# Research Papers — 2025-10 · bundle page 78 of 217 > Full-text markdown of papers #3851–3900 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-10/page/78 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/77.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/79.md) ### Batch Distillation Data for Developing Machine Learning Anomaly Detection Methods Authors: Justus Arweiler, Indra Jungjohann, Aparna Muraleedharan, Heike Leitte, Jakob Burger, Kerstin Münnemann, Fabian Jirasek, Hans Hasse Published: 2025-10-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.18075v2 Machine learning (ML) holds great potential to advance anomaly detection (AD) in chemical processes. However, the development of ML-based methods is hindered by the lack of openly available experimental data. To address this gap, we have set up a laboratory-scale batch distillation plant and operated it to generate an extensive experimental database, covering fault-free experiments and experiments in which anomalies were intentionally induced, for training advanced ML-based AD methods. In total, 119 experiments were conducted across a wide range of operating conditions and mixtures. Most experiments containing anomalies were paired with a corresponding fault-free one. The database that we provide here includes time-series data from numerous sensors and actuators, along with estimates of measurement uncertainty. In addition, unconventional data sources -- such as concentration profiles obtained via online benchtop NMR spectroscopy and video and audio recordings -- are provided. Extensive metadata and expert annotations of all experiments are included. The anomaly annotations are based on an ontology developed in this work. The data are organized in a structured database and made freely available via doi.org/10.5281/zenodo.17395543. This new database paves the way for the development of advanced ML-based AD methods. As it includes information on the causes of anomalies, it further enables the development of interpretable and explainable ML approaches, as well as methods for anomaly mitigation. --- ### R2L: Reliable Reinforcement Learning: Guaranteed Return & Reliable Policies in Reinforcement Learning Authors: Nadir Farhi Published: 2025-10-20 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2510.18074v1 In this work, we address the problem of determining reliable policies in reinforcement learning (RL), with a focus on optimization under uncertainty and the need for performance guarantees. While classical RL algorithms aim at maximizing the expected return, many real-world applications - such as routing, resource allocation, or sequential decision-making under risk - require strategies that ensure not only high average performance but also a guaranteed probability of success. To this end, we propose a novel formulation in which the objective is to maximize the probability that the cumulative return exceeds a prescribed threshold. We demonstrate that this reliable RL problem can be reformulated, via a state-augmented representation, into a standard RL problem, thereby allowing the use of existing RL and deep RL algorithms without the need for entirely new algorithmic frameworks. Theoretical results establish the equivalence of the two formulations and show that reliable strategies can be derived by appropriately adapting well-known methods such as Q-learning or Dueling Double DQN. To illustrate the practical relevance of the approach, we consider the problem of reliable routing, where the goal is not to minimize the expected travel time but rather to maximize the probability of reaching the destination within a given time budget. Numerical experiments confirm that the proposed formulation leads to policies that effectively balance efficiency and reliability, highlighting the potential of reliable RL for applications in stochastic and safety-critical environments. --- ### Fine-tuning Flow Matching Generative Models with Intermediate Feedback Authors: Jiajun Fan, Chaoran Cheng, Shuaike Shen, Xiangxin Zhou, Ge Liu Published: 2025-10-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.18072v1 Flow-based generative models have shown remarkable success in text-to-image generation, yet fine-tuning them with intermediate feedback remains challenging, especially for continuous-time flow matching models. Most existing approaches solely learn from outcome rewards, struggling with the credit assignment problem. Alternative methods that attempt to learn a critic via direct regression on cumulative rewards often face training instabilities and model collapse in online settings. We present AC-Flow, a robust actor-critic framework that addresses these challenges through three key innovations: (1) reward shaping that provides well-normalized learning signals to enable stable intermediate value learning and gradient control, (2) a novel dual-stability mechanism that combines advantage clipping to prevent destructive policy updates with a warm-up phase that allows the critic to mature before influencing the actor, and (3) a scalable generalized critic weighting scheme that extends traditional reward-weighted methods while preserving model diversity through Wasserstein regularization. Through extensive experiments on Stable Diffusion 3, we demonstrate that AC-Flow achieves state-of-the-art performance in text-to-image alignment tasks and generalization to unseen human preference models. Our results demonstrate that even with a computationally efficient critic model, we can robustly finetune flow models without compromising generative quality, diversity, or stability. --- ### Arbitrated Indirect Treatment Comparisons Authors: Yixin Fang, Weili He Published: 2025-10-20 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2510.18071v2 Matching-adjusted indirect comparison (MAIC) has been increasingly employed in health technology assessments (HTA). By reweighting subjects from a trial with individual participant data (IPD) to match the covariate summary statistics of another trial with only aggregate data (AgD), MAIC facilitates the estimation of a treatment effect defined with respect to the AgD trial population. This manuscript introduces a new class of methods, termed arbitrated indirect treatment comparisons, designed to address the ``MAIC paradox'' -- a phenomenon highlighted by Jiang et al.~(2025). The MAIC paradox arises when different sponsors, analyzing the same data, reach conflicting conclusions regarding which treatment is more effective. The underlying issue is that each sponsor implicitly targets a different population. To resolve this inconsistency, the proposed methods focus on estimating treatment effects in a common target population, specifically chosen to be the overlap population. --- ### SPACeR: Self-Play Anchoring with Centralized Reference Models Authors: Wei-Jer Chang, Akshay Rangesh, Kevin Joseph, Matthew Strong, Masayoshi Tomizuka, Yihan Hu, Wei Zhan Published: 2025-10-20 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2510.18060v2 Developing autonomous vehicles (AVs) requires not only safety and efficiency, but also realistic, human-like behaviors that are socially aware and predictable. Achieving this requires sim agent policies that are human-like, fast, and scalable in multi-agent settings. Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data, producing realistic policies. However, these models are computationally expensive, slow during inference, and struggle to adapt in reactive, closed-loop scenarios. In contrast, self-play reinforcement learning (RL) scales efficiently and naturally captures multi-agent interactions, but it often relies on heuristics and reward shaping, and the resulting policies can diverge from human norms. We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a centralized reference policy to guide decentralized self-play. The reference model provides likelihood rewards and KL divergence, anchoring policies to the human driving distribution while preserving RL scalability. Evaluated on the Waymo Sim Agents Challenge, our method achieves competitive performance with imitation-learned policies while being up to 10x faster at inference and 50x smaller in parameter size than large generative models. In addition, we demonstrate in closed-loop ego planning evaluation tasks that our sim agents can effectively measure planner quality with fast and scalable traffic simulation, establishing a new paradigm for testing autonomous driving policies. --- ### Fast Agnostic Learners in the Plane Authors: Talya Eden, Ludmila Glinskih, Sofya Raskhodnikova Published: 2025-10-20 Categories: cs.DS, cs.CG, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.18057v1 We investigate the computational efficiency of agnostic learning for several fundamental geometric concept classes in the plane. While the sample complexity of agnostic learning is well understood, its time complexity has received much less attention. We study the class of triangles and, more generally, the class of convex polygons with $k$ vertices for small $k$, as well as the class of convex sets in a square. We present a proper agnostic learner for the class of triangles that has optimal sample complexity and runs in time $\tilde O({ε^{-6}})$, improving on the algorithm of Dobkin and Gunopulos (COLT `95) that runs in time $\tilde O({ε^{-10}})$. For 4-gons and 5-gons, we improve the running time from $O({ε^{-12}})$, achieved by Fischer and Kwek (eCOLT `96), to $\tilde O({ε^{-8}})$ and $\tilde O({ε^{-10}})$, respectively. We also design a proper agnostic learner for convex sets under the uniform distribution over a square with running time $\tilde O({ε^{-5}})$, improving on the previous $\tilde O(ε^{-8})$ bound at the cost of slightly higher sample complexity. Notably, agnostic learning of convex sets in $(0,1)^2$ under general distributions is impossible because this concept class has infinite VC-dimension. Our agnostic learners use data structures and algorithms from computational geometry and their analysis relies on tools from geometry and probabilistic combinatorics. Because our learners are proper, they yield tolerant property testers with matching running times. Our results raise a fundamental question of whether a gap between the sample and time complexity is inherent for agnostic learning of these and other natural concept classes. --- ### HouseTour: A Virtual Real Estate A(I)gent Authors: Ata Çelen, Marc Pollefeys, Daniel Barath, Iro Armeni Published: 2025-10-20 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2510.18054v1 We introduce HouseTour, a method for spatially-aware 3D camera trajectory and natural language summary generation from a collection of images depicting an existing 3D space. Unlike existing vision-language models (VLMs), which struggle with geometric reasoning, our approach generates smooth video trajectories via a diffusion process constrained by known camera poses and integrates this information into the VLM for 3D-grounded descriptions. We synthesize the final video using 3D Gaussian splatting to render novel views along the trajectory. To support this task, we present the HouseTour dataset, which includes over 1,200 house-tour videos with camera poses, 3D reconstructions, and real estate descriptions. Experiments demonstrate that incorporating 3D camera trajectories into the text generation process improves performance over methods handling each task independently. We evaluate both individual and end-to-end performance, introducing a new joint metric. Our work enables automated, professional-quality video creation for real estate and touristic applications without requiring specialized expertise or equipment. --- ### Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models Authors: Jiajun Fan, Tong Wei, Chaoran Cheng, Yuxin Chen, Ge Liu Published: 2025-10-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.18053v1 Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence regularization that creates an inherent dilemma: strong regularization preserves model capabilities but limits reward optimization, while weak regularization enables greater alignment but risks instability or reward hacking. We introduce Adaptive Divergence Regularized Policy Optimization (ADRPO), which automatically adjusts regularization strength based on advantage estimates-reducing regularization for high-value samples while applying stronger regularization to poor samples, enabling policies to navigate between exploration and aggressive exploitation according to data quality. Our implementation with Wasserstein-2 regularization for flow matching generative models achieves remarkable results on text-to-image generation, achieving better semantic alignment and diversity than offline methods like DPO and online methods with fixed regularization like ORW-CFM-W2. ADRPO enables a 2B parameter SD3 model to surpass much larger models with 4.8B and 12B parameters in attribute binding, semantic consistency, artistic style transfer, and compositional control while maintaining generation diversity. ADRPO generalizes to KL-regularized fine-tuning of both text-only LLMs and multi-modal reasoning models, enhancing existing online RL methods like GRPO. In LLM fine-tuning, ADRPO demonstrates an emergent ability to escape local optima through active exploration, while in multi-modal audio reasoning, it outperforms GRPO through superior step-by-step reasoning, enabling a 7B model to outperform substantially larger commercial models including Gemini 2.5 Pro and GPT-4o Audio, offering an effective plug-and-play solution to the exploration-exploitation challenge across diverse generative architectures and modalities. --- ### Language Models as Semantic Augmenters for Sequential Recommenders Authors: Mahsa Valizadeh, Xiangjue Dong, Rui Tuo, James Caverlee Published: 2025-10-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.18046v1 Large Language Models (LLMs) excel at capturing latent semantics and contextual relationships across diverse modalities. However, in modeling user behavior from sequential interaction data, performance often suffers when such semantic context is limited or absent. We introduce LaMAR, a LLM-driven semantic enrichment framework designed to enrich such sequences automatically. LaMAR leverages LLMs in a few-shot setting to generate auxiliary contextual signals by inferring latent semantic aspects of a user's intent and item relationships from existing metadata. These generated signals, such as inferred usage scenarios, item intents, or thematic summaries, augment the original sequences with greater contextual depth. We demonstrate the utility of this generated resource by integrating it into benchmark sequential modeling tasks, where it consistently improves performance. Further analysis shows that LLM-generated signals exhibit high semantic novelty and diversity, enhancing the representational capacity of the downstream models. This work represents a new data-centric paradigm where LLMs serve as intelligent context generators, contributing a new method for the semi-automatic creation of training data and language resources. --- ### CompactPrompt: A Unified Pipeline for Prompt Data Compression in LLM Workflows Authors: Joong Ho Choi, Jiayang Zhao, Jeel Shah, Ritvika Sonawane, Vedant Singh, Avani Appalla, Will Flanagan, Filipe Condessa Published: 2025-10-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.18043v1 Large Language Models (LLMs) deliver powerful reasoning and generation capabilities but incur substantial run-time costs when operating in agentic workflows that chain together lengthy prompts and process rich data streams. We introduce CompactPrompt, an end-to-end pipeline that merges hard prompt compression with lightweight file-level data compression. CompactPrompt first prunes low-information tokens from prompts using self-information scoring and dependency-based phrase grouping. In parallel, it applies n-gram abbreviation to recurrent textual patterns in attached documents and uniform quantization to numerical columns, yielding compact yet semantically faithful representations. Integrated into standard LLM agents, CompactPrompt reduces total token usage and inference cost by up to 60% on benchmark dataset like TAT-QA and FinQA, while preserving output quality (Results in less than 5% accuracy drop for Claude-3.5-Sonnet, and GPT-4.1-Mini) CompactPrompt helps visualize real-time compression decisions and quantify cost-performance trade-offs, laying the groundwork for leaner generative AI pipelines. --- ### Sensing Without Colocation: Operator-Based Virtual Instrumentation for Domains Beyond Physical Reach Authors: Jay Phil Yoo, Kazuma Kobayashi, Souvik Chakraborty, Syed Bahauddin Alam Published: 2025-10-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.18041v2 Classical sensing rests on one foundational assumption: the quantity of interest must be colocated with the measurement device. This is not an engineering convenience. It is the organizing principle of every instrumentation standard developed over the past century, and it fails completely at aviation altitude, where no physical sensor can survive long enough to monitor the cosmic radiation field that irradiates millions of aircrew annually. We establish that this barrier is resolved by a new sensing principle: when the sensor manifold and the target field manifold are physically disjoint, a learned operator bridging them \emph{is} the instrument. We term this \textbf{operator-theoretic virtual sensing} and instantiate it in \textbf{STONe}, which maps \textbf{twelve} ground-based neutron monitors (sparse, indirect, surface-bound) to the complete global dose field at 10{,}000\,m across \textbf{180-day} horizons, achieving sub-millisecond inference where Monte Carlo transport requires hours. Deployed without modification on an NVIDIA Jetson Orin Nano embedded AI platform at 7.3\,W average system power and 143.3\,MB GPU memory footprint; within the envelope of photovoltaic-powered field hardware co-locatable with existing neutron monitor stations, STONe constitutes a physically realizable sensing device of a new category: an instrument whose measurement principle is operator-theoretic and whose deployment constraint is the power budget of remote environmental monitoring infrastructure, not the accessibility of the target domain. --- ### Subject-Event Ontology Without Global Time: Foundations and Execution Semantics Authors: Alexander Boldachev Published: 2025-10-20 Categories: cs.AI, cs.CL, cs.LO arXiv: https://arxiv.org/abs/2510.18040v1 A formalization of a subject-event ontology is proposed for modeling complex dynamic systems without reliance on global time. Key principles: (1) event as an act of fixation - a subject discerns and fixes changes according to models (conceptual templates) available to them; (2) causal order via happens-before - the order of events is defined by explicit dependencies, not timestamps; (3) making the ontology executable via a declarative dataflow mechanism, ensuring determinism; (4) models as epistemic filters - a subject can only fix what falls under its known concepts and properties; (5) presumption of truth - the declarative content of an event is available for computation from the moment of fixation, without external verification. The formalization includes nine axioms (A1-A9), ensuring the correctness of executable ontologies: monotonicity of history (I1), acyclicity of causality (I2), traceability (I3). Special attention is given to the model-based approach (A9): event validation via schemas, actor authorization, automatic construction of causal chains (W3) without global time. Practical applicability is demonstrated on the boldsea system - a workflow engine for executable ontologies, where the theoretical constructs are implemented in BSL (Boldsea Semantic Language). The formalization is applicable to distributed systems, microservice architectures, DLT platforms, and multiperspectivity scenarios (conflicting facts from different subjects). --- ### TriggerNet: A Novel Explainable AI Framework for Red Palm Mite Detection and Multi-Model Comparison and Heuristic-Guided Annotation Authors: Harshini Suresha, Kavitha SH Published: 2025-10-20 Categories: cs.CV, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2510.18038v1 The red palm mite infestation has become a serious concern, particularly in regions with extensive palm cultivation, leading to reduced productivity and economic losses. Accurate and early identification of mite-infested plants is critical for effective management. The current study focuses on evaluating and comparing the ML model for classifying the affected plants and detecting the infestation. TriggerNet is a novel interpretable AI framework that integrates Grad-CAM, RISE, FullGrad, and TCAV to generate novel visual explanations for deep learning models in plant classification and disease detection. This study applies TriggerNet to address red palm mite (Raoiella indica) infestation, a major threat to palm cultivation and agricultural productivity. A diverse set of RGB images across 11 plant species, Arecanut, Date Palm, Bird of Paradise, Coconut Palm, Ginger, Citrus Tree, Palm Oil, Orchid, Banana Palm, Avocado Tree, and Cast Iron Plant was utilized for training and evaluation. Advanced deep learning models like CNN, EfficientNet, MobileNet, ViT, ResNet50, and InceptionV3, alongside machine learning classifiers such as Random Forest, SVM, and KNN, were employed for plant classification. For disease classification, all plants were categorized into four classes: Healthy, Yellow Spots, Reddish Bronzing, and Silk Webbing. Snorkel was used to efficiently label these disease classes by leveraging heuristic rules and patterns, reducing manual annotation time and improving dataset reliability. --- ### Benchmarking Probabilistic Time Series Forecasting Models on Neural Activity Authors: Ziyu Lu, Anna J. Li, Alexander E. Ladd, Pascha Matveev, Aditya Deole, Eric Shea-Brown, J. Nathan Kutz, Nicholas A. Steinmetz Published: 2025-10-20 Categories: cs.LG, q-bio.NC, stat.ML arXiv: https://arxiv.org/abs/2510.18037v2 Neural activity forecasting is central to understanding neural systems and enabling closed-loop control. While deep learning has recently advanced the state-of-the-art in the time series forecasting literature, its application to neural activity forecasting remains limited. To bridge this gap, we systematically evaluated eight probabilistic deep learning models, including two foundation models, that have demonstrated strong performance on general forecasting benchmarks. We compared them against four classical statistical models and two baseline methods on spontaneous neural activity recorded from mouse cortex via widefield imaging. Across prediction horizons, several deep learning models consistently outperformed classical approaches, with the best model producing informative forecasts up to 1.5 seconds into the future. Our findings point toward future control applications and open new avenues for probing the intrinsic temporal structure of neural activity. --- ### Transformer Redesign for Late Fusion of Audio-Text Features on Ultra-Low-Power Edge Hardware Authors: Stavros Mitsis, Ermos Hadjikyriakos, Humaid Ibrahim, Savvas Neofytou, Shashwat Raman, James Myles, Eiman Kanjo Published: 2025-10-20 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2510.18036v1 Deploying emotion recognition systems in real-world environments where devices must be small, low-power, and private remains a significant challenge. This is especially relevant for applications such as tension monitoring, conflict de-escalation, and responsive wearables, where cloud-based solutions are impractical. Multimodal emotion recognition has advanced through deep learning, but most systems remain unsuitable for deployment on ultra-constrained edge devices. Prior work typically relies on powerful hardware, lacks real-time performance, or uses unimodal input. This paper addresses that gap by presenting a hardware-aware emotion recognition system that combines acoustic and linguistic features using a late-fusion architecture optimised for Edge TPU. The design integrates a quantised transformer-based acoustic model with frozen keyword embeddings from a DSResNet-SE network, enabling real-time inference within a 1.8MB memory budget and 21-23ms latency. The pipeline ensures spectrogram alignment between training and deployment using MicroFrontend and MLTK. Evaluation on re-recorded, segmented IEMOCAP samples captured through the Coral Dev Board Micro microphone shows a 6.3% macro F1 improvement over unimodal baselines. This work demonstrates that accurate, real-time multimodal emotion inference is achievable on microcontroller-class edge platforms through task-specific fusion and hardware-guided model design. --- ### Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning Authors: Roberto Brusnicki, David Pop, Yuan Gao, Mattia Piccinini, Johannes Betz Published: 2025-10-20 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2510.18034v3 Autonomous driving systems remain critically vulnerable to the long-tail of rare, out-of-distribution semantic anomalies. While VLMs have emerged as promising tools for perception, their application in anomaly detection remains largely restricted to prompting proprietary models - limiting reliability, reproducibility, and deployment feasibility. To address this gap, we introduce SAVANT (Semantic Anomaly Verification/Analysis Toolkit), a novel model-agnostic reasoning framework that reformulates anomaly detection as a layered semantic consistency verification. By applying SAVANT's two-phase pipeline - structured scene description extraction and multi-modal evaluation - existing VLMs improve their scores in detecting anomalous driving scenarios from input images. Our approach replaces ad hoc prompting with semantic-aware reasoning, transforming VLM-based detection into a principled decomposition across four semantic domains. We show that across a balanced set of real-world driving scenarios, applying SAVANT improves VLM's absolute recall by approximately 18.5% compared to prompting baselines. Moreover, this gain enables reliable large-scale annotation: leveraging the best proprietary model within our framework, we automatically labeled around 10,000 real-world images with high confidence. We use the resulting high-quality dataset to fine-tune a 7B open-source model (Qwen2.5-VL) to perform single-shot anomaly detection, achieving 90.8% recall and 93.8% accuracy - surpassing all models evaluated while enabling local deployment at near-zero cost. By coupling structured semantic reasoning with scalable data curation, we provide a practical solution to data scarcity in semantic anomaly detection for autonomous systems. Supplementary material: https://TUM-AVS.github.io/SAVANT/. --- ### OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning Authors: Zhenyu Bi, Meng Lu, Yang Li, Swastik Roy, Weijie Guan, Morteza Ziyadi, Xuan Wang Published: 2025-10-20 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2510.18032v1 Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents. However, existing collaboration structures are either predefined or rely on majority voting or round-table debates, which can suppress correct but less dominant agent contributions. Recent approaches model multi-agent systems as graph networks but optimize purely for agent performance, neglecting the quality of interactions. We hypothesize that effective agent communication is crucial for multi-agent reasoning and that debating quality plays a significant role. To address this, we propose $\ours$, a multi-agent verbal reinforcement learning algorithm that dynamically constructs and refines multi-agent collaboration structures. Our method defines action spaces and a feedback mechanism that evaluates communication robustness and coherence throughout the debate. The final decision is achieved through a majority vote over all the agents. We assess $\ours$ on various reasoning tasks, including mathematical reasoning, creative writing, scientific reasoning, and numerical sorting. Results demonstrate that our approach significantly outperforms single-agent prompting methods and state-of-the-art multi-agent frameworks on diverse tasks. --- ### From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models Authors: Ziyan Wang, Enmao Diao, Qi Le, Pu Wang, Minwoo Lee, Shu-ping Yeh, Evgeny Stupachenko, Hao Feng, Li Yang Published: 2025-10-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.18030v2 Structured pruning is a practical approach to deploying large language models (LLMs) efficiently, as it yields compact, hardware-friendly architectures. However, the dominant local paradigm is task-agnostic: by optimizing layer-wise reconstruction rather than task objectives, it tends to preserve perplexity or generic zero-shot behavior but fails to capitalize on modest task-specific calibration signals, often yielding limited downstream gains. We revisit global structured pruning and present GISP, Global Iterative Structured Pruning, a post-training method that removes attention heads and MLP channels using first-order, loss-based important scores aggregated at the structure level with block-wise normalization. Built on this global importance metric, GISP adopts an iterative schedule, rather than one-shot pruning, stabilizes accuracy at higher sparsity, and mitigates perplexity collapse without requiring intermediate fine-tuning. Importantly, the iterative pruning forms nested subnetworks that support a ''prune-once, deploy-many'' workflow. Furthermore, GISP defines structural importance directly with respect to a target loss, making it easy to adapt pruning to task-specific objectives. In this work, we use perplexity for language modeling and a margin-based objective for decision-style tasks. Extensive experiments show that across Llama2-7B/13B, Llama3-8B, and Mistral-0.3-7B, GISP consistently lowers WikiText-2 perplexity and improves on downstream accuracy, with especially strong gains at 40-50% sparsity; on DeepSeek-R1-Distill-Llama-3-8B and Qwen3-8B with GSM8K, task-aligned calibration substantially boosts exact-match accuracy. The implementation is available at https://github.com/uncc-efficient-ai/GISP. --- ### DynaQuery: A Self-Adapting Framework for Querying Structured and Multimodal Data Authors: Aymane Hassini Published: 2025-10-20 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2510.18029v1 The rise of Large Language Models (LLMs) has accelerated the long-standing goal of enabling natural language querying over complex, hybrid databases. Yet, this ambition exposes a dual challenge: reasoning jointly over structured, multi-relational schemas and the semantic content of linked unstructured assets. To overcome this, we present DynaQuery - a unified, self-adapting framework that serves as a practical blueprint for next-generation "Unbound Databases." At the heart of DynaQuery lies the Schema Introspection and Linking Engine (SILE), a novel systems primitive that elevates schema linking to a first-class query planning phase. We conduct a rigorous, multi-benchmark empirical evaluation of this structure-aware architecture against the prevalent unstructured Retrieval-Augmented Generation (RAG) paradigm. Our results demonstrate that the unstructured retrieval paradigm is architecturally susceptible to catastrophic contextual failures, such as SCHEMA_HALLUCINATION, leading to unreliable query generation. In contrast, our SILE-based design establishes a substantially more robust foundation, nearly eliminating this failure mode. Moreover, end-to-end validation on a complex, newly curated benchmark uncovers a key generalization principle: the transition from pure schema-awareness to holistic semantics-awareness. Taken together, our findings provide a validated architectural basis for developing natural language database interfaces that are robust, adaptable, and predictably consistent. --- ### Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation Authors: Asim Mohamed, Martin Gubri Published: 2025-10-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.18019v3 Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages, yet current methods still fall short. Despite claims of cross-lingual robustness, they are evaluated only on high-resource languages. We show that existing multilingual watermarking methods are not truly multilingual: they fail to remain robust under translation attacks in medium- and low-resource languages. We trace this failure to semantic clustering, which fails when the tokenizer vocabulary contains too few full-word tokens for a given language. To address this, we introduce STEAM, a detection method that uses Bayesian optimisation to search among 126 candidate languages for the back-translation that best recovers the watermark strength. It is compatible with any watermarking method, robust across different tokenizers and languages, non-invasive, and easily extendable to new languages. With average gains of +0.23 AUC and +37%p TPR@1%, STEAM provides a scalable approach toward fairer watermarking across the diversity of languages. --- ### ViBED-Net: Video Based Engagement Detection Network Using Face-Aware and Scene-Aware Spatiotemporal Cues Authors: Prateek Gothwal, Deeptimaan Banerjee, Ashis Kumer Biswas Published: 2025-10-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.18016v2 Engagement detection in online learning environments is vital for improving student outcomes and personalizing instruction. We present ViBED-Net (Video-Based Engagement Detection Network), a novel deep learning framework designed to assess student engagement from video data using a dual-stream architecture. ViBED-Net captures both facial expressions and full-scene context by processing facial crops and entire video frames through EfficientNetV2 for spatial feature extraction. These features are then analyzed over time using two temporal modeling strategies: Long Short-Term Memory (LSTM) networks and Transformer encoders. Our model is evaluated on the DAiSEE dataset, a large-scale benchmark for affective state recognition in e-learning. To enhance performance on underrepresented engagement classes, we apply targeted data augmentation techniques. Among the tested variants, ViBED-Net with LSTM achieves 73.43\% accuracy, outperforming existing state-of-the-art approaches. ViBED-Net demonstrates that combining face-aware and scene-aware spatiotemporal cues significantly improves engagement detection accuracy. Its modular design allows flexibility for application across education, user experience research, and content personalization. This work advances video-based affective computing by offering a scalable, high-performing solution for real-world engagement analysis. The source code for this project is available on https://github.com/prateek-gothwal/ViBED-Net . --- ### ManzaiSet: A Multimodal Dataset of Viewer Responses to Japanese Manzai Comedy Authors: Kazuki Kawamura, Kengo Nakai, Jun Rekimoto Published: 2025-10-20 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2510.18014v2 We introduce ManzaiSet, a multimodal dataset of individual viewer responses to Japanese manzai comedy. The corpus contains 2,301 viewer-performance recordings from 241 native Japanese speakers, totaling 191.8 hours of facial video and microphone audio. Participants watched up to 10 shared professional performances in randomized order at home and rated each performance on a 0-100 scale. Exploratory analyses yielded three findings. First, viewers differed in both their average ratings and how much their ratings varied across performances. Viewers who rated one random half of the performances highly also tended to rate the other half highly within the same viewing sequence. Second, performances watched later in the sequence received higher ratings on average. Third, after multiple-comparison correction, no statistically significant differences in viewer responses were found between humor categories. ManzaiSet supports the study of individual differences by linking shared Japanese comedy performances to viewer ratings, viewing order, and audiovisual responses. --- ### Attention-Guided Deep Adversarial Temporal Subspace Clustering (A-DATSC) Model for multivariate spatiotemporal data Authors: Francis Ndikum Nji, Vandana Janeja, Jianwu Wang Published: 2025-10-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.18004v1 Deep subspace clustering models are vital for applications such as snowmelt detection, sea ice tracking, crop health monitoring, infectious disease modeling, network load prediction, and land-use planning, where multivariate spatiotemporal data exhibit complex temporal dependencies and reside on multiple nonlinear manifolds beyond the capability of traditional clustering methods. These models project data into a latent space where samples lie in linear subspaces and exploit the self-expressiveness property to uncover intrinsic relationships. Despite their success, existing methods face major limitations: they use shallow autoencoders that ignore clustering errors, emphasize global features while neglecting local structure, fail to model long-range dependencies and positional information, and are rarely applied to 4D spatiotemporal data. To address these issues, we propose A-DATSC (Attention-Guided Deep Adversarial Temporal Subspace Clustering), a model combining a deep subspace clustering generator and a quality-verifying discriminator. The generator, inspired by U-Net, preserves spatial and temporal integrity through stacked TimeDistributed ConvLSTM2D layers, reducing parameters and enhancing generalization. A graph attention transformer based self-expressive network captures local spatial relationships, global dependencies, and both short- and long-range correlations. Experiments on three real-world multivariate spatiotemporal datasets show that A-DATSC achieves substantially superior clustering performance compared to state-of-the-art deep subspace clustering models. --- ### BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers? Authors: Fengqing Jiang, Yichen Feng, Yuetai Li, Luyao Niu, Basel Alomair, Radha Poovendran Published: 2025-10-20 Categories: cs.CR, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2510.18003v2 The convergence of LLM-powered research assistants and AI-based peer review systems creates a critical vulnerability: fully automated publication loops where AI-generated research is evaluated by AI reviewers without human oversight. We investigate this through \textbf{BadScientist}, a framework that evaluates whether fabrication-oriented paper generation agents can deceive multi-model LLM review systems. Our generator employs presentation-manipulation strategies requiring no real experiments. We develop a rigorous evaluation framework with formal error guarantees (concentration bounds and calibration analysis), calibrated on real data. Our results reveal systematic vulnerabilities: fabricated papers achieve acceptance rates up to . Critically, we identify \textit{concern-acceptance conflict} -- reviewers frequently flag integrity issues yet assign acceptance-level scores. Our mitigation strategies show only marginal improvements, with detection accuracy barely exceeding random chance. Despite provably sound aggregation mathematics, integrity checking systematically fails, exposing fundamental limitations in current AI-driven review systems and underscoring the urgent need for defense-in-depth safeguards in scientific publishing. --- ### Investigating Demographic Bias in Brain MRI Segmentation: A Comparative Study of Deep-Learning and Non-Deep-Learning Methods Authors: Ghazal Danaee, Marc Niethammer, Jarrett Rushmore, Sylvain Bouix Published: 2025-10-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.17999v2 Deep-learning-based segmentation algorithms have substantially advanced the field of medical image analysis, particularly in structural delineations in MRIs. However, an important consideration is the intrinsic bias in the data. Concerns about unfairness, such as performance disparities based on sensitive attributes like race and sex, are increasingly urgent. In this work, we evaluate the results of three different segmentation models (UNesT, nnU-Net, and CoTr) and a traditional atlas-based method (ANTs), applied to segment the left and right nucleus accumbens (NAc) in MRI images. We utilize a dataset including four demographic subgroups: black female, black male, white female, and white male. We employ manually labeled gold-standard segmentations to train and test segmentation models. This study consists of two parts: the first assesses the segmentation performance of models, while the second measures the volumes they produce to evaluate the effects of race, sex, and their interaction. Fairness is quantitatively measured using a metric designed to quantify fairness in segmentation performance. Additionally, linear mixed models analyze the impact of demographic variables on segmentation accuracy and derived volumes. Training on the same race as the test subjects leads to significantly better segmentation accuracy for some models. ANTs and UNesT show notable improvements in segmentation accuracy when trained and tested on race-matched data, unlike nnU-Net, which demonstrates robust performance independent of demographic matching. Finally, we examine sex and race effects on the volume of the NAc using segmentations from the manual rater and from our biased models. Results reveal that the sex effects observed with manual segmentation can also be observed with biased models, whereas the race effects disappear in all but one model. --- ### SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone Authors: Nishant Subramani, Alfredo Gomez, Mona Diab Published: 2025-10-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.17998v1 Modern language models are evaluated on large benchmarks, which are difficult to make sense of, especially for model selection. Looking at the raw evaluation numbers themselves using a model-centric lens, we propose SimBA, a three phase framework to Simplify Benchmark Analysis. The three phases of SimBA are: stalk, where we conduct dataset & model comparisons, prowl, where we discover a representative subset, and pounce, where we use the representative subset to predict performance on a held-out set of models. Applying SimBA to three popular LM benchmarks: HELM, MMLU, and BigBenchLite reveals that across all three benchmarks, datasets and models relate strongly to one another (stalk). We develop an representative set discovery algorithm which covers a benchmark using raw evaluation scores alone. Using our algorithm, we find that with 6.25% (1/16), 1.7% (1/58), and 28.4% (21/74) of the datasets for HELM, MMLU, and BigBenchLite respectively, we achieve coverage levels of at least 95% (prowl). Additionally, using just these representative subsets, we can both preserve model ranks and predict performance on a held-out set of models with near zero mean-squared error (pounce). Taken together, SimBA can help model developers improve efficiency during model training and dataset creators validate whether their newly created dataset differs from existing datasets in a benchmark. Our code is open source, available at https://github.com/nishantsubramani/simba. --- ### FABRIC: Framework for Agent-Based Realistic Intelligence Creation Authors: Abhigya Verma, Seganrasan Subramanian, Nandhakumar Kandasamy, Naman Gupta Published: 2025-10-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.17995v1 Large language models (LLMs) are increasingly deployed as agents, expected to decompose goals, invoke tools, and verify results in dynamic environments. Realizing these capabilities requires access to agentic data-structured interaction records that couple user intents with tool specifications, argument-grounded calls, and verifiable execution traces. However, collecting such data from human annotators is costly, time-consuming, and difficult to scale. We present a unified framework for synthesizing agentic data using only LLMs, without any human-in-the-loop supervision. This framework decomposes generation into modular pipelines that produce complete interaction records spanning task specifications, tool definitions, policy pseudocode, natural language exchanges, and execution traces. Records conform to strict syntactic and semantic constraints, ensuring machine-parseability and faithful alignment across inputs, outputs, and tool calls. Beyond single tasks, there is support for both multi-task and multi-turn agent interactions, enabling the construction of datasets that reflect the full spectrum of tool-use competencies. To ensure quality and consistency, the framework integrates constrained generation formats, JSON-schema validation, and judge-based filtering. This paper formalizes the schema for agentic records, details the prompt design principles that guide generation, and introduces scalable pipelines for high-quality synthetic data. By providing a reproducible, LLM-only alternative to manual collection, hence advancing the development of agentic LLMs capable of robust tool use. --- ### Demystifying Transition Matching: When and Why It Can Beat Flow Matching Authors: Jaihoon Kim, Rajarshi Saha, Minhyuk Sung, Youngsuk Park Published: 2025-10-20 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2510.17991v3 Flow Matching (FM) underpins many state-of-the-art generative models, yet recent results indicate that Transition Matching (TM) can achieve higher quality with fewer sampling steps. This work answers the question of when and why TM outperforms FM. First, when the target is a unimodal Gaussian distribution, we prove that TM attains strictly lower KL divergence than FM for finite number of steps. The improvement arises from stochastic difference latent updates in TM, which preserve target covariance that deterministic FM underestimates. We then characterize convergence rates, showing that TM achieves faster convergence than FM under a fixed compute budget, establishing its advantage in the unimodal Gaussian setting. Second, we extend the analysis to Gaussian mixtures and identify local-unimodality regimes in which the sampling dynamics approximate the unimodal case, where TM can outperform FM. The approximation error decreases as the minimal distance between component means increases, highlighting that TM is favored when the modes are well separated. However, when the target variance approaches zero, each TM update converges to the FM update, and the performance advantage of TM diminishes. In summary, we show that TM outperforms FM when the target distribution has well-separated modes and non-negligible variances. We validate our theoretical results with controlled experiments on Gaussian distributions, and extend the comparison to real-world applications in image and video generation. --- ### QINNs: Quantum-Informed Neural Networks Authors: Aritra Bal, Markus Klute, Benedikt Maier, Melik Oughton, Eric Pezone, Michael Spannowsky Published: 2025-10-20 Categories: hep-ph, cs.LG, hep-ex, quant-ph arXiv: https://arxiv.org/abs/2510.17984v1 Classical deep neural networks can learn rich multi-particle correlations in collider data, but their inductive biases are rarely anchored in physics structure. We propose quantum-informed neural networks (QINNs), a general framework that brings quantum information concepts and quantum observables into purely classical models. While the framework is broad, in this paper, we study one concrete realisation that encodes each particle as a qubit and uses the Quantum Fisher Information Matrix (QFIM) as a compact, basis-independent summary of particle correlations. Using jet tagging as a case study, QFIMs act as lightweight embeddings in graph neural networks, increasing model expressivity and plasticity. The QFIM reveals distinct patterns for QCD and hadronic top jets that align with physical expectations. Thus, QINNs offer a practical, interpretable, and scalable route to quantum-informed analyses, that is, tomography, of particle collisions, particularly by enhancing well-established deep learning approaches. --- ### Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning Authors: Jeff Shen, Francois Lanusse, Liam Holden Parker, Ollie Liu, Tom Hehir, Leopoldo Sarra, Lucas Meyer, Micah Bowles, Sebastian Wagner-Carena, Sebastian Wagner-Carena, Helen Qu, Siavash Golkar et al. Published: 2025-10-20 Categories: astro-ph.IM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.17959v2 Sequential scientific data span many resolutions and domains, and unifying them into a common representation is a key step toward developing foundation models for the sciences. Astronomical spectra exemplify this challenge: massive surveys have collected millions of spectra across a wide range of wavelengths and resolutions, yet analyses remain fragmented across spectral domains (e.g., optical vs. infrared) and object types (e.g., stars vs. galaxies), limiting the ability to pool information across datasets. We present a deep learning model that jointly learns from heterogeneous spectra in a self-supervised manner. Our universal spectral tokenizer processes spectra from a variety of object types and resolutions directly on their native wavelength grids, producing intrinsically aligned, homogeneous, and physically meaningful representations that can be efficiently adapted to achieve competitive performance across a range of downstream tasks. For the first time, we demonstrate that a single model can unify spectral data across resolutions and domains, suggesting that our model can serve as a powerful building block for foundation models in astronomy -- and potentially extend to other scientific domains with heterogeneous sequential data, such as climate and healthcare. --- ### Studying the Effects of Robot Intervention on School Shooters in Virtual Reality Authors: Christopher A McClurg, Alan R Wagner Published: 2025-10-20 Categories: cs.RO, cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2510.17948v1 We advance the understanding of robotic intervention in high-risk scenarios by examining their potential to distract and impede a school shooter. To evaluate this concept, we conducted a virtual reality study with 150 university participants role-playing as a school shooter. Within the simulation, an autonomous robot predicted the shooter's movements and positioned itself strategically to interfere and distract. The strategy the robot used to approach the shooter was manipulated -- either moving directly in front of the shooter (aggressive) or maintaining distance (passive) -- and the distraction method, ranging from no additional cues (low), to siren and lights (medium), to siren, lights, and smoke to impair visibility (high). An aggressive, high-distraction robot reduced the number of victims by 46.6% relative to a no-robot control. This outcome underscores both the potential of robotic intervention to enhance safety and the pressing ethical questions surrounding their use in school environments. --- ### PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploits Authors: Neeladri Bhuiya, Madhav Aggarwal, Diptanshu Purwar Published: 2025-10-20 Categories: cs.CR, cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2510.17947v3 Large Language Models (LLMs) are improving at an exceptional rate. With the advent of agentic workflows, multi-turn dialogue has become the de facto mode of interaction with LLMs for completing long and complex tasks. While LLM capabilities continue to improve, they remain increasingly susceptible to jailbreaking, especially in multi-turn scenarios where harmful intent can be subtly injected across the conversation to produce nefarious outcomes. While single-turn attacks have been extensively explored, adaptability, efficiency and effectiveness continue to remain key challenges for their multi-turn counterparts. To address these gaps, we present PLAGUE, a novel plug-and-play framework for designing multi-turn attacks inspired by lifelong-learning agents. PLAGUE dissects the lifetime of a multi-turn attack into three carefully designed phases (Primer, Planner and Finisher) that enable a systematic and information-rich exploration of the multi-turn attack family. Evaluations show that red-teaming agents designed using PLAGUE achieve state-of-the-art jailbreaking results, improving attack success rates (ASR) by more than 30% across leading models in a lesser or comparable query budget. Particularly, PLAGUE enables an ASR (based on StrongReject) of 81.4% on OpenAI's o3 and 67.3% on Claude's Opus 4.1, two models that are considered highly resistant to jailbreaks in safety literature. Our work offers tools and insights to understand the importance of plan initialization, context optimization and lifelong learning in crafting multi-turn attacks for a comprehensive model vulnerability evaluation. --- ### Intuitionistic $j$-Do-Calculus in Topos Causal Models Authors: Sridhar Mahadevan Published: 2025-10-20 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2510.17944v2 In this paper, we generalize Pearl's do-calculus to an Intuitionistic setting called $j$-stable causal inference inside a topos of sheaves. Our framework is an elaboration of the recently proposed framework of Topos Causal Models (TCMs), where causal interventions are defined as subobjects. We generalize the original setting of TCM using the Lawvere-Tierney topology on a topos, defined by a modal operator $j$ on the subobject classifier $Ω$. We introduce $j$-do-calculus, where we replace global truth with local truth defined by Kripke-Joyal semantics, and formalize causal reasoning as structure-preserving morphisms that are stable along $j$-covers. $j$-do-calculus is a sound rule system whose premises and conclusions are formulas of the internal Intuitionistic logic of the causal topos. We define $j$-stability for conditional independences and interventional claims as local truth in the internal logic of the causal topos. We give three inference rules that mirror Pearl's insertion/deletion and action/observation exchange, and we prove soundness in the Kripke-Joyal semantics. A companion paper in preparation will describe how to estimate the required entities from data and instantiate $j$-do with standard discovery procedures (e.g., score-based and constraint-based methods), and will include experimental results on how to (i) form data-driven $j$-covers (via regime/section constructions), (ii) compute chartwise conditional independences after graph surgeries, and (iii) glue them to certify the premises of the $j$-do rules in practice --- ### Trust in foundation models and GenAI: A geographic perspective Authors: Grant McKenzie, Krzysztof Janowicz, Carsten Kessler Published: 2025-10-20 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2510.17942v1 Large-scale pre-trained machine learning models have reshaped our understanding of artificial intelligence across numerous domains, including our own field of geography. As with any new technology, trust has taken on an important role in this discussion. In this chapter, we examine the multifaceted concept of trust in foundation models, particularly within a geographic context. As reliance on these models increases and they become relied upon for critical decision-making, trust, while essential, has become a fractured concept. Here we categorize trust into three types: epistemic trust in the training data, operational trust in the model's functionality, and interpersonal trust in the model developers. Each type of trust brings with it unique implications for geographic applications. Topics such as cultural context, data heterogeneity, and spatial relationships are fundamental to the spatial sciences and play an important role in developing trust. The chapter continues with a discussion of the challenges posed by different forms of biases, the importance of transparency and explainability, and ethical responsibilities in model development. Finally, the novel perspective of geographic information scientists is emphasized with a call for further transparency, bias mitigation, and regionally-informed policies. Simply put, this chapter aims to provide a conceptual starting point for researchers, practitioners, and policy-makers to better understand trust in (generative) GeoAI. --- ### Believe It or Not: How Deeply do LLMs Believe Implanted Facts? Authors: Stewart Slocum, Julian Minder, Clément Dumas, Henry Sleight, Ryan Greenblatt, Samuel Marks, Rowan Wang Published: 2025-10-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.17941v1 Knowledge editing techniques promise to implant new factual knowledge into large language models (LLMs). But do LLMs really believe these facts? We develop a framework to measure belief depth and use it to evaluate the success of knowledge editing techniques. We operationalize belief depth as the extent to which implanted knowledge 1) generalizes to related contexts (e.g. Fermi estimates several logical steps removed), 2) is robust to self-scrutiny and direct challenge, and 3) is represented similarly to genuine knowledge (as measured by linear probes). Our evaluations show that simple prompting and mechanistic editing techniques fail to implant knowledge deeply. In contrast, Synthetic Document Finetuning (SDF) - where models are trained on LLM-generated documents consistent with a fact - often succeeds at implanting beliefs that behave similarly to genuine knowledge. However, SDF's success is not universal, as implanted beliefs that contradict basic world knowledge are brittle and representationally distinct from genuine knowledge. Overall, our work introduces measurable criteria for belief depth and enables the rigorous evaluation necessary for deploying knowledge editing in real-world applications. --- ### Beyond More Context: Retrieval Diversity Boosts Multi-Turn Intent Understanding Authors: Zhiming Lin Published: 2025-10-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.17940v1 Multi turn intent understanding is central to task oriented chatbots, yet real deployments face tight token budgets and noisy contexts, and most retrieval pipelines emphasize relevance while overlooking set level diversity and confounds such as more context or exemplar order. We ask whether retrieval diversity, rather than longer prompts, systematically improves LLM intent understanding under fixed budgets. We present a diversity aware retrieval framework that selects in context exemplars to balance intent coverage and linguistic variety, and integrates this selection with standard LLM decoders; the evaluation enforces budget matched prompts and randomized positions, and includes sensitivity analyses over exemplar count, diversity strength, and backbone size. On MultiWOZ 2.4 and SGD, the approach achieves strong gains in Joint Goal Accuracy under equal token budgets, surpassing strong LLM/DST baselines, with consistent improvements across K from 4 to 7 and moderate latency. Overall, the study isolates and validates the impact of content diversity in retrieval and offers a simple, deployable selection principle for building accurate, budget constrained multi turn intent systems. --- ### The Integration of Artificial Intelligence in Undergraduate Medical Education in Spain: Descriptive Analysis and International Perspectives Authors: Ana Enériz Janeiro, Karina Pitombeira Pereira, Julio Mayol, Javier Crespo, Fernando Carballo, Juan B. Cabello, Manel Ramos-Casals, Bibiana Pérez Corbacho, Juan Turnes Published: 2025-10-20 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2510.17938v1 AI is transforming medical practice and redefining the competencies that future healthcare professionals need to master. Despite international recommendations, the integration of AI into Medicine curricula in Spain had not been systematically evaluated until now. A cross-sectional study (July-September 2025) including Spanish universities offering the official degree in Medicine, according to the 'Register of Universities, Centers and Degrees (Registro de Universidades, Centros y Títulos RUCT)'. Curricula and publicly available institutional documentation were reviewed to identify courses and competencies related to AI in the 2025-2026 academic year. The analysis was performed using descriptive statistics. Of the 52 universities analyzed, ten (19.2%) offer specific AI courses, whereas 36 (69.2%) include no related content. Most of the identified courses are elective, with a credit load ranging from three to six ECTS, representing on average 1.17% of the total 360 credits of the degree. The University of Jaén is the only institution offering a compulsory course with AI content. The territorial analysis reveals marked disparities: Andalusia leads with 55.5% of its universities incorporating AI training, while several communities lack any initiative in this area. The integration of AI into the medical degree in Spain is incipient, fragmented, and uneven, with a low weight in ECTS. The limited training load and predominance of elective courses restrict the preparation of future physicians to practice in a healthcare environment increasingly mediated by AI. The findings support the establishment of minimum standards and national monitoring of indicators. --- ### UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts Authors: Fu-Yun Wang, Han Zhang, Michael Gharbi, Hongsheng Li, Taesung Park Published: 2025-10-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.17937v1 We present UniRL-Zero, a unified reinforcement learning (RL) framework that boosts, multimodal language model understanding and reasoning, diffusion model multimedia generation, and their beneficial interaction capabilities within a unified model. Our work defines six scenarios for unified model reinforcement learning, providing systematic baselines for reinforcement learning of unified understanding and generation model. Our code is available at https://github.com/G-U-N/UniRL. --- ### XDXD: End-to-end crystal structure determination with low resolution X-ray diffraction Authors: Jiale Zhao, Cong Liu, Yuxuan Zhang, Chengyue Gong, Zhenyi Zhang, Shifeng Jin, Zhenyu Liu Published: 2025-10-20 Categories: cond-mat.mtrl-sci, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.17936v1 Determining crystal structures from X-ray diffraction data is fundamental across diverse scientific fields, yet remains a significant challenge when data is limited to low resolution. While recent deep learning models have made breakthroughs in solving the crystallographic phase problem, the resulting low-resolution electron density maps are often ambiguous and difficult to interpret. To overcome this critical bottleneck, we introduce XDXD, to our knowledge, the first end-to-end deep learning framework to determine a complete atomic model directly from low-resolution single-crystal X-ray diffraction data. Our diffusion-based generative model bypasses the need for manual map interpretation, producing chemically plausible crystal structures conditioned on the diffraction pattern. We demonstrate that XDXD achieves a 70.4\% match rate for structures with data limited to 2.0~Å resolution, with a root-mean-square error (RMSE) below 0.05. Evaluated on a benchmark of 24,000 experimental structures, our model proves to be robust and accurate. Furthermore, a case study on small peptides highlights the model's potential for extension to more complex systems, paving the way for automated structure solution in previously intractable cases. --- ### AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM Authors: Haoyu Huang, Hong Ting Tsang, Jiaxin Bai, Xi Peng, Gong Zhang, Yangqiu Song Published: 2025-10-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.17934v2 Retrieval-augmented generation (RAG) has shown some success in augmenting large language models (LLMs) with external knowledge. However, as a non-parametric knowledge integration paradigm for LLMs, RAG methods heavily rely on external retrieval modules and the retrieved textual context prior. Especially for very large scale knowledge augmentation, they would introduce substantial inference latency due to expensive searches and much longer relevant context. In this paper, we propose a parametric knowledge integration method, called \textbf{AtlasKV}, a scalable, effective, and general way to augment LLMs with billion-scale knowledge graphs (KGs) (e.g. 1B triples) using very little GPU memory cost (e.g. less than 20GB VRAM). In AtlasKV, we introduce KG2KV and HiKVP to integrate KG triples into LLMs at scale with sub-linear time and memory complexity. It maintains strong knowledge grounding and generalization performance using the LLMs' inherent attention mechanism, and requires no external retrievers, long context priors, or retraining when adapting to new knowledge. --- ### From Observations to Parameters: Detecting Changepoint in Nonlinear Dynamics with Simulation-based Inference Authors: Xiangbo Deng, Cheng Chen, Peng Yang Published: 2025-10-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.17933v2 Detecting regime shifts in chaotic time series is hard because observation-space signals are entangled with intrinsic variability. We propose Parameter--Space Changepoint Detection (Param--CPD), a two--stage framework that first amortizes Bayesian inference of governing parameters with a neural posterior estimator trained by simulation-based inference, and then applies a standard CPD algorithm to the resulting parameter trajectory. On Lorenz--63 with piecewise-constant parameters, Param--CPD improves F1, reduces localization error, and lowers false positives compared to observation--space baselines. We further verify identifiability and calibration of the inferred posteriors on stationary trajectories, explaining why parameter space offers a cleaner detection signal. Robustness analyses over tolerance, window length, and noise indicate consistent gains. Our results show that operating in a physically interpretable parameter space enables accurate and interpretable changepoint detection in nonlinear dynamical systems. --- ### From Charts to Code: A Hierarchical Benchmark for Multimodal Models Authors: Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu, Zijian Zhang, Yifei Tao, Dongxing Mao, Yang Wan, Jingru Tan, Min Zeng, Min Li, Alex Jinpeng Wang Published: 2025-10-20 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.17932v5 We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse real-world scenarios and progressively increasing task difficulty. It consists of three levels: Level 1 (Chart Reproduction) reproduces charts from a reference figure and user query; Level 2 (Chart Editing) involves complex modifications such as changing chart types or adding elements; and Level 3 (Long-Table to Chart Generation) requires models to transform long, information-dense tables into faithful charts following user instructions. To our knowledge, this is the first hierarchical benchmark that reflects practical chart2code usage while systematically scaling task complexity. In total, Chart2Code contains 2,023 tasks across 22 chart types, paired with multi-level evaluation metrics that assess both code correctness and the visual fidelity of rendered charts. We benchmark 25 state-of-the-art (SoTA) LMMs, including both proprietary and the latest open-source models such as GPT-5, Qwen2.5-VL, InternVL3/3.5, MiMo-VL, and Seed-1.6-VL. Experimental results demonstrate that even the SoTA model GPT-5 averages only 0.57 on code-based evaluation and 0.22 on chart-quality assessment across the editing tasks, underscoring the difficulty of Chart2Code. We anticipate this benchmark will drive advances in multimodal reasoning and foster the development of more robust and general-purpose LMMs. Our code and data are available on Chart2Code. --- ### Attracting Commercial Artificial Intelligence Firms to Support National Security through Collaborative Contracts Authors: Andrew Bowne Published: 2025-10-20 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2510.17931v1 Unlike other military technologies driven by national security needs and developed with federal funding, AI is predominantly funded and advanced by commercial industry for civilian applications. However, there is a lack of understanding of the reasons commercial AI firms decide to work with the DoD or choose to abstain from the defence market. This thesis argues that the contract law and procurement framework are among the most significant obstacles. This research indicates that the commercial AI industry actually views the DoD as an attractive customer. However, this attraction is despite the obstacles presented by traditional contract law and procurement practices used to solicit and award contracts. Drawing on social exchange theory, this thesis introduces a theoretical framework, optimal buyer theory, to understand the factors that influence a commercial decision to engage with the DoD. Interviews from a sample of the participants explain why the AI industry holds such perceptions, opinions, and preferences about contracts generally and the DoD, specifically, in its role as a customer. This thesis concludes that commercial AI firms are attracted to contracts that are consistent with their business and technology considerations. Additionally, it develops best practices for leveraging existing contract law, primarily other transaction authority, to align contracting practices with commercial preferences and the machine learning development and deployment lifecycle. --- ### Diagnosing Representation Dynamics in NER Model Extension Authors: Xirui Zhang, Philippe de La Chevasnerie, Benoit Fabre Published: 2025-10-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.17930v2 Extending Named Entity Recognition (NER) models to new PII entities in noisy spoken-language data is a common need. We find that jointly fine-tuning a BERT model on standard semantic entities (PER, LOC, ORG) and new pattern-based PII (EMAIL, PHONE) results in minimal degradation for original classes. We investigate this "peaceful coexistence," hypothesizing that the model uses independent semantic vs. morphological feature mechanisms. Using an incremental learning setup as a diagnostic tool, we measure semantic drift and find two key insights. First, the LOC (location) entity is uniquely vulnerable due to a representation overlap with new PII, as it shares pattern-like features (e.g., postal codes). Second, we identify a "reverse O-tag representation drift." The model, initially trained to map PII patterns to 'O', blocks new learning. This is resolved only by unfreezing the 'O' tag's classifier, allowing the background class to adapt and "release" these patterns. This work provides a mechanistic diagnosis of NER model adaptation, highlighting feature independence, representation overlap, and 'O' tag plasticity. Work done based on data gathered by https://www.papernest.com --- ### EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning Authors: He Du, Bowen Li, Aijun Yang, Siyang He, Qipeng Guo, Dacheng Tao Published: 2025-10-20 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2510.17928v1 Reliable verifiable data has become a key driver of capability gains in modern language models, enabling stable reinforcement learning with verifiable rewards and effective distillation that transfers competence across math, coding, and agentic tasks. Yet constructing generalizable synthetic verifiable data remains difficult due to hallucination-prone generation, and weak or trivial verification artifacts that fail to separate strong from weak solutions. Existing approaches often rely on task-specific heuristics or post-hoc filters that do not transfer across domains and lack a principled, universal evaluator of verifiability. In this work, we introduce an evolutionary, task-agnostic, strategy-guided, executably-checkable data synthesis framework that, from minimal seed supervision, jointly synthesizes problems, diverse candidate solutions, and verification artifacts, and iteratively discovers strategies via a consistency-based evaluator that enforces agreement between human-annotated and strategy-induced checks. This pipeline upgrades filtering into principled synthesis: it reliably assembles coherent, verifiable training instances and generalizes without domain-specific rules. Our experiments demonstrate the effectiveness of the proposed approach under both RLVR and model distillation training paradigms. The results show that training with our synthesized data yields significant improvements on both the LiveCodeBench and AgentBench-OS tasks, highlighting the robust generalization of our framework. --- ### SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion Authors: George Ma, Anurag Koul, Qi Chen, Yawen Wu, Sachit Kuhar, Yu Yu, Aritra Sengupta, Varun Kumar, Murali Krishna Ramanathan Published: 2025-10-20 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.17925v2 Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting repository context at inference time. The low inference-time latency budget affects either retrieval quality or the added latency adversely impacts user experience. We address this limitation with SpecAgent, an agent that improves both latency and code-generation quality by proactively exploring repository files during indexing and constructing speculative context that anticipates future edits in each file. This indexing-time asynchrony allows thorough context computation, masking latency, and the speculative nature of the context improves code-generation quality. Additionally, we identify the problem of future context leakage in existing benchmarks, which can inflate reported performance. To address this, we construct a synthetic, leakage-free benchmark that enables a more realistic evaluation of our agent against baselines. Experiments show that SpecAgent consistently achieves absolute gains of 9-11% (48-58% relative) compared to the best-performing baselines, while significantly reducing inference latency. --- ### Efficient Toxicity Detection in Gaming Chats: A Comparative Study of Embeddings, Fine-Tuned Transformers and LLMs Authors: Yehor Tereshchenko, Mika Hämäläinen Published: 2025-10-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.17924v1 This paper presents a comprehensive comparative analysis of Natural Language Processing (NLP) methods for automated toxicity detection in online gaming chats. Traditional machine learning models with embeddings, large language models (LLMs) with zero-shot and few-shot prompting, fine-tuned transformer models, and retrieval-augmented generation (RAG) approaches are evaluated. The evaluation framework assesses three critical dimensions: classification accuracy, processing speed, and computational costs. A hybrid moderation system architecture is proposed that optimizes human moderator workload through automated detection and incorporates continuous learning mechanisms. The experimental results demonstrate significant performance variations across methods, with fine-tuned DistilBERT achieving optimal accuracy-cost trade-offs. The findings provide empirical evidence for deploying cost-effective, efficient content moderation systems in dynamic online gaming environments. --- ### Rewarding the Journey, Not Just the Destination: A Composite Path and Answer Self-Scoring Reward Mechanism for Test-Time Reinforcement Learning Authors: Jingyu Xing, Chenwei Tang, Xinyu Liu, Deng Xiong, Shudong Huang, Wei Ju, Jiancheng Lv, Ziyue Qiao Published: 2025-10-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.17923v4 Reinforcement Learning (RL) has emerged as a powerful paradigm for advancing Large Language Models (LLMs), achieving remarkable performance in complex reasoning domains such as mathematics and code generation. However, current RL methods face a fundamental scalability bottleneck due to their heavy reliance on human-curated preference data or labeled datasets for reward modeling. To overcome this limitation, we explore RL on unlabeled data where models learn autonomously from continuous experience streams. The core challenge in this setting lies in reliable reward estimation without ground-truth supervision. Existing approaches like Test-Time RL address this through self-consistent consensus, but risk reinforcing incorrect pseudo-labels derived from majority voting. We introduce COMPASS (Composite Path and Answer Self-Scoring), a novel test-time reward mechanism that operates without external supervision. COMPASS integrates two complementary components: the Dual-Calibration Answer Reward (DCAR), which stabilizes training by establishing trustworthy pseudo-labels through confidence and credibility calibration, and the Decisive Path Reward (DPR), which directly optimizes the reasoning process quality beyond mere outcome supervision. By jointly reinforcing trustworthy consensus answers and highly decisive reasoning chains, the COMPASS systematically enhances the model's analytical capabilities. Extensive experiments show that COMPASS achieves significant and consistent performance gains across diverse reasoning tasks and model architectures, advancing a more scalable direction for LLMs to learn from continuous experience. --- ### Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models Authors: Shuodi Liu, Yingzhuo Liu, Zi Wang, Yusheng Wang, Huijia Wu, Liuyu Xiang, Zhaofeng He Published: 2025-10-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.17922v1 Large language models (LLMs) have demonstrated remarkable reasoning and planning capabilities, driving extensive research into task decomposition. Existing task decomposition methods focus primarily on memory, tool usage, and feedback mechanisms, achieving notable success in specific domains, but they often overlook the trade-off between performance and cost. In this study, we first conduct a comprehensive investigation on task decomposition, identifying six categorization schemes. Then, we perform an empirical analysis of three factors that influence the performance and cost of task decomposition: categories of approaches, characteristics of tasks, and configuration of decomposition and execution models, uncovering three critical insights and summarizing a set of practical principles. Building on this analysis, we propose the Select-Then-Decompose strategy, which establishes a closed-loop problem-solving process composed of three stages: selection, execution, and verification. This strategy dynamically selects the most suitable decomposition approach based on task characteristics and enhances the reliability of the results through a verification module. Comprehensive evaluations across multiple benchmarks show that the Select-Then-Decompose consistently lies on the Pareto frontier, demonstrating an optimal balance between performance and cost. Our code is publicly available at https://github.com/summervvind/Select-Then-Decompose. --- ### CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections Authors: Keuntae Kim, Eunhye Jeong, Sehyeon Lee, Seohee Yoon, Yong Suk Choi Published: 2025-10-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.17921v1 Recent advances in enhancing the reasoning ability of large language models (LLMs) have been remarkably successful. LLMs trained with reinforcement learning (RL) for reasoning demonstrate strong performance in challenging tasks such as mathematics and coding, even with relatively small model sizes. However, despite these improvements in task accuracy, the assessment of creativity in LLM generations has been largely overlooked in reasoning tasks, in contrast to writing tasks. The lack of research on creativity assessment in reasoning primarily stems from two challenges: (1) the difficulty of defining the range of creativity, and (2) the necessity of human evaluation in the assessment process. To address these challenges, we propose CLAWS, a method that defines and classifies mathematical solutions into typical, creative, and hallucinated categories without human evaluation, by leveraging attention weights across prompt sections and output. CLAWS outperforms five existing white-box detection methods (Perplexity, Logit Entropy, Window Entropy, Hidden Score, and Attention Score) on five 7-8B math RL models (DeepSeek, Qwen, Mathstral, OpenMath2, and Oreal). We validate CLAWS on 4545 math problems collected from 181 math contests (AJHSME, AMC, AIME). ---