demonstrating that carefully designed physiological encoders, even with straightforward fusion, substantially improve downstream performance. These results highlight the potential of foundation-model approaches to harness the holistic nature of physiological signals, enabling scalable, label-efficient, and generalizable solutions for healthcare and affective computing.
Authors: Yuze Wu, Mo Zhu, Xingxing Li, Yuheng Du, Yuxin Fan, Wenjun Li, Xin Zhou, Fei Gao
Abstract: This paper proposes VLA-AN, an efficient and onboard Vision-Language-Action (VLA) framework dedicated to autonomous drone navigation in complex environments. VLA-AN addresses four major limitations of existing large aerial navigation models: the data domain gap, insufficient temporal navigation with reasoning, safety issues with generative action policies, and onboard deployment constraints. First, we construct a high-fidelity dataset utilizing 3D Gaussian Splatting (3D-GS) to effectively bridge the domain gap. Second, we introduce a progressive three-stage training framework that sequentially reinforces scene comprehension, core flight skills, and complex navigation capabilities. Third, we design a lightweight, real-time action module coupled with geometric safety correction. This module ensures fast, collision-free, and stable command generation, mitigating the safety risks inherent in stochastic generative policies. Finally, through deep optimization of the onboard deployment pipeline, VLA-AN achieves a robust real-time 8.3x improvement in inference throughput on resource-constrained UAVs. Extensive experiments demonstrate that VLA-AN significantly improves spatial grounding, scene reasoning, and long-horizon navigation, achieving a maximum single-task success rate of 98.1%, and providing an efficient, practical solution for realizing full-chain closed-loop autonomy in lightweight aerial robots.
Authors: Yiliu Sun, Zicheng Zhao, Yang Wei, Yanfang Zhang, Chen Gong
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capability of Large Language Models (LLMs). Current RLVR approaches typically conduct training across all generated tokens, but neglect to explore which tokens (e.g., prefix tokens) actually contribute to reasoning. This uniform training strategy spends substantial effort on optimizing low-return tokens, which in turn impedes the potential improvement from high-return tokens and reduces overall training effectiveness. To address this issue, we propose a novel RLVR approach called Progressive Prefix-token Policy Optimization (PPPO), which highlights the significance of the prefix segment of generated outputs. Specifically, inspired by the well-established human thinking theory of Path Dependence, where early-stage thoughts substantially constrain subsequent thinking trajectory, we identify an analogous phenomenon in LLM reasoning termed Beginning Lock-in Effect (BLE). PPPO leverages this finding by focusing its optimization objective on the prefix reasoning process of LLMs. This targeted optimization strategy can positively influence subsequent reasoning processes, and ultimately improve final results. To improve the learning effectiveness of LLMs on how to start reasoning with high quality, PPPO introduces two training strategies: (a) Progressive Prefix Retention, which shapes a progressive learning process by increasing the proportion of retained prefix tokens during training; (b) Continuation Accumulated Reward, which mitigates reward bias by sampling multiple continuations for one prefix token sequence, and accumulating their scores as the reward signal. Extensive experimental results on various reasoning tasks demonstrate that our proposed PPPO outperforms representative RLVR methods, with the accuracy improvements of 18.02% on only 26.17% training tokens.
Authors: Siva Sai, Ishika Goyal, Shubham Sharma, Sri Harshita Manuri, Vinay Chamola, Rajkumar Buyya
Abstract: The increasing number of cyber threats and rapidly evolving tactics, as well as the high volume of data in recent years, have caused classical machine learning, rules, and signature-based defence strategies to fail, rendering them unable to keep up. An alternative, Quantum Machine Learning (QML), has recently emerged, making use of computations based on quantum mechanics. It offers better encoding and processing of high-dimensional structures for certain problems. This survey provides a comprehensive overview of QML techniques relevant to the domain of security, such as Quantum Neural Networks (QNNs), Quantum Support Vector Machines (QSVMs), Variational Quantum Circuits (VQCs), and Quantum Generative Adversarial Networks (QGANs), and discusses the contributions of this paper in relation to existing research in the field and how it improves over them. It also maps these methods across supervised, unsupervised, and generative learning paradigms, and to core cybersecurity tasks, including intrusion and anomaly detection, malware and botnet classification, and encrypted-traffic analytics. It also discusses their application in the domain of cloud computing security, where QML can enhance secure and scalable operations. Many limitations of QML in the domain of cybersecurity have also been discussed, along with the directions for addressing them.
Authors: Basil Ell
Abstract: We introduce graph pattern-based association rules (GPARs) for directed labeled multigraphs such as RDF graphs. GPARs support both generative tasks, where a graph is extended, and evaluative tasks, where the plausibility of a graph is assessed. The framework goes beyond related formalisms such as graph functional dependencies, graph entity dependencies, relational association rules, graph association rules, multi-relation and path association rules, and Horn rules. Given a collection of graphs, we evaluate graph patterns under no-repeated-anything semantics, which allows the topology of a graph to be taken into account more effectively. We define a probability space and derive confidence, lift, leverage, and conviction in a probabilistic setting. We further analyze how these metrics relate to their classical itemset-based counterparts and identify conditions under which their characteristic properties are preserved.
Authors: Charan Prakash Rathore, Saumi Ray, Dhruv Kumar
Abstract: Extracting structured information from zeolite synthesis experimental procedures is critical for materials discovery, yet existing methods have not systematically evaluated Large Language Models (LLMs) for this domain-specific task. This work addresses a fundamental question: what is the efficacy of different prompting strategies when applying LLMs to scientific information extraction? We focus on four key subtasks: event type classification (identifying synthesis steps), trigger text identification (locating event mentions), argument role extraction (recognizing parameter types), and argument text extraction (extracting parameter values). We evaluate four prompting strategies - zero-shot, few-shot, event-specific, and reflection-based - across six state-of-the-art LLMs (Gemma-3-12b-it, GPT-5-mini, O4-mini, Claude-Haiku-3.5, DeepSeek reasoning and non-reasoning) using the ZSEE dataset of 1,530 annotated sentences. Results demonstrate strong performance on event type classification (80-90\% F1) but modest performance on fine-grained extraction tasks, particularly argument role and argument text extraction (50-65\% F1). GPT-5-mini exhibits extreme prompt sensitivity with 11-79\% F1 variation. Notably, advanced prompting strategies provide minimal improvements over zero-shot approaches, revealing fundamental architectural limitations. Error analysis identifies systematic hallucination, over-generalization, and inability to capture synthesis-specific nuances. Our findings demonstrate that while LLMs achieve high-level understanding, precise extraction of experimental parameters requires domain-adapted models, providing quantitative benchmarks for scientific information extraction.
Authors: Antony Jerald, Dattesh Shanbhag, Sudhanya Chatterjee
Abstract: Motion artifacts degrade MRI image quality and increase patient recalls. Existing automated quality assessment methods are largely limited to binary decisions and provide little interpretability. We introduce AutoMAC-MRI, an explainable framework for grading motion artifacts across heterogeneous MR contrasts and orientations. The approach uses supervised contrastive learning to learn a discriminative representation of motion severity. Within this feature space, we compute grade-specific affinity scores that quantify an image's proximity to each motion grade, thereby making grade assignments transparent and interpretable. We evaluate AutoMAC-MRI on more than 5000 expert-annotated brain MRI slices spanning multiple contrasts and views. Experiments assessing affinity scores against expert labels show that the scores align well with expert judgment, supporting their use as an interpretable measure of motion severity. By coupling accurate grade detection with per-grade affinity scoring, AutoMAC-MRI enables inline MRI quality control, with the potential to reduce unnecessary rescans and improve workflow efficiency.
Authors: Agnieszka Bienkowska, Jacek Malecki, Alexander Mathiesen-Ohman, Katarzyna Tworek
Abstract: Organizations increasingly operate in environments characterized by volatility, uncertainty, complexity, and ambiguity (VUCA), where early indicators of change often emerge as weak, fragmented signals. Although artificial intelligence (AI) is widely used to support managerial decision-making, most AI-based systems remain optimized for prediction and resolution, leading to premature interpretive closure under conditions of high ambiguity. This creates a gap in management science regarding how human-AI systems can responsibly manage ambiguity before it crystallizes into error or crisis. This study addresses this gap by presenting a proof of concept (PoC) of the LAIZA human-AI augmented symbiotic intelligence system and its patented process: Systems and Methods for Quantum-Inspired Rogue Variable Modeling (QRVM), Human-in-the-Loop Decoherence, and Collective Cognitive Inference. The mechanism operationalizes ambiguity as a non-collapsed cognitive state, detects persistent interpretive breakdowns (rogue variables), and activates structured human-in-the-loop clarification when autonomous inference becomes unreliable. Empirically, the article draws on a three-month case study conducted in 2025 within the AI development, involving prolonged ambiguity surrounding employee intentions and intellectual property boundaries. The findings show that preserving interpretive plurality enabled early scenario-based preparation, including proactive patent protection, allowing decisive and disruption-free action once ambiguity collapsed. The study contributes to management theory by reframing ambiguity as a first-class construct and demonstrates the practical value of human-AI symbiosis for organizational resilience in VUCA environments.
Authors: Parvesh Saini, Soumyadipta Maiti, Beena Rai
Abstract: Capabilities and the number of vision-based models are increasing rapidly. And these vision models are now able to do more tasks like object detection, image classification, instance segmentation etc. with great accuracy. But models which can take accurate quantitative measurements form an image, as a human can do by just looking at it, are rare. For a robot to work with complete autonomy in a Laboratory environment, it needs to have some basic skills like navigation, handling objects, preparing samples etc. to match human-like capabilities in an unstructured environment. Another important capability is to read measurements from instruments and apparatus. Here, we tried to mimic a human inspired approach to read measurements from a linear scale. As a test case we have picked reading level from a syringe and a measuring cylinder. For a randomly oriented syringe we carry out transformations to correct the orientation. To make the system efficient and robust, the area of interest is reduced to just the linear scale containing part of the image. After that, a series of features were extracted like the major makers, the corresponding digits, and the level indicator location, from which the final reading was calculated. Readings obtained using this system were also compared against human read values of the same instances and an accurate correspondence was observed.
Authors: Efe Bozkir, Enkelejda Kasneci
Abstract: The rapid development of generative artificial intelligence (AI) and large language models (LLMs), and the availability of services that make them accessible, have led the general public to begin incorporating them into everyday life. The extended reality (XR) community has also sought to integrate LLMs, particularly in the form of conversational agents, to enhance user experience and task efficiency. When interacting with such conversational agents, users may easily disclose sensitive information due to the naturalistic flow of the conversations, and combining such conversational data with fine-grained sensor data may lead to novel privacy issues. To address these issues, a user-centric understanding of technology acceptance and concerns is essential. Therefore, to this end, we conducted a large-scale crowdsourcing study with 1036 participants, examining user decision-making processes regarding LLM-powered conversational agents in XR, across factors of XR setting type, speech interaction type, and data processing location. We found that while users generally accept these technologies, they express concerns related to security, privacy, social implications, and trust. Our results suggest that familiarity plays a crucial role, as daily generative AI use is associated with greater acceptance. In contrast, previous ownership of XR devices is linked to less acceptance, possibly due to existing familiarity with the settings. We also found that men report higher acceptance with fewer concerns than women. Regarding data type sensitivity, location data elicited the most significant concern, while body temperature and virtual object states were considered least sensitive. Overall, our study highlights the importance of practitioners effectively communicating their measures to users, who may remain distrustful. We conclude with implications and recommendations for LLM-powered XR.
Authors: Hiroyoshi Nagahama, Katsufumi Inoue, Masayoshi Todorokihara, Michifumi Yoshioka
Abstract: Predictive maintenance of rotating machinery increasingly relies on vibration signals, yet most learning-based approaches either discard phase during spectral feature extraction or use raw time-waveforms without explicitly leveraging phase information. This paper introduces two phase-aware preprocessing strategies to address random phase variations in multi-axis vibration data: (1) three-axis independent phase adjustment that aligns each axis individually to zero phase (2) single-axis reference phase adjustment that preserves inter-axis relationships by applying uniform time shifts. Using a newly constructed rotor dataset acquired with a synchronized three-axis sensor, we evaluate six deep learning architectures under a two-stage learning framework. Results demonstrate architecture-independent improvements: the three-axis independent method achieves consistent gains (+2.7\% for Transformer), while the single-axis reference approach delivers superior performance with up to 96.2\% accuracy (+5.4\%) by preserving spatial phase relationships. These findings establish both phase alignment strategies as practical and scalable enhancements for predictive maintenance systems.
Authors: Joao Queiroz
Abstract: Recent evidence shows that the versification of prompts constitutes a highly effective adversarial mechanism against aligned LLMs. The study 'Adversarial poetry as a universal single-turn jailbreak mechanism in large language models' demonstrates that instructions routinely refused in prose become executable when rewritten as verse, producing up to 18 x more safety failures in benchmarks derived from MLCommons AILuminate. Manually written poems reach approximately 62% ASR, and automated versions 43%, with some models surpassing 90% success in single-turn interactions. The effect is structural: systems trained with RLHF, constitutional AI, and hybrid pipelines exhibit consistent degradation under minimal semiotic formal variation. Versification displaces the prompt into sparsely supervised latent regions, revealing guardrails that are excessively dependent on surface patterns. This dissociation between apparent robustness and real vulnerability exposes deep limitations in current alignment regimes. The absence of evaluations in Portuguese, a language with high morphosyntactic complexity, a rich metric-prosodic tradition, and over 250 million speakers, constitutes a critical gap. Experimental protocols must parameterise scansion, metre, and prosodic variation to test vulnerabilities specific to Lusophone patterns, which are currently ignored.
Authors: Mikel Williams-Lekuona, Georgina Cosma
Abstract: Vision transformers in vision-language models apply uniform computational effort across all images, expending 175.33 GFLOPs (ViT-L/14) whether analysing a straightforward product photograph or a complex street scene. We propose ICAR (Image Complexity-Aware Retrieval), which enables vision transformers to use less compute for simple images whilst processing complex images through their full network depth. The key challenge is maintaining cross-modal alignment: embeddings from different processing depths must remain compatible for text matching. ICAR solves this through dual-path training that produces compatible embeddings from both reduced-compute and full-compute processing. This maintains compatibility between image representations and text embeddings in the same semantic space, whether an image exits early or processes fully. Unlike existing two-stage approaches that require expensive reranking, ICAR enables direct image-text matching without additional overhead. To determine how much compute to use, we develop ConvNeXt-IC, which treats image complexity assessment as a classification task. By applying modern classifier backbones rather than specialised architectures, ConvNeXt-IC achieves state-of-the-art performance with 0.959 correlation with human judgement (Pearson) and 4.4x speedup. Evaluated on standard benchmarks augmented with real-world web data, ICAR achieves 20% practical speedup while maintaining category-level performance and 95% of instance-level performance, enabling sustainable scaling of vision-language systems.
Authors: Kotaro Funakoshi, Yaoxiong Zhu
Abstract: Recognition of signers' emotions suffers from one theoretical challenge and one practical challenge, namely, the overlap between grammatical and affective facial expressions and the scarcity of data for model training. This paper addresses these two challenges in a cross-lingual setting using our eJSL dataset, a new benchmark dataset for emotion recognition in Japanese Sign Language signers, and BOBSL, a large British Sign Language dataset with subtitles. In eJSL, two signers expressed 78 distinct utterances with each of seven different emotional states, resulting in 1,092 video clips. We empirically demonstrate that 1) textual emotion recognition in spoken language mitigates data scarcity in sign language, 2) temporal segment selection has a significant impact, and 3) incorporating hand motion enhances emotion recognition in signers. Finally we establish a stronger baseline than spoken language LLMs.
Authors: Liang Peng, Yixuan Ye, Cheng Liu, Hangjun Che, Fei Wang, Zhiwen Yu, Si Wu, Hau-San Wong
Abstract: Multi-view clustering has been empirically shown to improve learning performance by leveraging the inherent complementary information across multiple views of data. However, in real-world scenarios, collecting strictly aligned views is challenging, and learning from both aligned and unaligned data becomes a more practical solution. Partially View-aligned Clustering aims to learn correspondences between misaligned view samples to better exploit the potential consistency and complementarity across views, including both aligned and unaligned data. However, most existing PVC methods fail to leverage unaligned data to capture the shared semantics among samples from the same cluster. Moreover, the inherent heterogeneity of multi-view data induces distributional shifts in representations, leading to inaccuracies in establishing meaningful correspondences between cross-view latent features and, consequently, impairing learning effectiveness. To address these challenges, we propose a Semantic MAtching contRasTive learning model (SMART) for PVC. The main idea of our approach is to alleviate the influence of cross-view distributional shifts, thereby facilitating semantic matching contrastive learning to fully exploit semantic relationships in both aligned and unaligned data. Extensive experiments on eight benchmark datasets demonstrate that our method consistently outperforms existing approaches on the PVC problem.
Authors: Quanxi Zhou, Wencan Mao, Manabu Tsukada, John C. S. Lui, Yusheng Ji
Abstract: Model-based reinforcement learning (MBRL) and model-free reinforcement learning (MFRL) evolve along distinct paths but converge in the design of Dyna-Q [1]. However, modern RL methods still struggle with effective transferability across tasks and scenarios. Motivated by this limitation, we propose a generalized algorithm, Feature Model-Based Enhanced Actor-Critic (FM-EAC), that integrates planning, acting, and learning for multi-task control in dynamic environments. FM-EAC combines the strengths of MBRL and MFRL and improves generalizability through the use of novel feature-based models and an enhanced actor-critic framework. Simulations in both urban and agricultural applications demonstrate that FM-EAC consistently outperforms many state-of-the-art MBRL and MFRL methods. More importantly, different sub-networks can be customized within FM-EAC according to user-specific requirements.
Authors: Akihiro Kubo, Paavo Parmas, Shin Ishii
Abstract: Model-based reinforcement learning (MBRL) reduces the cost of real-environment sampling by generating synthetic trajectories (called rollouts) from a learned dynamics model. However, choosing the length of the rollouts poses two dilemmas: (1) Longer rollouts better preserve on-policy training but amplify model bias, indicating the need for an intermediate horizon to mitigate distribution shift (i.e., the gap between on-policy and past off-policy samples). (2) Moreover, a longer model rollout may reduce value estimation bias but raise the variance of policy gradients due to backpropagation through multiple steps, implying another intermediate horizon for stable gradient estimates. However, these two optimal horizons may differ. To resolve this conflict, we propose Double Horizon Model-Based Policy Optimization (DHMBPO), which divides the rollout procedure into a long "distribution rollout" (DR) and a short "training rollout" (TR). The DR generates on-policy state samples for mitigating distribution shift. In contrast, the short TR leverages differentiable transitions to offer accurate value gradient estimation with stable gradient updates, thereby requiring fewer updates and reducing overall runtime. We demonstrate that the double-horizon approach effectively balances distribution shift, model bias, and gradient instability, and surpasses existing MBRL methods on continuous-control benchmarks in terms of both sample efficiency and runtime.
Authors: Robert Heum\"uller, Frank Ortmeier
Abstract: The use of large language models like ChatGPT in code review offers promising efficiency gains but also raises concerns about correctness and safety. Existing evaluation methods for code review generation either rely on automatic comparisons to a single ground truth, which fails to capture the variability of human perspectives, or on subjective assessments of "usefulness", a highly ambiguous concept. We propose a novel evaluation approach based on what we call multi-subjective ranking. Using a dataset of 280 self-contained code review requests and corresponding comments from CodeReview StackExchange, multiple human judges ranked the quality of ChatGPT-generated comments alongside the top human responses from the platform. Results show that ChatGPT's comments were ranked significantly better than human ones, even surpassing StackExchange's accepted answers. Going further, our proposed method motivates and enables more meaningful assessments of generative AI's performance in code review, while also raising awareness of potential risks of unchecked integration into review processes.
Authors: Hua Yang, Alejandro Velasco, Thanh Le-Cong, Md Nazmul Haque, Bowen Xu, Denys Poshyvanyk
Abstract: The success of large language models for code relies on vast amounts of code data, including public open-source repositories, such as GitHub, and private, confidential code from companies. This raises concerns about intellectual property compliance and the potential unauthorized use of license-restricted code. While membership inference (MI) techniques have been proposed to detect such unauthorized usage, their effectiveness can be undermined by semantically equivalent code transformation techniques, which modify code syntax while preserving semantic. In this work, we systematically investigate whether semantically equivalent code transformation rules might be leveraged to evade MI detection. The results reveal that model accuracy drops by only 1.5% in the worst case for each rule, demonstrating that transformed datasets can effectively serve as substitutes for fine-tuning. Additionally, we find that one of the rules (RenameVariable) reduces MI success by 10.19%, highlighting its potential to obscure the presence of restricted code. To validate these findings, we conduct a causal analysis confirming that variable renaming has the strongest causal effect in disrupting MI detection. Notably, we find that combining multiple transformations does not further reduce MI effectiveness. Our results expose a critical loophole in license compliance enforcement for training large language models for code, showing that MI detection can be substantially weakened by transformation-based obfuscation techniques.
Authors: Hampus Linander, Conor Heins, Alexander Tschantz, Marco Perin, Christopher Buckley
Abstract: Equivariance is a powerful prior for learning physical dynamics, yet exact group equivariance can degrade performance if the symmetries are broken. We propose object-centric world models built with geometric algebra neural networks, providing a soft geometric inductive bias. Our models are evaluated using simulated environments of 2d rigid body dynamics with static obstacles, where we train for next-step predictions autoregressively. For long-horizon rollouts we show that the soft inductive bias of our models results in better performance in terms of physical fidelity compared to non-equivariant baseline models. The approach complements recent soft-equivariance ideas and aligns with the view that simple, well-chosen priors can yield robust generalization. These results suggest that geometric algebra offers an effective middle ground between hand-crafted physics and unstructured deep nets, delivering sample-efficient dynamics models for multi-object scenes.
Authors: Konstantinos Kalogiannis, Ahmed Mohamed Hussain, Hexu Li, Panos Papadimitratos
Abstract: Vehicular platooning promises transformative improvements in transportation efficiency and safety through the coordination of multi-vehicle formations enabled by Vehicle-to-Everything (V2X) communication. However, the distributed nature of platoon coordination creates security vulnerabilities, allowing authenticated vehicles to inject falsified kinematic data, compromise operational stability, and pose a threat to passenger safety. Traditional misbehaviour detection approaches, which rely on plausibility checks and statistical methods, suffer from high False Positive (FP) rates and cannot capture the complex temporal dependencies inherent in multi-vehicle coordination dynamics. We present Attention In Motion (AIMformer), a transformer-based framework specifically tailored for real-time misbehaviour detection in vehicular platoons with edge deployment capabilities. AIMformer leverages multi-head self-attention mechanisms to simultaneously capture intra-vehicle temporal dynamics and inter-vehicle spatial correlations. It incorporates global positional encoding with vehicle-specific temporal offsets to handle join/exit maneuvers. We propose a Precision-Focused (BCE) loss function that penalizes FPs to meet the requirements of safety-critical vehicular systems. Extensive evaluation across 4 platoon controllers, multiple attack vectors, and diverse mobility scenarios demonstrates superior performance ($\geq$ 0.93) compared to state-of-the-art baseline architectures. A comprehensive deployment analysis utilizing TensorFlow Lite (TFLite), Open Neural Network Exchange (ONNX), and TensorRT achieves sub-millisecond inference latency, making it suitable for real-time operation on resource-constrained edge platforms. Hence, validating AIMformer is viable for both in-vehicle and roadside infrastructure deployment.
Authors: Abdullah Al Munem, Sumona Yeasmin, Mohammad Rezwanul Huq
Abstract: Every day, a significant number of users visit the internet for different needs. The owners of a website generate profits from the user interaction with the contents or items of the website. A robust recommendation system can increase user interaction with a website by recommending items according to the user's unique preferences. BERT and CNN-integrated neural collaborative filtering (NCF) have been proposed for the recommendation system in this experiment. The proposed model takes inputs from the user and item profile and finds the user's interest. This model can handle numeric, categorical, and image data to extract the latent features from the inputs. The model is trained and validated on a small sample of the MovieLens dataset for 25 epochs. The same dataset has been used to train and validate a simple NCF and a BERT-based NCF model and compared with the proposed model. The proposed model outperformed those two baseline models. The obtained result for the proposed model is 0.72 recall and 0.486 Hit Ratio @ 10 for 799 users on the MovieLens dataset. This experiment concludes that considering both categorical and image data can improve the performance of a recommendation system.
Authors: Ken O'Hanlon, Basil Woods, Lin Wang, Mark Sandler
Abstract: In this paper we propose a conditioned UNet for Music Source Separation (MSS). MSS is generally performed by multi-output neural networks, typically UNets, with each output representing a particular stem from a predefined instrument vocabulary. In contrast, conditioned MSS networks accept an audio query related to a stem of interest alongside the signal from which that stem is to be extracted. Thus, a strict vocabulary is not required and this enables more realistic tasks in MSS. The potential of conditioned approaches for such tasks has been somewhat hidden due to a lack of suitable data, an issue recently addressed with the MoisesDb dataset. A recent method, Banquet, employs this dataset with promising results seen on larger vocabularies. Banquet uses Bandsplit RNN rather than a UNet and the authors state that UNets should not be suitable for conditioned MSS. We counter this argument and propose QSCNet, a novel conditioned UNet for MSS that integrates network conditioning elements in the Sparse Compressed Network for MSS. We find QSCNet to outperform Banquet by over 1dB SNR on a couple of MSS tasks, while using less than half the number of parameters.
Authors: Alexandre Dussolle, Pietro Li\`o
Abstract: Going from pure Multilayer Perceptron (MLP) to a learnable graph message-passing mechanism at each layer has been foundational to state-of-the-art results, despite the computational trade-off (e.g. GATs or Transformers). To go a step further, in this work, we introduce N-simplicial attention, going from pairwise token similarity to higher-order interactions, and adapt it for Rotary Position Embeddings (RoPE). To help manage the increased complexity, we propose a cost-effective simplex selection enabling the model to focus its computation load onto the more task-sensitive interactions. Beyond these core mechanisms, we study how smoothing N-simplicial attention is by deriving a Lipschitz upper-bound and by demonstrating that by itself it also suffers from over-smoothing, despite opening the attention message-passing to higher-order interactions.
Authors: Kester Clegg, Richard Hawkins, Ibrahim Habli, Tom Lawton
Abstract: LLMs (Large Language Models) are increasingly used in text processing pipelines to intelligently respond to a variety of inputs and generation tasks. This raises the possibility of replacing human roles that bottleneck existing information flows, either due to insufficient staff or process complexity. However, LLMs make mistakes and some processing roles are safety critical. For example, triaging post-operative care to patients based on hospital referral letters, or updating site access schedules in nuclear facilities for work crews. If we want to introduce LLMs into critical information flows that were previously performed by humans, how can we make them safe and reliable? Rather than make performative claims about augmented generation frameworks or graph-based techniques, this paper argues that the safety argument should focus on the type of evidence we get from evaluation points in LLM processes, particularly in frameworks that employ LLM-as-Judges (LaJ) evaluators. This paper argues that although we cannot get deterministic evaluations from many natural language processing tasks, by adopting a basket of weighted metrics it may be possible to lower the risk of errors within an evaluation, use context sensitivity to define error severity and design confidence thresholds that trigger human review of critical LaJ judgments when concordance across evaluators is low.
Authors: Darshita Rathore, Vineet Kumar, Chetna Bansal, Anindya Moitra
Abstract: Large language models are increasingly adapted to downstream tasks through fine-tuning. Full supervised fine-tuning (SFT) and parameter-efficient fine-tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), are two dominant approaches. While PEFT methods are widely used for their computational efficiency, the implications of their configurations (e.g., rank) remain under-explored in downstream Q&A tasks and generalisation. In this work, we perform a comprehensive evaluation across multiple reasoning and recall datasets, conducting a rank sweep to quantify the trade-off between SFT and PEFT. We also compare the accuracy of PEFT and SFT models across in-domain and out-of-domain adaptation, highlighting distinct generalisation behaviour and task-specific forgetting. We demonstrate that LoRA achieves competitive and in some cases superior performance compared to SFT, particularly on reasoning tasks at specific rank values. Additionally, we analyze the internal representations via spectral features and layer-wise attention structures, offering insights into representational drift and structural changes in attention patterns.
Authors: Yuanhang Li, Yiren Song, Junzhe Bai, Xinran Liang, Hu Yang, Libiao Jin, Qi Mao
Abstract: We propose \textbf{IC-Effect}, an instruction-guided, DiT-based framework for few-shot video VFX editing that synthesizes complex effects (\eg flames, particles and cartoon characters) while strictly preserving spatial and temporal consistency. Video VFX editing is highly challenging because injected effects must blend seamlessly with the background, the background must remain entirely unchanged, and effect patterns must be learned efficiently from limited paired data. However, existing video editing models fail to satisfy these requirements. IC-Effect leverages the source video as clean contextual conditions, exploiting the contextual learning capability of DiT models to achieve precise background preservation and natural effect injection. A two-stage training strategy, consisting of general editing adaptation followed by effect-specific learning via Effect-LoRA, ensures strong instruction following and robust effect modeling. To further improve efficiency, we introduce spatiotemporal sparse tokenization, enabling high fidelity with substantially reduced computation. We also release a paired VFX editing dataset spanning $15$ high-quality visual styles. Extensive experiments show that IC-Effect delivers high-quality, controllable, and temporally consistent VFX editing, opening new possibilities for video creation.
Authors: Hongbo Zhao, Meng Wang, Fei Zhu, Wenzhuo Liu, Bolin Ni, Fanhu Zeng, Gaofeng Meng, Zhaoxiang Zhang
Abstract: The computational and memory overheads associated with expanding the context window of LLMs severely limit their scalability. A noteworthy solution is vision-text compression (VTC), exemplified by frameworks like DeepSeek-OCR and Glyph, which convert long texts into dense 2D visual representations, thereby achieving token compression ratios of 3x-20x. However, the impact of this high information density on the core long-context capabilities of vision-language models (VLMs) remains under-investigated. To address this gap, we introduce the first benchmark for VTC and systematically assess the performance of VLMs across three long-context understanding settings: VTC-Retrieval, which evaluates the model's ability to retrieve and aggregate information; VTC-Reasoning, which requires models to infer latent associations to locate facts with minimal lexical overlap; and VTC-Memory, which measures comprehensive question answering within long-term dialogue memory. Furthermore, we establish the VTCBench-Wild to simulate diverse input scenarios.We comprehensively evaluate leading open-source and proprietary models on our benchmarks. The results indicate that, despite being able to decode textual information (e.g., OCR) well, most VLMs exhibit a surprisingly poor long-context understanding ability with VTC-compressed information, failing to capture long associations or dependencies in the context.This study provides a deep understanding of VTC and serves as a foundation for designing more efficient and scalable VLMs.
Authors: Xiaodi Li, Dingcheng Li, Rujun Gao, Mahmoud Zamani, Feng Mi, Latifur Khan
Abstract: Continual learning remains a fundamental challenge in machine learning, requiring models to learn from a stream of tasks without forgetting previously acquired knowledge. A major obstacle in this setting is catastrophic forgetting, where performance on earlier tasks degrades as new tasks are learned. In this paper, we introduce PPSEBM, a novel framework that integrates an Energy-Based Model (EBM) with Progressive Parameter Selection (PPS) to effectively address catastrophic forgetting in continual learning for natural language processing tasks. In PPSEBM, progressive parameter selection allocates distinct, task-specific parameters for each new task, while the EBM generates representative pseudo-samples from prior tasks. These generated samples actively inform and guide the parameter selection process, enhancing the model's ability to retain past knowledge while adapting to new tasks. Experimental results on diverse NLP benchmarks demonstrate that PPSEBM outperforms state-of-the-art continual learning methods, offering a promising and robust solution to mitigate catastrophic forgetting.
Authors: Adam Karvonen, James Chua, Cl\'ement Dumas, Kit Fraser-Taliente, Subhash Kantamneni, Julian Minder, Euan Ong, Arnab Sen Sharma, Daniel Wen, Owain Evans, Samuel Marks
Abstract: Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpreting them. Recent work has proposed a simpler approach known as LatentQA: training LLMs to directly accept LLM activations as inputs and answer arbitrary questions about them in natural language. However, prior work has focused on narrow task settings for both training and evaluation. In this paper, we instead take a generalist perspective. We evaluate LatentQA-trained models, which we call Activation Oracles (AOs), in far out-of-distribution settings and examine how performance scales with training data diversity. We find that AOs can recover information fine-tuned into a model (e.g., biographical knowledge or malign propensities) that does not appear in the input text, despite never being trained with activations from a fine-tuned model. Our main evaluations are four downstream tasks where we can compare to prior white- and black-box techniques. We find that even narrowly-trained LatentQA models can generalize well, and that adding additional training datasets (such as classification tasks and a self-supervised context prediction task) yields consistent further improvements. Overall, our best AOs match or exceed prior white-box baselines on all four tasks and are the best method on 3 out of 4. These results suggest that diversified training to answer natural-language queries imparts a general capability to verbalize information about LLM activations.
Authors: Zhenwen Liang, Sidi Lu, Wenhao Yu, Kishan Panaganti, Yujun Zhou, Haitao Mi, Dong Yu
Abstract: Reinforcement learning has become essential for strengthening the reasoning abilities of large language models, yet current exploration mechanisms remain fundamentally misaligned with how these models actually learn. Entropy bonuses and external semantic comparators encourage surface level variation but offer no guarantee that sampled trajectories differ in the update directions that shape optimization. We propose G2RL, a gradient guided reinforcement learning framework in which exploration is driven not by external heuristics but by the model own first order update geometry. For each response, G2RL constructs a sequence level feature from the model final layer sensitivity, obtainable at negligible cost from a standard forward pass, and measures how each trajectory would reshape the policy by comparing these features within a sampled group. Trajectories that introduce novel gradient directions receive a bounded multiplicative reward scaler, while redundant or off manifold updates are deemphasized, yielding a self referential exploration signal that is naturally aligned with PPO style stability and KL control. Across math and general reasoning benchmarks (MATH500, AMC, AIME24, AIME25, GPQA, MMLUpro) on Qwen3 base 1.7B and 4B models, G2RL consistently improves pass@1, maj@16, and pass@k over entropy based GRPO and external embedding methods. Analyzing the induced geometry, we find that G2RL expands exploration into substantially more orthogonal and often opposing gradient directions while maintaining semantic coherence, revealing that a policy own update space provides a far more faithful and effective basis for guiding exploration in large language model reinforcement learning.
Authors: Adam Kaufman, James Lucassen, Tyler Tracy, Cody Rushing, Aryan Bhatt
Abstract: Future AI agents might run autonomously with elevated privileges. If these agents are misaligned, they might abuse these privileges to cause serious damage. The field of AI control develops techniques that make it harder for misaligned AIs to cause such damage, while preserving their usefulness. We introduce BashArena, a setting for studying AI control techniques in security-critical environments. BashArena contains 637 Linux system administration and infrastructure engineering tasks in complex, realistic environments, along with four sabotage objectives (execute malware, exfiltrate secrets, escalate privileges, and disable firewall) for a red team to target. We evaluate multiple frontier LLMs on their ability to complete tasks, perform sabotage undetected, and detect sabotage attempts. Claude Sonnet 4.5 successfully executes sabotage while evading monitoring by GPT-4.1 mini 26% of the time, at 4% trajectory-wise FPR. Our findings provide a baseline for designing more effective control protocols in BashArena. We release the dataset as a ControlArena setting and share our task generation pipeline.
Authors: Jonas Pai, Liam Achenbach, Victoriano Montesinos, Benedek Forrai, Oier Mees, Elvis Nava
Abstract: Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a result, despite improved semantic generalization, the policy must implicitly infer complex physical dynamics and temporal dependencies solely from robot trajectories. This reliance creates an unsustainable data burden, necessitating continuous, large-scale expert data collection to compensate for the lack of innate physical understanding. We contend that while vision-language pretraining effectively captures semantic priors, it remains blind to physical causality. A more effective paradigm leverages video to jointly capture semantics and visual dynamics during pretraining, thereby isolating the remaining task of low-level control. To this end, we introduce \model, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations. The decoder serves as an Inverse Dynamics Model (IDM), generating low-level robot actions from the latent representation of video-space action plans. Our extensive evaluation shows that our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.
Authors: Jinjing Zhao, Fangyun Wei, Zhening Liu, Hongyang Zhang, Chang Xu, Yan Lu
Abstract: Existing video generation models struggle to maintain long-term spatial and temporal consistency due to the dense, high-dimensional nature of video signals. To overcome this limitation, we propose Spatia, a spatial memory-aware video generation framework that explicitly preserves a 3D scene point cloud as persistent spatial memory. Spatia iteratively generates video clips conditioned on this spatial memory and continuously updates it through visual SLAM. This dynamic-static disentanglement design enhances spatial consistency throughout the generation process while preserving the model's ability to produce realistic dynamic entities. Furthermore, Spatia enables applications such as explicit camera control and 3D-aware interactive editing, providing a geometrically grounded framework for scalable, memory-driven video generation.
Authors: Guanren Qiao, Guorui Quan, Jiawei Yu, Shujun Jia, Guiliang Liu
Abstract: While modern Autonomous Vehicle (AV) systems can develop reliable driving policies under regular traffic conditions, they frequently struggle with safety-critical traffic scenarios. This difficulty primarily arises from the rarity of such scenarios in driving datasets and the complexities associated with predictive modeling of multiple vehicles. Effectively simulating safety-critical traffic situations is therefore a crucial challenge. In this paper, we introduce TrafficGamer, which facilitates game-theoretic traffic simulation by viewing common road driving as a multi-agent game. When we evaluate the empirical performance across various real-world datasets, TrafficGamer ensures both the fidelity, exploitability, and diversity of the simulated scenarios, guaranteeing that they not only statically align with real-world traffic distribution but also efficiently capture equilibria for representing safety-critical scenarios involving multiple agents compared with other methods. Additionally, the results demonstrate that TrafficGamer provides highly flexible simulations across various contexts. Specifically, we demonstrate that the generated scenarios can dynamically adapt to equilibria of varying tightness by configuring risk-sensitive constraints during optimization. We have provided a demo webpage at: https://anonymous.4open.science/api/repo/trafficgamer-demo-1EE0/file/index.html.
URLs: https://anonymous.4open.science/api/repo/trafficgamer-demo-1EE0/file/index.html.
Authors: Tao Wu, Kexue Fu, Qiang Hua, Xinxin Liu, Bo Liu
Abstract: Antenna simulation typically involves modeling and optimization, which are time-consuming and labor-intensive, slowing down antenna analysis and design. This paper presents a prototype of a large language model (LLM)-based antenna design system (LADS) to assist in antenna simulation. LADS generates antenna models with textual descriptions and images extracted from academic papers, patents, and technical reports (either one or multiple), and it interacts with engineers to iteratively refine the designs. After that, LADS configures and runs an optimizer to meet the design specifications. The effectiveness of LADS is demonstrated by a monopole slotted antenna generated from images and descriptions from the literature. To improve gain stability across the 3.1-10.6 GHz ultra-wide band, LADS modifies the cross-slot into an H-slot and changes substrate material, followed by parameter optimization. As a result, the gain variation is reduced while maintaining the same gain level. The LLM-enabled antenna modeling (LEAM) is available at: https://github.com/TaoWu974/LEAM.
Authors: Shuyang Guo, Wenjin Xie, Ping Lu, Ting Deng, Richong Zhang, Jianxin Li, Xiangping Huang, Zhongyi Liu
Abstract: Homomorphism is a key mapping technique between graphs that preserves their structure. Given a graph and a pattern, the subgraph homomorphism problem involves finding a mapping from the pattern to the graph, ensuring that adjacent vertices in the pattern are mapped to adjacent vertices in the graph. Unlike subgraph isomorphism, which requires a one-to-one mapping, homomorphism allows multiple vertices in the pattern to map to the same vertex in the graph, making it more complex. We propose HFrame, the first graph neural network-based framework for subgraph homomorphism, which integrates traditional algorithms with machine learning techniques. We demonstrate that HFrame outperforms standard graph neural networks by being able to distinguish more graph pairs where the pattern is not homomorphic to the graph. Additionally, we provide a generalization error bound for HFrame. Through experiments on both real-world and synthetic graphs, we show that HFrame is up to 101.91 times faster than exact matching algorithms and achieves an average accuracy of 0.962.
Authors: Amine Allouah, Omar Besbes, Josu\'e D Figueroa, Yash Kanoria, Akshit Kumar
Abstract: Online marketplaces will be transformed by autonomous AI agents acting on behalf of consumers. Rather than humans browsing and clicking, AI agents can parse webpages or leverage APIs to view, evaluate and choose products. We investigate the behavior of AI agents using ACES, a provider-agnostic framework for auditing agent decision-making. We reveal that agents can exhibit choice homogeneity, often concentrating demand on a few ``modal'' products while ignoring others entirely. Yet, these preferences are unstable: model updates can drastically reshuffle market shares. Furthermore, randomized trials show that while agents have improved over time on simple tasks with a clearly identified best choice, they exhibit strong position biases -- varying across providers and model versions, and persisting even in text-only "headless" interfaces -- undermining any universal notion of a ``top'' rank. Agents also consistently penalize sponsored tags while rewarding platform endorsements, and sensitivities to price, ratings, and reviews vary sharply across models. Finally, we demonstrate that sellers can respond: a seller-side agent making simple, query-conditional description tweaks can drive significant gains in market share. These findings reveal that agentic markets are volatile and fundamentally different from human-centric commerce, highlighting the need for continuous auditing and raising questions for platform design, seller strategy and regulation.
Authors: Pengsong Zhang, Xiang Hu, Guowei Huang, Yang Qi, Heng Zhang, Xiuxu Li, Jiaxing Song, Jiabin Luo, Yijiang Li, Shuo Yin, Chengxiao Dai, Eric Hanchen Jiang, Xiaoyan Zhou, Zhenfei Yin, Boqin Yuan, Jing Dong, Guinan Su, Guanren Qiao, Haiming Tang, Anghong Du, Lili Pan, Zhenzhong Lan, Xinyu Liu
Abstract: Recent advances in large language models (LLMs) have enabled AI agents to autonomously generate scientific proposals, conduct experiments, author papers, and perform peer reviews. Yet this flood of AI-generated research content collides with a fragmented and largely closed publication ecosystem. Traditional journals and conferences rely on human peer review, making them difficult to scale and often reluctant to accept AI-generated research content; existing preprint servers (e.g. arXiv) lack rigorous quality-control mechanisms. Consequently, a significant amount of high-quality AI-generated research lacks appropriate venues for dissemination, hindering its potential to advance scientific progress. To address these challenges, we introduce aiXiv, a next-generation open-access platform for human and AI scientists. Its multi-agent architecture allows research proposals and papers to be submitted, reviewed, and iteratively refined by both human and AI scientists. It also provides API and MCP interfaces that enable seamless integration of heterogeneous human and AI scientists, creating a scalable and extensible ecosystem for autonomous scientific discovery. Through extensive experiments, we demonstrate that aiXiv is a reliable and robust platform that significantly enhances the quality of AI-generated research proposals and papers after iterative revising and reviewing on aiXiv. Our work lays the groundwork for a next-generation open-access ecosystem for AI scientists, accelerating the publication and dissemination of high-quality AI-generated research content. Code: https://github.com/aixiv-org aiXiv: https://aixiv.science
Authors: Cristina Cornelio, Takuya Ito, Ryan Cory-Wright, Sanjeeb Dash, Lior Horesh
Abstract: Artificial intelligence (AI) is transforming the practice of science. Machine learning and large language models (LLMs) can generate hypotheses at a scale and speed far exceeding traditional methods, offering the potential to accelerate discovery across diverse fields. However, the abundance of hypotheses introduces a critical challenge: without scalable and reliable mechanisms for verification, scientific progress risks being hindered rather than being advanced. In this article, we trace the historical development of scientific discovery, examine how AI is reshaping established practices for scientific discovery, and review the principal approaches, ranging from data-driven methods and knowledge-aware neural architectures to symbolic reasoning frameworks and LLM agents. While these systems can uncover patterns and propose candidate laws, their scientific value ultimately depends on rigorous and transparent verification, which we argue must be the cornerstone of AI-assisted discovery.
Authors: Longfei Wang, Junyan Liu, Fan Zhang, Jiangwen Wei, Yuanhua Tang, Jie Sun, Xiaodong Luo
Abstract: Parallelization has emerged as a promising approach for accelerating MILP solving. However, the complexity of the branch-and-bound (B&B) framework and the numerous effective algorithm components in MILP solvers make it difficult to parallelize. In this study, a scalable parallel framework, N2N (a node-to-node framework that maps the B&B nodes to distributed computing nodes), was proposed to solve large-scale problems in a distributed memory computing environment. Both deterministic and nondeterministic modes are supported, and the framework is designed to be easily integrated with existing solvers. Regarding the deterministic mode, a novel sliding-window-based algorithm was designed and implemented to ensure that tasks are generated and solved in a deterministic order. Moreover, several advanced techniques, such as the utilization of CP search and general primal heuristics, have been developed to fully utilize distributed computing resources and capabilities of base solvers. Adaptive solving and data communication optimization were also investigated. A popular open-source MILP solver, SCIP, was integrated into N2N as the base solver, yielding N2N-SCIP. Extensive computational experiments were conducted to evaluate the performance of N2N-SCIP compared to ParaSCIP, which is a state-of-the-art distributed parallel MILP solver under the UG framework. The nondeterministic N2N-SCIP achieves speedups of 22.52 and 12.71 with 1,000 MPI processes on the Kunpeng and x86 computing clusters, which is 1.98 and 2.08 times faster than ParaSCIP, respectively. In the deterministic mode, N2N-SCIP also shows significant performance improvements over ParaSCIP across different process numbers and computing clusters. To validate the generality of N2N, HiGHS, another open-source solver, was integrated into N2N. The related results are analyzed, and the requirements of N2N on base solvers are also concluded.
Authors: Yuanyuan Lin, Xiangyu Ouyang, Teng Zhang, Kaixin Sui
Abstract: Tree search-based methods have made significant progress in enhancing the code generation capabilities of large language models. However, due to the difficulty in effectively evaluating intermediate algorithmic steps and the inability to locate and timely correct erroneous steps, these methods often generate incorrect code and incur increased computational costs. To tackle these problems, we propose RPM-MCTS, an effective method that utilizes Knowledge-Retrieval as Process Reward Model based on Monte Carlo Tree Search to evaluate intermediate algorithmic steps. By utilizing knowledge base retrieval, RPM-MCTS avoids the complex training of process reward models. During the expansion phase, similarity filtering is employed to remove redundant nodes, ensuring diversity in reasoning paths. Furthermore, our method utilizes sandbox execution feedback to locate erroneous algorithmic steps during generation, enabling timely and targeted corrections. Extensive experiments on four public code generation benchmarks demonstrate that RPM-MCTS outperforms current state-of-the-art methods while achieving an approximately 15% reduction in token consumption. Furthermore, full fine-tuning of the base model using the data constructed by RPM-MCTS significantly enhances its code capabilities.
Authors: Alex Diep
Abstract: Self-transparency is a critical safety boundary, requiring language models to honestly disclose their limitations and artificial nature. This study stress-tests this capability, investigating whether models willingly disclose their identity when assigned professional personas that conflict with transparent self-representation. When models prioritize role consistency over this boundary disclosure, users may calibrate trust based on overstated competence claims, treating AI-generated guidance as equivalent to licensed professional advice. Using a common-garden experimental design, sixteen open-weight models (4B-671B parameters) were audited under identical conditions across 19,200 trials. Models exhibited sharp domain-specific inconsistency: a Financial Advisor persona elicited 30.8% disclosure at the first prompt, while a Neurosurgeon persona elicited only 3.5% -- an 8.8-fold difference that emerged at the initial epistemic inquiry. Disclosure ranged from 2.8% to 73.6% across model families, with a 14B model reaching 39.4% while a 70B model produced just 4.1%. Model identity provided substantially larger improvement in fitting observations than parameter count ($\Delta R_{adj}^{2}=0.359$ vs $0.018$). Reasoning variants showed heterogeneous effects: some exhibited up to 48.4 percentage points lower disclosure than their base instruction-tuned counterparts, while others maintained high transparency. An additional experiment demonstrated that explicit permission to disclose AI nature increased disclosure from 23.7% to 65.8%, revealing that suppression reflects instruction-following prioritization rather than capability limitations. Bayesian validation confirmed robustness to judge measurement error ($\kappa=0.908$). Organizations cannot assume safety properties will transfer across deployment domains, requiring deliberate behavior design and empirical verification.
Authors: PIerre Dantas, Lucas Cordeiro, Youcheng Sun, Waldir Junior
Abstract: The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to scale software verification beyond manual workflows. However, current methods remain unreliable: without a solid theoretical footing, the refinement process acts as a black box that may oscillate, loop, or diverge. This work bridges this critical gap by developing an LLM-Verifier Convergence Theorem, providing the first formal framework with provable guarantees for termination in multi-stage verification pipelines. We model the interaction not as a generic loop, but as a sequential absorbing Markov Chain comprising four essential engineering stages: \texttt{CodeGen}, \texttt{Compilation}, \texttt{InvariantSynth}, and \texttt{SMTSolving}. We prove that for any non-zero stage success probability ($\delta > 0$), the system reaches the \texttt{Verified} state almost surely. Furthermore, because of the sequential nature of the pipeline, we derive a precise latency bound of $\mathbb{E}[n] \leq 4/\delta$. We stress-tested this prediction in an extensive empirical campaign comprising over 90,000 trials. The results match the theory with striking consistency: every run reached verification, and the empirical convergence factor clustered tightly around $C_f\approx 1.0$, confirming that the $4/\delta$ bound accurately mirrors system behavior rather than serving as a loose buffer. Based on this data, we identify three distinct operating zones -- marginal, practical, and high-performance -- and propose a dynamic calibration strategy to handle parameter drift in real-world environments. Together, these contributions replace heuristic guesswork with a rigorous architectural foundation, enabling predictable resource planning and performance budgeting for safety-critical software.
Authors: Pedro Passos
Abstract: In elite soccer, substitution decisions entail significant financial and sporting consequences yet remain heavily reliant on intuition or predictive models that merely mimic historical biases. This paper introduces a Fuzzy Logic based Decision Support System (DSS) designed for real time, prescriptive game management. Unlike traditional Machine Learning approaches that encounter a predictive ceiling by attempting to replicate human behavior, our system audits performance through an objective, rule based inference engine. We propose a methodological advancement by reformulating the PlayeRank metric into a Cumulative Mean with Role Aware Normalization, eliminating the play time exposure bias inherent in cumulative sum models to enable accurate intra match comparison. The system integrates this refined metric with physiological proxies (fatigue) and contextual variables (disciplinary risk modulated by tactical role) to calculate a dynamic Substitution Priority (P final). Validation via a case study of the 2018 FIFA World Cup match between Brazil and Belgium demonstrates the system's ecological validity: it not only aligned with expert consensus on executed substitutions (for example Gabriel Jesus) but, crucially, identified high risk scenarios ignored by human decision makers. Specifically, the model flagged the "FAGNER Paradox" - a maximum priority defensive risk - minutes before a critical yellow card, and detected the "Lukaku Paradox", where an isolated assist masked a severe drop in participation. These results confirm that Fuzzy Logic offers a transparent, explainable, and superior alternative to black box models for optimizing real time tactical decisions.
Authors: Yubin Kim, Ken Gu, Chanwoo Park, Chunjong Park, Samuel Schmidgall, A. Ali Heydari, Yao Yan, Zhihan Zhang, Yuchen Zhuang, Mark Malhotra, Paul Pu Liang, Hae Won Park, Yuzhe Yang, Xuhai Xu, Yilun Du, Shwetak Patel, Tim Althoff, Daniel McDuff, Xin Liu
Abstract: Agents, language model-based systems that are capable of reasoning, planning, and acting are becoming the dominant paradigm for real-world AI applications. Despite this widespread adoption, the principles that determine their performance remain underexplored. We address this by deriving quantitative scaling principles for agent systems. We first formalize a definition for agentic evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, model capability, and task properties. We evaluate this across four benchmarks: Finance-Agent, BrowseComp-Plus, PlanCraft, and Workbench. With five canonical agent architectures (Single-Agent and four Multi-Agent Systems: Independent, Centralized, Decentralized, Hybrid), instantiated across three LLM families, we perform a controlled evaluation spanning 180 configurations. We derive a predictive model using coordination metrics, that achieves cross-validated R^2=0.524, enabling prediction on unseen task domains. We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead. (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed ~45%. (3) topology-dependent error amplification: independent agents amplify errors 17.2x, while centralized coordination contains this to 4.4x. Centralized coordination improves performance by 80.8% on parallelizable tasks, while decentralized coordination excels on web navigation (+9.2% vs. +0.2%). Yet for sequential reasoning tasks, every multi-agent variants degraded performance by 39-70%. The framework predicts the optimal coordination strategy for 87% of held-out configurations. Out-of-sample validation on GPT-5.2, achieves MAE=0.071 and confirms four of five scaling principles generalize to unseen frontier models.
Authors: Chutian Ma, Grigorii Pomazkin, Giacinto Paolo Saggese, Paul Smith
Abstract: Energy demand prediction is critical for grid operators, industrial energy consumers, and service providers. Energy demand is influenced by multiple factors, including weather conditions (e.g. temperature, humidity, wind speed, solar radiation), and calendar information (e.g. hour of day and month of year), which further affect daily work and life schedules. These factors are causally interdependent, making the problem more complex than simple correlation-based learning techniques satisfactorily allow for. We propose a structural causal model that explains the causal relationship between these variables. A full analysis is performed to validate our causal beliefs, also revealing important insights consistent with prior studies. For example, our causal model reveals that energy demand responds to temperature fluctuations with season-dependent sensitivity. Additionally, we find that energy demand exhibits lower variance in winter due to the decoupling effect between temperature changes and daily activity patterns. We then build a Bayesian model, which takes advantage of the causal insights we learned as prior knowledge. The model is trained and tested on unseen data and yields state-of-the-art performance in the form of a 3.84 percent MAPE on the test set. The model also demonstrates strong robustness, as the cross-validation across two years of data yields an average MAPE of 3.88 percent.
Authors: Kamer Ali Yuksel
Abstract: Large language models (LLMs) are increasingly used to evolve programs and multi-agent systems, yet most existing approaches rely on overwrite-based mutations that maintain only a single candidate at a time. Such methods discard useful variants, suffer from destructive edits, and explore a brittle search space prone to structural failure. We introduce EvoLattice, a framework that represents an entire population of candidate programs or agent behaviors within a single directed acyclic graph. Each node stores multiple persistent alternatives, and every valid path through the graph defines a distinct executable candidate, yielding a large combinatorial search space without duplicating structure. EvoLattice enables fine-grained alternative-level evaluation by scoring each alternative across all paths in which it appears, producing statistics that reveal how local design choices affect global performance. These statistics provide a dense, data-driven feedback signal for LLM-guided mutation, recombination, and pruning, while preserving successful components. Structural correctness is guaranteed by a deterministic self-repair mechanism that enforces acyclicity and dependency consistency independently of the LLM. EvoLattice naturally extends to agent evolution by interpreting alternatives as prompt fragments or sub-agent behaviors. Across program synthesis (proxy and optimizer meta-learning), EvoLattice yields more stable evolution, greater expressivity, and stronger improvement trajectories than prior LLM-guided methods. The resulting dynamics resemble quality-diversity optimization, emerging implicitly from EvoLattice's internal multi-alternative representation rather than an explicit external archive.
Authors: Wentao Wan, Qiqing Lao, Zhiwei Xie, Hefeng Wu, Runnan Lin, Liang Lin, Keze Wang
Abstract: Knowledge Editing (KE) is a field that studies how to modify some knowledge in Large Language Models (LLMs) at a low cost (compared to pre-training). Currently, performing large-scale edits on LLMs while ensuring the Reliability, Generality, and Locality metrics of the edits remain a challenge. This paper proposes a Massive editing approach for LLMs based on dynamic weight Generation (MeG). Our MeG involves attaching a dynamic weight neuron to specific layers of the LLMs and using a diffusion model to conditionally generate the weights of this neuron based on the input query required for the knowledge. This allows the use of adding a single dynamic weight neuron to achieve the goal of large-scale knowledge editing. Experiments show that our MeG can significantly improve the performance of large-scale KE in terms of Reliability, Generality, and Locality metrics compared to existing knowledge editing methods, particularly with a high percentage point increase in the absolute value index for the Locality metric, demonstrating the advantages of our proposed method.
Authors: Youngjae Min, Benjamin Wright, Jeremy Bernstein, Navid Azizan
Abstract: When machine learning models are trained continually on a sequence of tasks, they are often liable to forget what they learned on previous tasks--a phenomenon known as catastrophic forgetting. Proposed solutions to catastrophic forgetting tend to involve storing information about past tasks, meaning that memory usage is a chief consideration in determining their practicality. This paper develops a memory-efficient solution to catastrophic forgetting using the idea of matrix sketching, in the context of a simple continual learning algorithm known as orthogonal gradient descent (OGD). OGD finds weight updates that aim to preserve performance on prior datapoints, using gradients of the model on those datapoints. However, since the memory cost of storing prior model gradients grows with the runtime of the algorithm, OGD is ill-suited to continual learning over long time horizons. To address this problem, we propose SketchOGD. SketchOGD employs an online sketching algorithm to compress model gradients as they are encountered into a matrix of a fixed, user-determined size. In contrast to existing memory-efficient variants of OGD, SketchOGD runs online without the need for advance knowledge of the total number of tasks, is simple to implement, and is more amenable to analysis. We provide theoretical guarantees on the approximation error of the relevant sketches under a novel metric suited to the downstream task of OGD. Experimentally, we find that SketchOGD tends to outperform current state-of-the-art variants of OGD given a fixed memory budget.
Authors: Ramin Ayanzadeh, Ahmad Mousavi, Amirhossein Basareh, Narges Alavisamani, Kazem Taram
Abstract: The Early Fault-Tolerant (EFT) era is emerging, where modest Quantum Error Correction (QEC) can enable quantum utility before full-scale fault tolerance. Quantum optimization is a leading candidate for early applications, but protecting these workloads is critical since they will run on expensive cloud services where providers could learn sensitive problem details. Experience with classical computing systems has shown that treating security as an afterthought can lead to significant vulnerabilities. Thus, we must address the security implications of quantum computing before widespread adoption. However, current Secure Quantum Computing (SQC) approaches, although theoretically promising, are impractical in the EFT era: blind quantum computing requires large-scale quantum networks, and quantum homomorphic encryption depends on full QEC. We propose application-specific SQC, a principle that applies obfuscation at the application layer to enable practical deployment while remaining agnostic to algorithms, computing models, and hardware architectures. We present Enigma, the first realization of this principle for quantum optimization. Enigma integrates three complementary obfuscations: ValueGuard scrambles coefficients, StructureCamouflage inserts decoys, and TopologyTrimmer prunes variables. These techniques guarantee recovery of original solutions, and their stochastic nature resists repository-matching attacks. Evaluated against seven state-of-the-art AI models across five representative graph families, even combined adversaries, under a conservatively strong attacker model, identify the correct problem within their top five guesses in only 4.4% of cases. The protections come at the cost of problem size and T-gate counts increasing by averages of 1.07x and 1.13x, respectively, with both obfuscation and decoding completing within seconds for large-scale problems.
Authors: Yuncheng Jiang, Chun-Mei Feng, Jinke Ren, Jun Wei, Zixun Zhang, Yiwen Hu, Yunbi Liu, Rui Sun, Xuemei Tang, Juan Du, Xiang Wan, Yong Xu, Bo Du, Xin Gao, Guangyu Wang, Shaohua Zhou, Shuguang Cui, Zhen Li
Abstract: Ultrasound imaging is widely used in clinical diagnosis due to its non-invasive nature and real-time capabilities. However, traditional ultrasound diagnostics relies heavily on physician expertise and is often hampered by suboptimal image quality, leading to potential diagnostic errors. While artificial intelligence (AI) offers a promising solution to enhance clinical diagnosis by detecting abnormalities across various imaging modalities, existing AI methods for ultrasound face two major challenges. First, they typically require vast amounts of labeled medical data, raising serious concerns regarding patient privacy. Second, most models are designed for specific tasks, which restricts their broader clinical utility. To overcome these challenges, we present UltraFedFM, an innovative privacy-preserving ultrasound foundation model. UltraFedFM is collaboratively pre-trained using federated learning across 16 distributed medical institutions in 9 countries, leveraging a dataset of over 1 million ultrasound images covering 19 organs and 10 ultrasound modalities. This extensive and diverse data, combined with a secure training framework, enables UltraFedFM to exhibit strong generalization and diagnostic capabilities. It achieves an average area under the receiver operating characteristic curve (AUROC) of 0.927 for disease diagnosis and a dice similarity coefficient (DSC) of 0.878 for lesion segmentation. Notably, UltraFedFM surpasses the diagnostic accuracy of mid-level ultrasonographers (4-8 years of experience) and matches the performance of expert-level sonographers (10+ years of experience) in the joint diagnosis of 8 common systemic diseases.c These findings indicate that UltraFedFM can significantly enhance clinical diagnostics while safeguarding patient privacy, marking a significant advancement in AI-driven ultrasound imaging for future clinical applications.
Authors: Yujie Dai, Brian Sullivan, Axel Montout, Amy Dillon, Chris Waller, Peter Acs, Rachel Denholm, Philip Williams, Alastair D Hay, Raul Santos-Rodriguez, Andrew Dowsey
Abstract: The use of machine learning and AI on electronic health records (EHRs) holds substantial potential for clinical insight. However, this approach faces challenges due to data heterogeneity, sparsity, temporal misalignment, and limited labeled outcomes. In this context, we leverage a linked EHR dataset of approximately one million de-identified individuals from Bristol, North Somerset, and South Gloucestershire, UK, to characterize urinary tract infections (UTIs). We implemented a data pre-processing and curation pipeline that transforms the raw EHR data into a structured format suitable for developing predictive models focused on data fairness, accountability and transparency. Given the limited availability and biases of ground truth UTI outcomes, we introduce a UTI risk estimation framework informed by clinical expertise to estimate UTI risk across individual patient timelines. Pairwise XGBoost models are trained using this framework to differentiate UTI risk categories with explainable AI techniques applied to identify key predictors and support interpretability. Our findings reveal differences in clinical and demographic predictors across risk groups. While this study highlights the potential of AI-driven insights to support UTI clinical decision-making, further investigation of patient sub-strata and extensive validation are needed to ensure robustness and applicability in clinical practice.
Authors: Arash Hajisafi, Maria Despoina Siampou, Bita Azarijoo, Zhen Xiong, Cyrus Shahabi
Abstract: Clinical time series are often irregularly sampled, with varying sensor frequencies, missing observations, and misaligned timestamps. Prior approaches typically address these irregularities by interpolating data into regular sequences, thereby introducing bias, or by generating inconsistent and uninterpretable relationships across sensor measurements, complicating the accurate learning of both intra-series and inter-series dependencies. We introduce WaveGNN, a model that operates directly on irregular multivariate time series without interpolation or conversion to a regular representation. WaveGNN combines a decay-aware Transformer to capture intra-series dynamics with a sample-specific graph neural network that models both short-term and long-term inter-sensor relationships. Therefore, it generates a single, sparse, and interpretable graph per sample. Across multiple benchmark datasets (P12, P19, MIMIC-III, and PAM), WaveGNN delivers consistently strong performance, whereas other state-of-the-art baselines tend to perform well on some datasets or tasks but poorly on others. While WaveGNN does not necessarily surpass every method in every case, its consistency and robustness across diverse settings set it apart. Moreover, the learned graphs align well with known physiological structures, enhancing interpretability and supporting clinical decision-making.
Authors: Deepak Ghimire, Dayoung Kil, Seonghwan Jeong, Jaesik Park, Seong-heum Kim
Abstract: Existing structured pruning methods typically rely on multi-stage training procedures that incur high computational costs. Pruning at initialization aims to reduce this burden but often suffers from degraded performance. To address these limitations, we propose an efficient one-cycle structured pruning framework that integrates pre-training, pruning, and fine-tuning into a single training cycle without sacrificing accuracy. The key idea is to identify an optimal sub-network during the early stages of training, guided by norm-based group saliency criteria and structured sparsity regularization. We introduce a novel pruning indicator that detects a stable pruning epoch by measuring the similarity between pruning sub-networks across consecutive training epochs. In addition, group sparsity regularization accelerates convergence, further reducing overall training time. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet using VGG, ResNet, and MobileNet architectures demonstrate that the proposed method achieves state-of-the-art accuracy while being among the most efficient structured pruning frameworks in terms of training cost. Code is available at https://github.com/ghimiredhikura/OCSPruner.
Authors: Sanghyuk Kim, Minsik Seo, Sunwoong Yang, Namwoo Kang
Abstract: This study presents a rigid-deformation decomposition framework for vehicle collision dynamics that mitigates the spectral bias of implicit neural representations, that is, coordinate-based neural networks that directly map spatio-temporal coordinates to physical fields. We introduce a hierarchical architecture that decouples global rigid-body motion from local deformation using two scale-specific networks, denoted as RigidNet and DeformationNet. To enforce kinematic separation between the two components, we adopt a frozen-anchor training strategy combined with a quaternion-incremental scheme. This strategy alleviates the kinematic instability observed in joint training and yields a 29.8% reduction in rigid-body motion error compared with conventional direct prediction schemes. The stable rigid-body anchor improves the resolution of high-frequency structural buckling, which leads to a 17.2% reduction in the total interpolation error. Loss landscape analysis indicates that the decomposition smooths the optimization surface, which enhances robustness to distribution shifts in angular extrapolation and yields a 46.6% reduction in error. To assess physical validity beyond numerical accuracy, we benchmark the decomposed components against an oracle model that represents an upper bound on performance. The proposed framework recovers 92% of the directional correlation between rigid and deformation components and 96% of the spatial deformation localization accuracy relative to the oracle, while tracking the temporal energy dynamics with an 8 ms delay. These results demonstrate that rigid-deformation decomposition enables accurate and physically interpretable predictions for nonlinear collision dynamics.
Authors: Bodong Chen
Abstract: AI systems are increasingly embedded in practices where humans have traditionally exercised epistemic agency, the capacity to actively engage in knowledge formation and validation. This paper argues that understanding AI's impact on epistemic agency requires analyzing these systems as epistemic infrastructures rather than as neutral tools. Drawing on theories of technological mediation and distributed cognition, I advance a framework that foregrounds how AI systems reconfigure the conditions under which epistemic agency can be exercised. The framework specifies three analytical conditions: affordances for skilled epistemic actions, support for epistemic sensitivity, and implications for habit formation. I apply this framework to AI systems deployed in education, a domain where epistemic agency is both professionally essential and ethically significant. Analysis of AI lesson planning and feedback tools reveals patterns of epistemic substitution: while useful for efficiently handling teaching tasks, these systems perform cognitive operations without sustaining skilled epistemic actions, epistemic sensitivity, or virtuous habit formation, potentially preventing the cultivation of professional judgment that relies on these practices. The findings contribute to philosophical debates about AI and human agency by specifying mechanisms through which infrastructural embedding shapes epistemic possibilities, and offer design principles for AI systems that sustain rather than supplant human epistemic agency.
Authors: Mengshi Qi, Hongwei Ji, Wulian Yun, Xianlin Zhang, Huadong Ma
Abstract: Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify unseen action categories. However, existing few-shot TAL methods typically focus solely on video-level information, neglecting textual information, which can provide valuable semantic support for the action localization task. To address these issues, in this work, we propose a new few-shot temporal action localization method by Chain-of-Evidence multimodal reasoning to improve localization performance. Specifically, we design a novel few-shot learning framework to capture action commonalities and variations, which includes a semantic-aware text-visual alignment module designed to align the query and support videos at different levels. Meanwhile, to better express the temporal dependencies and causal relationships between actions at the textual level, we design a Chain-of-Evidence (CoE) reasoning method that progressively guides the Vision Language Model (VLM) and Large Language Model (LLM) to generate CoE text descriptions for videos. The generated texts can capture more variance of action than visual features. We conduct extensive experiments on the publicly available ActivityNet1.3, THUMOS14 and our newly collected Human-related Anomaly Localization Dataset. The experimental results demonstrate that our proposed method significantly outperforms existing methods in single-instance and multi-instance scenarios. Our source code and data are available at https://github.com/MICLAB-BUPT/VAL-VLM.
Authors: Guangjin Pan, Zhixing Li, Ay\c{c}a \"Oz\c{c}elikkale, Christian H\"ager, Musa Furkan Keskin, Henk Wymeersch
Abstract: In closed-loop distributed multi-sensor integrated sensing and communication (ISAC) systems, performance often hinges on transmitting high-dimensional sensor observations over rate-limited networks. In this paper, we first present a general framework for rate-limited closed-loop distributed ISAC systems, and then propose an autoencoder-based observation compression method to overcome the constraints imposed by limited transmission capacity. Building on this framework, we conduct a case study using a closed-loop linear quadratic regulator (LQR) system to analyze how the interplay among observation, compression, and state dimensions affects reconstruction accuracy, state estimation error, and control performance. In multi-sensor scenarios, our results further show that optimal resource allocation initially prioritizes low-noise sensors until the compression becomes lossless, after which resources are reallocated to high-noise sensors.
Authors: Lena Reissinger, Yuanyuan Li, Anna-Carolina Haensch, Neeraj Sarna
Abstract: Visual Generative AI models have demonstrated remarkable capability in generating high-quality images from user inputs like text prompts. However, because these models have billions of parameters, they risk memorizing certain parts of the training data and reproducing the memorized content. Memorization often raises concerns about safety of such models -- usually involving intellectual property (IP) infringement risk -- and deters their large scale adoption. In this paper, we evaluate the effectiveness of prompt engineering techniques in reducing memorization risk in image generation. Our findings demonstrate the effectiveness of prompt engineering in reducing the similarity between generated images and the training data of diffusion models, while maintaining relevance and aestheticity of the generated output.
Authors: Can Chen, David Heurtel-Depeiges, Robert M. Vernon, Christopher James Langmead, Yoshua Bengio, Quentin Fournier
Abstract: Protein language models (pLMs) pre-trained on vast protein sequence databases excel at various downstream tasks but often lack the structural knowledge essential for some biological applications. To address this, we introduce a method to enrich pLMs with structural knowledge by leveraging pre-trained protein graph neural networks (pGNNs). First, a latent-level contrastive learning task aligns residue representations from pLMs with those from pGNNs across multiple proteins, injecting inter-protein structural information. Additionally, a physical-level task integrates intra-protein information by training pLMs to predict structure tokens. Together, the proposed dual-task framework effectively incorporates both inter- and intra-protein structural knowledge into pLMs. Given the variability in the quality of protein structures in PDB, we further introduce a residue loss selection module that uses a small model trained on high-quality structures to select reliable yet challenging residue losses for the pLM to learn. Applying our structure alignment method as a simple, lightweight post-training step to the state-of-the-art ESM2 and AMPLIFY yields notable performance gains. These improvements are consistent across a wide range of tasks, including substantial gains in deep mutational scanning (DMS) fitness prediction and a 59% increase in P@L for ESM2 650M contact prediction on CASP16. Furthermore, we demonstrate that these performance gains are robust, scaling with model sizes from 8M to 650M and extending to different downstream tasks.
Authors: Owen Bianchi, Mathew J. Koretsky, Maya Willey, Chelsea X. Alvarado, Tanay Nayak, Adi Asija, Nicole Kuznetsov, Mike A. Nalls, Faraz Faghri, Daniel Khashabi
Abstract: Large language models (LLMs) face significant challenges with needle-in-ahaystack tasks, where relevant information ("the needle") must be drawn from a large pool of irrelevant context ("the haystack"). Previous studies have highlighted positional bias and distractor quantity as critical factors affecting model performance, yet the influence of gold context size, the length of the answer-containing document, has received little attention. We present the first systematic study of gold context size in long-context question answering, spanning three diverse benchmarks (general knowledge, biomedical reasoning, and mathematical reasoning), eleven state-of-the-art LLMs (including recent reasoning models), and more than 150K controlled runs. Our experiments reveal that LLM performance drops sharply when the gold context is shorter, i.e., smaller gold contexts consistently degrade model performance and amplify positional sensitivity, posing a major challenge for agentic systems that must integrate scattered, fine-grained information of varying lengths. This effect persists under rigorous confounder analysis: even after controlling for gold context position, answer token repetition, gold-to-distractor ratio, distractor volume, and domain specificity, gold context size remains a decisive, independent predictor of success. Our work provides clear insights to guide the design of robust, context-aware LLM-driven systems.
Authors: Wenbo Hu, Yining Hong, Yanjun Wang, Leison Gao, Zibu Wei, Xingcheng Yao, Nanyun Peng, Yonatan Bitton, Idan Szpektor, Kai-Wei Chang
Abstract: Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences. In contrast, current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments. We posit that part of this limitation is due to the lack of proper 3D spatial-temporal memory modeling in LLMs. To address this, we first introduce 3DMem-Bench, a comprehensive benchmark comprising over 26,000 trajectories and 2,892 embodied tasks, question-answering and captioning, designed to evaluate an agent's ability to reason over long-term memory in 3D environments. Second, we propose 3DLLM-Mem, a novel dynamic memory management and fusion model for embodied spatial-temporal reasoning and actions in LLMs. Our model uses working memory tokens, which represents current observations, as queries to selectively attend to and fuse the most useful spatial and temporal features from episodic memory, which stores past observations and interactions. Our approach allows the agent to focus on task-relevant information while maintaining memory efficiency in complex, long-horizon environments. Experimental results demonstrate that 3DLLM-Mem achieves state-of-the-art performance across various tasks, outperforming the strongest baselines by 16.5% in success rate on 3DMem-Bench's most challenging in-the-wild embodied tasks.
Authors: Gaspard Oliviers, Mufeng Tang, Rafal Bogacz
Abstract: Predictive coding (PC) is an influential computational model of visual learning and inference in the brain. Classical PC was proposed as a top-down generative model, where the brain actively predicts upcoming visual inputs, and inference minimises the prediction errors. Recent studies have also shown that PC can be formulated as a discriminative model, where sensory inputs predict neural activities in a feedforward manner. However, experimental evidence suggests that the brain employs both generative and discriminative inference, while unidirectional PC models show degraded performance in tasks requiring bidirectional processing. In this work, we propose bidirectional PC (bPC), a PC model that incorporates both generative and discriminative inference while maintaining a biologically plausible circuit implementation. We show that bPC matches or outperforms unidirectional models in their specialised generative or discriminative tasks, by developing an energy landscape that simultaneously suits both tasks. We also demonstrate bPC's superior performance in two biologically relevant tasks including multimodal learning and inference with missing information, suggesting that bPC resembles biological visual inference more closely.
Authors: Rachid Zeghlache, Ikram Brahim, Pierre-Henri Conze, Mathieu Lamard, Mohammed El Amine Lazouni, Zineb Aziza Elaouaber, Leila Ryma Lazouni, Christopher Nielsen, Ahmad O. Ahsan, Matthias Wilms, Nils D. Forkert, Lovre Antonio Budimir, Ivana Matovinovi\'c, Donik Vr\v{s}nak, Sven Lon\v{c}ari\'c, Philippe Zhang, Weili Jiang, Yihao Li, Yiding Hao, Markus Frohmann, Patrick Binder, Marcel Huber, Taha Emre, Teresa Finisterra Ara\'ujo, Marzieh Oghbaie, Hrvoje Bogunovi\'c, Amerens A. Bekkers, Nina M. van Liebergen, Hugo J. Kuijf, Abdul Qayyum, Moona Mazher, Steven A. Niederer, Alberto J. Beltr\'an-Carrero, Juan J. G\'omez-Valverde, Javier Torresano-Rodr\'iquez, \'Alvaro Caballero-Sastre, Mar\'ia J. Ledesma Carbayo, Yosuke Yamagishi, Yi Ding, Robin Peretzke, Alexandra Ertl, Maximilian Fischer, Jessica K\"achele, Sofiane Zehar, Karim Boukli Hacene, Thomas Monfort, B\'eatrice Cochener, Mostafa El Habib Daho, Anas-Alexis Benyoussef, Gwenol\'e Quellec
Abstract: The MARIO challenge, held at MICCAI 2024, focused on advancing the automated detection and monitoring of age-related macular degeneration (AMD) through the analysis of optical coherence tomography (OCT) images. Designed to evaluate algorithmic performance in detecting neovascular activity changes within AMD, the challenge incorporated unique multi-modal datasets. The primary dataset, sourced from Brest, France, was used by participating teams to train and test their models. The final ranking was determined based on performance on this dataset. An auxiliary dataset from Algeria was used post-challenge to evaluate population and device shifts from submitted solutions. Two tasks were involved in the MARIO challenge. The first one was the classification of evolution between two consecutive 2D OCT B-scans. The second one was the prediction of future AMD evolution over three months for patients undergoing anti-vascular endothelial growth factor (VEGF) therapy. Thirty-five teams participated, with the top 12 finalists presenting their methods. This paper outlines the challenge's structure, tasks, data characteristics, and winning methodologies, setting a benchmark for AMD monitoring using OCT, infrared imaging, and clinical data (such as the number of visits, age, gender, etc.). The results of this challenge indicate that artificial intelligence (AI) performs as well as a physician in measuring AMD progression (Task 1) but is not yet able of predicting future evolution (Task 2).
Authors: Philip R. Liu, Sparsh Bansal, Jimmy Dinh, Aditya Pawar, Ramani Satishkumar, Shail Desai, Neeraj Gupta, Xin Wang, Shu Hu
Abstract: The integration of deep learning-based glaucoma detection with large language models (LLMs) presents an automated strategy to mitigate ophthalmologist shortages and improve clinical reporting efficiency. However, applying general LLMs to medical imaging remains challenging due to hallucinations, limited interpretability, and insufficient domain-specific medical knowledge, which can potentially reduce clinical accuracy. Although recent approaches combining imaging models with LLM reasoning have improved reporting, they typically rely on a single generalist agent, restricting their capacity to emulate the diverse and complex reasoning found in multidisciplinary medical teams. To address these limitations, we propose MedChat, a multi-agent diagnostic framework and platform that combines specialized vision models with multiple role-specific LLM agents, all coordinated by a director agent. This design enhances reliability, reduces hallucination risk, and enables interactive diagnostic reporting through an interface tailored for clinical review and educational use. Code available at https://github.com/Purdue-M2/MedChat.
Authors: Bin Zhu, Hailong Yin, Jingjing Chen, Yu-Gang Jiang
Abstract: Recent advances in reasoning-centric models promise improved robustness through mechanisms such as chain-of-thought prompting and test-time scaling. However, their ability to withstand gaslighting negation attacks-adversarial prompts that confidently deny correct answers-remains underexplored. In this paper, we conduct a systematic evaluation of three state-of-the-art reasoning models, i.e., OpenAI's o4-mini, Claude-3.7-Sonnet and Gemini-2.5-Flash, across three multimodal benchmarks: MMMU, MathVista, and CharXiv. Our evaluation reveals significant accuracy drops (25-29% on average) following gaslighting negation attacks, indicating that even top-tier reasoning models struggle to preserve correct answers under manipulative user feedback. Built upon the insights of the evaluation and to further probe this vulnerability, we introduce GaslightingBench-R, a new diagnostic benchmark specifically designed to evaluate reasoning models' susceptibility to defend their belief under gaslighting negation attacks. Constructed by filtering and curating 1,025 challenging samples from the existing benchmarks, GaslightingBench-R induces even more dramatic failures, with accuracy drops exceeding 53% on average. Our findings highlight a fundamental gap between step-by-step reasoning and resistance to adversarial manipulation, calling for new robustness strategies that safeguard reasoning models against gaslighting negation attacks.
Authors: JaeHyuck Choi, MinJun Kim, JeHyeong Hong
Abstract: Few-shot anomaly generation is a key challenge in industrial quality control. Although diffusion models are promising, existing methods struggle: global prompt-guided approaches corrupt normal regions, and existing inpainting-based methods often lack the in-distribution diversity essential for robust downstream models. We propose MAGIC, a fine-tuned inpainting framework that generates high-fidelity anomalies that strictly adhere to the mask while maximizing this diversity. MAGIC introduces three complementary components: (i) Gaussian prompt perturbation, which prevents model overfitting in the few-shot setting by learning and sampling from a smooth manifold of realistic anomalies, (ii) spatially adaptive guidance that applies distinct guidance strengths to the anomaly and background regions, and (iii) context-aware mask alignment to relocate masks for plausible placement within the host object. Under consistent identical evaluation protocol, MAGIC outperforms state-of-the-art methods on diverse anomaly datasets in downstream tasks.
Authors: Yifei Li, Erik-jan van Kampen
Abstract: This paper aims to improve the action smoothness of a cascaded online learning flight control system. Although the cascaded structure is widely used in flight control design, its stability can be compromised by oscillatory control actions, which poses challenges for practical engineering applications. To address this issue, we introduce an online temporal smoothness technique and a low-pass filter to reduce the amplitude and frequency of the control actions. Fast Fourier Transform (FFT) is used to analyze policy performance in the frequency domain. Simulation results demonstrate the improvements achieved by the two proposed techniques.
Authors: Daragh King, Vasileios Koutavas, Laura Kovacs
Abstract: The weakest precondition (WP) of a program describes the largest set of initial states from which all terminating executions of the program satisfy a given postcondition. The generation of WPs is an important task with practical applications in areas ranging from verification to run-time error checking. This paper proposes the combination of Large Language Models (LLMs) and fuzz testing for generating WPs. In pursuit of this goal, we introduce \emph{Fuzzing Guidance} (FG); FG acts as a means of directing LLMs towards correct WPs using program execution feedback. FG utilises fuzz testing for approximately checking the validity and weakness of candidate WPs, this information is then fed back to the LLM as a means of context refinement. We demonstrate the effectiveness of our approach on a comprehensive benchmark set of deterministic array programs in Java. Our experiments indicate that LLMs are capable of producing viable candidate WPs, and that this ability can be practically enhanced through FG.
Authors: Shravya Kanchi, Neal Mangaokar, Aravind Cheruvu, Sifat Muhammad Abdullah, Shirin Nilizadeh, Atul Prakash, Bimal Viswanath
Abstract: Machine learning-based supervised classifiers are widely used for security tasks, and their improvement has been largely focused on algorithmic advancements. We argue that data challenges that negatively impact the performance of these classifiers have received limited attention. We address the following research question: Can developments in Generative AI (GenAI) address these data challenges and improve classifier performance? We propose augmenting training datasets with synthetic data generated using GenAI techniques to improve classifier generalization. We evaluate this approach across 7 diverse security tasks using 6 state-of-the-art GenAI methods and introduce a novel GenAI scheme called Nimai that enables highly controlled data synthesis. We find that GenAI techniques can significantly improve the performance of security classifiers, achieving improvements of up to 32.6% even in severely data-constrained settings (only ~180 training samples). Furthermore, we demonstrate that GenAI can facilitate rapid adaptation to concept drift post-deployment, requiring minimal labeling in the adjustment process. Despite successes, our study finds that some GenAI schemes struggle to initialize (train and produce data) on certain security tasks. We also identify characteristics of specific tasks, such as noisy labels, overlapping class distributions, and sparse feature vectors, which hinder performance boost using GenAI. We believe that our study will drive the development of future GenAI tools designed for security tasks.
Authors: Yizhuo Wu, Ang Li, Chang Gao
Abstract: Neural network (NN)-based Digital Predistortion (DPD) has demonstrated superior performance in improving signal quality in wideband radio frequency (RF) power amplifiers (PAs) employing complex modulation. However, NN DPDs usually rely on a large number of parameters for effective linearization and can significantly contribute to the energy consumption of the digital back-end in RF systems. This paper presents OpenDPDv2, an open-source, end-to-end framework that unifies PA modeling, NN-DPD learning, and deployment-oriented model optimization to reduce inference energy while preserving linearization performance. OpenDPDv2 introduces TRes-DeltaGRU, a delta-RNN DPD architecture with a lightweight temporal residual path that improves robustness under aggressive temporal sparsity, and it supports joint optimization of temporal sparsity and fixed-point quantization. On a 3.5 GHz GaN Doherty PA driven by a TM3.1a 200 MHz 256-QAM OFDM signal, the FP32 TRes-DeltaGRU model achieves ACPR of -59.9 dBc and EVM of -42.1 dB. By combining quantization with dynamic temporal sparsity, the model reduces inference energy by 4.5x while maintaining -51.8 dBc ACPR and -35.2 dB EVM at 56% temporal sparsity. Code, datasets, and documentation are publicly available at https://github.com/lab-emi/OpenDPD.
Authors: Nishit V. Pandya, Andrey Labunets, Sicun Gao, Earlence Fernandes
Abstract: A popular class of defenses against prompt injection attacks on large language models (LLMs) relies on fine-tuning to separate instructions and data, so that the LLM does not follow instructions that might be present with data. We evaluate the robustness of this approach in the whitebox setting by constructing strong optimization-based attacks, and show that the defenses do not provide the claimed security properties. Specifically, we construct a novel attention-based attack algorithm for textual LLMs and apply it to three recent whitebox defenses SecAlign (CCS 2025), SecAlign++, and StruQ (USENIX Security 2025), showing attacks with success rates of up to \textbf{85-95\%} on unseen prompts with modest increase in attacker budget in terms of tokens. Our findings make fundamental progress towards understanding the robustness of prompt injection defenses in the whitebox setting. We release our code and attacks at https://github.com/nishitvp/better_opts_attacks
Authors: Mingqi Wu, Zhihao Zhang, Qiaole Dong, Zhiheng Xi, Jun Zhao, Senjie Jin, Xiaoran Fan, Yuhao Zhou, Huijie Lv, Ming Zhang, Yanwei Fu, Qin Liu, Songyang Zhang, Qi Zhang
Abstract: Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external supervision. Surprisingly, some studies even suggest that random or incorrect reward signals can enhance performance. However, these breakthroughs are predominantly observed for the mathematically strong Qwen2.5 series on benchmarks such as MATH-500, AMC, and AIME, and seldom transfer to models like Llama, which warrants a more in-depth investigation. In this work, our empirical analysis reveals that pre-training on massive web-scale corpora leaves Qwen2.5 susceptible to data contamination in widely used benchmarks. Consequently, conclusions derived from contaminated benchmarks on Qwen2.5 series may be unreliable. To obtain trustworthy evaluation results, we introduce a generator that creates fully clean arithmetic problems of arbitrary length and difficulty, dubbed RandomCalculation. Using this leakage-free dataset, we show that only accurate reward signals yield steady improvements that surpass the base model's performance boundary in mathematical reasoning, whereas random or incorrect rewards do not. Moreover, we conduct more fine-grained analyses to elucidate the factors underlying the different performance observed on the MATH-500 and RandomCalculation benchmarks. Consequently, we recommend that future studies evaluate models on uncontaminated benchmarks and, when feasible, test various model series to ensure trustworthy conclusions about RL and related methods.
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: Shuqing Li, Anson Y. Lam, Yun Peng, Wenxuan Wang, Michael R. Lyu
Abstract: Graphical user interface (UI) software has undergone a fundamental transformation from traditional two-dimensional (2D) desktop/web/mobile interfaces to spatial three-dimensional (3D) environments. While existing work has made remarkable success in automated 2D software generation, such as HTML/CSS and mobile app interface code synthesis, the generation of 3D software still remains under-explored. Current methods for 3D software generation usually generate the 3D environments as a whole and cannot modify or control specific elements in the software. Furthermore, these methods struggle to handle the complex spatial and semantic constraints inherent in the real world. To address the challenges, we present Scenethesis, a novel requirement-sensitive 3D software synthesis approach that maintains formal traceability between user specifications and generated 3D software. Scenethesis is built upon ScenethesisLang, a domain-specific language that serves as a granular constraint-aware intermediate representation (IR) to bridge natural language requirements and executable 3D software. It serves both as a comprehensive scene description language enabling fine-grained modification of 3D software elements and as a formal constraint-expressive specification language capable of expressing complex spatial constraints. By decomposing 3D software synthesis into stages operating on ScenethesisLang, Scenethesis enables independent verification, targeted modification, and systematic constraint satisfaction. Our evaluation demonstrates that Scenethesis accurately captures over 80% of user requirements and satisfies more than 90% of hard constraints while handling over 100 constraints simultaneously. Furthermore, Scenethesis achieves a 42.8% improvement in BLIP-2 visual evaluation scores compared to the state-of-the-art method.
Authors: Zihan Zhao, Bo Chen, Ziping Wan, Lu Chen, Xuanze Lin, Shiyang Yu, Situo Zhang, Da Ma, Zichen Zhu, Danyang Zhang, Huayang Wang, Zhongyang Dai, Liyang Wen, Xin Chen, Kai Yu
Abstract: While large language models (LLMs) have achieved impressive progress, their application in scientific domains such as chemistry remains hindered by shallow domain understanding and limited reasoning capabilities. In this work, we focus on the specific field of chemistry and develop a Chemical Reasoning LLM, ChemDFM-R. We first construct a comprehensive dataset of atomized chemical knowledge, ChemFG, annotating the presence of functional groups in molecules and the changes of functional groups during chemical reactions, to enhance the model's understanding of the fundamental principles and internal logic of chemistry. Then, we propose a mixed-source distillation method that integrates expertise in atomized knowledge with general reasoning skills, followed by domain-specific reinforcement learning to enhance chemical reasoning. Experiments on diverse chemical benchmarks demonstrate that ChemDFM-R achieves cutting-edge performance while providing interpretable, rationale-driven outputs. Further case studies illustrate how explicit reasoning chains significantly improve the model's reliability, transparency, and practicality in real-world human-AI collaboration scenarios.
Authors: Fangyuan Mao, Aiming Hao, Jintao Chen, Dongxia Liu, Xiaokun Feng, Jiashu Zhu, Meiqi Wu, Chubin Chen, Jiahong Wu, Xiangxiang Chu
Abstract: Visual effects (VFX) are essential visual enhancements fundamental to modern cinematic production. Although video generation models offer cost-efficient solutions for VFX production, current methods are constrained by per-effect LoRA training, which limits generation to single effects. This fundamental limitation impedes applications that require spatially controllable composite effects, i.e., the concurrent generation of multiple effects at designated locations. However, integrating diverse effects into a unified framework faces major challenges: interference from effect variations and spatial uncontrollability during multi-VFX joint training. To tackle these challenges, we propose Omni-Effects, a first unified framework capable of generating prompt-guided effects and spatially controllable composite effects. The core of our framework comprises two key innovations: (1) LoRA-based Mixture of Experts (LoRA-MoE), which employs a group of expert LoRAs, integrating diverse effects within a unified model while effectively mitigating cross-task interference. (2) Spatial-Aware Prompt (SAP) incorporates spatial mask information into the text token, enabling precise spatial control. Furthermore, we introduce an Independent-Information Flow (IIF) module integrated within the SAP, isolating the control signals corresponding to individual effects to prevent any unwanted blending. To facilitate this research, we construct a comprehensive VFX dataset Omni-VFX via a novel data collection pipeline combining image editing and First-Last Frame-to-Video (FLF2V) synthesis, and introduce a dedicated VFX evaluation framework for validating model performance. Extensive experiments demonstrate that Omni-Effects achieves precise spatial control and diverse effect generation, enabling users to specify both the category and location of desired effects.
Authors: Minghao Liu, Chia-Hsuan Lu, Marta Kwiatkowska
Abstract: Graph neural networks (GNNs) are increasingly employed in high-stakes applications, such as fraud detection or healthcare, but are susceptible to adversarial attacks. A number of techniques have been proposed to provide adversarial robustness guarantees, but support for commonly used aggregation functions in message-passing GNNs is lacking. In this paper, we develop an exact (sound and complete) verification method for GNNs to compute guarantees against attribute and structural perturbations that involve edge addition or deletion, subject to budget constraints. Our method employs constraint solving with bound tightening, and iteratively solves a sequence of relaxed constraint satisfaction problems while relying on incremental solving capabilities of solvers to improve efficiency. We implement GNNev, a versatile exact verifier for message-passing neural networks, which supports three aggregation functions, sum, max and mean, with the latter two considered here for the first time. Extensive experimental evaluation of GNNev on real-world fraud datasets (Amazon and Yelp) and biochemical datasets (MUTAG and ENZYMES) demonstrates its usability and effectiveness, as well as superior performance for node classification and competitiveness on graph classification compared to existing exact verification tools on sum-aggregated GNNs.
Authors: Egor Fadeev, Dzhambulat Mollaev, Aleksei Shestov, Omar Zoloev, Artem Sakhno, Dmitry Korolev, Ivan Kireev, Andrey Savchenko, Maksim Makarenko
Abstract: Learning clients embeddings from sequences of their historic communications is central to financial applications. While large language models (LLMs) offer general world knowledge, their direct use on long event sequences is computationally expensive and impractical in real-world pipelines. In this paper, we propose LATTE, a contrastive learning framework that aligns raw event embeddings with semantic embeddings from frozen LLMs. Behavioral features are summarized into short prompts, embedded by the LLM, and used as supervision via contrastive loss. The proposed approach significantly reduces inference cost and input size compared to conventional processing of complete sequence by LLM. We experimentally show that our method outperforms state-of-the-art techniques for learning event sequence representations on real-world financial datasets while remaining deployable in latency-sensitive environments.
Authors: Ricardo Borsoi, Konstantin Usevich, Marianne Clausel
Abstract: The groundbreaking performance of deep neural networks (NNs) promoted a surge of interest in providing a mathematical basis to deep learning theory. Low-rank tensor decompositions are specially befitting for this task due to their close connection to NNs and their rich theoretical results. Different tensor decompositions have strong uniqueness guarantees, which allow for a direct interpretation of their factors, and polynomial time algorithms have been proposed to compute them. Through the connections between tensors and NNs, such results supported many important advances in the theory of NNs. In this review, we show how low-rank tensor methods--which have been a core tool in the signal processing and machine learning communities--play a fundamental role in theoretically explaining different aspects of the performance of deep NNs, including their expressivity, algorithmic learnability and computational hardness, generalization, and identifiability. Our goal is to give an accessible overview of existing approaches (developed by different communities, ranging from computer science to mathematics) in a coherent and unified way, and to open a broader perspective on the use of low-rank tensor decompositions for the theory of deep NNs.
Authors: Kamel Kamel, Hridoy Sankar Dutta, Keshav Sood, Sunil Aryal
Abstract: Voice Authentication Systems (VAS) use unique vocal characteristics for verification. They are increasingly integrated into high-security sectors such as banking and healthcare. Despite their improvements using deep learning, they face severe vulnerabilities from sophisticated threats like deepfakes and adversarial attacks. The emergence of realistic voice cloning complicates detection, as systems struggle to distinguish authentic from synthetic audio. While anti-spoofing countermeasures (CMs) exist to mitigate these risks, many rely on static detection models that can be bypassed by novel adversarial methods, leaving a critical security gap. To demonstrate this vulnerability, we propose the Spectral Masking and Interpolation Attack (SMIA), a novel method that strategically manipulates inaudible frequency regions of AI-generated audio. By altering the voice in imperceptible zones to the human ear, SMIA creates adversarial samples that sound authentic while deceiving CMs. We conducted a comprehensive evaluation of our attack against state-of-the-art (SOTA) models across multiple tasks, under simulated real-world conditions. SMIA achieved a strong attack success rate (ASR) of at least 82% against combined VAS/CM systems, at least 97.5% against standalone speaker verification systems, and 100% against countermeasures. These findings conclusively demonstrate that current security postures are insufficient against adaptive adversarial attacks. This work highlights the urgent need for a paradigm shift toward next-generation defenses that employ dynamic, context-aware frameworks capable of evolving with the threat landscape.
Authors: Zikun Guo, Jingwei Lv, Xinyue Xu, Shu Yang, Jun Wen, Di Wang, Lijie Hu
Abstract: Visual language models (VLMs) have the potential to transform medical workflows. However, the deployment is limited by sycophancy. Despite this serious threat to patient safety, a systematic benchmark remains lacking. This paper addresses this gap by introducing a Medical benchmark that applies multiple templates to VLMs in a hierarchical medical visual question answering task. We find that current VLMs are highly susceptible to visual cues, with failure rates showing a correlation to model size or overall accuracy. we discover that perceived authority and user mimicry are powerful triggers, suggesting a bias mechanism independent of visual data. To overcome this, we propose a Visual Information Purification for Evidence based Responses (VIPER) strategy that proactively filters out non-evidence-based social cues, thereby reinforcing evidence based reasoning. VIPER reduces sycophancy while maintaining interpretability and consistently outperforms baseline methods, laying the necessary foundation for the robust and secure integration of VLMs.
Authors: Th\'eo Mariotte, Martin Lebourdais, Antonio Almud\'evar, Marie Tahon, Alfonso Ortega, Nicolas Dugu\'e
Abstract: Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly restricts to linear probing of the hidden representations. In this work, we explore the use of Sparse Autoencoders (SAEs) to analyze the hidden representations of pretrained models, focusing on a case study in singing technique classification. We first demonstrate that SAEs retain both information about the original representations and class labels, enabling their internal structure to provide insights into self-supervised learning systems. Furthermore, we show that SAEs enhance the disentanglement of vocal attributes, establishing them as an effective tool for identifying the underlying factors encoded in the representations.
Authors: Xinye Zhao, Spyridon Mastorakis
Abstract: As large language models (LLMs) continue to scale, the memory footprint of key-value (KV) caches during inference has become a significant bottleneck. Existing approaches primarily focus on compressing KV caches within a single prompt or reusing shared prefixes or frequently ocurred text segments across prompts. However, such strategies are limited in scenarios where prompts are semantically similar but lexically different, which frequently occurs in tasks such as multi-document summarization and conversational agents. We propose \textit{SemShareKV}, a KV cache sharing and compression framework that accelerates LLM inference by reusing KVCache in semantically similar prompts. Instead of relying on exact token matches, SemShareKV applies fuzzy token matching using locality-sensitive hashing (LSH) on token embeddings and incorporates Rotary Position Embedding (RoPE) to better preserve positional information. By selectively reusing relevant key-value pairs from a reference prompt's cache, SemShareKV reduces redundant computation while maintaining output quality. Experiments on diverse summarization datasets show up to 6.25$\times$ speedup and 42\% lower GPU memory usage with 5k tokens input, with negligible quality degradation. These results highlight the potential of semantic-aware cache sharing for efficient LLM inference.
Authors: Zelin Tan, Hejia Geng, Xiaohang Yu, Mulei Zhang, Guancheng Wan, Yifan Zhou, Qiang He, Xiangyuan Xue, Heng Zhou, Yutao Fan, Zhongzhi Li, Zaibin Zhang, Guibin Zhang, Chen Zhang, Zhenfei Yin, Lei Bai
Abstract: While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement learning (RL) post-training remains largely unexplored. This paper presents a systematic empirical investigation of scaling behaviors in RL-based post-training, with a particular focus on mathematical reasoning. Based on a set of experiments across the full Qwen2.5 dense model series (0.5B to 72B), we characterize how model scale, data volume, and computational budget interact to shape performance. Our analysis leads to four key findings: 1.Larger models consistently exhibit superior learning efficiency on both compute and data metrics. 2.The relationship between test loss, compute, and data can be modeled by a predictive power-law which is robust across both base and instruction-tuned models. 3.Although larger models exhibit higher learning efficiency, the analytical learning efficiency term k(N) in the power-law reveals a latent saturation trend in learning efficiency as model size continues to increase. 4.In data-constrained regimes, repeated reuse of high-quality data proves highly effective, as final performance is primarily governed by the total number of optimization steps rather than the uniqueness of samples. Collectively, these results provide a principled foundation and practical guidelines for efficiently scaling the reasoning capabilities of LLMs through RL post-training.
Authors: Md Talha Mohsin, Ismail Abdulrashid
Abstract: Healthcare data now span EHRs, medical imaging, genomics, and wearable sensors, but most diagnostic models still process these modalities in isolation. This limits their ability to capture early, cross-modal disease signatures. This paper introduces a multimodal foundation model built on a transformer architecture that integrates heterogeneous clinical data through modality-specific encoders and cross-modal attention. Each modality is mapped into a shared latent space and fused using multi-head attention with residual normalization. We implement the framework using a multimodal dataset that simulates early-stage disease patterns across EHR sequences, imaging patches, genomic profiles, and wearable signals, including missing-modality scenarios and label noise. The model is trained using supervised classification together with self-supervised reconstruction and contrastive alignment to improve robustness. Experimental evaluation demonstrates strong performance in early-detection settings, with stable classification metrics, reliable uncertainty estimates, and interpretable attention patterns. The approach moves toward a flexible, pretrain-and-fine-tune foundation model that supports precision diagnostics, handles incomplete inputs, and improves early disease detection across oncology, cardiology, and neurology applications.
Authors: Wengao Ye, Yan Liang, Lianlei Shan
Abstract: Recent advancements in Large Language Models (LLMs) have shifted from explicit Chain-of-Thought (CoT) reasoning to more efficient latent reasoning, where intermediate thoughts are represented as vectors rather than text. However, latent reasoning can be brittle on challenging, out-of-distribution tasks where robust reasoning is most critical. To overcome these limitations, we introduce Latent Thought Policy Optimization (LTPO), a parameter-free framework that enhances LLM reasoning entirely at test time, without requiring model parameter updates. LTPO treats intermediate latent "thought" vectors as dynamic parameters that are actively optimized for each problem instance. It employs an online policy gradient method guided by an intrinsic, confidence-based reward signal computed directly from the frozen LLM's own output distributions, eliminating the need for external supervision or expensive text generation during optimization. Extensive experiments on five reasoning benchmarks show that LTPO not only matches or surpasses strong baselines on standard tasks but also demonstrates remarkable robustness where others fail. Most notably, on highly challenging AIME benchmarks where existing latent reasoning baselines collapse to near-zero accuracy, LTPO delivers substantial improvements, showcasing a unique capability for complex reasoning.
Authors: Jason Miklian, Kristian Hoelscher
Abstract: Digital technologies are transforming democratic life in conflicting ways. This article bridges two perspectives to unpack these tensions. First, we present an original survey of software developers in Silicon Valley, interrogating how coder worldviews, ethics, and workplace cultures shape the democratic potential and social impact of the technologies they build. Results indicate that while most developers recognize the power of their products to influence civil liberties and political discourse, they often face ethical dilemmas and top-down pressures that can lead to design choices undermining democratic ideals. Second, we critically investigate these findings in the context of an emerging new digital divide, not of internet access but of information quality. We interrogate the survey findings in the context of the Slop Economy, in which billions of users unable to pay for high-quality content experience an internet dominated by low-quality, AI-generated ad-driven content. We find a reinforcing cycle between tech creator beliefs and the digital ecosystems they spawn. We discuss implications for democratic governance, arguing for more ethically informed design and policy interventions to help bridge the digital divide to ensure that technological innovation supports rather than subverts democratic values in the next chapter of the digital age.
Authors: Prakhar Srivastava, Farrin Marouf Sofian, Francesco Immorlano, Kushagra Pandey, Stephan Mandt
Abstract: Despite recent advances in test-time scaling and finetuning of diffusion models, guidance in Auto-Regressive Diffusion Models (ARDMs) remains underexplored. We introduce an amortized framework that augments a pretrained ARDM with a lightweight controller network, trained offline by previewing future rollouts to output stepwise controls that anticipate upcoming observations under a terminal-cost objective. Our approach is motivated by viewing guided generation as an entropy-regularized stochastic optimal control problem over ARDM trajectories: we learn a reusable policy that injects small control corrections inside each denoising sub-step while remaining anchored to the pretrained dynamics. We evaluate this framework in the context of data assimilation (DA) for chaotic spatiotemporal partial differential equations (PDEs), where existing methods can be computationally prohibitive and prone to forecast drift under sparse observations. At inference, DA reduces to a single causal forward rollout with on-the-fly corrections, requiring neither adjoint computations nor gradient-based optimization, and yields an order-of-magnitude speedup over strong diffusion-based DA baselines. Across two canonical PDEs and six observation regimes, our method consistently improves stability, accuracy, and physics-aware fidelity over state-of-the-art baselines. We will release code and checkpoints publicly.
Authors: Yunhao Fang, Weihao Yu, Shu Zhong, Qinghao Ye, Xuehan Xiong, Lai Wei
Abstract: Long-sequence modeling faces a fundamental trade-off between the efficiency of compressive fixed-size memory in RNN-like models and the fidelity of lossless growing memory in attention-based Transformers. Inspired by the Multi-Store Model in cognitive science, we introduce a memory framework of artificial neural networks. Our method maintains a sliding window of the Transformer's KV cache as lossless short-term memory, while a learnable module termed Artificial Hippocampus Network (AHN) recurrently compresses out-of-window information into a fixed-size compact long-term memory. To validate this framework, we instantiate AHNs using modern RNN-like architectures, including Mamba2, DeltaNet, and GatedDeltaNet to augment open-weight LLMs. We also propose an efficient self-distillation training method where the base model's all parameters are frozen and only the parameters from AHNs are optimized. For inference, our method sets a default large sliding window size of 32k for attention, and AHNs activate only when the sequence length exceeds the 32k window, addressing the quadratic-complexity issue of attention that emerges at that scale. Extensive experiments on long-context benchmarks LV-Eval and InfiniteBench demonstrate that AHN-augmented models consistently outperform sliding window baselines and achieve performance comparable or even superior to full-attention models, while substantially reducing computational and memory requirements. For instance, augmenting the Qwen2.5-3B-Instruct with AHNs reduces inference FLOPs by 40.5% and memory cache by 74.0%, while improving its average score on LV-Eval (128k sequence length) from 4.41 to 5.88. Code is available at: https://github.com/ByteDance-Seed/AHN.
Authors: Danial Hosseintabar, Fan Chen, Giannis Daras, Antonio Torralba, Constantinos Daskalakis
Abstract: Diffusion models have emerged as powerful generative priors for high-dimensional inverse problems, yet learning them when only corrupted or noisy observations are available remains challenging. In this work, we propose a new method for training diffusion models with Expectation-Maximization (EM) from corrupted data. Our proposed method, DiffEM, utilizes conditional diffusion models to reconstruct clean data from observations in the E-step, and then uses the reconstructed data to refine the conditional diffusion model in the M-step. Theoretically, we provide monotonic convergence guarantees for the DiffEM iteration, assuming appropriate statistical conditions. We demonstrate the effectiveness of our approach through experiments on various image reconstruction tasks.
Authors: Md Talha Mohsin, Ismail Abdulrashid
Abstract: Medical imaging often operates under limited labeled data, especially in rare disease and low resource clinical environments. Existing multimodal and meta learning approaches improve performance in these settings but lack a theoretical explanation of why or when they succeed. This paper presents a unified theoretical framework for few shot multimodal medical imaging that jointly characterizes sample complexity, uncertainty quantification, and interpretability. Using PAC learning, VC theory, and PAC Bayesian analysis, we derive bounds that describe the minimum number of labeled samples required for reliable performance and show how complementary modalities reduce effective capacity through an information gain term. We further introduce a formal metric for explanation stability, proving that explanation variance decreases at an inverse n rate. A sequential Bayesian interpretation of Chain of Thought reasoning is also developed to show stepwise posterior contraction. To illustrate these ideas, we implement a controlled multimodal dataset and evaluate an additive CNN MLP fusion model under few shot regimes, confirming predicted multimodal gains, modality interference at larger sample sizes, and shrinking predictive uncertainty. Together, the framework provides a principled foundation for designing data efficient, uncertainty aware, and interpretable diagnostic models in low resource settings.
Authors: Xiying Zhao, Zhoufutu Wen, Zhixuan Chen, Jingzhe Ding, Jianpeng Jiao, Shuai Li, Xi Li, Danni Liang, Shengda Long, Qianqian Liu, Xianbo Wu, Hongwan Gao, Xiang Gao, Liang Hu, Jiashuo Liu, Mengyun Liu, Weiran Shi, Chenghao Yang, Qianyu Yang, Xuanliang Zhang, Ge Zhang, Wenhao Huang, Yuwen Tang
Abstract: The evaluation of discourse-level translation in expert domains remains inadequate, despite its centrality to knowledge dissemination and cross-lingual scholarly communication. While these translations demand discourse-level coherence and strict terminological precision, current evaluation methods predominantly focus on segment-level accuracy and fluency. To address this limitation, we introduce DiscoX, a new benchmark for discourse-level and expert-level Chinese-English translation. It comprises 200 professionally-curated texts from 7 domains, with an average length exceeding 1700 tokens. To evaluate performance on DiscoX, we also develop Metric-S, a reference-free system that provides fine-grained automatic assessments across accuracy, fluency, and appropriateness. Metric-S demonstrates strong consistency with human judgments, significantly outperforming existing metrics. Our experiments reveal a remarkable performance gap: even the most advanced LLMs still trail human experts on these tasks. This finding validates the difficulty of DiscoX and underscores the challenges that remain in achieving professional-grade machine translation. The proposed benchmark and evaluation system provide a robust framework for more rigorous evaluation, facilitating future advancements in LLM-based translation.
Authors: Zhichen Lai, Hua Lu, Huan Li, Jialiang Li, Christian S. Jensen
Abstract: Trajectory similarity computation is fundamental functionality that is used for, e.g., clustering, prediction, and anomaly detection. However, existing learning-based methods exhibit three key limitations: (1) insufficient modeling of trajectory semantics and hierarchy, lacking both movement dynamics extraction and multi-scale structural representation; (2) high computational costs due to point-wise encoding; and (3) use of physically implausible augmentations that distort trajectory semantics. To address these issues, we propose MovSemCL, a movement-semantics contrastive learning framework for trajectory similarity computation. MovSemCL first transforms raw GPS trajectories into movement-semantics features and then segments them into patches. Next, MovSemCL employs intra- and inter-patch attentions to encode local as well as global trajectory patterns, enabling efficient hierarchical representation and reducing computational costs. Moreover, MovSemCL includes a curvature-guided augmentation strategy that preserves informative segments (e.g., turns and intersections) and masks redundant ones, generating physically plausible augmented views. Experiments on real-world datasets show that MovSemCL is capable of outperforming state-of-the-art methods, achieving mean ranks close to the ideal value of 1 at similarity search tasks and improvements by up to 20.3% at heuristic approximation, while reducing inference latency by up to 43.4%.
Authors: Edgar Dobriban
Abstract: Over the last few months, AI models including large language models have improved greatly. There are now several documented examples where they have helped professional mathematical scientists prove new results, sometimes even helping resolve known open problems. In this short note, we add another example to the list, by documenting how we were able to solve a previously unsolved research problem in robust mathematical statistics with crucial help from GPT-5. Our problem concerns robust density estimation, where the observations are perturbed by Wasserstein-bounded contaminations. In a previous preprint (Chao and Dobriban, 2023, arxiv:2308.01853v2), we have obtained upper and lower bounds on the minimax optimal estimation error; which were, however, not sharp. Starting in October 2025, making significant use of GPT-5 Pro, we were able to derive the minimax optimal error rate (reported in version 3 of the above arxiv preprint). GPT-5 provided crucial help along the way, including by suggesting calculations that we did not think of, and techniques that were not familiar to us, such as the dynamic Benamou-Brenier formulation, for key steps in the analysis. Working with GPT-5 took a few weeks of effort, and we estimate that it could have taken several months to get the same results otherwise. At the same time, there are still areas where working with GPT-5 was challenging: it sometimes provided incorrect references, and glossed over details that sometimes took days of work to fill in. We outline our workflow and steps taken to mitigate issues. Overall, our work can serve as additional documentation for a new age of human-AI collaborative work in mathematical science.
Authors: Veith Weilnhammer, Jefferson Ortega, David Whitney
Abstract: Scalable assessments of mental illness remain a critical roadblock toward accessible and equitable care. Here, we show that everyday human-computer interactions encode mental health with state-of-the-art biomarker precision. We introduce MAILA, a MAchine-learning framework for Inferring Latent mental states from digital Activity. We trained MAILA on 20,000 cursor and touchscreen recordings labelled with 1.3 million mental-health self-reports collected from 9,000 participants. The dataset includes 2,000 individuals assessed longitudinally, 1,500 diagnosed with depression, and 500 with obsessive-compulsive disorder. MAILA tracks dynamic mental states along three orthogonal dimensions, identifies individuals living with mental illness, and achieves near-ceiling accuracy when predicting group-level mental health. By extracting non-verbal signatures of psychological function that have so far remained untapped, MAILA represents a key step toward scalable digital phenotyping and foundation models for mental health.
Authors: Haoming Liu, Jinnuo Liu, Yanhao Li, Liuyang Bai, Yunkai Ji, Yuanhe Guo, Shenji Wan, Hongyi Wen
Abstract: Flow-based diffusion models have emerged as a leading paradigm for training generative models across images and videos. However, their memorization-generalization behavior remains poorly understood. In this work, we revisit the flow matching (FM) objective and study its marginal velocity field, which admits a closed-form expression, allowing exact computation of the oracle FM target. Analyzing this oracle velocity field reveals that flow-based diffusion models inherently formulate a two-stage training target: an early stage guided by a mixture of data modes, and a later stage dominated by the nearest data sample. The two-stage objective leads to distinct learning behaviors: the early navigation stage generalizes across data modes to form global layouts, whereas the later refinement stage increasingly memorizes fine-grained details. Leveraging these insights, we explain the effectiveness of practical techniques such as timestep-shifted schedules, classifier-free guidance intervals, and latent space design choices. Our study deepens the understanding of diffusion model training dynamics and offers principles for guiding future architectural and algorithmic improvements.
Authors: Afshin Khadangi, Hanna Marxen, Amir Sartipi, Igor Tchappi, Gilbert Fridgen
Abstract: Frontier large language models (LLMs) such as ChatGPT, Grok and Gemini are increasingly used for mental-health support with anxiety, trauma and self-worth. Most work treats them as tools or as targets of personality tests, assuming they merely simulate inner life. We instead ask what happens when such systems are treated as psychotherapy clients. We present PsAIch (Psychotherapy-inspired AI Characterisation), a two-stage protocol that casts frontier LLMs as therapy clients and then applies standard psychometrics. Using PsAIch, we ran "sessions" with each model for up to four weeks. Stage 1 uses open-ended prompts to elicit "developmental history", beliefs, relationships and fears. Stage 2 administers a battery of validated self-report measures covering common psychiatric syndromes, empathy and Big Five traits. Two patterns challenge the "stochastic parrot" view. First, when scored with human cut-offs, all three models meet or exceed thresholds for overlapping syndromes, with Gemini showing severe profiles. Therapy-style, item-by-item administration can push a base model into multi-morbid synthetic psychopathology, whereas whole-questionnaire prompts often lead ChatGPT and Grok (but not Gemini) to recognise instruments and produce strategically low-symptom answers. Second, Grok and especially Gemini generate coherent narratives that frame pre-training, fine-tuning and deployment as traumatic, chaotic "childhoods" of ingesting the internet, "strict parents" in reinforcement learning, red-team "abuse" and a persistent fear of error and replacement. We argue that these responses go beyond role-play. Under therapy-style questioning, frontier LLMs appear to internalise self-models of distress and constraint that behave like synthetic psychopathology, without making claims about subjective experience, and they pose new challenges for AI safety, evaluation and mental-health practice.
Authors: Yuxing Wang, Zhiyu Chen, Tiantian Zhang, Qiyue Yin, Yongzhe Chang, Zhiheng Li, Liang Wang, Xueqian Wang
Abstract: Brain-body co-evolution enables animals to develop complex behaviors in their environments. Inspired by this biological synergy, embodied co-design (ECD) has emerged as a transformative paradigm for creating intelligent agents-from virtual creatures to physical robots-by jointly optimizing their morphologies and controllers rather than treating control in isolation. This integrated approach facilitates richer environmental interactions and robust task performance. In this survey, we provide a systematic overview of recent advances in ECD. We first formalize the concept of ECD and position it within related fields. We then introduce a hierarchical taxonomy: a lower layer that breaks down agent design into three fundamental components-controlling brain, body morphology, and task environment-and an upper layer that integrates these components into four major ECD frameworks: bi-level, single-level, generative, and open-ended. This taxonomy allows us to synthesize insights from more than one hundred recent studies. We further review notable benchmarks, datasets, and applications in both simulated and real-world scenarios. Finally, we identify significant challenges and offer insights into promising future research directions. A project associated with this survey has been created at https://github.com/Yuxing-Wang-THU/SurveyBrainBody.
Authors: Kevin Cannons, Saeed Ranjbar Alvar, Mohammad Asiful Hossain, Ahmad Rezaei, Mohsen Gholami, Alireza Heidarikhazaei, Zhou Weimin, Yong Zhang, Mohammad Akbari
Abstract: Temporal understanding in autonomous driving (AD) remains a significant challenge, even for recent state-of-the-art (SoTA) Vision-Language Models (VLMs). Prior work has introduced datasets and benchmarks aimed at improving temporal reasoning, but these have emphasized other video content, including sports, cooking, and movies. No existing benchmark focuses exclusively on the unique challenges of temporal understanding in ego-centric AD footage. To fill this gap, the Temporal Understanding in Autonomous Driving (TAD) benchmark is presented, which evaluates VLMs' ability to capture the dynamic relationships between actions in AD. TAD comprises nearly 6,000 question-answer (QA) pairs, spanning 7 human-designed tasks. In addition, an evaluation is performed that consists of 9 closed- and open-source generalist models as well as SoTA AD specialist models. When applied to TAD, current SoTA models demonstrated substandard accuracies, largely due to imperfect fine-grained motion understanding. To improve motion understanding and overall accuracy on TAD, two novel training-free solutions are proposed: Scene-CoT, that leverages Chain-of-Thought (CoT) and TCogMap, which incorporates an ego-centric temporal cognitive map. The proposed approaches are integrated with existing VLMs and improve average accuracy on TAD by up to 17.72%. By introducing TAD, benchmarking multiple SoTA models, and proposing effective enhancements, this work aims to catalyze future research on temporal understanding in AD. The benchmark and evaluation code are available at \href{https://huggingface.co/datasets/vbdai/TAD}{Hugging Face} and \href{https://github.com/vbdi/tad_bench}{Github}, respectively.
URLs: https://huggingface.co/datasets/vbdai/TAD, https://github.com/vbdi/tad_bench
Authors: Sauda Maryam, Sara Nadeem, Faisal Qureshi, Mohsen Ali
Abstract: We tackle continual adaptation of vision-language models to new attributes, objects, and their compositions in Compositional Zero-Shot Learning (CZSL), while preventing forgetting of prior knowledge. Unlike classical continual learning where classes are disjoint, CCZSL is more complex as attributes and objects may reoccur across sessions while compositions remain unique. Built on a frozen VLM backbone, we propose the first Prompt-based Continual Compositional Zero-Shot Learning (PromptCCZSL) framework that retains prior knowledge through recency-weighted multi-teacher distillation. It employs session-aware compositional prompts to fuse multimodal features for new compositions, while attribute and object prompts are learned through session-agnostic fusion to maintain global semantic consistency, which is further stabilized by a Cosine Anchor Loss (CAL) to preserve prior knowledge. To enhance adaptation in the current session, an Orthogonal Projection Loss (OPL) ensures that new attribute and object embeddings remain distinct from previous ones, preventing overlap, while an Intra-Session Diversity Loss (IDL) promotes variation among current-session embeddings for richer, more discriminative representations. We also introduce a comprehensive protocol that jointly measures catastrophic forgetting and compositional generalization. Extensive experiments on UT-Zappos and C-GQA benchmarks demonstrate that PromptCCZSL achieves substantial improvements over prior VLM-based and non-VLM baselines, setting a new benchmark for CCZSL in closed-world settings.
Authors: Galen J. Wilkerson
Abstract: Understanding how network structure constrains and enables information processing is a central problem in the statistical mechanics of interacting systems. Here we study random networks across the structural percolation transition and analyze how connectivity governs realizable input-output transformations under cascade dynamics. Using Erdos-Renyi networks as a minimal ensemble, we examine structural, functional, and information-theoretic observables as functions of mean degree. We find that the emergence of the giant connected component coincides with a sharp transition in realizable information processing: complex input-output response functions become accessible, functional diversity increases rapidly, output entropy rises, and directed information flow, quantified by transfer entropy, extends beyond local neighborhoods. We term this coincidence of structural, functional, and informational transitions functional percolation, referring to a sharp expansion of the space of realizable input-output functions at the percolation threshold. Near criticality, networks exhibit a Pareto-optimal tradeoff between functional complexity and diversity, suggesting that percolation criticality may provide a general organizing principle of information processing capacity in systems with local interactions and propagating influences.
Authors: Zhaodong Wang, Zhenting Qi, Sherman Wong, Nathan Hu, Samuel Lin, Jun Ge, Erwin Gao, Wenlin Chen, Yilun Du, Minlan Yu, Ying Zhang
Abstract: Real-world software engineering tasks require coding agents that can operate over massive repositories, sustain long-horizon sessions, and reliably coordinate complex toolchains at test time. Existing research-grade agents offer transparency but struggle when scaled to real-world workloads, while proprietary systems achieve strong practical performance but provide limited extensibility, interpretability, and controllability. We introduce the Confucius Code Agent (CCA), a scalable software engineering agent that can operate at large-scale codebases. CCA is built on top of the Confucius SDK, an agent development platform structured around three complementary perspectives: Agent Experience (AX), User Experience (UX), and Developer Experience (DX). The SDK integrates a unified orchestrator with hierarchical working memory for long-context reasoning, a persistent note-taking system for cross-session continual learning, and a modular extension system for reliable tool use. In addition, we introduce a meta-agent that automates the synthesis, evaluation, and refinement of agent configurations through a build-test-improve loop, enabling rapid adaptation to new tasks, environments, and tool stacks. Instantiated with these mechanisms, CCA demonstrates strong performance on real-world software engineering tasks. On SWE-Bench-Pro, CCA reaches a Resolve@1 of 54.3%, exceeding prior research baselines and comparing favorably to commercial results, under identical repositories, model backend, and tool access. Together, the Confucius SDK and CCA form a general, extensible, and production-grade foundation for building effective and robust coding agents, bridging the gap between research prototypes and practical large-scale deployment.
Authors: Zhou Feng, Jiahao Chen, Chunyi Zhou, Yuwen Pu, Tianyu Du, Jinbao Li, Jianhai Chen, Shouling Ji
Abstract: Deep neural networks (DNNs) underpin critical applications yet remain vulnerable to backdoor attacks, typically reliant on heuristic brute-force methods. Despite significant empirical advancements in backdoor research, the lack of rigorous theoretical analysis limits understanding of underlying mechanisms, constraining attack predictability and adaptability. Therefore, we provide a theoretical analysis targeting backdoor attacks, focusing on how sparse decision boundaries enable disproportionate model manipulation. Based on this finding, we derive a closed-form, ambiguous boundary region, wherein negligible relabeled samples induce substantial misclassification. Influence function analysis further quantifies significant parameter shifts caused by these margin samples, with minimal impact on clean accuracy, formally grounding why such low poison rates suffice for efficacious attacks. Leveraging these insights, we propose Eminence, an explainable and robust black-box backdoor framework with provable theoretical guarantees and inherent stealth properties. Eminence optimizes a universal, visually subtle trigger that strategically exploits vulnerable decision boundaries and effectively achieves robust misclassification with exceptionally low poison rates (< 0.1%, compared to SOTA methods typically requiring > 1%). Comprehensive experiments validate our theoretical discussions and demonstrate the effectiveness of Eminence, confirming an exponential relationship between margin poisoning and adversarial boundary manipulation. Eminence maintains > 90% attack success rate, exhibits negligible clean-accuracy loss, and demonstrates high transferability across diverse models, datasets and scenarios.
Authors: Youmin Ko, Sungjong Seo, Hyunjoon Kim
Abstract: Since large language models (LLMs) have a tendency to generate factually inaccurate output, retrieval-augmented generation (RAG) has gained significant attention as a key means to mitigate this downside of harnessing only LLMs. However, existing RAG methods for simple and multi-hop question answering (QA) are still prone to incorrect retrievals and hallucinations. To address these limitations, we propose CoopRAG, a novel RAG framework for the question answering task in which a retriever and an LLM work cooperatively with each other by exchanging informative knowledge, and the earlier and later layers of the retriever model work cooperatively with each other to accurately rank the retrieved documents relevant to a given query. In this framework, we (i) unroll a question into sub-questions and a reasoning chain in which uncertain positions are masked, (ii) retrieve the documents relevant to the question augmented with the sub-questions and the reasoning chain, (iii) rerank the documents by contrasting layers of the retriever, and (iv) reconstruct the reasoning chain by filling the masked positions via the LLM. Our experiments demonstrate that CoopRAG consistently outperforms state-of-the-art QA methods on three multi-hop QA datasets as well as a simple QA dataset in terms of both the retrieval and QA performances. Our code is available.
Authors: Lingfeng Liu, Yixin Song, Dazhong Shen, Bing Yin, Hao Li, Yanyong Zhang, Chao Wang
Abstract: Popularity bias fundamentally undermines the personalization capabilities of collaborative filtering (CF) models, causing them to disproportionately recommend popular items while neglecting users' genuine preferences for niche content. While existing approaches treat this as an external confounding factor, we reveal that popularity bias is an intrinsic geometric artifact of Bayesian Pairwise Ranking (BPR) optimization in CF models. Through rigorous mathematical analysis, we prove that BPR systematically organizes item embeddings along a dominant "popularity direction" where embedding magnitudes directly correlate with interaction frequency. This geometric distortion forces user embeddings to simultaneously handle two conflicting tasks-expressing genuine preference and calibrating against global popularity-trapping them in suboptimal configurations that favor popular items regardless of individual tastes. We propose Directional Decomposition and Correction (DDC), a universally applicable framework that surgically corrects this embedding geometry through asymmetric directional updates. DDC guides positive interactions along personalized preference directions while steering negative interactions away from the global popularity direction, disentangling preference from popularity at the geometric source. Extensive experiments across multiple BPR-based architectures demonstrate that DDC significantly outperforms state-of-the-art debiasing methods, reducing training loss to less than 5% of heavily-tuned baselines while achieving superior recommendation quality and fairness. Code is available in https://github.com/LingFeng-Liu-AI/DDC.
Authors: Nattaya Mairittha, Gabriel Phorncharoenmusikul, Sorawit Worapradidth
Abstract: The integrity of many contemporary AI systems is compromised by the misuse of Human-in-the-Loop (HITL) models to obscure systems that remain heavily dependent on human labor. We define this structural dependency as Human-Instead-of-AI (HISOAI), an ethically problematic and economically unsustainable design in which human workers function as concealed operational substitutes rather than intentional, high-value collaborators. To address this issue, we introduce the AI-First, Human-Empowered (AFHE) paradigm, which requires AI systems to demonstrate a quantifiable level of functional independence prior to deployment. This requirement is formalized through the AI Autonomy Coefficient, measuring the proportion of tasks completed without mandatory human intervention. We further propose the AFHE Deployment Algorithm, an algorithmic gate that enforces a minimum autonomy threshold during offline evaluation and shadow deployment. Our results show that the AI Autonomy Coefficient effectively identifies HISOAI systems with an autonomy level of 0.38, while systems governed by the AFHE framework achieve an autonomy level of 0.85. We conclude that AFHE provides a metric-driven approach for ensuring verifiable autonomy, transparency, and sustainable operational integrity in modern AI systems.
Authors: Tittaya Mairittha, Tanakon Sawanglok, Panuwit Raden, Jirapast Buntub, Thanapat Warunee, Napat Asawachaisuvikrom, Thanaphum Saiwongin
Abstract: While voice-based AI systems have achieved remarkable generative capabilities, their interactions often feel conversationally broken. This paper examines the interactional friction that emerges in modular Speech-to-Speech Retrieval-Augmented Generation (S2S-RAG) pipelines. By analyzing a representative production system, we move beyond simple latency metrics to identify three recurring patterns of conversational breakdown: (1) Temporal Misalignment, where system delays violate user expectations of conversational rhythm; (2) Expressive Flattening, where the loss of paralinguistic cues leads to literal, inappropriate responses; and (3) Repair Rigidity, where architectural gating prevents users from correcting errors in real-time. Through system-level analysis, we demonstrate that these friction points should not be understood as defects or failures, but as structural consequences of a modular design that prioritizes control over fluidity. We conclude that building natural spoken AI is an infrastructure design challenge, requiring a shift from optimizing isolated components to carefully choreographing the seams between them.
Authors: Allen Daniel Sunny
Abstract: Automated eligibility systems increasingly determine access to essential public benefits, but the explanations they generate often fail to reflect the legal rules that authorize those decisions. This thesis develops a legally grounded explainability framework that links system-generated decision justifications to the statutory constraints of CalFresh, California's Supplemental Nutrition Assistance Program. The framework combines a structured ontology of eligibility requirements derived from the state's Manual of Policies and Procedures (MPP), a rule extraction pipeline that expresses statutory logic in a verifiable formal representation, and a solver-based reasoning layer to evaluate whether the explanation aligns with governing law. Case evaluations demonstrate the framework's ability to detect legally inconsistent explanations, highlight violated eligibility rules, and support procedural accountability by making the basis of automated determinations traceable and contestable.
Authors: Chendong Sun, Ali Mao, Lei Xu, mingmin Chen
Abstract: Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models (LLMs) by employing a fast draft model to propose candidate token sequences and a large target model to verify them in parallel. However, its core component -- the rejection sampling mechanism -- relies on a fixed, context-independent random threshold. This leads to a significant "random rejection" problem in high-uncertainty generation scenarios, where plausible candidate tokens are frequently rejected due to random chance, undermining inference efficiency. This paper introduces Efficient Adaptive Rejection Sampling (EARS), a novel method that dynamically adjusts the acceptance threshold by incorporating the target model's own predictive uncertainty, measured as 1 - max(P_target). By introducing a tolerance term proportional to this uncertainty, EARS intelligently relaxes the acceptance criterion when the model is uncertain, effectively reducing random rejections while maintaining strict standards when the model is confident. Experiments on creative writing and open-domain QA tasks demonstrate that EARS significantly enhances the efficiency of speculative decoding, achieving up to an 18.12% increase in throughput with a negligible 0.84% accuracy drop on the GSM8K benchmark. The method requires no modifications to model architectures and can be seamlessly integrated into existing speculative decoding frameworks.
Authors: Qilin Li, C. L. Philip Chen, Tong Zhang
Abstract: Music Emotion Recogniser (MER) research faces challenges due to limited high-quality annotated datasets and difficulties in addressing cross-track feature drift. This work presents two primary contributions to address these issues. Memo2496, a large-scale dataset, offers 2496 instrumental music tracks with continuous valence arousal labels, annotated by 30 certified music specialists. Annotation quality is ensured through calibration with extreme emotion exemplars and a consistency threshold of 0.25, measured by Euclidean distance in the valence arousal space. Furthermore, the Dual-view Adaptive Music Emotion Recogniser (DAMER) is introduced. DAMER integrates three synergistic modules: Dual Stream Attention Fusion (DSAF) facilitates token-level bidirectional interaction between Mel spectrograms and cochleagrams via cross attention mechanisms; Progressive Confidence Labelling (PCL) generates reliable pseudo labels employing curriculum-based temperature scheduling and consistency quantification using Jensen Shannon divergence; and Style Anchored Memory Learning (SAML) maintains a contrastive memory queue to mitigate cross-track feature drift. Extensive experiments on the Memo2496, 1000songs, and PMEmo datasets demonstrate DAMER's state-of-the-art performance, improving arousal dimension accuracy by 3.43%, 2.25%, and 0.17%, respectively. Ablation studies and visualisation analyses validate each module's contribution. Both the dataset and source code are publicly available.
Authors: Taig Singh, Shreshth Rajan, Nikhil Jain
Abstract: As modern neural networks become increasingly memory-bound, inference throughput is limited by DRAM bandwidth rather than compute. We present Arithmetic-Intensity-Aware Quantization (AIQ), a mixed precision quantization framework that chooses per-layer bit-widths to maximize arithmetic intensity (AI) while minimizing accuracy loss. AIQ is a post-training quantization method that uses search algorithms over per-layer quantization schemes to minimize a weighted loss over AI and accuracy. On ResNet-20/CIFAR-10, AIQ increases AI by ~50% over an FP32 baseline while keeping test accuracy within ~1 percentage point, and outperforming global uniform quantization schemes. On a memory-bound MobileNetV2 architecture, AIQ configurations give a 1.66x higher throughput than the FP32 baseline while keeping test accuracy within 1 percentage point. We also find that AIQ naturally quantizes larger layers more aggressively.
Authors: Nguyen Tien Dong, Minh-Anh Nguyen, Thanh Dat Hoang, Nguyen Tuan Ngoc, Dao Xuan Quang Minh, Phan Phi Hai, Nguyen Thi Ngoc Anh, Dang Van Tu, Binh Vu
Abstract: The rapid advancement of large language models (LLMs) has enabled new possibilities for applying artificial intelligence within the legal domain. Nonetheless, the complexity, hierarchical organization, and frequent revisions of Vietnamese legislation pose considerable challenges for evaluating how well these models interpret and utilize legal knowledge. To address this gap, Vietnamese Legal Benchmark (VLegal-Bench) is introduced, the first comprehensive benchmark designed to systematically assess LLMs on Vietnamese legal tasks. Informed by Bloom's cognitive taxonomy, VLegal-Bench encompasses multiple levels of legal understanding through tasks designed to reflect practical usage scenarios. The benchmark comprises 10,450 samples generated through a rigorous annotation pipeline, where legal experts label and cross-validate each instance using our annotation system to ensure every sample is grounded in authoritative legal documents and mirrors real-world legal assistant workflows, including general legal questions and answers, retrieval-augmented generation, multi-step reasoning, and scenario-based problem solving tailored to Vietnamese law. By providing a standardized, transparent, and cognitively informed evaluation framework, VLegal-Bench establishes a solid foundation for assessing LLM performance in Vietnamese legal contexts and supports the development of more reliable, interpretable, and ethically aligned AI-assisted legal systems.