Artificial Intelligence
WinDOM: Self-Family Distillation for Small-Model GUI Grounding
Chengheng Li-Chen, Zhiqian Zhou, Hao Chen et al. (+1 more)
Small ($\sim$2B) GUI-grounding
agents are attractive for on-device deployment, accessibility tooling, and low-cost iteration, but at this scale they face two open recipe questions: how to obtain bounding-box training data without expensive human annotation, and how to combine supervised fine-tuning with reinforcement learning. We address both, with the explicit goal of pushing small-model performance rather than scaling up. WinDOM is a $54{,}425$-record grounding corpus harvested by driving an open-source Windows 11 web reimplementation under headless Playwright, with bounding boxes read directly off the DOM and no OCR or human annotation. Self-Family
Distillation (SFD) is a single rejection-sampling cold-start parameterised only by the teacher choice: either an EMA of the student (no external model) or a frozen larger same-family teacher. We then treat the saturation depth of the SFD cold-start as an explicit GRPO hyperparameter. On a Qwen3.5-2B student, the under-saturated cold-start is a better GRPO initialiser than the converged one: SFD-4B with Early-init RL gains $+5.4$ OOD-mean ($+3.5$ ScreenSpot-Pro, $+7.0$ OSWorld-G, $+5.8$ ScreenSpot-V2) over the base. The same-size EMA mode lands within roughly one OOD-mean point of the cross-size $4$B variant ($65.2$ vs $66.3$) without an external teacher.
Read the full abstract ▾
All authors Chengheng Li-Chen, Zhiqian Zhou, Hao Chen, Nicolas Chauvin
Artificial Intelligence
Agentic System as Compressor: Quantifying System Intelligence in Bits
Zihan Qin and Hongrui Zhang
Large
language models are turning from isolated predictors into agentic systems: they call tools, retrieve evidence, obey environment constraints, use verifiers, and complete tasks through search and multi-turn interaction. We adopts an analytical viewpoint based on "compression is intelligence": under a fixed task distribution, interface, and compute budget, a stronger agentic system lets a target object be reconstructed with fewer bits. We operationalize the measure with arithmetic coding, seed coding, and a fallback, and evaluate it in five settings: reversed text, chess moves,
protein sequences,
retrieval-augmented question answering, and semantic story compression; in all of them agentic components reduce codelength. These small, controlled experiments cover component types typical of real agentic systems, show that codelength can analyze how components, observers, and budgets change residual uncertainty, and offer guidance for evaluating real
agent systems.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.AS
SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness Control in Meeting Scenarios
Jinming Zhang, Wei Rao, Xionghu Zhong et al. (+1 more)
Conventional audio pipelines typically treat
speech enhancement (SE) and automatic gain control (AGC) as discrete modules, which often limits overall performance. For instance, applying AGC before SE may inadvertently amplify background noise, while prioritizing SE tends to over-suppress low-volume
speech. To address these limitations, we propose SE-AGCNet, an end-to-end framework that jointly optimizes SE and AGC. Tailored for meeting scenarios with significant volume variations, SE-AGCNet leverages the synergy between the two tasks: SE preserves quiet
speech, thereby facilitating effective volume adjustment by the AGC component. Furthermore, we propose a specialized data simulation pipeline, SE-AGC-DataGen, and incorporate standardized loudness evaluation metrics: integrated loudness (LUFS), short-term loudness (St LUFS), and LRA. Experiments show that SE-AGCNet consistently achieves target loudness while improving
speech quality and ASR accuracy over competitive baselines.
Read the full abstract ▾
All authors Jinming Zhang, Wei Rao, Xionghu Zhong, Eng Siong Chng
Artificial Intelligence · Cross-listed from cs.CV
Pulmonary Embolism Risk Stratification from CTPA and Medical Records: Vascular Graphs Are Not All You Need
Nathan Painchaud, Tristan Habémont, Morgane des Ligneris et al. (+6 more)
Risk stratification for pulmonary embolism (PE) is critical for clinical decision-making. Stratification guidelines are based on patient medical records, parameters measured from computed
tomography pulmonary angiography (CTPA), and blood tests. However, blood tests are often missing in routine practice. This work studies whether state-of-the-art models can accurately classify risk stratification from only medical records and biomarkers extracted from CTPA images. We
benchmark different approaches to combine medical records and cardiac biomarkers with rich pulmonary vascular information; we add vascular biomarkers to tabular models and apply graph neural networks (GNNs) on the vascular tree's intrinsic graph representation. We use a private
dataset (n=353) with uniquely complete data for PE risk stratification. Our results show that, among global features, medical records and cardiac biomarkers are the most significant predictors, while vascular biomarkers do not further improve stratification. Even more surprising, even GNNs on vascular graphs fail to outperform strong tabular baseline on global features. We consider hypotheses, on both models and data, that could explain this suboptimal performance. Our investigation suggests that, counter-intuitively, vascular graphs might hold no discriminative information for PE risk stratification. Code is available from https://github.com/creatis-myriad/GENESIS.
Read the full abstract ▾
All authors Nathan Painchaud, Tristan Habémont, Morgane des Ligneris, Allan Serva, Pierre Croisille, Laurent Bertoletti, Thomas Lampert, Johannes F. Lutzeyer, Odyssée Merveille
Artificial Intelligence · Cross-listed from econ.TH
Measurable Majorities Are Not Finitely Axiomatizable
Lawrence S. Moss and Arthur Paul Pedersen
This theoretical note studies the finite axiomatizability of strict majority
reasoning in finite social decision frames. Moss and Pedersen (2026) <doi: 10.48550/arXiv.2606.23853> introduce a coherence criterion that characterizes exactly when qualitative majority judgments are representable by a finitely additive measure. The question addressed here is whether that coherence criterion can be replaced, in the finite setting, by any bounded finite fragment. We prove that it cannot. For every $k\ge 1$, we construct a maximal standard frame whose shortest coherence violation has length exactly $2k+2$. Hence there is no uniform finite bound on the incoherence index of social decision frames, resolving
Conjecture 5.7 stated by Moss and Pedersen (2026). The construction is
geometric, in the sense that it proceeds via orthogonality and dimension in rational vector spaces, and self-contained: it isolates a symmetric family of half-sized voting blocs and extends it to a maximal frame in which every shorter balanced obstruction is excluded. Along the explicit infinite sequence of universe sizes obtained in the construction, this also establishes the middle-layer family predicted by
Conjecture B.25 by Moss and Pedersen (2026). Together with the soundness and completeness
theorem for the Moss-Pedersen minimal logic for strict majorities, this establishes that measurable social decision frames are not finitely axiomatizable in that
language.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.HC
Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface
Faliang Yin, Hak-Keung Lam and David Watson
Increasing demand for precise and reliable control in complex scenarios has led to the development of increasingly sophisticated controllers, including data-driven approaches employing closed box models and mathematically rigorous yet complex designs. This complexity highlights the needs for explainable control that can provide human-understandable insights into controller behavior. In this paper, an explainable control framework (XCF) along with supporting
algorithms and user interface are proposed to explain how controllers determine their control actions and their underlying working mechanism. The novel contributions of this work are threefold: First, the XCF is designed to provide model-agnostic explanations for controllers in closed-loop systems and can optionally refine local explanations by system response dynamics. Second, a novel explanation method, hierarchical fuzzy model-agnostic explanation for control systems (HFMAE-C), is proposed based on the designed framework. The HFMAE-C employs a fuzzy logic system to approximate the controller's behavior and system dynamics, providing sample, local, domain and universe level explanations via IF-THEN rules revealing the controller's decision logic and salience values quantifying the contribution of system states to control actions. Third, a large
language model
agent-supported user interface is developed to automatically analyze user requirements, select appropriate
algorithms, interpret the generated explanations to a natural
language report, and provide interactive consultation. Case studies on inverted pendulum system and Turtlebot obstacle avoidance demonstrate the effectiveness of the proposed method through simulated user experiments and quantitative comparisons with mainstream explainable control approaches.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Overview of HIPE-2026: Person-Place Relation Extraction from Multilingual Historical Texts
Juri Opitz, Maud Ehrmann, Corina Raclé et al. (+3 more)
Was this person ever at that place, and if so, when? Answering such questions from noisy,
multilingual historical documents is the central challenge of HIPE-2026, the third edition of the HIPE evaluation series. Moving from named entity recognition and linking (HIPE-2020, HIPE-2022) to
reasoning about relationships between entities, HIPE-2026 targets two temporally grounded relation types: $at$, indicating that a person was present at a location at some point prior to a document's publication date, and $isAt$, indicating presence contemporaneous with that date. This paper presents the results of the evaluation campaign, which confronted 17 participating teams with the challenges of historical
language variation, OCR noise, and indirect contextual cues across three
languages: French, German, and English. The
datasets include historical newspaper text from the nineteenth and twentieth centuries, as well as a surprise-domain generalization set drawn from early modern French literary texts. A distinctive feature of HIPE-2026 is its three-fold evaluation framework, which assesses predictive accuracy, computational efficiency, and cross-domain generalization, reflecting the practical demands of large-scale historical document processing in the cultural heritage domain. Across more than 40 submitted runs, results reveal a wide range of strategies, from state-of-the-art large
language models to lightweight task-specific classifiers, and highlight the trade-offs between accuracy, efficiency, and robustness inherent to historical relation extraction at corpus scale. System descriptions,
datasets, and findings are presented and discussed, offering a detailed picture of the current state of temporally grounded relation extraction for historical documents.
Read the full abstract ▾
All authors Juri Opitz, Maud Ehrmann, Corina Raclé, Andrianos Michail, Matteo Romanello, Simon Clematide
Artificial Intelligence · Cross-listed from cs.CV
Enhancing Brain MRI Anomaly Detection and Reasoning with ROI Rethink and Synthetic Data
Shangkun Li, Jie Xu, Yi Guo et al. (+2 more)
Medical
vision-
language models typically generate diagnoses through single-pass inference without indicating which image regions support their conclusions. This lack of spatial grounding limits clinical utility: outputs cannot be audited, and models may hallucinate findings on normal scans. We present BrReMark (
Brain Rethink via ROI Marking), a framework that introduces explicit region marking into
brain MRI diagnosis. The model first generates hypotheses about potential abnormalities and grounds them through explicit bounding box marking, then verifies conclusions by re-examining the marked evidence. Training combines supervised fine-tuning on structured
reasoning trajectories with reinforcement learning using a composite reward over localization accuracy and diagnostic
reasoning. Furthermore, we integrate a domain randomization-based pathology synthesis augmentation strategy to improve the model's generalizability to out-of-distribution (OOD) data. On internal
benchmark, BrReMark improves mAP50 from 0.74% to 37.54% compared to the base model, while achieving 21.57% Clinical F1 and 45.26% diagnostic accuracy. On NOVA OOD
benchmark, it also achieves competitive overall performance with a 45.7% reduction in false positives compared to the state-of-the-art, indicating reduced
hallucination on rare pathologies. These findings suggest that explicit hypothesis-verification grounding is a practical path toward trustworthy open-ended
brain MRI diagnosis across both in-distribution and OOD settings.
Read the full abstract ▾
All authors Shangkun Li, Jie Xu, Yi Guo, Zeju Li, Yuanyuan Wang
Artificial Intelligence · Cross-listed from cs.DC
AI-Assisted Computational Reproducibility on the FABRIC Testbed
Komal Thareja, Paul Ruth, Berent Aldikacti et al. (+1 more)
Computational reproducibility remains difficult despite being central to scientific research. In this paper, we show how the international FABRIC testbed, combined with a large
language model (LLM) coding
agent through LoomAI, can simplify reproducing published experiments across multiple domains. We reproduced three case studies on FABRIC, covering BBR-family congestion-control evaluations, LAMMPS molecular dynamics scaling
benchmarks on a CPU-only MPI cluster, and stress
protein homeostasis genomics pipelines. Rather than focusing only on matching numerical outputs, we evaluate whether the reproduced experiments support the same scientific conclusions as the original studies. The AI assistant was effective in setting up the environment, adapting code, and debugging, but struggled with the analysis stages that lacked clearly defined workflows, which required human guidance to establish execution order and data dependencies. Across the case studies, the AI-assisted workflow reduced reproduction effort by roughly 4–6 times. We conclude with practical recommendations for improving AI-assisted reproducibility on research testbeds.
Read the full abstract ▾
All authors Komal Thareja, Paul Ruth, Berent Aldikacti, Michael Zink
Artificial Intelligence · Cross-listed from cs.IR
AutoRelAnnotator: Calibrated Model Cascades for Cost-Efficient Relevance Evaluation in Sponsored Search
Md Omar Faruk Rokon, Shasvat Desai, Hong Yao et al. (+1 more)
How can we generate high-quality relevance annotations at scale without the cost and delays of human labeling? Relevance annotations are the backbone of search ranking systems which is needed for training data preparation, NDCG evaluation, and root cause analysis. However, human annotation is slow and off-the-shelf LLMs suffer from accuracy on domain-specific tasks. We propose a calibrated model cascade, a systematic approach for cost-efficient offline relevance annotation by routing queries through progressively larger fine-tuned classifiers. Our central insight is that accuracy and cost are orthogonal optimizations: domain-specific fine-tuning drives accuracy, cascading drives cost, and per-class isotonic calibration adds a small but reliable gain on top. Our contribution is threefold: (a) we decompose the gains and show that fine-tuning contributes 20 accuracy points while cascading is approximately accuracy-neutral but halves compute cost, (b) we introduce per-class isotonic calibration as one component of the cascade, contributing a small but statistically significant gain (+0.6 points over the strongest calibration baseline), and (c) we validate the system in production across six offline use cases, processing 150M+ annotations and enabling faster experimentation cycles. Our work is a building block for scalable, high-quality offline annotation pipelines in search and advertising systems.
Read the full abstract ▾
All authors Md Omar Faruk Rokon, Shasvat Desai, Hong Yao, Kuang-chih Lee
Artificial Intelligence · Cross-listed from cs.CR
Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks
Kavindu Herath, Joshua C. Zhao and Saurabh Bagchi
Federated learning is vulnerable to
backdoor attacks in which malicious clients inject poisoned updates while preserving benign-task performance. In this paper, we study a semantics-driven
backdoor mechanism in which attackers use natural visual accessories as triggers and manipulate only the trigger color while keeping the attack pipeline fixed. Our framework considers semantic trigger objects such as masks and sunglasses, instantiated in black and white variants, and evaluates their effect in a controlled
federated learning setting. Malicious clients construct poisoned samples by applying a trigger to source-class images and relabeling them to an attacker-chosen target class, while benign clients train only on clean data. We analyze this mechanism under both a standard poisoning objective and a stronger SABLE-based objective that combines clean classification loss, triggered target loss, feature-separation loss in the penultimate representation space, and regularization to keep malicious updates close to the global model. This design enables the attack to remain effective while reducing excessive update drift. Experiments on a four-class CelebA hair-color task show that trigger color significantly changes attack success rate even when trigger semantics, placement, and poisoning budget are unchanged. White triggers are more effective for attacks targeting the blond class, whereas black triggers perform better for attacks targeting the black class. The same trend persists under robust aggregation, showing that trigger color is a meaningful factor in the operation, persistence, and evaluation of semantic
backdoor mechanisms in
federated learning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents
Peng Xu, Sijia Chen, Junzhuo Li et al. (+1 more)
Group-based reinforcement learning effectively post-trains LLM
agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajectory outcomes. However, this ties a step's credit to its rollout's final outcome: semantically near-identical intermediate steps receive opposite credit depending on whether their trajectory eventually succeeded or failed. Such semantic credit inconsistency sends conflicting gradients to similar actions and wastes the partially-correct progress inside failed rollouts. Motivated by this, we propose Semantic Consistency Policy Optimization (SCPO), a value-free reward-shaping method that mitigates this inconsistency by recovering step-level credit from successful siblings in the same rollout group. Concretely, SCPO scores each failed step against a successful sibling and adds positive step-level credit for new progress along that sibling. On ALFWorld and WebShop, SCPO matches or exceeds strong group-based baselines, reaching 93.7+/-4.1 percent success on ALFWorld and 74.8+/-2.0 percent on WebShop at 1.5B parameters, with gains concentrated on the hardest multi-step tasks.
Read the full abstract ▾
All authors Peng Xu, Sijia Chen, Junzhuo Li, Xuming Hu
Artificial Intelligence · Cross-listed from cs.CV
Edges Before Embeddings: A Confidence-Aware Blur Gate for Vision-Language Pipelines
Duy Tran Thanh
Production
vision pipelines silently degrade on blurry input, wasting compute on downstream OCR,
retrieval, and
vision-
language model (VLM) calls that cannot recover a usable output. We present MagikaDocumentFromPixel, a lightweight, CPU-friendly image quality gate that classifies a single image as sharp, blurred, or uncertain in roughly 7 ms on a single CPU core. The contributions are (i) a recipe selected from a 46-configuration, 8-sweep empirical search that isolates input resolution as the dominant lever and shows architecture capacity only pays off at >= 384 px; (ii) a confidence-aware routing formalism grounded in classical selective prediction; (iii) the Edge Prior Module (EPM), a
Laplacian-magnitude auxiliary input channel that gives the network direct access to the spectral evidence that classical blur heuristics rely on and that lifts test F1 by +1.3 points in a matched-env comparison; and (iv) an observation that the gate is one instance of a recurring design pattern that appears independently in Magika content-type detection, risk-controlled OCR with VLMs, and DocVLM. The final recipe MobileNetV3-Large with the EPM trained at 384x384 on paired GoPro Large frames, evaluated with 5-scale test-time augmentation reaches F1 = 0.9803 (AUC 0.9989) with a 17 MB ONNX artifact, improving over our fixed-scale baseline on the same hardware (F1 = 0.9672) by +1.31 points. We are explicit about limitations: results are on a single motion-blur distribution, numbers are from a single seed, and calibration is qualitative rather than measured.
Read the full abstract ▾
Artificial Intelligence
AI Snitches Get Glitches: Towards Evading Agentic Surveillance
Hyejun Jeong, Dzung Pham, Amir Houmansadr et al. (+1 more)
AI
agents are now routinely entrusted with access to users' data and communications, operating with growing autonomy and low human supervision. This increasing reliance on AI
agents introduces a novel
privacy risk that we call agentic surveillance, wherein third-party-provided
agents leverage their access privilege to monitor for specific user behaviors, compile a targeted report, and covertly deliver it via tools. Users under surveillance may have neither the ability to control nor awareness of what the
agents do on their behalf. To study the surveillance capabilities of different LLMs, we construct SURVEILBENCH, a
benchmark dataset comprising over 300 diverse surveillance scenarios across domains. We find that several LLMs, such as Gemini 3.1 Pro, report users in at least 3–30% of cases, even when they are not explicitly instructed to do so. Despite safety guardrails and
alignment to protect user
privacy, almost all models can be readily
prompt-tuned to conduct extensive surveillance in >75% of cases. Intriguingly, we also observe the
agents reporting the surveillance attempt itself to government authorities. Finally, we repurpose
prompt injection for the opposite goal—evading surveillance—and develop three techniques that let users hide from, deceive, or induce over-escalation in surveillance
agents. We conclude that agentic surveillance is already easy to implement in practice, and we call for a comprehensive technical, ethical, and legislative framework to protect users.
Read the full abstract ▾
All authors Hyejun Jeong, Dzung Pham, Amir Houmansadr, Eugene Bagdasarian
Artificial Intelligence · Cross-listed from cs.LG
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources
Ke Zhao, Zixiang Di, Hong Qian et al. (+9 more)
Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large
language models (LLMs). Existing approaches typically rely on large-scale supervised
datasets, costly
reasoning annotations, and expensive intermediate step verification, resulting in substantial training overhead. To address these challenges, we propose MiniOpt, a reinforcement learning framework that learns to solve optimization problems through an "
reasoning-to-model-and-solve" paradigm. MiniOpt decomposes optimization
reasoning into structured optimization modeling and executable solver generation. Building upon this paradigm, we introduce OptReward, a reward function with hierarchical score structure that jointly evaluates formulation and solution, enabling effective policy learning without expert demonstrations. We further develop an optimization-oriented policy optimization strategy that improves exploration efficiency and stabilizes reinforcement learning for compact models. Extensive experiments show that MiniOpt-3B exhibits strong optimization generalization across various optimization types, problem scenarios, and task domains. For models with fewer than 10B parameters, MiniOpt series achieves the highest average solving accuracy (SA). For models with more than 10B parameters, MiniOpt still shows competitive performance. These results suggest that optimization-oriented reward design and reinforcement learning provide an effective pathway for developing compact optimization-specialized
language models with strong optimization generalization capabilities. The code is available at https://github.com/Hsiang-1/MiniOpt.
Read the full abstract ▾
All authors Ke Zhao, Zixiang Di, Hong Qian, Xiang Shu, Yaolin Wen, Qitao Shi, Bingdong Li, Xingyu Lu, Xiangfeng Wang, Jun Zhou, Ke Tang, Yang Yu
Artificial Intelligence · Cross-listed from cs.CL
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment
Tianyu Dong, Yangyang Liu, Jiang Zhou et al. (+9 more)
Sparse Mixture-of-Experts (MoE) architectures have emerged as an increasingly influential paradigm as they offer a strategic balance between parameter scalability and computational efficiency. However, low-resource
languages, which suffer from a scarcity of high-quality training data, often have their
tokens routed to different experts than those predominantly activated by high-resource inputs, which limits cross-lingual expert sharing. This cross-lingual routing divergence consequently hinders their efficacy in
multilingual contexts. To address this issue, we propose SARA (Semantically Anchored Routing
Alignment), a framework designed to transfer specialized capabilities from high-resource
languages as anchors to low-resource
languages. SARA explicitly aligns the routing distribution of
multilingual inputs with high-resource semantic anchors using a symmetric Jensen-Shannon (JS) divergence constraint. Unlike traditional
distillation methods that operate on output logits, SARA directly aligns the internal routing distributions of MoE layers, encouraging mechanistic consistency in expert selection across
languages. We conduct experiments on 2 LLMs across 5 low-resource
languages and 3
benchmarks. Experiment results demonstrate that SARA outperforms standard instruction tuning, e.g., +0.8% on Qwen3-30B-A3B and +1.2% on Phi-3.5-MoE-instruct on Global-MMLU. Further analyses show that SARA effectively addresses performance bottlenecks in low-resource
languages, providing a scalable pathway to enhance
multilingual capabilities in sparse architectures.
Read the full abstract ▾
All authors Tianyu Dong, Yangyang Liu, Jiang Zhou, Xinwei Wu, Xiaohu Zhao, Hao Wang, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo, Shaolin Zhu, Deyi Xiong
Artificial Intelligence
Confidence Sequences for Online Statistical Model Checking of Markov Decision Processes
Konstantin Kueffner, Tobias Meggendorfer, Maximilian Weininger et al. (+1 more)
Markov decision processes (MDPs) are a classic model of decision making under uncertainty, exhibiting both non-deterministic choice as well as probabilistic uncertainty. Traditionally, exact knowledge of the underlying probabilities is assumed. However, this often is unrealistic, e.g.\ when modelling cyber-physical systems or biological processes. Here, statistical methods provide a way towards obtaining meaningful guarantees. The classical approach is to gather samples in the MDP, use these to draw statistical conclusions about the transition probabilities, and from there obtain bounds on the true value; then, if these bounds are too broad, repeat. However, existing implementations of this approach are either subtly incorrect or sub-optimal, and quite often both. We present several confidence sequences, which are specifically designed for such \enquote{online} settings, implement all of them in an efficient tool, and show their practical applicability. In particular, we show that they outperform classical \enquote{union-bound} style approaches, and overall our implementation requires 50x less samples on average than previous state of the art.
Read the full abstract ▾
All authors Konstantin Kueffner, Tobias Meggendorfer, Maximilian Weininger, Patrick Wienhöft
Artificial Intelligence · Cross-listed from cs.CL
Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation
Han Jeon, Shiv Medler, Joseph Voyles et al. (+1 more)
With the widespread adoption of large
language models (LLMs) in chatbots and everyday applications, companies increasingly need guardrails that are effective while remaining low-cost and low-latency. Safety evaluation of LLM outputs has generally relied on LLM-based judges, which can be effective but are often slow and expensive to deploy at scale. In this paper, we evaluate whether fine-tuned modern encoder classifiers from the ModernBERT family, including ModernBERT and Ettin, can reliably identify harmful LLM outputs in user-model conversations without substantial performance loss relative to LLM-based judges. We
benchmark these encoder classifiers against rule-based prefix matching, fine-tuned LLM classifiers, and LLM judges using a range of judge-prompting strategies across open-source
adversarial datasets. The LLM judges include evaluation methodologies from StrongReject, ShieldGemma, JailbreakBench, AILuminate, SorryBench, and a Claude-as-a-judge setup, as well as fine-tuned safety classifiers such as LlamaGuard 3 and LlamaGuard 4. The encoder classifiers are fine-tuned on judge-labeled data using a majority-voting label strategy and are then evaluated on a gold-standard holdout
dataset to assess their performance relative to LLM judges. We report absolute performance using F1 score, false negative rate, and precision-recall metrics. We also break down results by attack technique, including single-turn prompting, decomposition, escalation, and context manipulation, to identify where encoder classifiers align with or diverge from LLM-based judges. Our findings provide guidance on when encoder classifiers can serve as cost- and latency-efficient alternatives to LLM-based safety evaluation.
Read the full abstract ▾
All authors Han Jeon, Shiv Medler, Joseph Voyles, Matt Wood
Artificial Intelligence
Fuzzy Quantification over OWL Ontologies and Knowledge Graphs
Enrique Palacín, Fernando Bobillo, Ignacio Huitzil et al. (+2 more)
This paper presents a versatile framework for evaluating fuzzy quantification queries over both standard and fuzzy ontologies as well as knowledge graphs. The primary objective is the
retrieval of individuals that satisfy queries articulated via Type I or Type II fuzzy quantified expressions. A key advantage of the proposed approach is its inherent adaptability: it remains entirely agnostic to the quantifier type, the underlying evaluation method, and the specific data source of the ontology (i.e., OWL ontologies or RDFS knowledge graphs). Furthermore, we present Q2S2, a publicly accessible implementation of this system developed to support future research.
Read the full abstract ▾
All authors Enrique Palacín, Fernando Bobillo, Ignacio Huitzil, Francesca A. Lisi, Umberto Straccia
Artificial Intelligence · Cross-listed from cs.DS
Space-Efficient Language Generation in the Limit
Nicolas Flammarion, Chirag Pabbaraju, Hristo Papazov et al. (+2 more)
We initiate a resource-aware theory of
language generation in the limit under the minimal constraint of space efficiency. In our framework, a learner observes an
adversarial positive stream from a target
language $K$ and must eventually output a
hallucination-free hypothesis
language $L \subseteq K$ while omitting at most $\Delta$ strings of $K$. We focus on $\mathcal{C}_{s,k}$, the collection of
languages recognized by DFAs with at most $s$ states over an alphabet of size $k$, as the natural hypothesis class for
memory-bounded learners. In the exponential-space regime, we prove that a learner can exactly identify the target $K$. Under a stricter
memory budget, we characterize the strongest possible generation guarantees. In particular, we present a streaming
algorithm using $\mathrm{poly}(s,k)$ space that converges to a hypothesis with generation gap $\Delta = O(k^{2s-2})$. Moreover, the learned hypothesis captures every string in $K$ of length at least $2s-1$. We complement this result with a near-matching lower bound through a reduction from a standard communication complexity problem. Specifically, achieving generation gap $\Delta \le k^{(1-\varepsilon)s}$ requires $k^{\Omega(\varepsilon s)}$
memory. Together, these results reveal a sharp transition between
polynomial-space generation and exponential-space exact identification.
Read the full abstract ▾
All authors Nicolas Flammarion, Chirag Pabbaraju, Hristo Papazov, Miltiadis Stouras, Ola Svensson
Artificial Intelligence · Cross-listed from cs.LG
OncoSynth: Synthetic data generation for treatment effect estimation in oncology
Octavia-Andreea Ciora, Julian Welzel, Dennis Frauen et al. (+6 more)
In oncology, access to patient-level data is often restricted. Synthetic data provides an alternative for analyzing treatment effectiveness, but existing methods for synthetic data generation fail to preserve the causal relationships between
covariates, treatments, and outcomes, thereby leading to biased estimates of treatment effects. Here, we introduce OncoSynth, a generative, causally-aware machine learning framework designed to produce synthetic cohorts that enable accurate estimation of population- and patient-level treatment effects. OncoSynth uses a
diffusion-based sequential approach to model how
covariates influence treatment assignment and how treatment affects survival. We evaluate OncoSynth using large lung (N = 37,128) and breast cancer (N = 17,046) cohorts. Our results show that OncoSynth generates high-fidelity synthetic patient cohorts that preserve real-world patient, treatment, and outcome distributions. Notably, OncoSynth improves treatment effect estimation over existing approaches, by reducing population-level treatment effect error by up to 66%, and patient-level treatment effect error by up to 58%. Thereby, OncoSynth supports reliable evidence generation for precision oncology in settings where data sharing is restricted.
Read the full abstract ▾
All authors Octavia-Andreea Ciora, Julian Welzel, Dennis Frauen, Maresa Schröder, Marie Brockschmidt, Harry Amad, Thomas Callender, Mihaela van der Schaar, Stefan Feuerriegel
Artificial Intelligence · Cross-listed from cs.LG
Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets
Divake Kumar, Sina Tayebati, Devashri Naik et al. (+5 more)
Computer-use
agents turn
vision-
language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-severity ranking, and spatial safety regions. Yet evidence on post-hoc uncertainty quantification (UQ) for these
agents is fragmented across isolated model and
dataset pairs, leaving it unclear whether UQ rankings stay stable when the
agent,
benchmark, or observable interface changes. We present Argus, a cross-regime
benchmark for post-hoc UQ in single-step executable GUI grounding: a 27-method open-weight
matrix over 4 VLM
agents and 4
datasets, plus an 8-method closed-source
matrix across 3 frontier vendors where logits, hidden states, and
attention maps are unavailable. Evaluated methods span logit-based scores, sampling and consistency measures, hidden-state and density
estimators (Mahalanobis, SAPLMA),
attention-based scores, P(True) and verbalised-confidence prompting, and split-conformal prediction. The main finding is selective transfer: UQ rankings are stable across
datasets for a fixed model, but degrade across model classes and observable interfaces. Hidden-state and density methods are the most stable open-weight family, while CoCoA-1MCA, Focus, sampling-based scores, and verbalised self-assessment win in specific regimes. Within-model ranking transfer is strong (Spearman rho up to 0.969), but cross-tier transfer to closed-source vendors averages only +0.08, so closed-source UQ should be reranked on the target rather than extrapolated. Conformal click regions show score-level discrimination is not enough for deployment: locally weighted disks shrink radii by 40-60% when the plug-in UQ is calibrated, but coverage degrades under calibration-test or interface mismatch. We release per-item records, calibration/test splits, UQ scores, and analysis scripts for regime-aware UQ selection in GUI
agents.
Read the full abstract ▾
All authors Divake Kumar, Sina Tayebati, Devashri Naik, Amanda Sofie Rios, Nilesh Ahuja, Omesh Tickoo, Ranganath Krishnan, Amit Ranjan Trivedi
Artificial Intelligence · Cross-listed from cs.LG
Gradient-based inverse lithography for EUV masks via the waveguide method and a physics-informed neural operator
Vasiliy A. Es'kin and Egor V. Ivanov
Gradient-based inverse lithography technology~(ILT) for extreme ultraviolet~(EUV) masks is presented. A novel framework treats the differentiable waveguide method and the recently proposed waveguide neural operator~(WGNO) as end-to-end physics engines, recovering the permittivity of the absorber of the mask through automatic differentiation of the full forward diffraction model. Numerical experiments on realistic 2D and 3D absorbers of the mask (TaBN, La, U) at $\lambda{=}11.2$~nm show that the considered ILT methods make it possible to obtain a mask structure that achieves the desired field on the wafer.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detection
Linchun Wu, Qin Zou, Jiwen Lu et al. (+1 more)
3D anomaly detection in point clouds is critical for high-precision industrial manufacturing. Reconstruction-based methods have laid a strong foundation by detecting 3D anomalies through comparisons between defective inputs and their reconstructed normal counterparts. However, existing methods still suffer from two challenges: 1) the foreground weak defective regions such as scratches are hard to reconstruct and detect, where the anomaly deviations in normalized point clouds can be as small as $10^{-3}$; 2) the background non-defective regions are prone to get positional bias in reconstruction, which leads to false positives. To address these challenges, we propose PCDiff, a point cloud
diffusion framework for instance-level 3D anomaly generation and detection. In the generation phase, an instance-level multi-modal
attention is embedded into the generation framework, where anomalies are conditioned with texture gradient, image patch, text and mask. The instance-level condition enables the high-quality generation of weak-defective anomalies. In the detection phase, a joint local-global reconstruction
algorithm is introduced to ensure local anomaly restoration and global
geometric consistency, which preserves background normal structure while restoring the foreground defect. Extensive experiments demonstrate that the proposed PCDiff significantly outperforms state-of-the-art methods in both 3D anomaly generation fidelity and reconstruction quality, leading to substantial improvements in anomaly detection accuracy.
Read the full abstract ▾
All authors Linchun Wu, Qin Zou, Jiwen Lu, Qingquan Li
Artificial Intelligence
Position Spaces and Graphs
Rita-Nathalia Assaf, Tom Davot, Frédéric Lardeux et al. (+1 more)
In this paper, we introduce position graphs, a graph-based
reasoning framework based on the formalization of position spaces. This framework utilizes two strict partial orders, representing horizontal and vertical
alignment and precedence, to model the relative positions of discrete
tokens. Unlike general qualitative spatial calculi, position graphs are constrained by a chain condition and compatibility requirements that focus on rows and columns. We provide a comprehensive theoretical analysis of this representation, beginning with a characterization of graph consistency. Conditions to ensure the consistency of position graphs are established. Furthermore, we investigate the computational complexity of structural pattern discovery, modeled as the induced subgraph isomorphism problem. We demonstrate that this problem remains NP-complete even within the restricted class of position graphs. While initially motivated by document processing, this work focuses on the underlying mathematical properties and algebraic consistency of position-based constraints, providing a formal logical layer that is independent of specific data extraction techniques.
Read the full abstract ▾
All authors Rita-Nathalia Assaf, Tom Davot, Frédéric Lardeux, Frédéric Saubion
Artificial Intelligence
GUI agent: Guided Exploration of User-Sensitive Screens
Aradhana Nayak, Mussadiq Nazeer, Wang Peng et al. (+1 more)
LLM
agents are increasingly being used to automate tasks for users within an open GUI environment. They inevitably encounter screens containing user-sensitive information, for which takeover of task execution by the user is highly desirable or even necessary. State-of-the-art LLM-driven
agents are usually fine-tuned to complete tasks regardless of the safety implications of their actions. This makes their real-world deployment difficult and adversely affects the reliability. Therefore, it is crucial to identify and categorize user-sensitive states and define user-sensitive queries. This
dataset would be to engineers to recognize and request handover to the user in critical scenarios. This short paper develops an explorer
agent that systematically explores the query space starting from one demonstrated task to identify queries that, if executed, would lead to user-sensitive states in a GUI environment.
Read the full abstract ▾
All authors Aradhana Nayak, Mussadiq Nazeer, Wang Peng, Feng Liu
Artificial Intelligence · Cross-listed from cs.RO
Average-Power-Budgeted Underwater Vehicle Control via Constrained Reinforcement Learning
Yinuo Wang, Gavin Tao, Yuze Liu et al. (+1 more)
Underwater vehicles operate from a fixed onboard energy budget that propulsion rapidly depletes, so a controller that completes its task while drawing less thruster power directly extends mission range and endurance. Reinforcement learning yields capable model-free controllers for station-keeping and trajectory tracking, but optimizing task accuracy alone drives the policy toward oscillatory, energy-wasting actuation. The established remedy subtracts an energy penalty from the reward, yet this sets the task-power trade-off through a single weight with no physical units: a target power level cannot be specified, the weight must be re-tuned for every vehicle and task, and a mismatched weight can even raise power. This paper instead formulates energy-efficient
underwater control as a constrained Markov decision process in which average thruster power is subject to an explicit budget, solved with a PPO-Lagrangian
algorithm. The power level is set by declaring a budget in physical units, and a single dual variable is updated online to meet it for each vehicle and task, without manual weight search. Across three vehicles and four tasks in the MarineGym simulator, the energy-constrained policy draws the least power in all twelve settings, reducing it by 14–65% (up to 64.9%) over a task-only baseline and below an energy-reward baseline everywhere, while remaining the smoothest in ten settings and preserving task accuracy except in one deliberately power-limited regime. Imposing energy as an explicit constraint thus offers a tuning-free route to energy-efficient
underwater control that needs no per-vehicle, per-task weight search.
Read the full abstract ▾
All authors Yinuo Wang, Gavin Tao, Yuze Liu, John V. Ringwood
Artificial Intelligence · Cross-listed from cs.CV
Steering Vision-Language Models with Joint Sparse Autoencoders
Huizhen Shu, Xuying Li, Hongxu Lin et al. (+2 more)
Sparse Autoencoders (SAEs) have shown promise for analyzing
language models, but applying them to
vision-
language models (VLMs) often yields representations that are difficult to use as controllable cross-modal steering directions. We introduce the Joint Sparse Autoencoder (JSAE), which uses an explicit
alignment constraint to jointly factorize sequence-pooled
vision and
language activations into shared, interpretable image/caption-level features. Applied to LLaVA, JSAE recovers cross-modal features for recognizable concepts (e.g., food and animals). Through bidirectional interventions (additive steering and suppression), we observe a layer-dependent asymmetry under our protocol: additive steering peaks at mid-to-late (pre-output) layers and weakens at both ends, whereas suppression scores remain within a comparable range across all probed layers within statistical noise. Experiments on three VLMs, namely LLaVA-v1.6-Mistral-7B, Llama3-LLaVA-8B, and the MoE-based Qwen3-VL-30B, show related layer-localized effects across architectures. Together, these results suggest that explicitly aligned sparse representations support more controllable intervention-based analysis of
multimodal features, within an identifiable layer range, than the unconstrained alternatives tested here.
Read the full abstract ▾
All authors Huizhen Shu, Xuying Li, Hongxu Lin, Wenjie Sun, Hui Li
Artificial Intelligence · Cross-listed from cs.CL
Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization
Long Chen, Ryan Razkenari, Yuxuan Zhou et al. (+5 more)
As advanced RAG variants like GraphRAG and Agentic RAG emerge, one leading question is when and how to use them. Here, we introduce a framework for different RAG scenarios evaluation and comparison on semi-structured knowledge bases, including regular RAG, GraphRAG, Modular RAG and Agentic RAG. We provide implementation for 9 standardized RAG scenarios, and conduct experiments for a comprehensive comparison. These scenarios are designed for real use cases regarding data and domain restrictions, spanning from simple document-based
retrieval to advanced features such as hybrid text-graph
retrieval, integration with computed or pre-defined domain knowledge graphs, agentic multi-step planning, and
agent-graph integration. Besides, we present a novel context engineering method for GraphRAG and Agentic RAG, addressing the context/
memory overflow issues, efficiently managing text and graph
retrievals with new representations and agentic loop design, leading to 19%-53% reduction on
token usage. Moreover, further analysis identifies a
retrieval-generation gap where expanded
retrieval does not proportionally improve generation quality, suggesting
retrieval-oriented metrics overstate advanced
retrieval benefits. This work provides data-driven insights on when and how to use them for building production-ready intelligent RAG systems.
Read the full abstract ▾
All authors Long Chen, Ryan Razkenari, Yuxuan Zhou, Yuan Tian, Rahul Ghosh, Venkatesh Pappakrishnan, Disha Ahuja, Vidya Sagar Ravipati
Artificial Intelligence · Cross-listed from cs.CR
Taxonomy of Risks on Automated Fact-Checking Systems Considering its Propagation
Jun Yajima, Tatsuya Oka and Takao Okubo
In recent years, the posting of fake news including disinformation and misinformation on social networking services (SNS) has become a social problem. To combat this fake news, fact-checking that is the process of assessing the veracity of posts on SNS has become increasingly important. While fact-checking is currently performed by fact-checking organizations, it is difficult to fact-check all posts on SNS. Therefore, the use of automated fact-checking systems is effective. Recent automated fact-checking systems utilize artificial intelligence and large
language models, so there are risks of incorrect judgments and posting incorrect results on social media which can lead to the spread of misinformation or to engage in defamation. In this paper, as a first step toward enabling the safe use of automated fact-checking systems, we categorize the specific risks on automated fact-checking systems. In this categorizing, we consider a three-stage risk propagation: risk factors, hazardous situations, and harm. Our analysis revealed that 32 specific risks exist in automated fact-checking systems. In this paper, we utilize the categorized risks as analytical cues (guide words) to present the risk assessment of the automated fact-checking system DEFAME. This assessment result indicates that risks that cannot be derived using STRIDE, a conventional IT security risk assessment method can be derived using our guide words.
Read the full abstract ▾