# Research Papers — 2026-05 · bundle page 158 of 326

> Full-text markdown of papers #7851–7900 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/158
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/157.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/159.md)

### Iterative Chow Filtering for Learning with Distribution Shift

Authors: Gautam Chandrasekaran, Georgios Gkrinias, Adam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan
Published: 2026-05-17
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2605.17251v1

Recent work due to Goel et al. gave the first efficient algorithms for learning with distribution shift in the challenging PQ framework. In this setting, a learner receives labeled training examples, unlabeled test examples, and must make correct predictions on the test set but is allowed to abstain from predicting on out-of-distribution points. Their results rely on ${\cal L}_2$ sandwiching approximations, a strong requirement that leads to poor bounds for several basic function classes such as DNF formulas. Here, we show that the weaker notion of ${\cal L}_1$ sandwiching suffices for efficient PQ learning. As a consequence, we obtain the first quasipolynomial-time PQ learning algorithm for DNFs under the uniform distribution and essentially match the guarantees known for ordinary PAC learning. More broadly, our bounds provide exponential improvements for several classes including constant depth circuits and constant degree polynomial threshold functions. Our main technical ingredient is Iterative Chow Filtering, a new procedure that uses low-degree Chow parameters to identify and remove test points incompatible with the training distribution.

---

### Towards Principled Test-Time Adaptation for Time Series Forecasting

Authors: Haochun Wang, Ruichen Xu, Georgios Kementzidis, Karen Cho, Sebastian Ramirez Villarreal, Yuefan Deng
Published: 2026-05-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.17250v1

Test-time adaptation (TTA) has recently emerged as a promising approach for improving time series forecasting (TSF) under distribution shift. Existing TSF-TTA methods differ in how they utilize revealed targets, yet the resulting adaptation protocols remain heterogeneous and lack a clearly unified formulation. To address this issue, we revisit TSF-TTA from the perspective of protocol cleanliness and propose an adaptation protocol based solely on matured ground truth, yielding a more principled setting for adaptation. Under this protocol, we further diagnose existing adapters in the frequency domain and find that their prediction corrections often exhibit limited and weakly structured spectral modifications. Motivated by this diagnosis, we propose Frequency-Aware Calibration (FAC), a lightweight calibration method that directly parameterizes prediction corrections in the frequency domain. Across diverse datasets, forecasting horizons, and source forecasters, FAC achieves competitive and consistent performance while requiring substantially fewer trainable parameters than the compared TSF-TTA adapters.

---

### Image-to-Video Diffusion: From Foundations to Open Frontiers

Authors: Xianlong Wang, Wenbo Pan, Shijia Zhou, Ke Li, Yuqi Wang, Zeyu Ye, Hangtao Zhang, Leo Yu Zhang, Xiaohua Jia
Published: 2026-05-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.17248v1

Diffusion-based \textit{image-to-video} (I2V) generation has become a central direction in generative models by turning a reference image, with optional conditions, into a temporally coherent video. Compared with broader video generation settings, this task places stricter demands on content consistency, identity preservation, and motion coherence. Although the literature grows rapidly, existing works mostly discuss I2V generation within broader topics and still lack a dedicated taxonomy together with a systematic analysis centered on this field. This work addresses that gap by treating diffusion I2V generation as a standalone subject. It first reviews the task formulation, model architectures, datasets, and evaluation metrics, and then organizes existing methods through a taxonomy based on architecture and training paradigm. It further distills four core designs, namely condition encoding, temporal modeling, noise prior design, and spatial-temporal upsampling, and discusses representative application scenarios together with major open challenges.

---

### Towards Robust Argumentative Essay Understanding via TIDE: An Interactive Framework with Trial and Debate

Authors: Zheqin Yin, Yupei Ren, Yadong Zhang, Yujiang Lu, Man Lan
Published: 2026-05-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.17247v1

Argumentative essays serve as a vital medium for assessing critical thinking and reasoning skills, yet there is limited works on accurately understanding and evaluating such texts via prompt. In this work, we propose TIDE, a novel framework designed to improve criteria-based prompt optimization for argument-related tasks by integrating TrIal and DEbate mechanism. Our method addresses key limitations of criteria-based prompt optimizing by mitigating the influence of noisy training data and enhancing optimization stability. We evaluate TIDE on three core tasks: Automated Essay Scoring, Argument Component Detection, and Argument Relation Identification. Results demonstrate that our framework improves performance across tasks. These findings underscore the potential of combining prompt-based methods for advanced argument understanding.

---

### Fidelity Probes for Specification--Code Alignment

Authors: Ferhat Erata, Hao Zhou, Jun Huan
Published: 2026-05-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.17246v2

Software modernization often relies on natural-language specifications recovered from an existing implementation. Incorrect or missing requirements can lead to defects in the modernized system. We introduce fidelity probes to check a specification against the code and guide its revision. Each probe pairs a question about program behaviour with a reference answer derived from the code. A language model answers the question using only the specification, and the fraction of agreeing answers defines fidelity. Disagreements flag conflicting claims or missing information and guide proposed corrections and additions to the requirements. An LLM generates probes directly from code or phrases facts selected through control-flow, data-flow, and call-graph analysis. We use an observability rule to focus probe questions on behaviour that the modernized system is intended to preserve, including user-visible outputs, changes to stored business data, and interactions with other systems. We revise the specification using fresh probes and evaluate each version on a fixed held-out set. A repair-regression model describes how new failures can offset the gains from repairs. On CardDemo, held-out fidelity improves from 0.59 to 0.89, exceeding free-form revision from source code. We also evaluate the method on industrial systems and public documentation, and assess probe quality and reported defects through human reviews and comparison with an independent requirements audit.

---

### Fidelity Probes for Specification--Code Alignment

Authors: Ferhat Erata, Hao Zhou, Luke Huan
Published: 2026-05-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.17246v1

We introduce fidelity probes: natural-language questions generated from a reference artifact with code-derived ground-truth answers, answered from a candidate specification. The fraction of agreeing probes, which we call the fidelity, decomposes into contradiction and coverage-gap rates that drive targeted spec edits to convergence. On a 15-program, roughly 12k-line COBOL benchmark (AWS CardDemo), we raise frozen-test specification fidelity from 0.63 to 0.94 over eight iterations, with the plateau location predicted by a two-state Markov fixed point $F^\dagger$ from just four iterations of rate data. Probes come from an LLM reading the code or from a static-analysis pipeline over its control-flow, data-flow, and system-dependence graphs, with a tunable mixture. A probe-resampling protocol with a frozen held-out set gives a Hoeffding-bounded overfitting discriminant; our measured train/test gap stays more than an order of magnitude below this envelope. Three graph-grounded mixtures lift fidelity by +16 to +30 points; cross-distribution evaluation shows the LLM and symbolic channels are empirically complementary. A cross-family generator sweep on five independent LLM lineages (Anthropic, DeepSeek, Google, Alibaba, OpenAI) confirms the convergence behaviour is not tied to any single model family: three of five non-Claude generators produce trajectories consistent with the Markov fixed-point prediction, and the frozen-test protocol actively falsifies the two generators whose probe distributions drift across iterations. The method applies to any pair of artifacts that are supposed to describe the same behaviour.

---

### An Efficient Machine Learning-based Framework for Detection and Prevention of Frauds in Telecom Networks

Authors: Praveen Hegde, Mishal Shah
Published: 2026-05-17
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2605.17245v1

Telecommunication fraud is an acute problem that leads to substantial material losses and compromises the reliability of telecom systems worldwide. Only effective and efficient detection mechanisms can help to deal with these threats, though there are certain shifts in the approaches to fraud detection. This paper evaluates the performance of AI-driven models for fraud detection in telecommunication networks using Call Detail Record (CDR) datasets. This study focuses on fraud detection in telecom networks using the Telecom CDR dataset, which contains 101,174 customer records with 17 attributes, including 8,830 fraud cases. In feature preprocessing, missing values were dealt with, followed by data scaling using Min-Max scaling and data balancing using the SMOTE technique. The dataset was trained for predictive analysis using Random Forest (RF) and XGBoost models. F1-score, ROC AUC, recall, accuracy, time, and precision were used as indicators with which to compare performance of the two models. RF recorded a high level of accuracy at 99.9% while XGBoost at 99.7%. Findings show that the suggested framework successfully detects fraud with few misclassifications. Several machine learning models were evaluated and contrasted, such as RF, XGBoost, DBSCAN, RoBERTa, and K-means. Among all the models, RF was seen to give the highest performance with an accuracy of 99.9% and precision of 99.9%, recall of 99.9% and F1-score of 99.9%, XGBoost, GNN and BERT. The findings emphasize RF as the most effective model for detecting fraudulent activities in telecom networks, ensuring robust and reliable prevention of fraud.

---

### Drift Flow Matching

Authors: Chenrui Ma, Xi Xiao, Lin Zhao, Tianyang Wang, Ferdinando Fioretto, Yanning Shen
Published: 2026-05-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.17244v1

Iterative generative models such as Flow Matching and Diffusion models have demonstrated strong test-time scaling behavior, where additional inference computation can improve generation quality. In contrast, Drift Models offer efficient one-step generation, but their direct generation paradigm limits such flexibility. In this work, we propose Drift Flow Matching (DFM), a framework that connects drifting generative modeling with flow-based iterative generation. DFM preserves the efficiency of direct transport maps while enabling generation to be refined through multiple inference steps when desired. This bridges the gap between one-step Drift Models and multi-step Flow Matching methods, and provides a novel generative paradigm that can adapt sampling computation to different quality--efficiency requirements. Extensive experiments across different tasks and datasets demonstrate the effectiveness and generality of the proposed framework.

---

### Learning in Position-Aware Multinomial Logit Bandits: From Multiplicative to General Position Effects

Authors: Xi Chen, Shibo Dai, Jiameng Lyu, Yuan Zhou
Published: 2026-05-17
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.17238v1

We study the dynamic joint assortment selection and positioning problem, where the attraction of each product depends on both its intrinsic appeal and its display position under a Multinomial Logit (MNL) choice framework. Our study ranges from the multiplicative position effects model, in which each product's attraction is scaled by a position-specific factor, to a general position effects model assigning independent attraction parameters to every product--position pair to capture heterogeneous synergies. For both models, we design round-based learning algorithms that update decisions after every single feedback, and establish the first regret-optimal characterization. Besides, our round-based algorithms provide the prompt operations needed by modern platforms. For the multiplicative model, we develop a cross-position pairwise maximum likelihood estimator with a clipping mechanism, and prove that our algorithm P2MLE-UCB attains a regret of $\tilde{O}(\sqrt{NT})$, matching the lower bound and closing the $\sqrt{K}$ gap left by prior epoch-based analyses. For the general model, we establish a minimax lower bound and propose GP2-UCB with a matching upper bound. Moreover, we design an efficient subroutine for the per-round joint assortment and positioning optimization based on Dinkelbach's method and maximum-weight bipartite matching. Numerical experiments on synthetic data and the Expedia dataset show that our algorithms consistently outperform state-of-the-art benchmarks.

---

### Systematic Evaluation of Vision Transformers for Automated Cervical Cancer Classification: Optimization, Statistical Validation, and Clinical Interpretability

Authors: Nisreen Albzour, Sarah S. Lam
Published: 2026-05-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.17236v1

Manual Pap smear analysis for cervical cancer screening is limited by inter-observer variability, time constraints, and restricted expert availability. Although convolutional neural networks (CNNs) have automated cervical cell classification, they remain limited in modeling long-range spatial dependencies and often lack clinical interpretability. In this study, Vision Transformer (ViT) architectures were systematically optimized to enhance automated cervical cancer screening, which resulted in improved interpretability. The Herlev dataset (917 images: 242 normal, 675 abnormal) was utilized to optimize ViT-Tiny, a lightweight Vision Transformer architecture designed for reduced computational complexity, through a comprehensive evaluation of augmentation strategies, class weighting, and hyperparameters. The optimal configuration achieved 94.9%-95.2% cross-validation accuracy, in which random horizontal flipping and class weighting (0.7 x 1.3) were identified as most effective. Gradient-weighted Class Activation Mapping (Grad-CAM) analysis confirmed that model attention corresponded to clinically relevant morphological features, which include nuclear regions, cell boundaries, and chromatin texture, which align with cytopathological criteria. These findings indicate that Vision Transformers can deliver accurate and interpretable decision support for cervical cancer screening, which fulfills both clinical performance and transparency requirements essential for medical AI deployment.

---

### Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning

Authors: Viktoria Schram, Markus Hiller, Daniel Beck, Trevor Cohn
Published: 2026-05-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.17234v2

Predicting model performance at larger scales enables the design of training strategies and architectures tailored to specific performance targets. Empirical scaling law research identifies functional forms to aid this prediction task. These describe the relationship between loss and compute using a loss-compute frontier defined by learning curves. Due to the empirical nature of this approach, the computational burden is substantial, making strategic resource allocation essential - yet it remains surprisingly underexplored. In this work, we address this shortcoming by exploring the suitability of Successive Halving (SH) and SH combined with parametric and non-parametric surrogate models. In addition to enabling a more systematic allocation of a given compute budget, our findings show that SH paired with surrogate models yields a set of learning curves that includes one with a lower loss-compute value than what naive uniform allocation or an SH-only approach can obtain. Our experiments demonstrate mean relative improvements of up to 2.84% and 5.47% on real-world and synthetic learning curve datasets. This strategic resource allocation enables us to obtain accurate scaling laws at significantly reduced computational costs, saving up to 98.7% over the traditional exhaustive approach.

---

### Vocabulary-size-independent Convergence of Discrete Diffusion Models: adjoint equations induce the right space

Authors: Kelvin Kan, Xingjian Li, Benjamin J. Zhang, Tuhin Sahai, Stanley Osher, Markos A. Katsoulakis
Published: 2026-05-17
Categories: cs.LG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2605.17232v5

Discrete diffusion has become a leading framework for generative modeling in various applications including language, vision, and biology. Existing convergence theory, however, exhibits fundamental limitations. KL-based analyses diverge under singular priors such as the masked distribution, while bounds in total variation (TV) depend on the vocabulary size $S$ and become vacuous for modern language tasks, where vocabularies contain hundreds of thousands of tokens. We develop a unified adjoint-equation-based framework that establishes vocabulary-size-independent convergence guarantees in any integral probability metric (IPM). To the best of our knowledge, our bounds are the first to be entirely free of $S$ and applicable to both masked and uniform priors. Importantly, our results can extend existing step complexity guarantees to any IPM. Also, our theory relies only on a single standard rate-matrix regularity assumption and applies to general priors. Five novel techniques drive our improvements: 1. working in the space of observables via adjoint equations rather than directly with probability measures; 2. a regularity analysis that yields bounds on any IPM; 3. a coupling argument that removes $S$-dependence under uniform transitions; and 4. score-marginal cancellation and 5. exit-routing techniques that remove $S$-dependence under masked transitions. Our framework thus sharply departs from prior analyses and avoids the shortcomings of pathspace-KL and existing TV-based approaches. Beyond convergence bounds, our framework provides a versatile toolkit for further theoretical study of discrete diffusion models, including principled choices of loss functions and vocabulary-size-independent step complexity.

---

### Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space

Authors: Kelvin Kan, Xingjian Li, Benjamin J. Zhang, Tuhin Sahai, Stanley Osher, Markos A. Katsoulakis
Published: 2026-05-17
Categories: cs.LG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2605.17232v4

Discrete diffusion has become a leading framework for generative modeling in various applications including language, vision, and biology. Existing convergence theory, however, exhibits fundamental limitations. KL-based analyses diverge under singular priors such as the masked distribution, while bounds in total variation (TV) depend on the state space size $S$ and become vacuous for modern language tasks, where vocabularies contain hundreds of thousands of tokens. We develop a unified adjoint-equation-based framework that establishes dimension-free convergence guarantees in any integral probability metric (IPM). To the best of our knowledge, our bounds are the first to be entirely free of $S$ and applicable to both masked and uniform priors. Importantly, our results can extend existing step complexity guarantees to any IPM. In addition, our theory relies only on a single standard rate-matrix regularity assumption and applies to general priors. Five novel techniques drive our improvements: 1. working in the space of observables via adjoint equations rather than directly with probability measures; 2. a regularity analysis that yields bounds on any IPM; 3. a coupling argument that removes $S$-dependence under uniform transitions; and 4. score-marginal cancellation and 5. exit-routing techniques that remove $S$-dependence under masked transitions. Our framework thus sharply departs from prior analyses and avoids the shortcomings of pathspace-KL and existing TV-based approaches. Beyond convergence bounds, our framework provides a versatile toolkit for further theoretical study of discrete diffusion models, including principled choices of loss functions and dimension-free step complexity.

---

### FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers

Authors: Sihan Wang, Jiayi Zhao, Qingyan Cao, Hongbo Yao, Lin Shu
Published: 2026-05-17
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.17231v2

Activation steering has emerged as a lightweight approach for modifying language model behavior without parameter updates, yet existing methods remain brittle: unstable across layers and prone to disturbing behavior unrelated to the target concept. We trace these failures to a hidden assumption shared by widely-used methods such as CAA, ActAdd, and ITI: that the intermediate activation space is Euclidean. We show this assumption is fundamentally flawed. The metric that actually governs how a hidden-state perturbation changes the output is the Fisher information metric of the softmax layer, pulled back to the intermediate layer through the Jacobian of the intervening layers. From it we derive a closed-form steering direction, applied to a hidden state at an intermediate layer, that reaches a target concept change with the least non-target distortion. The framework is sharpest in the early and middle intermediate layers, where the metric is strongly non-Euclidean and geometric correction matters most. We evaluate it on three verb-morphology concepts: third-person-singular, progressive, and past-tense inflection, following standard counterfactual-concept evaluation. On GPT-2 Small, this non-Euclidean geometry is borne out empirically, and our method lowers off-target KL divergence by median factors of 1.4--6.5x against individual steering baselines. On Llama-3-8B and Qwen3-8B, it lowers off-target KL by median factors of 1.8--3.6x against individual baselines at the early and middle layers. These results show that geometric correction retains its advantage on larger models with more complex internal structure.

---

### FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers

Authors: Sihan Wang, Jiayi Zhao
Published: 2026-05-17
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.17231v1

Activation steering methods modify intermediate representations of language models to control output behavior, but universally assume the activation space is Euclidean. We show this assumption fails drastically: the local geometry induced by the model's own output behavior -- the Fisher information metric of the softmax layer, pulled back through the Jacobian of subsequent layers -- deviates from the Euclidean metric by over 97% in relative spectral norm on GPT-2, with an effective dimensionality of only 2--17% of the ambient space. From this pullback Fisher metric, we derive a closed-form steering equation that identifies the minimum-distortion direction for any target concept, yielding a closed-form optimal direction at each point that can be applied iteratively without manifold fitting or data-driven geometry estimation. We call the resulting framework FishBack. The metric admits a layer-wise recursive decomposition, which reveals that existing methods -- CAA, ActAdd, ITI, and others -- each implicitly adopt a particular approximate metric, and that their performance gaps are quantitatively predicted by a single spectral diagnostic: the ratio of their implicit metric's cost to the Fisher-optimal cost. On GPT-2, iterative pullback steering consistently outperforms all Euclidean baselines across three verb-morphology concepts and four layers, with off-target KL reductions of $1.3\times$--$2.5\times$ relative to Euclidean gradient ascent and $1.5\times$ relative to CAA at matched concept probability.

---

### Maximum Likelihood Decoding of Quantum Error Correction Codes

Authors: Hanyan Cao, Ge Yan, Yuxuan Du, Feng Pan
Published: 2026-05-17
Categories: quant-ph, cond-mat.dis-nn, cond-mat.stat-mech, cs.LG
arXiv: https://arxiv.org/abs/2605.17230v1

Quantum error correction (QEC) is indispensable for realizing fault-tolerant quantum computation, yet its effectiveness hinges critically on the classical decoding algorithm that interprets noisy syndrome measurements. Among all possible decoding strategies, maximum likelihood decoding (MLD) is provably optimal, since it identifies the logical group with largest likelihood by summing over all possible errors within logical class consistent with the observed syndrome. Despite its optimality, MLD is computationally intractable in general (#P-hard), motivating a rich landscape of exact and approximate algorithms. In this topical review, we provide a unified perspective on MLD by surveying recent advances through three complementary lenses: statistical mechanics, tensor networks, and artificial intelligence. From the statistical mechanics viewpoint, the MLD problem maps onto evaluating partition functions of disordered spin models, enabling exact solutions for certain codes and noise models as well as threshold estimation via phase-transition analysis. From the tensor network perspective, approximate contraction of tensor networks on the code's factor graph yields decoders that closely approach MLD accuracy with polynomial computational cost. From the artificial intelligence perspective, neural-network-based decoders, including autoregressive generative models and recurrent transformers, learn to approximate the MLD distribution from data, achieving high accuracy with the parallelism afforded by modern hardware accelerators. We discuss the connections among these three approaches, review their application to both simulated and experimental quantum hardware, and outline open challenges including real-time decoding, scalability to large code distances, and generalization to high-rate quantum low-density parity-check codes.

---

### Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making

Authors: Jen-tse Huang, Didi Zhou, Faith Kamau, Amy Oh, Anne R. Links, Mark Dredze, Mary Catherine Beach, Somnath Saha
Published: 2026-05-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.17228v1

Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decision support and medical documentation. However, the robustness of these models against subtle linguistic variations, specifically stigmatizing language (SL) commonly found in human-authored clinical notes, remains critically under-explored. In this work, we investigate whether frontier LLMs inherit and propagate this human bias when processing clinical text. We systematically evaluate nine frontier LLMs across four stigmatized medical conditions, utilizing clinical vignettes injected with varying intensities and phenotypes of SL (doubt, blame, and maligning). Our results demonstrate that all evaluated models exhibit substantial bias, with clinical decision-making significantly skewed towards less aggressive patient management. Notably, we observe a high sensitivity to linguistic framing, where a single SL sentence is sufficient to alter model outputs, revealing a clear dose-response relationship. Furthermore, we evaluate standard prompt-based mitigation strategies, including Chain-of-Thought (CoT) reasoning and model self-debiasing. These approaches show limited efficacy; models struggle to explicitly identify SL while remaining implicitly influenced by it. Our findings expose a critical vulnerability in current LLMs regarding fairness and robustness in clinical NLP, underscoring the need for rigorous algorithmic guardrails to prevent the automation of health disparities.

---

### Integration of AI in Cybersecurity: Current Trends with a Focused Look at Intrusion Detection Applications

Authors: S. Tazili, A. Mansour, M. Y. Chkouri
Published: 2026-05-17
Categories: cs.CR, cs.AI, cs.LG, cs.NI, eess.SP
arXiv: https://arxiv.org/abs/2605.17219v1

Artificial Intelligence (AI) is widely adopted today for its ability to detect patterns, automate tasks, and reduce time and cost across various applications. Its integration into Cybersecurity has garnered significant attention, particularly in areas such as intrusion detection, malware analysis, and phishing or spam detection. As AI and cybersecurity evolve, new methods and approaches emerge regularly. Current trends include the use of Generative AI, Natural Language Processing, Federated Learning for privacy-preserving collaborative training, and eXplainable AI to ensure interpretability and trust, which are vital in cybersecurity. This paper presents an interesting review of current AI-based cybersecurity trends, focusing on intrusion detection approaches and aiming to uncover meaningful insights through comparative analysis based on the employed AI techniques and reported performance.

---

### Toward Near-Real-Time Marine Oil Spill Detection in SAR Imagery using Quantum-Assisted SVM

Authors: Joseph Strauss, Jyotsna Sharma
Published: 2026-05-17
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2605.17217v1

Marine oil spills require rapid detection to mitigate severe ecological and economic damage. While satellite-based Synthetic Aperture Radar (SAR) provides essential all-weather monitoring, analyzing this data remains challenging. Deep learning models often require massive datasets and incur high latency. To address this, a pixel-wise quantum-assisted Support Vector Machine (QSVM) bagging ensemble is developed. Quantum annealing is leveraged to optimize the support vectors of individual weak SVMs on small data subsets, which are then classically aggregated. The approach is evaluated on Sentinel-1 imagery using both quantum simulation and physical quantum annealing hardware. The quantum-assisted pipeline achieved performance comparable to a rigorous classical baseline, yielding an Intersection-over-Union (IoU) of 0.60 and a balanced accuracy of 0.89. Complementary experiments with gate-based quantum computing demonstrated similar segmentation accuracy, although the annealing approach offered superior inference efficiency. Generalization was further assessed on independent oil spill imagery from the Strait of Hormuz, demonstrating the potential transferability of the trained pipeline to geographically distinct spill events. These results establish the feasibility of quantum-assisted, segmentation pipelines for near-real-time environmental monitoring.

---

### ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding

Authors: Mingyang Rao, Kehua Feng, Zhihui Zhu, Jiangzhen Fu, Hao Yu, Keyan Ding, Huajun Chen
Published: 2026-05-17
Categories: cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2605.17214v1

While Large Language Models (LLMs) have revolutionized scientific text processing, they exhibit a significant capability gap when interpreting chemical reaction diagrams. We identify two fundamental bottlenecks restricting current systems: a Visual Deficit, where generic vision encoders struggle to resolve the strict topological connectivity of dense molecular graphs, and a Semantic Disconnect, where standard linear strings, such as SMILES, fail to effectively activate the model's latent chemical reasoning. To bridge these gaps, we propose the Chemical Visual Activation (ChemVA) framework, which employs a Visual Anchor mechanism to ground functional groups via hybrid-granularity detection, followed by a semantic alignment approach that translates visual features into entity names to maximize knowledge activation in LLMs. We evaluate our approach on OCRD-Bench, a newly constructed dataset featuring dense visual-semantic contexts and comprehensive reaction coverage to evaluate the full spectrum from recognition to reasoning. Extensive experiments on OCRD-Bench demonstrate that ChemVA achieves 92.0% structural recognition accuracy. By bridging visual and semantic bottlenecks, our framework delivers a consistent performance gain of approximately 20 percentage points across 9 diverse LLMs, enabling open-weight models to rival proprietary SOTA systems in complex chemical reasoning tasks.

---

### Anytime PAC-Bayes for Constrained Density-Ratio Networks under Covariate Shift

Authors: Paulo Akira F. Enabe, Rodrigo Provasi
Published: 2026-05-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.17212v3

A unified framework for learning under covariate shift is presented, in which a constrained density-ratio network approximates the Radon-Nikodym derivative $r^\star = dP/dQ$ and feeds an anytime PAC-Bayes generalization certificate. A change-of-measure identity decomposes the gap between target risk and importance-weighted source risk into a ratio-bias term governed by $\|r_θ- r^\star\|_{L^2(Q)}$ and a generalization-gap term governed by the variability of the weighted loss. Normalization and moment-matching identities are enforced as hard integral constraints through an augmented-Lagrangian scheme, with a second-moment penalty controlling the effective sample size. PAC-Bayes is instantiated on the weighted risk in a fixed-time regime that yields Bernoulli-KL bounds, identifies the network-weighted Gibbs posterior as the unique KL-regularized minimizer, and quantifies stability under $L^2(Q)$ perturbations of the learned ratio, and is then strengthened by geometric peeling to an anytime certificate uniform in $t \geq t_{\min}$. A pre-registered two-campaign protocol combining a patch test against analytic ground truth with a real-data deployment validates the framework: the network produces calibrated ratios, reduces target $0/1$ loss against unweighted ERM and classical direct ratio-estimation baselines, and attains the anytime certificate. A single fixed-time coverage failure is recorded, with per-split coverage aligning one-to-one with the magnitude of the label shift, confirming that the covariate-only assumption is operationally tight rather than a defect of the certificate.

---

### LLMs for automatic annotation of Mandarin narrative transcripts

Authors: Qingwen Zhao, Hongao Zhu, Yunqi He, Rui Wang, Aijun Huang, Hai Hu
Published: 2026-05-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.17205v1

Linguistic annotation of transcribed speech is essential for research in language acquisition, language disorders, and sociolinguistics, yet remains labor-intensive and time-consuming. While Large Language Models (LLMs) have shown promise in automating annotation tasks, their ability to handle complex discourse-level annotation in non-English languages remains understudied. This study evaluates whether LLMs can reliably annotate narrative macrostructure-the hierarchical organization of story grammar elements-in spoken Mandarin, using the Multilingual Assessment Instrument for Narratives (MAIN) as a testbed. We compared four LLMs against trained human annotators on narratives produced by children, young adults, and older adults. The best-performing model achieved agreement with human raters (k=.794) approaching human-human reliability levels (k=.872) while reducing annotation time by 65%, whereas the locally deployable lightweight model performed substantially worse. Annotation difficulty varied systematically by macrostructure element type, with categories requiring subtle semantic differentiation posing persistent challenges. Furthermore, model reliability decreased on young adult narratives, which exhibited greater lexical variation, semantic ambiguity, and multi-element integration within single utterances. These findings suggest that LLMs can effectively support discourse-level annotation in non-English spoken corpora, while highlighting the continued need for human oversight in semantically complex tasks. Our prompt templates are open sourced for future use.

---

### Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies

Authors: Xinchen Jin, Aditya Chatterjee, Pranav Kumar, Rohan Paleja
Published: 2026-05-17
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2605.17204v1

Vision-Language-Action (VLA) policies translate language and visual inputs into robot actions, where their hidden representations directly shape closed-loop behavior. However, mechanistic interpretability tools from language and vision-language models do not transfer cleanly to VLAs: outputs are robot actions rather than human-readable tokens, and interventions can only be tested via expensive closed-loop rollouts. We propose an event-grounded interpretability pipeline that anchors SAE feature analysis to behavioral events rather than text contexts. End-effector keyframes are clustered within each task using visual, state, and temporal cues, linking SAE features to behaviorally salient events and, via optional VLM annotations, to semantic context. To our knowledge, our pipeline is among the first to ground SAE-based VLA analysis in closed-loop behavioral events. Across two simulation architectures and a real-robot study, event-grounded ranking yields the strongest causal effects on OpenVLA and transfers to the continuous action chunks of $π_{0.5}$. SAE is a sparse but imperfect intervention basis: usability varies with architecture and intervention site, and aggressive intervention reveals safety and interpretability limits. Overall, event-grounded SAE analysis emerges as a practical starting point for behavior-anchored VLA interpretability, motivating future work on SAE features beyond action-aligned coordinates, finer-grained closed-loop evaluation, and safe interventions for high-stakes VLA deployments. Code is available at \url{https://github.com/xc-j/Event-SAE}.

---

### Filter-then-Verify: A Multiphase GNN and ModernBERT Framework for Social Engineering Detection in Email Networks

Authors: Barsat Khadka, Prasant Koirala, Kshitiz Neupane, Nick Rahimi
Published: 2026-05-17
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2605.17201v1

Social engineering attacks exploit human trust rather than software vulnerabilities, making them difficult to detect using conventional filters. We propose a two-stage filter-then-verify framework combining inductive Graph Neural Networks (GNNs) for structural anomaly detection with a co-attention ModernBERT model for content verification. The GNN identifies anomalous sender-receiver patterns, while BERT analyzes message context to reduce false positives. Using the Enron dataset augmented with realistic synthetic campaigns, we show that the framework achieves 86% recall in structural filtering and over 92% precision after BERT refinement, effectively detecting both external attacks and insider threats. Our results demonstrate that combining structural and content analysis allows practical, scalable detection of multi-stage social engineering attacks in email networks.

---

### Reliable LLM-Powered Decision Engines for Large-Scale Supply Chain Operations: Architecture, Safety, and Performance Guarantees

Authors: Nirmal Kumar Jingar
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.24889v1

Current large-scale supply chains are highly uncertain, dynamic, and disruption prone that are challenging to serve up timely and resilient decisions through traditional rule-based and optimization-only systems. The increasing supply of heterogeneous data sources, such as transactional demand signals and unstructured disruption report, presents a chance of intelligent systems, which could reason, adapt and optimize at the same time. A hybrid architecture that combines large language models (LLMs) with mathematical optimization, probabilistic forecasting, and safety-constrained decision filtering is proposed in this paper as a performance of a Decision Engine, which is called LLM-Powered Decision Engine (LLM-DE). In comparison to purely data-driven or heuristic solutions, LLM-DE integrates semantic reasoning with LLM with a set of performance and safety guarantees that allow safe decision-making in large-scale supply chain processes. The suggested framework enables the end-to-end decision making such as demand forecasting, inventory optimization, and transportation routing and disruption mitigation. The findings affirm that language-based reasoning combined with optimization and formal constraints can be used to come up with not only smarter but also safer and more scalable supply chain decisions. This research provides a new architecture, a complete pipeline of algorithm, and a formulation based on mathematical constructs of the operational decision systems incorporating LLM. The proposed model offers a pragmatic and theoretical basis of the next-generation intelligent supply chain infrastructures that can be implemented to work dependably in the face of uncertainty and massive complexity.

---

### Evaluating the Impact of Reviewer Guideline Design on LLM-Based Automated Peer Review

Authors: Haowen Li, Yoichi Ishibashi, Masafumi Oyamada
Published: 2026-05-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2607.22553v1

Peer review is an essential process in scientific research, yet the growing workload has made its automation increasingly necessary. In this study, we analyze how different types of reviewer guidelines, such as official conference guidelines and reviewer-imitating ones generated from high-quality human reviews using LLMs, affect automated peer review. Our experiments show that official conference guidelines produce review results most consistent with human judgments, suggesting that evaluation criteria refined through conference practice serve as effective guidance for automated reviewing as well. In contrast, reviewer-imitating guidelines were generally less effective than official conference guidelines. Furthermore, enforcing strict rubric-style scoring consistently degraded performance, highlighting the importance of allowing subjective and holistic scoring.

---

### Spectral Flow Certificates for Depth-Aware Long-Range Propagation in Graph Neural Networks

Authors: Ranjan Veerabhadraswamy, Ajith Jubilson Emerson
Published: 2026-05-16
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2607.21607v1

Graph Neural Networks propagate information through local message passing, but the graph topologies themselves can silently prevent any amount of training from solving long-range tasks. When we deploy GNNs on new graphs, there is currently no inexpensive way to know, before training begins, whether the graphs' structures will allow information to travel far enough between distant nodes. We address this gap by proposing Spectral Flow Certificates (SFCs), single scalars computed from the graphs' normalised Laplacians in seconds, requiring no model training and no labelled data. An SFC fuses a graph's algebraic connectivity with the chosen message-passing depth into one number that measures how much of the critical spectral bottleneck can be traversed within the available depth budget. Unlike raw spectral gaps, which are static and depth-agnostic, SFCs adapt as the number of layers increases and therefore carry strictly more diagnostic information when depths vary. Compared with classical structural statistics such as average effective resistance and graph diameter, SFCs explain more than twice as much variance in trained GNN long-range accuracy. Across twenty-five synthetic graph families spanning paths, cycles, grids, regular graphs, and random graphs, SFCs predict trained accuracy before any gradients are computed, achieving explanatory power above ninety percent at all tested depths. The same predictive relationships hold on one hundred fifty real molecular graph topologies drawn from three independent benchmark datasets, confirming that the findings are not artefacts of their synthetic construction. Taken together, these results show that a single eigenvalue computation is sufficient to flag topology-limited graphs before committing to expensive training pipelines, providing a principled first filter for GNN deployments.

---

### TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward

Authors: Debottam Dutta, Jaehoon Hahm, Jianchong Chen, Romit Roy Choudhury
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.21606v1

Recent advances in powerful text-to-image generation models have made it increasingly important to develop test-time methods that modify the sampling trajectory to produce images more faithful to complex compositional prompts. We present TILT, a training-free framework for compositional text-to-image generation via test-time reward alignment. We interpret compositional failures as overlap modes between joint and single-concept distributions, and define a reward that favors samples where all concepts are jointly present. This reward is intrinsic to the base model and does not require any external supervision or reward models. This yields a KL-constrained objective with a closed-form tilted target distribution and principled guiding steps for diffusion sampling. The interaction of concept distributions together with the above reward naturally leads to two different guidance strategies while a hybrid approach that balances their respective benefits produces stronger performance. Experiments on prompts from T2ICompBench show that our method improves compositional alignment while preserving image quality compared to previous baselines.

---

### Marking the Wrong Symptoms: Evaluating LLM Watermarks in Medical Texts

Authors: Melanie Rieff, Robin Staab, Thibaud Gloaguen, Stefan Hegselmann, Martin Vechev
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.20462v1

Large language models (LLMs) are increasingly integrated into clinical workflows, stressing the need for reliable traceability of model-generated output with watermarking. Yet, most watermarks are evaluated on general-purpose benchmarks, leaving domains like medicine, where small token-level perturbations can result in significant semantic changes, underexplored. In this work, we present the first rigorous study of how LLM watermarks affect medical performance, benchmarking 5 watermarking schemes across 11 LLMs and 7 VLMs on various tasks spanning unimodal and multimodal clinical reasoning. Importantly, we complement existing evaluations by introducing a human-expert-validated pipeline for systematically auditing medical reasoning quality, terminological precision, and induced hallucinations. Our results reveal that watermarking can induce substantial degradation across multiple failure modes, including lexical corruption, hallucinated terminology, and amplified misattribution or omission of image findings. Notably, we find that the absence of domain-specific analyses, combined with aggregate metrics that miss failures inherent to clinical text, can systematically obscure practical watermark-induced degradations. Our findings establish domain-specific evaluation as a prerequisite for the safe deployment of watermarked models in medicine, where current benchmarks can otherwise mask clinically consequential failures.

---

### Position: AI/ML Deepfake Research is Misaligned with AI-Generated Non-Consensual Intimate Imagery (AIG-NCII)

Authors: Li Qiwei, Wells Lucas Santo, Sarita Schoenebeck, Eric Gilbert
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.18263v2

AI-generated non-consensual intimate imagery (AIG-NCII) is not adequately addressed in AI/ML literature regarding AI-generated media, commonly referred to as "deepfakes". While research on deepfakes currently focuses on its epistemic harms -- or harms relating to truth and authenticity -- this is misaligned with the dominant reality of generative AI abuse involving sexualized imagery. We conduct a landscape analysis of highly-cited works to demonstrate that technical interventions addressing deepfakes almost entirely ignore AIG-NCII, limiting the research ecosystem to authenticity detection tools. In this position paper, we argue that existing interventions address viewer-centric epistemic harms, such as fraud or scams, but ignore subject-centric dignity harms, such as AIG-NCII. We illustrate that knowing an image is synthetic does not mitigate harms to subjects and may, in some cases, even exacerbate them. We conclude by offering recommendations to realign the field, including updating threat models to consider subject-centric harms and addressing AIG-NCII in AI safety research. Finally, we caution that researchers should only engage in this high-risk domain if they implement safety guardrails for both subjects and researchers and establish partnerships with domain experts in sexual violence prevention.

---

### ProbSPARQL: Querying Knowledge Graphs with Multi-dimensional, Uncertain Numeric Data

Authors: Jingcheng Wu, Ratan Bahadur Thapa, Daniel Hernandez, Hongkuan Zhou, Steffen Staab
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.18262v2

The SFB 1574 Circular Factory is building a shared knowledge graph infrastructure for integrating data about returned products. A central challenge is that circular-factory data include numeric measurements that (i) originate from sensors or are derived from sensor-based measurements, (ii) are frequently multi-dimensional, and (iii) are inherently uncertain, while downstream triage, validation, reliability-modeling, and reassembly-planning modules require queryable uncertainty representations. Current RDF and SPARQL technologies lack native support for harmonized querying and analysis of such uncertain numeric measurement data. To address this gap, we present ProbSPARQL, an upward-compatible SPARQL extension developed as an early-stage query-layer pilot for this infrastructure. ProbSPARQL models uncertain numeric values as random variables whose distributions are encoded by probabilistic RDF literal datatypes, and supports distribution-aware expressions, probabilistic filters, and divergence-based joins. We implement ProbSPARQL on Apache Jena ARQ and expose it through a Fuseki-compatible execution layer. We assess real-data applicability using project-derived measurement fragments covering GMM-encoded uncertainty and histogram-based empirical roughness distributions, and evaluate scalability separately on controlled ontology-conformant benchmarks with up to 5,000 angle-grinder instances and 1.5M triples. The results show feasible in-engine execution, filter-pushdown speedups over application-layer post-processing, and latency-accuracy trade-offs among divergence-join decision strategies.

---

### ProbSPARQL: Querying Knowledge Graphs with Multi-dimensional, Uncertain Numeric Data

Authors: Jingcheng Wu, Ratan Bahadur Thapa, Daniel Hernandez, Hongkuan Zhou, Steffen Staab
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.18262v1

The SFB 1574 Circular Factory is building a shared knowledge graph infrastructure for integrating data about returned products. A central challenge is that circular-factory data include numeric measurements that (i) originate from sensors or are derived from sensor-based measurements, (ii) are frequently multi-dimensional, and (iii) are inherently uncertain, while downstream triage, validation, reliability-modeling, and reassembly-planning modules require queryable uncertainty representations. Current RDF and SPARQL technologies lack native support for harmonized querying and analysis of such uncertain numeric measurement data. To address this gap, we present ProbSPARQL, an upward-compatible SPARQL extension developed as an early-stage query-layer pilot for this infrastructure. ProbSPARQL models uncertain numeric values as random variables whose distributions are encoded by probabilistic RDF literal datatypes, and supports distribution-aware expressions, probabilistic filters, and divergence-based joins. We implement ProbSPARQL on Apache Jena ARQ and expose it through a Fuseki-compatible execution layer. We assess real-data applicability using project-derived measurement fragments covering GMM-encoded uncertainty and histogram-based empirical roughness distributions, and evaluate scalability separately on controlled ontology-conformant benchmarks with up to 5,000 angle-grinder instances and 1.5M triples. The results show feasible in-engine execution, filter-pushdown speedups over application-layer post-processing, and latency-accuracy trade-offs among divergence-join decision strategies.

---

### When JSON Is Not Enough: Semantic Reliability of Schema-Constrained LLM Ordering Agents

Authors: Yin Li
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.18261v1

LLM agents are increasingly used as transaction compilers: a user states an intent in natural language, and the model emits a structured object that an API can execute. JSON Schema and provider-level structured-output modes are useful because they remove a large class of parse failures, but they do not by themselves decide whether the object is a safe, faithful transaction. We introduce OrderBench, a deterministic benchmark for restaurant ordering agents that separates syntactic validity, schema validity, status decisions, exact item semantics, constraint preservation, and unsafe acceptances. Across 2,400 Nebius Token Factory calls to four open models in prompt-only and JSON-schema modes, we find that schema-valid output can still have large semantic error rates. In the strongest model, both modes achieve 100% schema validity, yet semantic success remains near 80%; in weaker models, schema-valid unsafe acceptances occur in double digits. The result is a concrete engineering warning: structured output is a necessary interface layer, not a substitute for domain verification and fail-closed execution.

---

### FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis

Authors: Soham Dan
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.18260v1

We introduce FindStatBench, an execution benchmark for evaluating large language models on combinatorial code synthesis. Built from FindStat, it contains 2,329 tasks across 24 collections and 5.52M hidden instances, covering statistic synthesis, which maps objects to integers, and map synthesis, which maps objects to objects. Each task gives a mathematical description and at most five public input-output examples; a model must emit one Python solve function with no retrieval, tool use, execution feedback, voting, or reranking. Submissions are scored by exact sandboxed execution on held-out combinatorial objects. We evaluate eleven systems: four closed-source production models and seven open-weight models served through one inference provider. FindStatBench reveals three main patterns. First, the strongest open- and closed-source systems converge within 1 pp instance accuracy, and both an oracle over all systems and five-way sampling from one mid-tier model yield only limited task-accuracy gains. Second, examples can hurt: several classical bijections are solved perfectly with zero examples but fail under five-example prompts. Third, some failures reflect output-budget mechanics, as reasoning can exhaust the visible response before code is emitted. Overall, statistic synthesis is much easier than map synthesis, some collections remain near-zero, long prompts cause a sharp accuracy cliff, and exact symbolic rule induction remains brittle.

---

### Algorithmic Constitutionalism

Authors: Oren Perez, Nurit Wimer
Published: 2026-05-16
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2606.12437v1

The increasing encroachment of artificial intelligence (AI) on social life raises significant risks for society, particularly within the infospheres created and controlled by companies such as Google, Facebook, Apple, and Amazon. This article examines these risks through an in-depth analysis of Facebook's content moderation regime, which is already partially governed by algorithms. We argue that the idea of ethical engineering, often proposed in the literature as a solution to the governance challenges posed by AI, is inadequate for several reasons. In response, we develop an alternative framework, which we term "algorithmic constitutionalism." Our approach rests on three pillars: (a) a layered architecture consisting of two levels of code: (i) an operative or object level and (ii) a meta level designed to protect the system's core principles from algorithmically initiated change; (b) algorithmic meta-reasoning, which enables the system to operate simultaneously at both levels so that it can monitor, verify, and potentially correct in real time operations at the object level that depart from principles protected at the meta-code level; and (c) correction through deliberation. The article elaborates the concept of algorithmic constitutionalism and demonstrates how it may be applied to Facebook's content moderation regime. As part of this analysis, we examine the tension between societal constitutionalism and algorithmic constitutionalism. Paradoxically, attempts to subject AI systems to external deliberative control may also enable AI agents to intervene in that process, potentially undermining its purpose. The article concludes by considering the implications of this argument for the European Digital Services Act, which entered into force in October 2022.

---

### Auditing Discriminatory Patterns in Mortgage Lending Through Association Rules and Fair Binning

Authors: Archit Rathod, Dhwani Chande, Het Nagda
Published: 2026-05-16
Categories: cs.CY, cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2606.12435v1

Mortgage lending in the United States exhibits persistent racial and gender disparities. We investigate whether standard data preprocessing steps, specifically attribute binning, amplify these disparities in downstream pattern mining. Using 103,481 cleaned mortgage applications from the HMDA 2023 dataset (Chicago metropolitan area), we build a three-stage pipeline: (1) a PySpark data cleaning and binning pipeline that implements both standard equal-frequency binning and the epsilon-biased fair binning algorithm from Asudeh et al. (1), (2) FP-Growth association rule mining that compares denial patterns under both binning regimes, and (3) K-Means clustering with a per-cluster disparate impact audit. Our standard binning shows 9.63% racial bias in income discretization, consistent with the 8-10% reported in prior work. Fair binning with seven race groups is infeasible at epsilon=0.03 and only succeeds at epsilon=0.08 with a Price of Fairness of 29.4%. FP-Growth reveals that high debt-to-income ratio is the dominant denial predictor (67.2% confidence, 2.81 lift), while racial bias does not appear as explicit high-support rules. However, K-Means clustering followed by a disparate impact audit flags 10 out of 45 cluster-group pairs, showing that Black applicants face significantly higher denial rates than White applicants even among financially similar groups.

---

### Large language models reorganize representational geometry during in-context learning

Authors: Hua-Dong Xiong, Li Ji-An, Robert C. Wilson, Kwonjoon Lee, Xue-Xin Wei
Published: 2026-05-16
Categories: cs.CL, cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2605.28854v3

Large language models (LLMs) show remarkable flexibility in adapting to novel tasks without parameter updates, a capacity known as in-context learning (ICL). Prior work has sought to understand ICL by studying the circuits, algorithms, and representations that support it. Yet why some ICL tasks are easy to solve while others are difficult remains unresolved. In this paper, we ask whether LLMs can adapt their representations arbitrarily to solve a simple linear classification task. Specifically, we construct a family of binary classification tasks in which labels are defined by projecting LLMs' own representations onto different axes. Surprisingly, although all tasks are linearly separable by construction, their in-context learnability varies systematically across axes. We find that successful ICL is accompanied by a geometric reorganization of internal representations that increases task-relevant separability. Causal interventions that amplify neural activity along the axis defining the task are insufficient to improve behavioral performance or induce this representational reorganization. We also show that LLM behavior is best described by a prototype-like algorithm operating on representations that are themselves reorganized in context to adapt to the task. Together, these findings offer a geometric account of ICL in LLMs, showing that representations acquired through training constrain what can be exploited through in-context learning.

---

### Large language models reorganize representational geometry during in-context learning

Authors: Hua-Dong Xiong, Li Ji-An, Robert C. Wilson, Kwonjoon Lee, Xue-Xin Wei
Published: 2026-05-16
Categories: cs.CL, cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2605.28854v1

Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a capability known as in-context learning (ICL). Prior work on synthetic tasks has shown that ICL can implement specific algorithms, demonstrating architectural competence, and mechanistic analyses have identified key circuits that support this behavior. However, because in-context computation -- regardless of its algorithmic form -- relies on transformations in high-dimensional representation space, it remains unclear how the geometry of that space shapes ICL effectiveness. Motivated by the neuroscience view of classification as the untangling of neural representations, we hypothesize that ICL depends on the successful online untangling of task-relevant representations. To test this idea, we study how LLMs classify in-context examples whose labels are defined by the model's own internal representations with known structure. We show that ICL performance correlates systematically with the representational structure of the underlying classification task and that successful ICL is accompanied by geometric reorganization that increases online separability. We further find that LLM behavior is well described by a prototype-like algorithm that integrates evidence while reshaping representations to support classification. These findings offer a geometric account of ICL in pretrained LLMs, establish representational geometry as a mechanistic constraint on ICL, and quantify the gap between what pretrained representations afford and what in-context learning can exploit.

---

### Financially Guided Deep Portfolio Optimization

Authors: Rahul Fernandes, Travis Desell
Published: 2026-05-16
Categories: q-fin.PM, cs.LG
arXiv: https://arxiv.org/abs/2605.28853v2

Portfolio optimization in real-world financial markets is notoriously difficult due to non-stationarity, noisy data, and high transaction costs. Standard predict-then-optimize methods first forecast returns and then solve for weights, compounding prediction errors and often failing under regime shifts. We propose an end-to-end framework that directly optimizes differentiable surrogates of key financial metrics (Sharpe ratio, Omega ratio, Conditional Value-at-Risk, and risk parity), allowing neural networks to learn portfolio weights via backpropagation. Our expanding-window walk-forward procedure, applied to 50 S&P 500 stocks from 2007 to 2023, incorporates realistic bid-ask spread costs and rebalances quarterly. On the challenging out-of-sample test period (2022-2023), the best model, an AttentionLSTM with the Omega-CVaR-RiskParity loss, achieves an annualized Sharpe of 0.29 and a total compounded return of +7.86%, while the S&P 500 delivers -4.52% total compounded return and an annualized Sharpe of -0.02. This outperforms the S&P 500 by 12.38 percentage points, while keeping tail risk (CVaR) nearly unchanged. The framework outperforms the equal-weight portfolio, S&P 500, and traditional methods (MVP, HRP, NCO, ERC), demonstrating that embedding financial objectives directly into model training yields robust, economically meaningful outperformance even in adverse market conditions.

---

### Financially Guided Deep Portfolio Optimization

Authors: Rahul Fernandes, Travis Desell
Published: 2026-05-16
Categories: q-fin.PM, cs.LG
arXiv: https://arxiv.org/abs/2605.28853v1

Portfolio optimization in real-world financial markets is notoriously difficult due to non-stationarity, noisy data, and high transaction costs. Standard predict-then-optimize methods first forecast returns and then solve for weights, compounding prediction errors and often failing under regime shifts. We propose an end-to-end framework that directly optimizes differentiable surrogates of key financial metrics - Sharpe ratio, Omega ratio, Conditional Value-at-Risk (CVaR), and Risk Parity - allowing neural networks to learn portfolio weights via backpropagation. Our expanding-window walk-forward procedure, applied to 50 S&P 500 stocks from 2007 to 2023, incorporates realistic bid-ask spread costs and rebalances quarterly. On the challenging out-of-sample test period (2022-2023), the best model - an AttentionLSTM with the Omega-CVaR-RiskParity loss - achieves an annualized Sharpe of 0.29 and a total compounded return of +7.86%, while the S&P 500 delivers -4.52% total return and an annualized Sharpe of -0.02. This outperforms the S&P 500 by 12.38 percentage points (a relative improvement of over 270%), while keeping tail risk (CVaR) nearly unchanged. The framework consistently outperforms the equal-weight portfolio, S&P 500, and traditional methods (MVP, HRP, NCO), demonstrating that embedding financial objectives directly into model training yields robust, economically meaningful outperformance even in adverse market conditions.

---

### Towards a Foundation Model for the Martian Atmosphere

Authors: Sujit Roy, Udayshankar Nair, Yuling Wu, Georgios Priftis, Liping Wang, Anastasia Georgiou, Anne Jones, Björn Lütjens, Johannes Schmude, Campbell Watson, Rachel A. Slank, Ankur Kumar et al.
Published: 2026-05-16
Categories: astro-ph.EP, astro-ph.IM, cs.LG, physics.ao-ph
arXiv: https://arxiv.org/abs/2605.28851v1

The martian atmosphere hosts dynamical phenomena ranging from planet-encircling dust storms to mesoscale orographic clouds and nocturnal low-level jets. General circulation model show capability to simulate these phenomena, but is computationally expensive at resolution needed to resolve mesoscale features. While assimilation of satellite remote sensing observation enable forecasting capabilities using such models, observation record is often sparse, short and fragmented across instrument generators. These constraints motivate the development of a data-driven foundation model for the Martian atmosphere. Foundation models live in a complex design landscape. There is an interplay between the available data, the physics of the underlying processes and corresponding developments in AI. Even though the idea of a foundation model is to address multiple use cases in a data- and compute-efficient manner, it is important to have a clear picture what applications can sensibly addressed by a single model. The purpose of this paper is to elucidate this design landscape. We discuss available data ranging from atmospheric retrievals to reanalysis datasets as well as existing physical models. Moreover, we identify a wide range of candidate downstream applications. Finally, we consider relevant recent developments in artificial intelligence (AI) that can be leveraged in this context. Here, we put a particular emphasis on AI models for atmospheric physics, data-driven approaches to data assimilation as well as methods to work in a limited data setting.

---

### Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents

Authors: Weicheng Xue
Published: 2026-05-16
Categories: cs.LG, q-fin.CP
arXiv: https://arxiv.org/abs/2605.28850v3

We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. TradeArena, an auditable trading-agent testbed with risk reports, execution simulation, memory, and replayable trajectories, lets us analyze how rationales, positions, and interventions evolve under market stress. Code and data artifacts are available through the \href{https://github.com/weich97/TreLLM-public}{TradeArena repository}. We find pre-failure signatures: planning embeddings drift from normal centroids, fused plan-risk representations separate normal from pre-drawdown states, and local manifolds exhibit effective-rank contraction. Across 80 rolling failure anchors and eight LLM trajectories, this pattern persists across hash, LSA, Transformer, and white-box hidden-state probes. Stress tests with CoT-free target weights, lexical controls, OHLCV noise, and false audits show that rationale-level contraction can vanish without rationales, while intent-space and fused signatures remain informative. Structured risk feedback can act as an external alignment signal without fine-tuning, but not as a universal performance enhancer: true audit feedback improves calibration for some models, returns for others, and exposes cases where placebo or hidden feedback has higher short-horizon return but weaker alignment diagnostics. A 51-stock intraday experiment reveals a correlation blind spot: LLM rationales justify exposure to coupled assets that the risk layer clips. Finally, a financial-audit task suite shifts comparison from ``which model trades best'' to whether models can audit trajectories, respect execution boundaries, reproduce artifacts, and avoid claim overreach. These results support a research claim, not a profitability claim: auditable risk feedback and representation trajectories reveal when LLM financial reasoning is aligning, drifting, or failing.

---

### Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents

Authors: Weicheng Xue
Published: 2026-05-16
Categories: cs.LG, q-fin.CP
arXiv: https://arxiv.org/abs/2605.28850v2

We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. TradeArena, an auditable trading-agent testbed with risk reports, execution simulation, memory, and replayable trajectories, lets us analyze how rationales, positions, and interventions evolve under market stress. Code and data artifacts are available through the \href{https://github.com/weich97/TradeArena.git}{TradeArena repository}. We find pre-failure signatures: planning embeddings drift from normal centroids, fused plan-risk representations separate normal from pre-drawdown states, and local manifolds exhibit effective-rank contraction. Across 80 rolling failure anchors and eight LLM trajectories, this pattern persists across hash, LSA, Transformer, and white-box hidden-state probes. Stress tests with CoT-free target weights, lexical controls, OHLCV noise, and false audits show that rationale-level contraction can vanish without rationales, while intent-space and fused signatures remain informative. Structured risk feedback can act as an external alignment signal without fine-tuning, but not as a universal performance enhancer: true audit feedback improves calibration for some models, returns for others, and exposes cases where placebo or hidden feedback has higher short-horizon return but weaker alignment diagnostics. A 51-stock intraday experiment reveals a correlation blind spot: LLM rationales justify exposure to coupled assets that the risk layer clips. Finally, a financial-audit task suite shifts comparison from ``which model trades best'' to whether models can audit trajectories, respect execution boundaries, reproduce artifacts, and avoid claim overreach. These results support a research claim, not a profitability claim: auditable risk feedback and representation trajectories reveal when LLM financial reasoning is aligning, drifting, or failing.

---

### Behavior-Induced Mirror-Prox Temporal-Difference Learning for Faster Off-Policy Prediction

Authors: Xingguo Chen, Yuchen Shen, Shangdong Yang, Chao Li, Guang Yang, Wenhao Wang
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.28849v1

Gradient temporal-difference methods provide stable off-policy prediction with linear function approximation, but their practical performance is strongly affected by the geometry induced by the auxiliary-variable metric. Existing Mirror-Prox TD methods typically use the feature covariance metric, whereas hybrid TD methods suggest that behavior-policy transition information can provide a more informative update geometry. This paper proposes a behavior-induced Mirror-Prox temporal-difference method, called STHTD-MP, which replaces the covariance metric in the primal-dual saddle-point formulation with the symmetric part of the behavior-policy Bellman matrix. The method keeps a single learning rate for the primal and auxiliary variables and applies a Mirror-Prox prediction-correction step to the resulting hybrid saddle-point operator. We provide a formal convergence analysis for fixed-policy linear prediction under standard stochastic approximation assumptions: the behavior-induced metric is positive definite, the joint mean system is Hurwitz, boundedness follows from a Lyapunov argument, and the stochastic recursion converges by the ODE method. We further derive projected-oracle ergodic gap bounds and an exact mean-operator comparison with GTD2-MP based on the spectral radius of the deterministic Mirror-Prox error matrix. The analysis shows that STHTD-MP can have a smaller mean contraction factor than GTD2-MP when the behavior-induced metric improves the saddle-point geometry. Exact numerical mean-operator analysis on two-state, Random Walk, and Boyan Chain benchmarks supports this condition, while Baird's counterexample is identified as a singular boundary case where the strict assumptions fail.

---

### GPF-LiveNews: A Streaming Evaluation Protocol for Group-Conditioned Framing in Large Language Models

Authors: Mohd Ariful Haque, Fahad Rahman, Kishor Datta Gupta, Roy George
Published: 2026-05-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.28848v1

Deployed language models are evaluated in a non-stationary environment: model versions, retrieval layers, safety systems, and real-world inputs all change over time. Static bias benchmarks remain useful, but they do not show how models frame newly emerging events for different prompted audiences. We introduce GPF-LIVENEWS, a streaming evaluation protocol and benchmark snapshot for auditing group-conditioned framing in open-ended LLM outputs. The protocol expands fresh BBC/Reuters news anchors across 42 identity labels and seven prompt families, then evaluates response bundles using semantic-sensitivity and sentiment-disparity signals. In a pilot over 12 monitoring runs and 23 hosted models, Policy/Action prompts produce the strongest semantic movement, while sentiment variation is flatter across dimensions and prompt families. The released artifact includes article metadata, prompt templates, instantiated prompts, model-output metadata, score tables, documentation, and reproduction scripts. We interpret all scores as observed-window audit signals for human review, not as permanent fairness rankings or direct proof of harmful bias.

---

### MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing

Authors: Han Chen, Zining Zhang, Wenqi Pei, Bingsheng He, Ming Wu, Jason Zeng, Michael Heinrich, Wei Wu, Hongbao Zhang
Published: 2026-05-16
Categories: cs.DB, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2605.23986v3

Memory is a fundamental component for long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, many stateful systems retain sequential autoregressive extraction or state-dependent maintenance on the write path, delaying when new evidence becomes queryable. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data-management problem. MemForest breaks the sequential bottleneck via parallel extraction, decoupling memory construction into concurrent, independent operations. We further introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees and replaces global rewrites with localized dirty-path refresh. Dirty summaries can be refreshed in parallel across nodes and trees. End-to-end work remains proportional to incoming content; the logarithmic bound applies only to structural insertion and level-dependent refresh depth in balanced trees. We evaluate MemForest on two long-context benchmarks, LongMemEval-S and LoCoMo. Experiments use Qwen3-4B, Qwen3-30B, and Gemma-4-12B-IT. With Qwen3-30B, MemForest reaches 81.8 percent pass at 1 on LongMemEval-S, while its input-normalized build rate is 6.0 times that of EverMemOS. On LoCoMo categories 1 to 4, it reaches 84.09 percent, within 0.13 percentage points of EverMemOS; on a matched conversation, its build rate is 9.5 times higher. These results show that MemForest reduces memory-freshness latency while retaining strong answer quality.

---

### MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing

Authors: Han Chen, Zining Zhang, Wenqi Pei, Bingsheng He, Ming Wu, Jason Zeng, Michael Heinrich, Wei Wu, Hongbao Zhang
Published: 2026-05-16
Categories: cs.DB, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2605.23986v2

Memory is a fundamental component for long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, many stateful systems retain sequential autoregressive extraction or state-dependent maintenance on the write path, delaying when new evidence becomes queryable. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data-management problem. MemForest breaks the sequential bottleneck via parallel extraction, decoupling memory construction into concurrent, independent operations. We further introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees and replaces global rewrites with localized dirty-path refresh. Dirty summaries can be refreshed in parallel across nodes and trees. End-to-end work remains proportional to incoming content; the logarithmic bound applies only to structural insertion and level-dependent refresh depth in balanced trees. We evaluate MemForest on two long-context benchmarks, LongMemEval-S and LoCoMo. Experiments use Qwen3-4B, Qwen3-30B, and Gemma-4-12B-IT. With Qwen3-30B, MemForest reaches 81.8 percent pass at 1 on LongMemEval-S, while its input-normalized build rate is 6.0 times that of EverMemOS. On LoCoMo categories 1 to 4, it reaches 84.09 percent, within 0.13 percentage points of EverMemOS; on a matched conversation, its build rate is 9.5 times higher. These results show that MemForest reduces memory-freshness latency while retaining strong answer quality.

---

### ObjectCache: Layerwise Object-Storage Retrieval for KV Cache Reuse

Authors: Yu Zhu, Aditya Dhakal, Yunming Xiao, Dejan Milojicic, Gustavo Alonso
Published: 2026-05-16
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2605.22850v1

Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests that share a prefix (i.e., the system prompt). However, the accumulated KV cache is often larger than what GPU memory and local DRAM can hold. To preserve latency, current systems keep the KV cache in remote DRAM pools, increasing serving-cluster size and cost. In this paper, we explore a different approach: storing the KV cache in S3-compatible object storage so that capacity is no longer the constraint, while minimizing the impact on TTFT. We propose ObjectCache, which co-designs the storage protocol and transfer schedule so that the storage server delivers KV cache data in the order the GPU consumes it, overlapping data transfer with compute across concurrent requests. We prototype ObjectCache on a 100 Gbps RoCE cluster with NIXL (an inference library that abstracts storage and memory), Ceph RGW (an Object Gateway for clusters), and DAOS (an open source storage system). For 64K contexts, common in today's systems, ObjectCache adds only 5.6\% latency over local DRAM; for 4K contexts, where less compute is available to mask transfer, ObjectCache adds 56--75\,ms over the optimal local layerwise baseline. Under shared bandwidth caps, our scheduler reduces added TTFT by 1.2--1.8x compared with equal bandwidth sharing.

---

### Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine

Authors: Wei Huang, Andi Han, Mingyuan Bai, Huanjian Zhou, Qixin Zhang, Taiji Suzuki, Kenji Fukumizu
Published: 2026-05-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.20235v1

Diffusion models generate high-dimensional data with remarkable quality, yet how their training efficiently learns the score function, bypassing the curse of dimensionality when data is supported on low-dimensional manifolds, remains theoretically unexplained. We identify a collapse-and-refine mechanism driven by the geometry of the score function itself: at small noise scales, the diverging singularity of the score drives a rapid dimensional collapse of the induced denoising map onto the data manifold projection; at moderate noise scales, training refines the intrinsic density on the learned manifold. We instantiate this principle as Score-induced Latent Diffusion (SiLD), a two-stage framework in which both manifold learning and density estimation emerge from a single denoising score matching objective, replacing the heuristic KL regularization of VAE-based latent diffusion models. We prove that the resulting sample complexity depends on the intrinsic dimension rather than the ambient dimension. Experiments on Stacked MNIST, CelebA variants, and molecular generation benchmarks show that SiLD matches or outperforms VAE-based LDMs in generation quality and consistently improves reconstruction, validating our theoretical predictions.

---

### TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data

Authors: Cormac Cureton, Narges Armanfard
Published: 2026-05-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.20234v1

Prior-Data Fitted networks (PFNs) have been very successful in tabular contexts, handling prediction tasks in context. However, they are designed for single-task inference, meaning that predicting several target values within a context requires repeated forward calls and precludes inter-task information sharing. We propose TabPFN-MT, which is trained on an expanded multi-target synthetic prior to capture inter-task dependencies in context. This model uses an expanded $y$-encoder and a shared decoder head to enable multitask in-context learning and simultaneous inference. The model is uniquely specialized for small-to-medium datasets by relying on in-context learning rather than traditional gradient-based training. Within this regime (averaging fewer than 1,000 samples), extensive evaluations across 344 datasets demonstrate that TabPFN-MT establishes a new state-of-the-art for deep tabular multitask learning. Furthermore, despite the inherent compute asymmetry of joint optimization, our model remains highly competitive with the latest state-of-the-art single-task ensembles. Notably, on multitask datasets it achieves an overall Accuracy rank of 4.89, the highest average rank among all models tested. Crucially, TabPFN-MT delivers this highly competitive performance while reducing the inference cost for $T$ tasks from $O(T)$ to $O(1)$ forward passes, offering a massive computational efficiency improvement for multi-target tabular applications.

---