# Research Papers — 2026-05 · bundle page 224 of 326

> Full-text markdown of papers #11151–11200 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-05/page/224
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/223.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/225.md)

### Navigating the Sea of LLM Evaluation: Investigating Bias in Toxicity Benchmarks

Authors: Regina Gugg, Selina Niederländer, Andreas Stöckl, Martin Flechl
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10639v1

The rapid adoption of LLMs in both research and industry highlights the challenges of deploying them safely and reveals a gap in the systematic evaluation of toxicity benchmarks. As organizations increasingly rely on these benchmarks to certify models for customer-facing applications and automated moderation, unrecognized evaluation biases could lead to the deployment of vulnerable or unsafe systems. This work investigates the robustness of established benchmarking setups and examines how to measure currently neglected intrinsic biases, such as those related to model choice, metrics, and task types. Our experiments uncover significant discrepancies in benchmark behaviors when evaluation setups are altered. Specifically, shifting the task from text completion to summarization increases the tendency of benchmarks to flag content as harmful. Additionally, certain benchmarks fail to maintain consistent behavior when the input data domain is changed. Furthermore, we observe model-specific instabilities, demonstrating a clear need for more robust and comprehensive safety evaluation frameworks.

---

### Teacher-Aware Evolution of Heuristic Programs from Learned Optimization Policies

Authors: Minyu Chen, Song Qin, Ling-I Wu, Jianxin Xue, Guoqiang Li
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10634v1

LLM-based automatic heuristic design has shown promise for generating executable heuristics for combinatorial optimization, but existing methods mainly rely on delayed endpoint performance. We propose a \emph{teacher-aware evolutionary framework} that uses independently trained learned optimization policies as behavioral teachers. Instead of deploying or imitating the teacher, our method queries it on states visited by candidate heuristic programs and uses its action preferences as local feedback for evolution. The resulting search discovers static executable heuristics guided by both task performance and teacher-derived behavioral signals. Experiments on scheduling, routing, and graph optimization benchmarks show that our method improves over performance-driven LLM heuristic evolution baselines while requiring no neural inference at deployment. These results suggest that learned optimization policies can be repurposed as behavioral feedback sources for automatic heuristic discovery.

---

### Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs

Authors: Krishak Aneja, Manas Mittal, Anmol Goel, Ponnurangam Kumaraguru, Vamshi Krishna Bonagiri
Published: 2026-05-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.10633v1

Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work links these failures to specific directions in the activation space, their relationship to the model's broader persona remains unexplored. We map the latent personality space of LLMs through established psychometric profiles like the Big Five, Dark Triad, and LLM-specific behaviors (e.g. evil, sycophancy), and show that the semantic geometry is highly stable across aligned models and their corrupted fine-tunes. Through causal interventions, we find that directions isolating social valence, such as the 'Evil' persona vector, and a Semantic Valence Vector (SVV) that we introduce, function as intrinsic guardrails: ablating them drives the misalignment rates above $40$%, while amplifying them suppresses the failure mode to less than $3$%. Leveraging the structural stability of the personality space, we show that vectors extracted $\textit{a priori}$ from an instruct-tuned model transfer zero-shot to successfully regulate EM in corrupted fine-tunes. Overall, our findings suggest that harmful fine-tuning does not overwrite a model's internal representation of personality, allowing conserved representations to serve as robust, cross-distribution guardrails.

---

### Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI Reconstruction

Authors: Laurenz Nagler, Martin Zach, Thomas Pock
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10629v1

Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However, most existing methods rely on large networks with opaque time-conditioning mechanisms, and require offline coil sensitivity estimation. This results in limited interpretability of the reconstruction process and reduced flexibility in the acquisition setup. To address these limitations, we jointly reconstruct the image and the coil sensitivities by combining the parameter-efficient product-of-Gaussian-mixture diffusion model as an image prior with a classical smoothness prior on the coil sensitivities. The proposed method is fast and robust to both contrast and anatomical distribution shifts as well as changing k-space trajectories. Finally, we propose a more expressive parameterization of the image prior which improves results in denoising and magnetic resonance image reconstruction.

---

### Hyper-FSAD: Training-Free and Language-Free Few-Shot Anomaly Detection via Sparse Hyper Matching

Authors: Guohuan Xie, Xin He, Dingying Fan, Siqi Li, Yun Liu
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10628v2

Few-shot anomaly detection (FSAD) is particularly valuable when only a few normal images are available in a new target domain, while anomalous cases are rare, diverse, and difficult to enumerate in advance. However, existing methods often still require task-specific fitting or language prompts, and their patch-level retrieval commonly relies on brittle nearest-neighbor or fixed Top-$p$ rules. We propose \textbf{Hyper-FSAD}, a training-free and language-free framework that performs support-only inference with a frozen visual encoder. We formulate FSAD as support-only scoring in frozen feature space and establish the selective stability of sparse retrieval and sufficient conditions for normal--anomaly separation. Guided by this analysis, \textbf{Sparse Hyper Matching} uses \textit{sparsemax} to adaptively select support patches for each query patch, exactly suppressing below-threshold distractors without a manually specified retrieval hyperparameter. \textbf{Dual-Branch Image Scoring} further combines local reconstruction discrepancies with support-conditioned global <CLS> deviation. Across four industrial and two medical benchmarks, Hyper-FSAD achieves the best overall performance across the 1/2/4-shot settings, while requiring only 52.6\,ms per image and 0.89\,GB GPU memory. The code will be released.

---

### Hypergraph-Enhanced Training-Free and Language-Free Few-Shot Anomaly Detection

Authors: Guohuan Xie, Xin He, Dingying Fan, Siqi Li, Yun Liu
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10628v1

Few-shot anomaly detection (FSAD) has made significant strides, yet existing methods still face critical challenges: (i) dependence on task- or dataset-specific training/fine-tuning, (ii) reliance on language supervision or carefully hand-crafted prompts, and (iii) limited robustness across domains. In this paper, we introduce HyperFSAD, a novel FSAD framework that is training-free, language-free, and robust across domains, offering a powerful solution to these challenges. Built upon DINOv3 and a hypergraph-based inference mechanism, our approach performs inference without any task-specific optimization or text prompts, while remaining competitive. Specifically, we replace sensitive nearest-neighbor / top-$n$ matching with \textbf{Sparse Hyper Matching}: \textit{sparsemax} first selects the most relevant support patches, which are then aggregated into a \textit{hyperedge} as compact normal evidence to suppress background noise and distractors. We further introduce \textbf{Dual-Branch Image Scoring}, which fuses \emph{spatial anomaly evidence} from the patch-grid anomaly map with \emph{global semantic deviation} captured by support-aware CLS matching, yielding a robust image-level anomaly score in a strictly visual manner. Notably, all components of HyperFSAD are purely visual, eliminating the need for labor-intensive hand-crafted text prompts. Under the stringent training-free and language-free setting, HyperFSAD achieves state-of-the-art performance across six datasets spanning four industrial datasets (MVTecAD, VisA, MPDD, BTAD) and two medical datasets (RESC, BraTS).

---

### Interpretable Coreference Resolution Evaluation Using Explicit Semantics

Authors: Bruno Gatti, Giuliano Martinelli, Roberto Navigli
Published: 2026-05-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.10627v1

Coreference resolution is typically evaluated using aggregate statistical metrics such as CoNLL-F1, which measure structural overlap between predicted and gold clusters. While widely used, these metrics offer limited diagnostic insights, penalizing errors without revealing whether a system struggles with specific semantic categories, such as people, locations, or events, and making it difficult to interpret model capabilities or derive actionable improvements. We address this gap by introducing a semantically-enhanced evaluation framework for coreference resolution. Our approach overlays Concept and Named Entity Recognition (CNER) onto coreference outputs, assigning semantic labels to nominal mentions and propagating them to entire coreference clusters. This enables the computation of typed scores aimed at evaluating mention extraction and linking capabilities stratified by semantic class. Across our experiments on OntoNotes, LitBank, and PreCo, we show that our framework uncovers systematic weaknesses that remain obscured by aggregate metrics. Furthermore, we demonstrate that these diagnostics can be used to design targeted, low-cost data augmentation strategies, achieving measurable out-of-domain improvements.

---

### Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive Control

Authors: Ramesh Arvind Naagarajan, Zühal Wagner, Stefan Streif
Published: 2026-05-11
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.10624v1

Model Predictive Control (MPC) is widely used to operate safety-critical infrastructure by predicting future trajectories and optimizing control actions. However, nonlinear dynamics, hard safety constraints, and numerical optimization often render individual control moves opaque to human operators, undermining trust and hindering deployment. This paper presents Hierarchical Causal Abduction (HCA), which combines (i) physics-informed reasoning via domain knowledge graphs, (ii) optimization evidence from Karush--Kuhn--Tucker (KKT) multipliers, and (iii) temporal causal discovery via the PCMCI algorithm to generate faithful, human-interpretable explanations for control actions computed by nonlinear MPC. Across three diverse control applications (greenhouse climate, building HVAC, chemical process engineering) with expert validation, HCA improves explanation accuracy by 53\% over LIME (0.478 vs. 0.311) using a single set of cross-domain parameters without per-domain tuning; domain-specific KKT-threshold calibration over 2--3 days further increases accuracy to 0.88. Ablation studies confirm that each evidence source is essential, with 32--37\% accuracy degradation when any component is removed, and HCA's ranking-and-validation methodology generalizes beyond MPC to other prediction-based decision systems, including learning-based control and trajectory planning.

---

### Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination

Authors: Yangneng Chen, Junlin Li, Weijun Yao, Xilai Ma, Guodong Du, Wenya Wang, Jing Li
Published: 2026-05-11
Categories: cs.MM, cs.CV
arXiv: https://arxiv.org/abs/2605.10622v1

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet their reliability is persistently undermined by hallucinations-generating text that contradicts visual input. Recent studies often attribute these errors to inadequate visual attention. In this work, we analyze the attention mechanisms via the logit lens, uncovering a distinct anomaly we term Vocabulary Hijacking. We discover that specific visual tokens, defined as Inert Tokens, disproportionately attract attention. Crucially, when their intermediate hidden states are projected into the vocabulary space, they consistently decode to a fixed set of unrelated words (termed Hijacking Anchors) across layers, revealing a rigid semantic collapse. Leveraging this semantic rigidity, we propose Hijacking Anchor-Based Identification (HABI), a robust strategy to accurately localize these Inert Tokens. To quantify the impact of this phenomenon, we introduce the Non-Hijacked Visual Attention Ratio (NHAR), a novel metric designed to identify attention heads that remain resilient to hijacking and are critical for factual accuracy. Building on these insights, we propose Hijacking-Aware Visual Attention Enhancement (HAVAE), a training-free intervention that selectively strengthens the focus of these identified heads on salient visual content. Extensive experiments across multiple benchmarks demonstrate that HAVAE significantly mitigates hallucinations with no additional computational overhead, while preserving the model's general capabilities. Our code is publicly available at https://github.com/lab-klc/HAVAE.

---

### Hierarchical End-to-End Taylor Bounds for Complete Neural Network Verification

Authors: Taha Entesari, Mahyar Fazlyab
Published: 2026-05-11
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2605.10621v1

Reachability analysis of neural networks, which seeks to compute or bound the set of outputs attainable over a given input domain, is central to certifying safety and robustness in learning-enabled physical systems. Since exact reachable set computation is generally intractable, existing methods typically rely on tractable overapproximations. Examining the state of the art for smooth, twice-differentiable networks, we observe that existing approaches exploit at most second-order information and do not systematically leverage higher-order information. In this work, we introduce \textsc{HiTaB}, a novel verification framework that exploits second-order smoothness through both the Hessian, $\nabla^2 f$, and its Lipschitz constant, $L_{\nabla^2 f}$. We further develop a unified hierarchy of zeroth-, first-, and second-order bounds, together with precise conditions under which higher-order approximations yield provable improvements. Our main technical contribution is a compositional procedure for efficiently bounding $L_{\nabla^2 f}$ in deep neural networks via layerwise propagation of curvature bounds. We extend the framework to both $\ell_2$- and $\ell_\infty$-constrained input sets and show how it can be integrated into branch-and-bound verification pipelines. To our knowledge, this is the first practical reachability analysis framework for smooth neural networks that systematically exploits Lipschitz continuity of curvature, leading to tighter and more informative safety certificates.

---

### MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image

Authors: Alan Arazi, Eilam Shapira, Shoham Grunblat, Mor Ventura, Elad Hoffer, Gioia Blayer, David Holzmüller, Lennart Purucker, Gaël Varoquaux, Frank Hutter, Roi Reichart
Published: 2026-05-11
Categories: cs.LG, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2605.10616v2

Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack native support for unstructured modalities such as text and image, and rely on frozen, pretrained embeddings to process them. On established Multimodal Tabular Learning benchmarks, we show that tuning the embeddings to the task improves performance. Existing benchmarks, however, often focus on the mere co-occurrence of modalities; this leads to high variance across datasets and masks the benefits of task-specific tuning. To address this gap, we introduce MulTaBench, a benchmark of 40 datasets, split equally between image-tabular and text-tabular tasks. We focus on predictive tasks where the modalities provide complementary predictive signal, and where generic embeddings lose critical information, necessitating Target-Aware Representations that are aligned with the task. Our experimental results demonstrate that the gains from target-aware representation tuning generalize across both text and image modalities, several tabular learners, encoder scales, and embedding dimensions. MulTaBench constitutes the largest image-tabular benchmarking effort to date, spanning high-impact domains such as healthcare and e-commerce. It is designed to enable the research of novel architectures which incorporate joint modeling and target-aware representations, paving the way for the development of novel Multimodal Tabular Foundation Models.

---

### MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image

Authors: Alan Arazi, Eilam Shapira, Shoham Grunblat, Mor Ventura, Elad Hoffer, Gioia Blayer, David Holzmüller, Lennart Purucker, Gaël Varoquaux, Frank Hutter, Roi Reichart
Published: 2026-05-11
Categories: cs.LG, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2605.10616v1

Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack native support for unstructured modalities such as text and image, and rely on frozen, pretrained embeddings to process them. On established Multimodal Tabular Learning benchmarks, we show that tuning the embeddings to the task improves performance. Existing benchmarks, however, often focus on the mere co-occurrence of modalities; this leads to high variance across datasets and masks the benefits of task-specific tuning. To address this gap, we introduce MulTaBench, a benchmark of 40 datasets, split equally between image-tabular and text-tabular tasks. We focus on predictive tasks where the modalities provide complementary predictive signal, and where generic embeddings lose critical information, necessitating Target-Aware Representations that are aligned with the task. Our experimental results demonstrate that the gains from target-aware representation tuning generalize across both text and image modalities, several tabular learners, encoder scales, and embedding dimensions. MulTaBench constitutes the largest image-tabular benchmarking effort to date, spanning high-impact domains such as healthcare and e-commerce. It is designed to enable the research of novel architectures which incorporate joint modeling and target-aware representations, paving the way for the development of novel Multimodal Tabular Foundation Models.

---

### Responsible Benchmarking of Fairness for Automatic Speech Recognition

Authors: Felix Herron, Ange Richard, François Portet, Alexandre Allauzen, Solange Rossato
Published: 2026-05-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.10615v1

Many studies have shown automatic speech processing (ASR) systems have unequal performance across speakergroups (SG's). However, the manner in which such studies arrive at this conclusion is inconsistent. To pave the wayfor more reliable results in future studies, we lay out best practices for benchmarking ASR fairness based on literaturefrom machine learning fairness, social sciences, and speech science. We first describe the importance of preciselythe fairness hypothesis being interrogated, and tailoring fairness metrics to apply specifically to said hypothesis.We then examine several benchmarks used to rate ASR systems on fairness and discuss how their results can bemisconstrued without assiduous oversight into the intersections between SG's. We find that evaluating fairnessbased on single heterogeneous SG's, such as they are defined in fairness benchmarks, can lead to misidentifyingwhich SG's are actually being mistreated by ASR systems. We advocate for as fine-grained an analysis as possibleof the intersectionality of as many demographic variables as are available in the metadata of fairness corpora in orderto tease out such spurious correlations

---

### PRISM: Generation-Time Detection and Mitigation of Secret Leakage in Multi-Agent LLM Pipelines

Authors: Riya Tapwal, Abhishek Kumar, Carsten Maple
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10614v1

Multi-agent LLM systems introduce a security risk in which sensitive information accessed by one agent can propagate through shared context and reappear in downstream outputs, even without explicit adversarial intent. We formalise this phenomenon as propagation amplification, where leakage risk increases across agent boundaries as sensitive content is repeatedly exposed to downstream generators. Existing defences, including prompt-based safeguards, static pattern matching, and LLM-as-judge filtering, are not designed for this setting: they either operate after generation, rely primarily on surface-form patterns, or add substantial latency without modelling the generation process itself. To resolve these issues, we propose PRISM, a real-time defence that treats credential leakage as a sequential risk accumulation problem during generation. At each decoding step, PRISM combines 16 signals spanning lexical, structural, information-theoretic, behavioural, and contextual features into a calibrated risk score, enabling per-token intervention through green, yellow, and red risk zones. Our central observation is that credential reproduction is often preceded by a measurable shift in generation dynamics, characterised by entropy collapse and increasing logit concentration. When combined with text-structural cues such as identifier-pattern detection, these temporal signals provide an early warning of leakage before a secret is fully reconstructed. Across a 2,000-task adversarial benchmark covering 13 attack categories and three pressure levels in a heterogeneous four-agent pipeline, PRISM achieves F1 = 0.832 with precision = 1.000 and recall = 0.712, while producing no observed leakage on our benchmark (0.0% task-level leak rate) and preserving output utility of 0.893. It substantially outperforms the strongest baseline, Span Tagger, which achieves F1 = 0.719 with a 15.0% task-level leak rate.

---

### Exact Fixed-Point Constraints in Neural-ODEs with Provable Universality

Authors: Feliciano Giuseppe Pacifico, Duccio Fanelli, Lorenzo Buffoni, Lorenzo Chicchi, Diego Febbe, Raffaele Marino
Published: 2026-05-11
Categories: cond-mat.dis-nn, cs.LG, physics.bio-ph
arXiv: https://arxiv.org/abs/2605.10613v1

We introduce a technique that enables Neural-ODEs to approximate arbitrary velocity fields with a priori planted fixed-points. Specifically, a recipe is given to explicitly accommodate for a finite collection of points in the reference multi-dimensional space of the Neural-ODE where the velocity field is exactly equal to zero. In this way, the gradient-based training is rigorously constrained inside the prescribed hypothesis class while leaving the expressive power of the Neural-ODE unaltered. We rigorously prove the universality of the Neural-ODE under any local constraints in the velocity field and give a computationally convenient way of imposing the fixed points. Our method is then tested on two paradigmatic physical models.

---

### Reconfigurable Computing Challenge: Real-Time Graph Neural Networks for Online Event Selection in Big Science

Authors: Marc Neu, Frank Baptist, Thomas Lobmaier, Fabio Papagno, Torben Ferber, Jürgen Becker
Published: 2026-05-11
Categories: cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2605.10612v1

Graph neural networks are increasingly adopted in trigger systems for collider experiments, where strict latency and throughput constraints render deployment on embedded platforms challenging. As detectors move towards higher granularity, the number of inputs per inference increase and FPGA-only solutions face resource bottlenecks. This work presents an end-to-end demonstrator for the real-time deployment of a dynamic Graph Neural Network for the Belle II electromagnetic calorimeter hardware trigger on the AMD Versal VCK190, leveraging both FPGA fabric and AI Engine tiles. We develop a Python-based semi-automated design flow covering operator fusion, partitioning, mapping, spatial parallelization, and kernel-level optimization. Our design achieves a throughput of 2.94 million events per second at an end-to-end latency of 7.15 microseconds. Compared to the FPGA-only baseline, this represents a 53% throughput improvement while reducing DSP utilization from 99% to 19% at 29% AI Engine tile utilization. To validate the deployment, an interactive visualization pipeline enables real-time monitoring of inference results on the physical demonstrator.

---

### Re-Triggering Safeguards within LLMs for Jailbreak Detection

Authors: Zheng Lin, Zhenxing Niu, Haoxuan Ji, Yuzhe Huang, Haichang Gao
Published: 2026-05-11
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2605.10611v1

This paper proposes a jailbreaking prompt detection method for large language models (LLMs) to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts that bypass them. We argue that such jailbreaking prompts are inherently fragile, and thus introduce an embedding disruption method to re-activate the safeguards within LLMs. Unlike previous defense methods that aim to serve as standalone solutions, our approach instead cooperates with the LLM's internal defense mechanisms by re-triggering them. Moreover, through extensive analysis, we gain a comprehensive understanding of the disruption effects and develop an efficient search algorithm to identify appropriate disruptions for effective jailbreak detection. Extensive experiments demonstrate that our approach effectively defends against state-of-the-art jailbreak attacks in white-box and black-box settings, and remains robust even against adaptive attacks.

---

### Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings

Authors: Benjamin Icard, Lila Sainero, Alice Breton, Evangelia Zve, Jean-Gabriel Ganascia
Published: 2026-05-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.10606v1

Large language models (LLMs) can convincingly imitate human writing styles, yet it remains unclear how much stylistic information is encoded in embeddings from any language model and retained after LLM rewriting. We investigate these questions in French, using a controlled literary dataset to quantify the effect of stylistic variation via changes in embedding dispersion. We observe that embeddings reliably capture authorial stylistic features and that these signals persist after rewriting, while also exhibiting LLM-specific patterns. These analytical results offer promising directions for authorship imitation detection in the era of language models.

---

### Where do aspectual variants of light verb constructions belong?

Authors: Aggeliki Fotopoulou, Eric Laporte, Takuya Nakamura
Published: 2026-05-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.10605v1

Expressions with an aspectual variant of a light verb, e.g. 'take on debt' vs. 'have debt', are frequent in texts but often difficult to classify between verbal idioms, light verb constructions or compositional phrases. We investigate the properties of such expressions with a disputed membership and propose a selection of features that determine more satisfactory boundaries between the three categories in this zone, assigning the expressions to one of them.

---

### Fairness vs Performance: Characterizing the Pareto Frontier of Algorithmic Decision Systems

Authors: Mieke Wilms, Christoph Heitz
Published: 2026-05-11
Categories: cs.LG, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2605.10604v1

Designing fair algorithmic decision systems requires balancing model performance with fairness toward affected individuals: More fairness might require sacrificing some performance and vice versa, yet the space of possible trade-offs is still poorly understood. We investigate fairness in binary prediction-based decision problems by conceptualizing decision making as a multi-objective optimization problem that simultaneously considers decision-maker utility and group fairness. We investigate the set of Pareto-optimal decision rules for arbitrary utility functions for decision maker, arbitrary population distributions, and a wide range of group fairness metrics. We find that the Pareto frontier consists of deterministic, group-specific threshold rules applied to individuals' success probability. This complements existing optimality theorems from literature which, for specific fairness constraints, posit lower-bound threshold rules only. However we also show that, depending on the used fairness metric, the Pareto frontier may include upper-bound threshold rules, thus preferring individuals with lower success probabilities. We show that the location of the Pareto frontier depends only on population characteristics, utility functions and fairness score, but not on the technical design of the algorithm - our findings hold for pre-, in-, and post-processing approaches alike. Our results generalize existing optimality theorems for fairness-constrained classification and extend them to generalized fairness metrics and fairness principles, and to partial fairness regimes. This paper connects formal fairness research with legal and ethical requirements to search for less discriminatory alternatives, offering a principled foundation for evaluating and comparing algorithmic decision systems.

---

### Segment Anything with Robust Uncertainty-Accuracy Correlation

Authors: Hongyou Zhou, Marc Toussaint, Ling Shao, Zihan Ye
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10603v3

Despite strong zero-shot performance, SAM is unreliable under domain shift due to Mask-level Confidence Confusion (MCC), where a single IoU-based mask score fails to reflect pixel-wise reliability near boundaries. Motivated by the contrast between texture-biased shortcuts in neural networks and shape-centric processing in human vision, we model out-of-domain variation as appearance shifts and non-rigid deformations that jointly stress calibration. We propose Segment Anything with Robust Uncertainty-Accuracy Correlation (RUAC) for robust pixel-wise uncertainty estimation under appearance and deformation shifts. RUAC adds a lightweight uncertainty head, trains it with a collaborative style-deformation attack that jointly perturbs texture and geometry, and applies Uncertainty-Accuracy Alignment to ensure uncertainty consistently highlights erroneous pixels even under adversarial perturbations. Across 23 zero-shot domains, RUAC improves segmentation quality and yields more faithful uncertainty with stronger uncertainty-accuracy correlation. Project page: https://hongyouzhou.github.io/ruac/.

---

### The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime

Authors: Phongsakon Mark Konrad, Tim Lukas Adam, Ane Cathrine Holst Merrild, Riccardo Terrenzi, Rebecca De Rosa, Toygar Tanyel, Serkan Ayvaz
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10601v1

AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. This often leads to an excessive reliance on mechanistic interpretability to address a deployment challenge beyond its intended scope. We argue that the gate should instead be calibrated verification: authorization should be domain-scoped, independently checkable, monitored after release, accountable, contestable, and revocable. The reason is twofold. First, model capability is uneven across nearby tasks, so authorization must attach to a specific use rather than to a model in general. Second, societies have long governed opaque expertise through credentials, monitoring, liability, appeal, and revocation rather than mechanism-level explanation. Recent evidence reinforces this distinction between mechanistic understanding and deployment authority: a 53-percentage-point gap between internal representations and output correction shows that understanding may not translate into action, while one scoping review found that only 9.0% of FDA-approved AI/ML device documents contained a prospective post-market surveillance study. We propose Verification Coverage, a six-component reportable standard with a minimum-composition rule, as the metric that should sit beside capability scores in model cards, leaderboards, and regulatory disclosures.

---

### Budget-Efficient Automatic Algorithm Design via Code Graph

Authors: Maxime Bouscary, Manxi Wu, Saurabh Amin
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10598v1

Large language models (LLMs) have emerged as powerful tools for automatic algorithm design (AAD). However, existing pipelines remain inefficient. They operate at the granularity of full algorithms, redundantly rewriting recurring substructures and discarding low-fitness candidates that may contain valuable algorithmic features. We formalize budget-efficient automatic algorithm design, wherein the search policy maximizes realized fitness subject to limited computational cost. We propose a directed acyclic graph representation of algorithms and build a search framework that fully exploits the LLM's output. Instead of querying the LLM for full algorithms, we use it to obtain corrections: compact operators that add, replace, or remove code blocks. Each correction augments the graph, yielding new algorithms that compose with prior corrections. This graph structure decomposes algorithms into sets of corrections, enabling correction-level credit assignment that informs subsequent queries. We complement this framework with theoretical insights into the ideal balance between search depth and breadth at different budget levels. We validate our method empirically on three combinatorial optimization problems, demonstrating consistent superiority of our graph-based search over full-algorithm search at equal token budget. Finally, our experiments suggest that rich contexts help only when the LLM's prior knowledge is shallow, and can hinder performance otherwise.

---

### CrackMeBench: Binary Reverse Engineering for Agents

Authors: Isaac David, Arthur Gervais
Published: 2026-05-11
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2605.10597v1

Benchmarks for coding agents increasingly measure source-level software repair, and cybersecurity benchmarks increasingly measure broad capture-the-flag performance. Classical binary reverse engineering remains less precisely specified: given only an executable, can an agent recover validation logic and produce an input, serial, artifact, or key generator accepted by the program? We introduce CrackMeBench, a benchmark for evaluating language-model agents on educational CrackMe-style reverse-engineering tasks. CrackMeBench focuses on deterministic binary validation problems with executable oracles, symbol-poor binaries, explicit local tool access, and externally scored submissions rather than free-form explanations. The v0 benchmark combines eight public calibration CrackMes with twelve generated main-score tasks built from seeded C, Rust, and Go templates, and agents run through an equal shell interface in a no-network Linux Docker sandbox with standard reverse-engineering tools. In a three-model evaluation with a five-minute budget and three scored submissions per task, pass@3 on the generated split is 11/12 tasks (92%) for GPT-5.5, 7/12 (58%) for Claude Opus 4.7, and 5/12 (42%) for Kimi K2. The harder generated half separates the models more sharply, with pass@3 of 5/6, 2/6, and 1/6, respectively; on the eight-task public calibration split, pass@3 is 3/8, 2/8, and 1/8. CrackMeBench records pass@1 and pass@3, scored submissions, wall-clock time, command traces, tool categories, provider-reported token usage, estimated cost, and qualitative failure labels, providing a reproducible testbed for measuring progress from source-code reasoning toward autonomous binary analysis while restricting scope to educational, purpose-built programs.

---

### LLARS: Enabling Domain Expert & Developer Collaboration for LLM Prompting, Generation and Evaluation

Authors: Philipp Steigerwald, Mara Stieler, Jennifer Burghardt, Eric Rudolph, Jens Albrecht
Published: 2026-05-11
Categories: cs.AI, cs.CL, cs.HC, cs.SE
arXiv: https://arxiv.org/abs/2605.10593v1

We demonstrate LLARS (LLM Assisted Research System), an open-source platform that bridges the gap between domain experts and developers for building LLM-based systems. It integrates three tightly connected modules into an end-to-end pipeline: Collaborative Prompt Engineering for real-time co-authoring with version control and instant LLM testing, Batch Generation for configurable output production across user-selected prompts $\times$ models $\times$ data with cost control, and Hybrid Evaluation where human and LLM evaluators jointly assess outputs through diverse assessment methods, with live agreement metrics and provenance analysis to identify the best model-prompt combination for a given use case. New prompts and models are automatically available for batch generation and completed batches can be turned into evaluation scenarios with a single click. Interviews with six domain experts and three developers in online counselling confirmed that LLARS feels intuitive, saves considerable time by keeping everything in one place and makes interdisciplinary collaboration seamless.

---

### A Resilient Solution for Sewer Overflow Monitoring across Cloud and Edge

Authors: Vipin Singh, Tianheng Ling, Peter Ghaly, Felix Grimmeisen, Gregor Schiele, Felix Biessmann
Published: 2026-05-11
Categories: cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2605.10592v2

Aging combined sewer systems in many historical cities are increasingly stressed by extreme rainfall events, which can trigger combined sewer overflows (CSO) with significant environmental and public health impacts. Forecasting the filling dynamics of overflow basins is critical for anticipating capacity exceedance and enabling timely preventive actions for CSO. We present a web-based demonstrator that integrates Deep Learning forecasting methods in both cloud and edge settings into an interactive monitoring dashboard for overflow monitoring, resilient to network outages. A video showcase is available online (https://cloud.bht-berlin.de/index.php/s/b9xt4T3SdiLBiFZ).

---

### Amortizing Causal Sensitivity Analysis via Prior Data-Fitted Networks

Authors: Emil Javurek, Dennis Frauen, Marie Brockschmidt, Jonas Schweisthal, Stefan Feuerriegel
Published: 2026-05-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2605.10590v1

Causal sensitivity analysis aims to provide bounds for causal effect estimates in the presence of unobserved confounding. However, existing methods for causal sensitivity analysis are per-instance procedures, meaning that changes to the dataset, causal query, sensitivity level, or treatment require new computation. Here, we instead present an in-context learning approach. Specifically, we propose an amortized approach to causal sensitivity analysis based on prior-data fitted networks. A key challenge is that the sensitivity bounds are not directly available when sampling training data. To address this, we develop a general prior-data construction that is applicable across the class of generalized treatment sensitivity models. Our construction involves a Lagrangian scalarization of the objective to generate training labels for the bounds through a tradeoff between causal effect min/max-imization and sensitivity model violation, which avoids model-specific analytical derivations. We further show that, under standard convexity and linearity conditions, our objective recovers the full Pareto frontier of solutions. Empirically, we demonstrate our amortized approach across various datasets, causal queries, and sensitivity levels, where our approach achieves a test-time computation that is orders of magnitude faster than per-instance methods. To the best of our knowledge, ours is the first foundation model for in-context learning for causal sensitivity analysis.

---

### Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence

Authors: Yanbing Zhang, Bo Wang, Jianhui Liu, Nan Jiang, Jiaxiu Jiang, Haoze Sun, Yijun Yang, Shenghe Zheng, Lin Song, Haoyang Huang, Nan Duan, Wenbo Li
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10588v1

Current Large Multimodal Models (LMMs) struggle with spatial reasoning tasks requiring viewpoint-dependent understanding, largely because they are confined to a single, static observation. We propose Thinking with Novel Views (TwNV), a paradigm that integrates generative novel-view synthesis into the reasoning loop: a Reasoner LMM identifies spatial ambiguity, instructs a Painter to synthesize an alternative viewpoint, and re-examines the scene with the additional evidence. Through systematic experiments we address three research questions. (1) Instruction format: numerical camera-pose specifications yield more reliable view control than free-form language. (2) Generation fidelity: synthesized view quality is tightly coupled with downstream spatial accuracy. (3) Inference-time visual scaling: iterative multi-turn view refinement further improves performance, echoing recent scaling trends in language reasoning. Across four spatial subtask categories and four LMM architectures (both closed- and open-source), TwNV consistently improves accuracy by +1.3 to +3.9 pp, with the largest gains on viewpoint-sensitive subtasks. These results establish novel-view generation as a practical lever for advancing spatial intelligence of LMMs.

---

### CausalGS: Learning Physical Causality of 3D Dynamic Scenes with Gaussian Representations

Authors: Nengbo Lu, Minghua Pan
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10586v1

Learning a physical model from video data that can comprehend physical laws and predict the future trajectories of objects is a formidable challenge in artificial intelligence. Prior approaches either leverage various Partial Differential Equations (PDEs) as soft constraints in the form of PINN losses, or integrate physics simulators into neural networks; however, they often rely on strong priors or high-quality geometry reconstruction. In this paper, we propose CausalGS, a framework that learns the causal dynamics of complex dynamic 3D scenes solely from multi-view videos, while dispensing with the reliance on explicit priors. At its core is an inverse physics inference module that decouples the complex dynamics problem from the video into the joint inference of two factors: the initial velocity field representing the scene's kinematics, and the intrinsic material properties governing its dynamics. This inferred physical information is then utilized within a differentiable physics simulator to guide the learning process in a physics-regularized manner. Extensive experiments demonstrate that CausalGS surpasses the state-of-the-art on the highly challenging task of long-term future frame extrapolation, while also exhibiting advanced performance in novel view interpolation. Crucially, our work shows that, without any human annotation, the model is able to learn the complex interactions between multiple physical properties and understand the causal relationships driving the scene's dynamic evolution, solely from visual observations.

---

### Controllability in preference-conditioned multi-objective reinforcement learning

Authors: Pau de las Heras Molins, Beyazit Yalcinkaya, Lasse Peters, David Fridovich-Keil, Georgios Bakirtzis
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10585v1

Multi-objective reinforcement learning (MORL) allows a user to express preference over outcomes in terms of the relative importance of the objectives, but standard metrics cannot capture whether changes in preference reliably change the agent's behavior in the intended way, a property termed controllability. As a result, preference-conditioned agents can score well on standard MORL metrics while being insensitive to the preference input. If the ability to control agents cannot be reliably assessed, the symbolic interface that MORL provides between user intent and agent behavior is broken. Mainstream MORL metrics alone fail to measure the controllability of preference-conditioned agents, motivating a complementary metric specifically designed to that end. We hope the results spur discussion in the community on existing evaluation protocols to consolidate advances in preference adaptation in MORL to larger and more complex problems.

---

### An agentic framework for gravitational-wave counterpart association in the multi-messenger era

Authors: Yiming Dong, Yacheng Kang, Junjie Zhao, Xinyuan Zhu, Ziming Wang, Lijing Shao
Published: 2026-05-11
Categories: astro-ph.IM, cs.AI, gr-qc
arXiv: https://arxiv.org/abs/2605.10584v2

With the detection of gravitational waves (GWs), multi-messenger astronomy has opened a new window for advancing our understanding of astrophysics, dense matter, gravitation, and cosmology. The GW sources detected to date are from mergers of compact object binaries, which possess the potential to generate detectable electromagnetic (EM) counterparts. Searching for associations between GW signals and their EM counterparts is an essential step toward enabling subsequent multi-messenger studies. In the era of next-generation GW and EM detectors, the rapid increase in the number of events brings not only unprecedented scientific opportunities, but also substantial challenges to the existing data analysis paradigm. To help address these challenges, we develop GW-Eyes, an agentic framework powered by large language models (LLMs). For the first time, GW-Eyes integrates domain-specific tools and autonomously performs counterpart association tasks between GW and candidate EM events. It supports natural language interaction to assist human experts with auxiliary tasks such as catalog management, skymap visualization, and rapid verification. Our framework leverages the complex decision-making capabilities of LLMs and their traceable reasoning processes, offering a new perspective to the multi-messenger astronomy.

---

### An agentic framework for gravitational-wave counterpart association in the multi-messenger era

Authors: Yiming Dong, Yacheng Kang, Junjie Zhao, Xinyuan Zhu, Ziming Wang, Lijing Shao
Published: 2026-05-11
Categories: astro-ph.IM, cs.AI, gr-qc
arXiv: https://arxiv.org/abs/2605.10584v1

With the detection of gravitational waves (GWs), multi-messenger astronomy has opened a new window for advancing our understanding of astrophysics, dense matter, gravitation, and cosmology. The GW sources detected to date are from mergers of compact object binaries, which possess the potential to generate detectable electromagnetic (EM) counterparts. Searching for associations between GW signals and their EM counterparts is an essential step toward enabling subsequent multi-messenger studies. In the era of next-generation GW and EM detectors, the rapid increase in the number of events brings not only unprecedented scientific opportunities, but also substantial challenges to the existing data analysis paradigm. To help address these challenges, we develop GW-Eyes, an agentic framework powered by large language models (LLMs). For the first time, GW-Eyes integrates domain-specific tools and autonomously performs counterpart association tasks between GW and candidate EM events. It supports natural language interaction to assist human experts with auxiliary tasks such as catalog management, skymap visualization, and rapid verification. Our framework leverages the complex decision-making capabilities of LLMs and their traceable reasoning processes, offering a new perspective to the multi-messenger astronomy.

---

### FrequencyCT: Frequency Domain Self-supervised Low-dose CT Denoising

Authors: Guoquan Wei, Liu Shi, Chong Chen, Qiegen Liu
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10583v2

Despite extensive research on computed tomography (CT) denoising, few studies exploit projection-domain data characteristics to mitigate noise correlation. To bridge this gap, this work proposes FrequencyCT, the first zero-shot self-supervised method for pseudo-sample generation in the frequency domain for low-dose CT denoising. Specifically, by exploiting the distinct frequency-domain distributions of noise and true signal, a regional low-frequency anchoring technique is proposed. Applying phase-preserving noise and mask perturbations to the high-frequency region generates pseudo-samples for self-supervision. Driven by the exponential correlation between noise variance of noisy projections and the underlying true signal, consistent data truncation is applied to the generated samples to stabilize optimization gradients. Evaluation results on multiple public and real datasets confirm the clinical application potential of this research, which provides an innovative perspective for the field of denoising. The code is available at: https://github.com/yqx7150/FrequencyCT.

---

### Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing

Authors: Zheng Lin, Zhenxing Niu, Haoxuan Ji, Haichang Gao
Published: 2026-05-11
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2605.10582v1

This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel smoothing-based defense method, termed Disrupt-and-Rectify Smoothing (DR-Smoothing). Specifically, we integrate a two-stage prompt processing scheme-first disrupting the input prompt, then rectifying it-into the conventional smoothing defense framework. This disrupt-and-rectify approach improves upon previous disrupt-only approaches by restoring out-of-distribution disrupted prompts to an in-distribution form, thereby reducing the risk of unpredictable LLM behavior. In addition, this two-stage scheme offers a distinct advantage in striking a balance between harmlessness and helpfulness in jailbreaking defense. Notably, we present a theoretical analysis for generic smoothing framework, offering a tight bound for the defense success probability and the requirements on the disruption strength. Our approach can defend against both token-level and prompt-level jailbreaking attacks, under both established and adaptive attacking scenarios. Extensive experiments demonstrate that our approach surpasses current state-of-the-art defense methods in terms of both harmlessness and helpfulness.

---

### Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention

Authors: Yuanyuan Peng, Wen Li
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10581v2

Retinal vessel segmentation is crucial for diagnosis and assessment of ocular diseases. Notably, segmentation of small retinal vessels has been consistently recognized as a challenging and complex task. To tackle this challenge, we design a hybrid CNN-Mamba fusion network that integrates polygon scanning mamba and space-frequency collaborative attention mechanism for the detection of small vessels. Considering that the traditional mamba architecture with horizontal-vertical scanning may compromise the topological integrity of target structures and result in local discontinuities in small retinal vessels, we present a polygon scanning visual state space model (PS-VSS) to identify small vessel structural features by multi-layer reverse scanning way. Which effectively preserves pixels connectivity, thereby substantially mitigating the loss of information pertaining to small vessels. Furthermore, as we all known that the spatial domain prioritizes positional and structural information, while the frequency domain emphasizes global perception and local detail components, a space-frequency collaborative attention mechanism (SFCAM) is introduced within the skip connection to extract efficient features from the spatial and frequency domains. This strategy empowers the model to dynamically enhance the key features while effectively suppressing clutters. To assess the efficacy of our model, it was tested on three publicly available datasets: DRIVE, STARE, and CHASE_DB1. Compared to manual annotations, our model demonstrated F1 scores of 0.8283, 0.8282, and 0.8251, Area Under Curve (AUC) values of 0.9806, 0.9840, and 0.9866, and Sensitivity (SE) values of of 0.8268, 0.8314, and 0.8484 across three datasets, respectively. The effectiveness of our model was validated through both visual inspection and quantitative analysis.

---

### VISTA: A Controllable Platform for Generating and Auditing Egocentric Assistance Scenarios

Authors: Yu-Hsiang Liu, Yu-Chien Tang, An-Zi Yen
Published: 2026-05-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.10579v2

Evaluating whether AI agents can proactively assist humans in daily activities, ranging from routine household tasks to urgent safety-critical situations, requires diverse visual data. However, collecting such scenarios in the real world is often difficult, costly, or unsafe, and simulation environments often lack the social commonsense needed to simulate the consequences of different actions. In this work, we present VISTA, a controllable platform that uses a user-provided scenario seed, defined as a short natural-language description of the intended assistance situation, to generate editable plans, egocentric videos, and an auditable review trail. VISTA structures scenario intent around three interaction modes, including reactive, explicit proactive, and implicit proactive, and two consequence families, including safety-critical and everyday inconvenience, with no-assistance cases as controls. Its six-stage pipeline exposes the design brief, timed event script, first-frame plan, motion plan, and video plan, allowing users to revise each artifact in natural language before explicitly authorizing media generation. A human evaluation shows that videos retained by the complete VISTA workflow align more closely with their scenario seeds than outputs from two one-pass baselines. VISTA thereby makes targeted egocentric scenario generation inspectable, revisable, and empirically auditable.

---

### SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models

Authors: Chen Zhong, Xiao An, Jiaxing Sun, Zihan Gui, Guangyi Yang, Wei He
Published: 2026-05-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.10576v1

Low-level visual perception underpins reliable remote sensing (RS) image analysis, yet current image quality assessment (IQA) methods output uninterpretable scalar scores rather than characterizing physics-driven RS degradations, deviating markedly from the diagnostic needs of RS experts. While Vision-Language Models (VLMs) present a compelling alternative by delivering language-grounded IQA, their visual priors are heavily biased toward ground-level natural images. Consequently, whether VLMs can overcome this domain gap to perceive and articulate RS artifacts remains insufficiently studied. To bridge this gap, we propose \textbf{SenseBench}, the first dedicated diagnostic benchmark for RS low-level visual perception and description. Driven by a physics-based hierarchical taxonomy that unifies both non-reference and reference-based paradigms, SenseBench features over 10K meticulously curated instances across 6 major and 22 fine-grained RS degradation categories. Specifically, two complementary protocols are designed for evaluation: objective low-level visual \textit{perception} and subjective diagnostic \textit{description}. Comprehensive evaluation of 29 state-of-the-art VLMs reveals not only skewed domain priors and multi-distortion collapse, but also \textit{fluency illusion} and a \textit{perception-description inversion} effect. We hope SenseBench provides a robust evaluation testbed and high-quality diagnostic data to advance the development of VLMs in RS low-level perception. Code and datasets are available \href{https://github.com/Zhong-Chenchen/SenseBench}{\textcolor{blue}{here}}.

---

### Acceptance Cards:A Four-Diagnostic Standard for Safe Fine-Tuning Defense Claims

Authors: Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz
Published: 2026-05-11
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.10575v1

Safe fine-tuning defenses are often endorsed on the basis of a held-out gap reduction, but the same reduction can come from sampling noise, subject artifacts, capability loss, or a mechanism that does not transfer. We introduce Acceptance Cards: an evaluation protocol, a documentation object, an executable audit package, and a claim-specific evidential standard for safe fine-tuning defense claims. The protocol checks statistical reliability, fresh semantic generalization, mechanism alignment, and cross-task transfer before treating a gap reduction as a full-card pass. Re-scored under this installed-gap protocol, SafeLoRA fails the full-card pass on Gemma-2-2B-it: under strict mechanism-class coding it fails all four diagnostics, and under a permissive shrinkage relabel it still fails three of four. This is a narrow installed-gap audit on one model family, not a global judgment of SafeLoRA's effectiveness. In a 46-cell audit, no cell satisfies the strict conjunction. The closest family is a near miss that passes reliability and mechanism checks where the required data are available, but fails the fresh-subject threshold, lacks a strict transfer pass, and carries a measurable deployment-accuracy cost.

---

### LLM Jaggedness Unlocks Scientific Creativity

Authors: Shray Mathur, J. Anibal Boscoboinik, Esther H. R. Tsai, Kevin G. Yager
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10574v3

As artificial intelligence advances, models are not improving uniformly. Instead, progress unfolds in a jagged fashion, with capabilities growing unevenly across tasks, domains, and model scales. In this work, we examine this dynamic jaggedness through the lens of scientific idea generation. We introduce SciAidanBench, a benchmark of open-ended scientific questions designed to measure the scientific creativity of large language models (LLMs). Given a scientific question, models are asked to generate as many unique and coherent ideas as possible, with the total number of valid responses serving as a proxy for creative potential. Evaluating 19 base models across 8 providers (30 total variants including reasoning versions), we find that jaggedness manifests both across models and within models. First, in a cross-task comparison between general and scientific creativity, improvements in general creativity do not translate uniformly to scientific creativity, revealing divergent capability profiles across models. Second, at the prompt level, stronger models do not improve uniformly; instead, they exhibit high variability, with bursts of creativity on some questions and limited performance on others. Third, at the domain level, individual models display uneven strengths across scientific subfields, reflecting fragmented internal capability profiles. Finally, we show that this jaggedness can be harnessed. We explore mechanisms of inference-time compute, knowledge pooling, and brainstorming to combine models effectively and construct meta-model ensembles that outperform any single model. Our results position jaggedness not as a limitation, but as a resource, a structural feature of AI progress that, when understood and leveraged, can amplify LLM-driven scientific creativity.

---

### Online Sharp-Calibrated Bayesian Optimization

Authors: Marshal Arijona Sinaga, Julien Martinelli, Teemu Turpeinen, Samuel Kaski
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10572v1

Bayesian optimization (BO) is a widely used framework for optimizing expensive black-box functions, commonly based on Gaussian process (GP) surrogate models. Its effectiveness relies on uncertainty quantification that is both sharp (informative) and well-calibrated along the BO trajectory. In practice, GP kernel hyperparameters are unknown and are refit online from sequentially collected (non-i.i.d.) data, which can yield miscalibrated or overly conservative uncertainty and lies outside the fixed-kernel assumptions of standard BO regret theory. We propose Online Sharp-Calibrated Bayesian Optimization (OSCBO), a BO algorithm that adaptively balances GP sharpness and calibration by casting hyperparameter selection as a constrained online-learning problem. We also show that OSCBO preserves sublinear regret bounds by leveraging the theoretical guarantees of the underlying online learning algorithm. Empirically, OSCBO performs competitively across synthetic and real-world benchmarks, ranking among the strongest methods in final simple regret while maintaining robust cumulative-regret behavior.

---

### Set-Based Groupwise Registration for Variable-Length, Variable-Contrast Cardiac MRI

Authors: Yi Zhang, Yidong Zhao, Tijmen Toxopeus, Maša Božić-Iven, Sebastian Weingärtner, Qian Tao
Published: 2026-05-11
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2605.10571v1

Quantitative cardiac magnetic resonance imaging (MRI) enables non-invasive myocardial tissue characterization but relies on robust motion correction within these variable-length, variable-contrast image sequences. Groupwise registration, which simultaneously aligns all images, has shown greater robustness than pairwise registration for motion correction. However, current deep-learning-based groupwise registration methods cannot generalize across MRI sequences: the architecture typically encodes input data as a fixed-length channel stack, which rigidly couples network design to protocol-specific sequence length, input ordering, and contrast dynamics. At inference time, any change in imaging protocols will render the network unusable. In this work, we introduce \emph{\AnyTwoReg}, a new set-based groupwise registration framework that takes a quantitative MRI sequence as an unordered set. This set formulation fundamentally decouples network design from sequence length and input ordering. By utilizing a shared encoder and correlation-guided feature aggregation, \emph{\AnyTwoReg} constructs a permutation-invariant canonical reference for registration, and learns a permutation-equivariant mapping from images to deformation fields. Additionally, we extract contrast-insensitive image features from an existing foundation model to handle extreme contrast variations. Trained exclusively on a single public $T_1$ mapping dataset (STONE, sequence length $L=11$), \AnyTwoReg generalizes to two unseen quantitative MRI datasets (MOLLI, ASL) with variable lengths ($L \in (11, 60)$) and different contrast dynamics. It achieves strong cross-protocol generalization in a zero-shot manner, and consistently improves downstream quantitative mapping quality. Notably, while designed for quantitative MRI sequences, our framework is directly applicable to Cine MRI sequences for inter-cardiac-phase registration.

---

### Deep Arguing

Authors: Adam Gould, Francesca Toni
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10569v1

Deep learning has become the dominant approach for creating high capacity, scalable models across diverse data modalities. However, because these models rely on a large number of learned parameters, tightly couple feature extraction with task objectives, and often lack explicit reasoning mechanisms, it is difficult for humans to understand how they arrive at their predictions. Understanding what representations emerge and why they arise from the training data remains an open challenge. We introduce Deep Arguing, a novel neurosymbolic approach that integrates deep learning with argumentation construction and reasoning for interpretable classification with different data modalities. In our approach deep neural networks construct an argumentation structure wherein data points support their assigned label and attack different ones. Using differentiable argumentation semantics for reasoning, the model is trained end-to-end to jointly learn feature representation and argumentative interactions. This results in argumentation structures providing faithful case-based explanations for predictions. Structure constraints over the argumentation graph guide learning, improving both interpretability and predictive performance. Experiments with tabular and imaging datasets show that Deep Arguing achieves performance competitive with standard baselines whilst offering interpretable argumentative reasoning.

---

### VeloGauss: Learning Physically Consistent Gaussian Velocity Fields from Videos

Authors: Nengbo Lu, Bin Zhao
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10567v1

In this paper, we aim to jointly model the geometry, appearance, and physical information of 3D scenes solely from dynamic multi-view videos, without relying on any physical priors. Existing works typically employ physical losses merely as soft constraints or integrate physical simulations into neural networks; however, these approaches often fail to effectively learn complex motion physics. Although modeling velocity fields holds the potential to capture authentic physical information, due to the lack of appropriate physical constraints, current methods are unable to correctly learn the interaction mechanisms between rigid and non-rigid particles. To address this, we propose VeloGauss, designed to learn the physical properties of complex dynamic 3D scenes without physical priors. Our method learns the velocity field for each Gaussian particle by introducing a Physics Code and a Particle Dynamics System, and ultimately incorporates Global Physical Constraints to ensure the physical consistency of the scene. Extensive experiments on four public datasets demonstrate that our method outperforms achieves state-of-the-art performance in both Novel View Interpolation and Future Frame Extrapolation tasks.

---

### Affine Tracing: A New Paradigm for Probabilistic Linear Solvers

Authors: Disha Hegde, Marvin Pförtner, Jon Cockayne
Published: 2026-05-11
Categories: stat.ML, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2605.10566v1

Probabilistic linear solvers (PLSs) return probability distributions that quantify uncertainty due to limited computation in the solution of linear systems. The literature has traditionally distinguished between Bayesian PLSs, which condition a prior on information obtained from projections of the linear system, and probabilistic iterative methods (PIMs), which lift classical iterative solvers to probability space. In this work we show this dichotomy to be false: Bayesian PLSs are a special case of non-stationary affine PIMs. In addition, we prove that any realistic affine PIM is calibrated. These results motivate a focus on (non-stationary) affine PIMs, but their practical adoption has been limited by the significant manual effort required to implement them. To address this, we introduce affine tracing, an algorithmic framework that automatically constructs a PIM from a standard implementation of an affine iterative method by passing symbolic tracers through the computation to build an affine computational graph. We show how this graph can be transformed to compute posterior covariances, and how equality saturation can be used to perform algebraic simplifications required for computation under specific prior choices. We demonstrate the framework by automatically generating a probabilistic multigrid solver and evaluate its performance in the context of Gaussian process approximation.

---

### DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving

Authors: Lingjun Zhang, Changjie Wu, Linzhe Shi, Jiangyang Li, Jiaxin Liu, Lei Yang, Hang Zhang, Mu Xu, Hong Wang
Published: 2026-05-11
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2605.10564v1

End-to-end autonomous driving systems are increasingly integrating Vision-Language Model (VLM) architectures, incorporating text reasoning or visual reasoning to enhance the robustness and accuracy of driving decisions. However, the reasoning mechanisms employed in most methods are direct adaptations from general domains, lacking in-depth exploration tailored to autonomous driving scenarios, particularly within visual reasoning modules. In this paper, we propose a driving world model that performs parallel prediction of latent semantic features for consecutive future frames in the bird's-eye-view (BEV) space, thereby enabling long-horizon modeling of future world states. We also introduce an efficient and adaptive text reasoning mechanism that utilizes additional social knowledge and reasoning capabilities to further improve driving performance in challenging long-tail scenarios. We present a novel, efficient, and effective approach that achieves state-of-the-art (SOTA) results on the closed-loop Bench2drive benchmark. Codes are available at: https://github.com/hotdogcheesewhite/DeepSight.

---

### ThreatCore: A Benchmark for Explicit and Implicit Threat Detection

Authors: Davide Bruni, Carlo Bardazzi, Maurizio Tesconi
Published: 2026-05-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.10563v1

Threat detection in Natural Language Processing lacks consistent definitions and standardized benchmarks, and is often conflated with broader phenomena such as toxicity, hate speech, or offensive language. In this work, we introduce ThreatCore, a public available benchmark dataset for fine-grained threat detection that distinguishes between explicit threats, implicit threats, and non-threats. The dataset is constructed by aggregating multiple publicly available resources and systematically re-annotating them under a unified operational definition of threat, revealing substantial inconsistencies across existing labels. To improve the coverage of underrepresented cases, particularly implicit threats, we further augment the dataset with synthetic examples, which are manually validated using the same annotation protocol adopted for the re-annotation of the public datasets, ensuring consistency across all data sources. We evaluate Perspective API, zero-shot classifiers, and recent language models on ThreatCore, showing that implicit threats remain substantially harder to detect than explicit ones. Our results also indicate that incorporating Semantic Role Labeling as an intermediate representation can improve performance by making the structure of harmful intent more explicit. Overall, ThreatCore provides a more consistent benchmark for studying fine-grained threat detection and highlights the challenges that current models still face in identifying indirect expressions of harmful intent.

---

### ICT-NLP at SemEval-2026 Task 3: Less Is More -- Multilingual Encoder with Joint Training and Adaptive Ensemble for Dimensional Aspect Sentiment Regression

Authors: Liyuan Huang, Jiawei He, Wutao Shen, Lin Li, Jin Zhang
Published: 2026-05-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.10560v1

This paper describes our system to SemEval-2026 Task 3 Track A Subtask 1 on Dimensional Aspect Sentiment Regression (DimASR). We propose a lightweight and resource-efficient system built entirely on multilingual pre-trained encoders, without relying on LLMs or external corpora. We adopt joint multilingual and multi-domain training to facilitate cross-lingual transfer and alleviate data sparsity, introduce a bounded regression transformation that improves training stability while constraining predictions within the valid range, and employ an adaptive ensemble strategy via subset search to reduce prediction variance. Experimental results demonstrate that our system achieves strong and consistent performance, ranking 1st on zho-res, 2nd on zho-lap, and 3rd on jpn-hot, with all remaining datasets placed within the top half of participating teams.

---

### EnergyLens: Interpretable Closed-Form Energy Models for Multimodal LLM Inference Serving

Authors: Vittorio Palladino, Gianluca Palermo, Michael E. Papka, Zhiling Lan
Published: 2026-05-11
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.10556v2

As large language models span dense, mixture-of-experts, and state-space architectures and are deployed on heterogeneous accelerators under increasingly diverse multimodal workloads, optimising inference energy has become as critical as optimizing latency and throughput. Existing approaches either treat latency as an energy proxy or rely on data-hungry black-box surrogates. Both fail under varying parallelism strategies: latency and energy optima diverge in over 20% of configurations we tested, and black-box surrogates require hundreds of profiling samples to generalize across model families and hardware. We present EnergyLens, which uses symbolic regression as a structure-discovery tool over profiling data to derive a single twelve-parameter closed-form energy model expressed in terms of system properties such as degree of parallelism, batch size, and sequence length. Unlike black-box surrogates, EnergyLens decouples tensor and pipeline parallelism contributions and separates prefill from decode energy, making its predictions physically interpretable and actionable. Fitted from as few as 50 profiling measurements, EnergyLens achieves 88.2% Top-1 configuration selection accuracy across many evaluation scenarios compared to 60.9% for the closest prior analytical baseline, matches the predictive accuracy of ensemble ML methods with 10x fewer profiling samples, and extrapolates reliably to unseen batch sizes and hardware platforms without structural modification, making it a practical, interpretable tool for energy-optimal LLM deployment.

---

### Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systems

Authors: Kai Pan, Rong Hou
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10555v2

As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between conventional APIs and autonomous agent requirements: exact-identifier dependence, rendering-oriented responses, single-shot interaction assumptions, user-equivalent authorization, and opaque error semantics. We propose the Agent-First Tool API paradigm, comprising three integrated mechanisms: (1) a Six-Verb Semantic Protocol that decomposes tool interactions into search, resolve, preview, execute, verify, and recover phases; (2) a Normalized Tool Contract (NTC) providing structured decision-support metadata including confidence scores, evidence chains, and suggested next actions; and (3) a dual-layer governance pipeline combining static capability policies with dynamic risk escalation. The paradigm is implemented and validated in a production multi-tenant SaaS platform serving 85 registered tools across 6 business domains. Comparative experiments on 50 real operational tasks demonstrate that Agent-First APIs achieve 88% end-to-end task success rate versus 64% for optimized CRUD baselines (+37.5%), while reducing required human interventions by 72.7% and improving autonomous error recovery by 5.8x. We establish that the paradigm is orthogonal and complementary to transport-layer standards such as MCP, operating as the semantic application layer above existing tool discovery and invocation protocols.

---

### Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systems

Authors: Kai Pan
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10555v1

As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between conventional APIs and autonomous agent requirements: exact-identifier dependence, rendering-oriented responses, single-shot interaction assumptions, user-equivalent authorization, and opaque error semantics. We propose the Agent-First Tool API paradigm, comprising three integrated mechanisms: (1) a Six-Verb Semantic Protocol that decomposes tool interactions into search, resolve, preview, execute, verify, and recover phases; (2) a Normalized Tool Contract (NTC) providing structured decision-support metadata including confidence scores, evidence chains, and suggested next actions; and (3) a dual-layer governance pipeline combining static capability policies with dynamic risk escalation. The paradigm is implemented and validated in a production multi-tenant SaaS platform serving 85 registered tools across 6 business domains. Comparative experiments on 50 real operational tasks demonstrate that Agent-First APIs achieve 88% end-to-end task success rate versus 64% for optimized CRUD baselines (+37.5%), while reducing required human interventions by 72.7% and improving autonomous error recovery by 5.8x. We establish that the paradigm is orthogonal and complementary to transport-layer standards such as MCP, operating as the semantic application layer above existing tool discovery and invocation protocols.

---