# Research Papers — 2026-04 · bundle page 120 of 233

> Full-text markdown of papers #5951–6000 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-04/page/120
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/119.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/121.md)

### A short proof of near-linear convergence of adaptive gradient descent under fourth-order growth and convexity

Authors: Damek Davis, Dmitriy Drusvyatskiy
Published: 2026-04-15
Categories: math.OC, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2604.13393v1

Davis, Drusvyatskiy, and Jiang showed that gradient descent with an adaptive stepsize converges locally at a nearly-linear rate for smooth functions that grow at least quartically away from their minimizers. The argument is intricate, relying on monitoring the performance of the algorithm relative to a certain manifold of slow growth -- called the ravine. In this work, we provide a direct Lyapunov-based argument that bypasses these difficulties when the objective is in addition convex and a has a unique minimizer. As a byproduct of the argument, we obtain a more adaptive variant than the original algorithm with encouraging numerical performance.

---

### ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold

Authors: Chenlang Yi, Gang Li, Zizhan Xiong, Tue Minh Cao, Yanmin Gong, My T. Thai, Tianbao Yang
Published: 2026-04-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.13392v2

Tabular data remains prevalent in high-stakes domains such as healthcare and finance, where predictive models are expected to provide both high accuracy and faithful, human-understandable reasoning. While symbolic models offer verifiable logic, they lack semantic expressiveness. Meanwhile, general-purpose LLMs often require specialized fine-tuning to master domain-specific tabular reasoning. To address the dual challenges of scalable data curation and reasoning consistency, we propose ReSS, a systematic framework that bridges symbolic and neural reasoning models. ReSS leverages a decision-tree model to extract instance-level decision paths as symbolic scaffolds. These scaffolds, alongside input features and labels, guide an LLM to generate grounded natural-language reasoning that strictly adheres to the underlying decision logic. The resulting high-quality dataset is used to fine-tune a pretrained LLM into a specialized tabular reasoning model, further enhanced by a scaffold-invariant data augmentation strategy to improve generalization and explainability. To rigorously assess faithfulness, we introduce quantitative metrics including hallucination rate, explanation necessity, and explanation sufficiency. Experimental results on medical and financial benchmarks demonstrate that ReSS-trained models improve traditional decision trees and standard fine-tuning approaches up to $10\%$ while producing faithful and consistent reasoning

---

### Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling

Authors: Erik Nordby, Tasha Pais, Aviel Parrack
Published: 2026-04-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.13386v1

Linear probes can detect when language models produce outputs they "know" are wrong, a capability relevant to both deception and reward hacking. However, single-layer probes are fragile: the best layer varies across models and tasks, and probes fail entirely on some deception types. We show that combining probes from multiple layers into an ensemble recovers strong performance even where single-layer probes fail, improving AUROC by +29% on Insider Trading and +78% on Harm-Pressure Knowledge. Across 12 models (0.5B--176B parameters), we find probe accuracy improves with scale: ~5% AUROC per 10x parameters (R=0.81). Geometrically, deception directions rotate gradually across layers rather than appearing at one location, explaining both why single-layer probes are brittle and why multi-layer ensembles succeed.

---

### On the Use of Evolutionary Optimization for the Dynamic Chance Constrained Open-Pit Mine Scheduling Problem

Authors: Ishara Hewa Pathiranage, Aneta Neumann
Published: 2026-04-15
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2604.13385v1

Open-pit mine scheduling is a complex real world optimization problem that involves uncertain economic values and dynamically changing resource capacities. Evolutionary algorithms are particularly effective in these scenarios, as they can easily adapt to uncertain and changing environments. However, uncertainty and dynamic changes are often studied in isolation in real-world problems. In this paper, we study a dynamic chance-constrained open-pit mine scheduling problem in which block economic values are stochastic and mining and processing capacities vary over time. We adopt a bi-objective evolutionary formulation that simultaneously maximizes expected discounted profit and minimizes its standard deviation. To address dynamic changes, we propose a diversity-based change response mechanism that repairs a subset of infeasible solutions and introduces additional feasible solutions whenever a change is detected. We evaluate the effectiveness of this mechanism across four multi-objective evolutionary algorithms and compare it with a baseline re-evaluation-based change-response strategy. Experimental results on six mining instances demonstrate that the proposed approach consistently outperforms the baseline methods across different uncertainty levels and change frequencies.

---

### UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization

Authors: Jiatao Dai, Wei Dong, Han Zhou, Chengzhou Tang, Jun Chen
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.13383v1

Ambient Lighting Normalization (ALN) aims to restore images degraded by complex, spatially varying illumination conditions. Existing methods, such as IFBlend, leverage frequency-domain priors to model illumination variations, but still suffer from limited global context modeling and insufficient spatial adaptivity, leading to suboptimal restoration in challenging regions. In this paper, we propose UniBlendNet, a unified framework for ambient lighting normalization that jointly models global illumination, multi-scale structures, and region-adaptive refinement. Specifically, we enhance global illumination understanding by integrating a UniConvNet-based module to capture long-range dependencies. To better handle complex lighting variations, we introduce a Scale-Aware Aggregation Module (SAAM) that performs pyramid-based multi-scale feature aggregation with dynamic reweighting. Furthermore, we design a mask-guided residual refinement mechanism to enable region-adaptive correction, allowing the model to selectively enhance degraded regions while preserving well-exposed areas. This design effectively improves illumination consistency and structural fidelity under complex lighting conditions. Extensive experiments on the NTIRE Ambient Lighting Normalization benchmark demonstrate that UniBlendNet consistently outperforms the baseline IFBlend and achieves improved restoration quality, while producing visually more natural and stable restoration results.

---

### Young people's perceptions and recommendations for conversational generative artificial intelligence in youth mental health

Authors: Adam Poulsen, Ian B. Hickie, Carla Gorban, Zsofi de Haan, William Capon, Ebenezer Eyeson-Annan, Jalal Radwan, Elizabeth M. Scott, Frank Iorfino, Haley M. LaMonica
Published: 2026-04-15
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2604.13381v1

Conversational generative artificial intelligence agents (or genAI chatbots) could benefit youth mental health, yet young people's perspectives remain underexplored. We examined the Mental health Intelligence Agent (Mia), a genAI chatbot originally designed for professionals in Australian youth services. Following co-design, 32 young people participated in online workshops exploring their perceptions of genAI chatbots in youth mental health and to develop recommendations for reconceptualising Mia for consumers and integrating it into services. Four themes were developed: (1) Humanising AI without dehumanising care, (2) I need to know what's under the hood, (3) Right tool, right place, right time?, and (4) Making it mine on safe ground. This study offers insights into young people's attitudes, needs, and requirements regarding genAI chatbots in youth mental health, with key implications for service integration. Additionally, by co-designing system requirements, this work informs the ethics, design, development, implementation, and governance of genAI chatbots in youth mental health contexts.

---

### Empirical Evidence of Complexity-Induced Limits in Large Language Models on Finite Discrete State-Space Problems with Explicit Validity Constraints

Authors: Md. Fahad Ullah Utsho, Mohd. Ruhul Ameen, Akif Islam, Md. Golam Rashed, Dipankar Das
Published: 2026-04-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.13371v1

Large Language Models (LLMs) are increasingly described as possessing strong reasoning capabilities, supported by high performance on mathematical, logical, and planning benchmarks. However, most existing evaluations rely on aggregate accuracy over fixed datasets, obscuring how reasoning behavior evolves as task complexity increases. In this work, we introduce a controlled benchmarking framework to systematically evaluate the robustness of reasoning in Large Reasoning Models (LRMs) under progressively increasing problem complexity. We construct a suite of nine classical reasoning tasks: Boolean Satisfiability, Cryptarithmetic, Graph Coloring, River Crossing, Tower of Hanoi, Water Jug, Checker Jumping, Sudoku, and Rubik's Cube, each parameterized to precisely control complexity while preserving underlying semantics. Using deterministic validators, we evaluate multiple open and proprietary LRMs across low, intermediate, and high complexity regimes, ensuring that only fully valid solutions are accepted. Our results reveal a consistent phase transition like behavior: models achieve high accuracy at low complexity but degrade sharply beyond task specific complexity thresholds. We formalize this phenomenon as reasoning collapse. Across tasks, we observe substantial accuracy declines, often exceeding 50%, accompanied by inconsistent reasoning traces, constraint violations, loss of state tracking, and confidently incorrect outputs. Increased reasoning length does not reliably improve correctness, and gains in one problem family do not generalize to others. These findings highlight the need for evaluation methodologies that move beyond static benchmarks and explicitly measure reasoning robustness under controlled complexity.

---

### AeTHERON: Autoregressive Topology-aware Heterogeneous Graph Operator Network for Fluid-Structure Interaction

Authors: Sushrut Kumar
Published: 2026-04-15
Categories: physics.comp-ph, cs.LG, physics.flu-dyn
arXiv: https://arxiv.org/abs/2604.13369v1

Surrogate modeling of body-driven fluid flows where immersed moving boundaries couple structural dynamics to chaotic, unsteady fluid phenomena remains a fundamental challenge for both computational physics and machine learning. We present AeTHERON, a heterogeneous graph neural operator whose architecture directly mirrors the structure of the sharp-interface immersed boundary method (IBM): a dual-graph representation separating fluid and structural domains, coupled through sparse cross-attention that reflects the compact support of IBM interpolation stencils. This physics-informed inductive bias enables AeTHERON to learn nonlinear fluid-structure coupling in a shared high-dimensional latent space, with continuous sinusoidal time embeddings providing temporal generalization across lead times. We evaluate AeTHERON on direct numerical simulations of a flapping flexible caudal fin, a canonical FSI benchmark featuring leading-edge vortex formation, large membrane deformation, and chaotic wake shedding across a 4x5 parameter grid of membrane thickness (h* = 0.01-0.04) and Strouhal number (St = 0.30-0.50). As a proof-of-concept, we train on the first 150 timesteps of a representative case using a 70/30 train/validation split and evaluate on the fully unseen extrapolation window t=150-200. AeTHERON captures large-scale vortex topology and wake structure with qualitative fidelity, achieving a mean extrapolation MAE of 0.168 without retraining, with error peaking near flapping half-cycle transitions where flow reorganization is most rapid -- a physically interpretable pattern consistent with the nonlinear fluid-membrane coupling. Inference requires milliseconds per timestep on a single GPU versus hours for equivalent DNS computation. This is a continuously developing preprint; results and figures will be updated in subsequent versions.

---

### TLoRA+: A Low-Rank Parameter-Efficient Fine-Tuning Method for Large Language Models

Authors: Yarui Cao, Kai Liu
Published: 2026-04-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.13368v1

Fine-tuning large language models (LLMs) aims to adapt pre-trained models to specific tasks using relatively small and domain-specific datasets. Among Parameter-Efficient Fine-Tuning (PEFT) methods, Low-Rank Adaptation (LoRA) stands out by matching the performance of full fine-tuning while avoiding additional inference latency. In this paper, we propose a novel PEFT method that incorporates the TLoRA+ optimizer into the weight matrices of pre-trained models. The proposed approach not only preserves the efficiency of low-rank adaptation but also further enhances performance without significantly increasing computational cost. We conduct experiments on the GLUE benchmark across diverse model architectures. Numerical experiments consistently demonstrate the effectiveness and robustness of our proposed method.

---

### A 3D SAM-Based Progressive Prompting Framework for Multi-Task Segmentation of Radiotherapy-induced Normal Tissue Injuries in Limited-Data Settings

Authors: Caiwen Jiang, Lei Zeng, Wei Liu
Published: 2026-04-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.13367v1

Radiotherapy-induced normal tissue injury is a clinically important complication, and accurate segmentation of injury regions from medical images could facilitate disease assessment, treatment planning, and longitudinal monitoring. However, automatic segmentation of these lesions remains largely unexplored because of limited voxel-level annotations and substantial heterogeneity across injury types, lesion size, and imaging modality. To address this gap, we curate a dedicated head-and-neck radiotherapy-induced normal tissue injury dataset covering three manifestations: osteoradionecrosis (ORN), cerebral edema (CE), and cerebral radiation necrosis (CRN). We further propose a 3D SAM-based progressive prompting framework for multi-task segmentation in limited-data settings. The framework progressively incorporates three complementary prompts: text prompts for task-aware adaptation, dose-guided box prompts for coarse localization, and click prompts for iterative refinement. A small-target focus loss is introduced to improve local prediction and boundary delineation for small and sparse lesions. Experiments on ORN, CE, and CRN demonstrate that the proposed method achieves reliable segmentation performance across diverse injury types and outperforms state-of-the-art methods.

---

### Diffusion Sequence Models for Generative In-Context Meta-Learning of Robot Dynamics

Authors: Angelo Moroncelli, Matteo Rufolo, Gunes Cagin Aydin, Asad Ali Shahid, Loris Roveda
Published: 2026-04-15
Categories: cs.LG, cs.RO, eess.SY
arXiv: https://arxiv.org/abs/2604.13366v2

Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints. In this work, we formulate system identification as an in-context meta-learning problem and compare deterministic and generative sequence models for forward dynamics prediction. We take a Transformer-based meta-model, as a strong deterministic baseline, and introduce to this setting two complementary diffusion-based approaches: (i) inpainting diffusion (Diffuser), which learns the joint input-observation distribution, and (ii) conditioned diffusion models (CNN and Transformer), which generate future observations conditioned on control inputs. Through large-scale randomized simulations, we analyze performance across in-distribution and out-of-distribution regimes, as well as computational trade-offs relevant for control. We show that diffusion models significantly improve robustness under distribution shift, with inpainting diffusion achieving the best performance in our experiments. Finally, we demonstrate that warm-started sampling enables diffusion models to operate within real-time constraints, making them viable for control applications. These results highlight generative meta-models as a promising direction for robust system identification in robotics.

---

### Refracted Light Interaction in Turbulent Bubbling Water (RLITBW): A Macroscopic Fluid-Optic Entropy Source

Authors: Nirjhar Debnath, Dwaipayan Datta, Kousik Dasgupta
Published: 2026-04-14
Categories: cs.ET, cs.CR, cs.NE
arXiv: https://arxiv.org/abs/2609.13147v1

The demand for high quality, unpredictable random numbers is a fundamental requirement in cryptography, stochastic simulation, and optimization. While pseudo-random number generators (PRNGs) are computationally efficient, their deterministic nature limits their suitability for security-critical applications. True random number generators (TRNGs), although physically grounded, often rely on expensive quantum or tightly controlled electronic phenomena. This paper introduces a low-cost, macroscopic TRNG based on Refracted Light Interaction in Turbulent Bubbling Water (RLITBW). The proposed system exploits compound classical chaos arising from multiphase fluid dynamics and time-varying optical refraction. A physical-mathematical model is developed to describe the cascade of non-linear processes from stochastic bubble nucleation and turbulent ascent to chaotic optical path scrambling that collectively amplify microscopic uncertainties into measurable entropy.The raw optical signal is digitized and processed using a provably secure entropy-conditioning pipeline based on Toeplitz universal hashing, followed by deterministic cryptographic expansion. The chaotic nature of the physical source is empirically validated using phase-space reconstruction, Lyapunov exponent estimation, autocorrelation analysis, and entropy metrics. The conditioned output successfully passes the full NIST SP 800-22 statistical test suite and nonlinear dynamical measures including Lyapunov exponents and sample entropy. Beyond statistical validation, the generated randomness is applied to population-based optimization algorithms, demonstrating practical usability as a replacement for conventional PRNGs. Finally, deployment architectures and scalability considerations are discussed, positioning RLITBW as an accessible, reproducible, and economically viable entropy source for real-world systems.

---

### Revisiting Classic Thought Experiments to Measure Consciousness for Artificial Intelligence Safety

Authors: Peter David Fagan
Published: 2026-04-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.00001v1

This research note revisits Leibniz's mill, Turing's imitation game, and Searle's Chinese Room through the Conservation-Congruent Encoding (CCE) framework. It formalises a toy symbolic setting in which successful behaviour is measured by task performance ($W_{causal,T}$), while the efficiency with which preserved internal structure supports that behaviour is measured by operational consciousness ($κ_T$). Within this setup, an uncompressed lookup system and a compact generative system can in principle achieve comparable behavioural success, yet diverge sharply in $κ_T$: the former relies on an expanding standing store of unreused mappings, whereas the latter reuses compact internal structure. The note therefore reframes classic disputes about understanding by separating outward performance from the organisation that sustains it, and motivates why this distinction may matter for later AI-safety analysis.

---

### Rater State Bias in RLHF Preference Data: An Audit Framework

Authors: Elena Kopteva, Vitaliy Hlynianyi-Zhuk
Published: 2026-04-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.16195v3

We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compared outputs, but they may also reflect the rater's state during annotation. Under sustained stressful or distressing conditions, raters' preferences may shift over time, so that preference data encode rater state alongside judgments about response quality. We argue that, if present, such shifts would differ from ordinary disagreement or random label noise. They would be state dependent, could be shared across annotators under similar conditions, and would not necessarily cancel during aggregation, reward modeling, and policy optimization. We propose rater state shift as a plausible and testable source of structured bias in RLHF preference data. This paper develops a hypothesis and an audit framework for studying this source of bias. We define rater state shift, rater state confound, and correlated rater state bias. We also propose survival level emotional authenticity as a candidate output signature, defined by lexical, pragmatic, discourse, and safety features whose reliability and validity remain to be demonstrated. We show that systematic rater state bias can survive aggregation and may enter the learned reward signal. We state five testable predictions, together with effect size thresholds for an initial audit, and note which require proprietary data. Finally, we present an audit protocol and pilot study plan that can be applied to publicly available instruction tuned models. We do not infer the training history of any specific deployed model.

---

### Rater State Bias in RLHF Preference Data: An Audit Framework

Authors: Elena Kopteva, Vitaliy Hlynianyi-Zhuk
Published: 2026-04-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.16195v2

We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compared outputs, but they may also reflect the rater's state during annotation. Under sustained stressful or distressing conditions, raters' preferences may shift over time, so that preference data encode rater state alongside judgments about response quality. We argue that, if present, such shifts would differ from ordinary disagreement or random label noise. They would be state dependent, could be shared across annotators under similar conditions, and would not necessarily cancel during aggregation, reward modeling, and policy optimization. We propose rater state shift as a plausible and testable source of structured bias in RLHF preference data. This paper develops a hypothesis and an audit framework for studying this source of bias. We define rater state shift, rater state confound, and correlated rater state bias. We also propose survival level emotional authenticity as a candidate output signature, defined by lexical, pragmatic, discourse, and safety features whose reliability and validity remain to be demonstrated. We analyze the conditions under which correlated rater state bias would not be averaged out during aggregation and could enter the learned reward signal. We state five predictions that distinguish this mechanism from generic engagement optimization, together with effect size thresholds for an initial audit, and note which require proprietary data. Finally, we present an audit protocol and pilot study plan that can be applied to publicly available instruction tuned models. We do not infer the training history of any specific deployed model.

---

### Artificial Intelligence Index Report 2026

Authors: Sha Sajadieh, Loredana Fattorini, Raymond Perrault, Yolanda Gil, Vanessa Parli, Lapo Santarlasci, Juan Pava, Nestor Maslej, Russ Altman, Erik Brynjolfsson, Carla Brodley, Jack Clark et al.
Published: 2026-04-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.15708v3

Welcome to the ninth edition of the AI Index report. As AI continues to advance rapidly, the question becomes whether the systems built around it can keep up. Governance frameworks, evaluation methods, education systems, and the data infrastructure needed to track AI's impact are struggling to match the pace of the technology itself. That gap between what AI can do and how prepared we are to manage it runs through every chapter of this year's report. New in this edition, the report tracks how AI is being tested more ambitiously across reasoning, safety, and real-world task execution, and why those measurements are increasingly difficult to rely on. It also features new estimates of generative AI's economic value alongside emerging evidence of its labor market effects, an analytical framework on AI sovereignty, and a science chapter developed in collaboration with Schmidt Sciences. For the first time, the report features standalone chapters on AI in science and AI in medicine, reflecting AI's growing impact across these two domains.

---

### Epidemiology of Model Collapse: Modeling Synthetic Data Contamination via Bilayer SIR Dynamics

Authors: Xiangyu Wang
Published: 2026-04-14
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2606.05168v1

Training on synthetic data causes model collapse, but existing analyses treat this as single-chain degradation. In reality, the AI ecosystem involves cross-contamination: models ingest synthetic data from other models, produce new synthetic text, and contaminate shared corpora. We propose a bilayer coupled SIR/SIRS framework -- a phenomenological mean-field model treating data corpora and AI models as two interacting populations, each with susceptible, infected, and recovered compartments linked by cross-layer transmission. The SIRS variant (our primary recommendation) incorporates immunity waning, reflecting that filtered corpora and retrained models remain susceptible to re-contamination. We derive the basic reproduction number $R_0 = \sqrt{β_D β_M / ((γ_D+μ_D)(γ_M+μ_M))}$ via the Next Generation Matrix and apply standard epidemic threshold results to the bilayer system. Illustrative scenario-based calibration from public AI text prevalence data yields supercritical dynamics ($R_0 > 1$) across three scenarios; Sobol sensitivity analysis identifies synthetic-text detection as the highest-leverage parameter. A bipartite-network agent-based model confirms mean-field consistency ($R^2 > 0.96$) for dense networks but degrades under heterogeneity. GPT-2 contamination chain experiments (192 runs across WikiText and Shakespeare) show dose-response degradation and diversity loss qualitatively consistent with the threshold picture. Matched-budget source-diversity experiments (1,088 runs) provide suggestive evidence that multi-source mixing modestly attenuates collapse, but the effect vanishes at lower contamination fractions. Intervention analysis identifies detection-based filtering and herd immunity as the highest-leverage strategies.

---

### Early Detection of Alzheimer's Disease Using Explainable Machine Learning on Clinical Biomarkers: A Multi-Class Classification Study Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) Dataset

Authors: Afshan Hashmi
Published: 2026-04-14
Categories: cs.LG, cs.AI, q-bio.QM
arXiv: https://arxiv.org/abs/2606.03995v1

Background: Alzheimer's disease (AD) affects over 55 million people worldwide. Accurate, interpretable detection of normal cognition (NC), mild cognitive impairment (MCI), and AD from routine clinical assessments remains a critical unmet need. Methods: An XGBoost classifier was developed for three-class detection using eight clinical features from the Alzheimer's Disease Neuroimaging Initiative (ADNI): MMSE, CDR Global, CDR Sum of Boxes (CDR-SB), MoCA, FAQ, age, sex, and education. Hyperparameters were optimised using Optuna (50 trials); class imbalance was addressed with SMOTE. Performance was evaluated by macro AUC-ROC with 1,000-iteration bootstrap 95% confidence intervals, macro F1, balanced accuracy, and Cohen's kappa. SHAP values provided feature-level explainability. Results: The dataset comprised 1,641 baseline subjects (608 NC, 767 MCI, 266 AD). On five-fold cross-validation, mean macro AUC was 0.983 (SD 0.007), accuracy 0.944 (SD 0.006), and macro F1 0.929 (SD 0.008). On the held-out test set (n = 247), macro AUC was 0.982 (95% CI: 0.965--0.995), accuracy 0.943, balanced accuracy 0.932, macro F1 0.927, and Cohen's kappa 0.909. SHAP analysis identified CDR Global as the dominant predictor for NC and MCI, while CDR-SB and MMSE together drove AD classification. Conclusion: An explainable machine learning model trained on routine clinical assessments achieves near-perfect three-class Alzheimer's detection. SHAP analysis reveals clinically plausible, class-specific feature importance patterns supporting clinical validity. Future work will extend this framework with speech biomarkers for multimodal detection.

---

### lmfaoooo at SemEval-2026 Task 1: Humor Is an Audience. Preference Modeling for Constrained Humor Generation

Authors: Alexey Tikhonov, Alexey Ivanov
Published: 2026-04-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.00022v1

Humor generation remains difficult not only because producing fluent, novel jokes is hard, but because "funny" is audience-dependent and supervision is noisy -- preferences vary with audience, context, and culture, and annotator agreement is often low. In this paper, we describe our system for the SemEval-2026 Task-1 (MWAHAHA), which focuses on humor generation under explicit constraints. The task evaluates submitted systems via human preference judgments in 1-on-1 arena-style comparisons. We adopt a "generate-many -> select-best" strategy. First, we generate a diverse pool of candidates per instance using multi-step prompting, model ensembling, and diversity-oriented decoding. Second, we select outputs using a preference model that approximates a "reader" by learning from human comparisons rather than absolute funniness scores. To support this approach, we release 2.5K human pairwise judgments collected through the Humor Arena prototype. We further propose an interpretable pipeline that converts labeled comparisons into a preference model. Across three preference datasets, our models consistently outperform baselines and show stronger cross-domain transfer. Finally, we apply the learned preference model to rank candidates for the MWAHAHA setting and release intermediate artifacts (candidate pools and rankings) to facilitate follow-up work. Our system ranked 1st in the English and Chinese subtasks of MWAHAHA and 2nd in the Spanish subtask.

---

### SENSE: Semantic Embedding Navigation with Soft-gated Evaluation for Retrieval-based Speculative Decoding

Authors: Shaowen Chen, Zhicheng Liao, Hongwei Wang
Published: 2026-04-14
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2606.00021v1

Speculative Decoding (SD) accelerates Large Language Model (LLM) inference by employing a lightweight draft model to propose candidate tokens, which are verified in parallel by the target model, without compromising generation quality. While Retrieval-based Speculative Decoding (RSD) is favored for its plug-and-play versatility, its potential is impeded by rigid lexical dependencies, rendering both retrieval and verification brittle to surface-level variations. To address this, we propose SENSE (Semantic Embedding Navigation with Soft-gated Evaluation). By anchoring retrieval on the hidden states of the target model, SENSE establishes robust semantic alignment, which empowers the Soft-gated Evaluation module to validate semantic equivalence rather than surface forms. To ensure rigorous benchmarking, we deconstruct existing methods into atomic primitives within a unified framework, facilitating granular, component-level comparison. Extensive experiments across diverse domains demonstrate that SENSE outperforms multiple baselines on the LLaMA and Qwen families, attaining up to 4.09 mean acceptance length and 3.26x speedup, while preserving generation quality. Our code will be released upon publication.

---

### CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards

Authors: Wei Tian, Yuhao Zhou, Man Lan
Published: 2026-04-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.00020v1

Large Language Model (LLM) based Chinese Grammatical Error Correction (CGEC) systems face two critical challenges: general-purpose models lack specialized linguistic priors for subtle grammatical distinctions, and Supervised Fine-Tuning (SFT) with Maximum Likelihood Estimation fails to optimize for precision-focused metrics, leading to systematic over-correction. We propose CSRP, a three-stage framework that progressively builds correction capability through Continual Pre-training (CPT) on 5.9M balanced samples to internalize domain knowledge, Chain-of-Thought SFT with explicit error reasoning for diagnostic transparency, and Group Relative Policy Optimization with a novel Efficiency-Aware Reward that explicitly penalizes unnecessary edits. On the NACGEC benchmark, CSRP achieves state-of-the-art performance with 50.99 $F_{0.5}$ and 57.17 precision, substantially outperforming previous best results while effectively mitigating the over-correction bias inherent in MLE-trained models. Our method also advances CSCD spelling correction to 59.61 F1, surpassing GPT-4 by 5.20 points. Comprehensive ablation studies demonstrate that the RL alignment stage contributes a 8\% relative gain over the SFT baseline, and that this gain is orthogonal to the contribution of large-scale CPT, validating that explicit optimization for edit efficiency is essential for high-quality grammatical error correction. Our code is available at https://github.com/TW-NLP/ChineseErrorCorrector.

---

### Understanding Stigmatizing Language in Clinical Documentation: A Paired Comparison of Ambient AI Drafts and Clinician Finalized Notes

Authors: Yiliang Zhou, Yawen Guo, Sairam Sutari, Jasmine Dhillon, Alexandra L. Beck, Emilie Chow, Steven Tam, Danielle Perret, Deepti Pandita, Gelareh Sadigh, Archana J. McEligot, Kai Zheng
Published: 2026-04-14
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2606.00019v1

Ambient artificial intelligence (AI) documentation tools are increasingly deployed to reduce clinician documentation burden, but their implications for biased language in clinical notes remain unclear. We conducted a large-scale comparison analysis of AI drafts and corresponding clinician finalized notes to quantify stigmatizing language changes pre- and post-editing. Using a lexicon-based natural language processing (NLP) pipeline, we measured (1) the prevalence of stigmatizing language in AI drafts, (2) the prevalence and term composition in final notes, and (3) the frequency of removal or introduction of stigmatizing terms. Across 66,297 paired note sections, 21.4% of AI draft sections contained at least one stigmatizing language mention, rising to 24.0% in clinician finalized versions. Introductions occurred more often than removals, suggesting clinician editing can be a net source of stigmatizing language entering the EHR with using Ambient AI.

---

### Examine Clinicians' Modification of Hedging Language in Ambient AI Documentation: A Comparative Study of AI Drafts and Final Notes

Authors: Yiliang Zhou, Yawen Guo, Di Hu, Sairam Sutari, Emilie Chow, Steven Tam, Danielle Perret, Deepti Pandita, Kai Zheng
Published: 2026-04-14
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2606.00018v1

Ambient AI documentation systems generate clinical note drafts that clinicians frequently revise before signing off into electronic health records, yet how these edits alter hedging language remains unclear. We conducted paired analysis of clinician-edited portions of ambient AI drafts and final notes to examine (1) whether these edits change the prevalence of hedging language, (2) whether these edits exhibit a systematic shift toward greater certainty or uncertainty, and (3) whether these changes in hedging prevalence and directionality differ by ambient AI vendors and clinical specialties. Among 62,811 paired note sections, hedging terms were more often introduced into previously non-hedged text than removed from previously hedged text, and post-edit text contained more hedging mentions than pre-edit text. Directionality analyses showed a significant overall tendency toward greater uncertainty in hedging-related replacement edits. Vendor and specialty analyses revealed substantial heterogeneity in hedging prevalence, pre-to-post changes in hedging mentions, and directionality.

---

### Memory-Based vs. Context-Only Conditioning Produces Distinct Behavioral Patterns in Stateful Personalization

Authors: Junsoo Park, Youssef Medhat, Htet Phyo Wai, Ploy Thajchayapong, Ashok K. Goel
Published: 2026-04-14
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.27389v1

We study how conditioning context shapes personalization behavior in a teacher-facing educational recommender system. We compare contextual conditioning based on the current student question with memory-based conditioning using persistent learner information. Using deviation correlation and paired statistical tests, we find that contextual recommendations exhibit stronger question-level responsiveness, while memory-based recommendations exhibit history-dependent behaviors, including learner-specific differentiation under identical input. Teacher-facing evaluation signals suggest these recommendations are interpretable and actionable. These results indicate that embedding-based similarity metrics capture responsiveness to the current question but do not characterize personalization grounded in learner history, motivating behavior-level diagnostics for studying conditioning effects.

---

### Multi-Persona Debate System for Automated Scientific Hypothesis Generation

Authors: Jaeha Oh, Byungchan Kim, Ju Li, Yang Jeong Park, Jin-Sung Park
Published: 2026-04-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.23917v1

Modern scientific discovery is bottlenecked not by data scarcity, but by the inability to synthesize fragmented knowledge into actionable hypotheses. This challenge is especially acute in battery materials research, where electrochemical performance, interfacial behavior, and manufacturing feasibility must be optimized simultaneously. Here, we present the Multi-Persona Debate System (MPDS), a literature-grounded framework for automated scientific hypothesis generation that combines literature retrieval, long-context large language model reasoning, corpus-driven persona induction, and structured multi-agent debate. MPDS constructs literature snapshots of up to 500 papers, grounds agents in role-specific evidence pools, and conducts a three-round citation-aware debate followed by moderator synthesis, enabling negotiation between personas while preserving evidence traceability. We evaluate MPDS using a temporally controlled protocol excluding direct access to target papers, including two held-out battery-materials case studies and a blinded comparison across 30 matched cases. In sodium-ion anode and all-solid-state battery cathode design tasks, MPDS recovered design logics aligned with experimentally validated solution spaces and generated more mechanistically explicit, process-aware proposals than simpler baselines. To assess the impact of personas and debate, we introduce Integrative Hypothesis Quality scoring. In ablation studies, MPDS achieved the highest mean score among five conditions, with its largest advantage in cross-perspective integration. A laboratory follow-up suggests utility as a diagnostic aid for identifying practical bottlenecks in workflows. These results indicate that structured debate over literature snapshots improves hypothesis formation under coupled engineering constraints and provides a reusable workflow for text-intensive scientific discovery.

---

### ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation

Authors: Gibson Nkhata, Uttamasha Anjally Oyshi, Quan Mai, Susan Gauch
Published: 2026-04-14
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.18769v1

Personalized Retrieval-Augmented Generation (RAG) relies on accurately selecting user-relevant documents. In practice, existing RAG approaches often suffer from high retrieval costs and overlook that collaborative signals from similar users can enhance personalized generation for the current user. We propose ClusterRAG, a Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation. ClusterRAG represents users through their profile documents, organizes users into semantically coherent clusters using density-based clustering, and performs retrieval at both the cluster and document levels via cluster-level similarity and fine-grained ranking. Extensive experiments on the LaMP benchmark demonstrate that jointly leveraging the target user's profile and profiles from top similar users consistently yields the best performance across diverse tasks. Further analysis shows that ClusterRAG integrates seamlessly with different dense retrievers and rankers, and remains effective when paired with both fine-tuned and zero-shot language models.

---

### Are Researchers Being Replaced by Artificial Intelligence?

Authors: Angelo A. Salatino, Ansgar Scherp, Christin Katharina Kreutz, Sahar Vahdati
Published: 2026-04-14
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2605.16294v1

A Nature survey from 2023 involving 1,600 researchers shows that scientists are ``concerned, as well as excited, by the increasing use of artificial-intelligence tools in research.'' This tension frames our central question: Are researchers being replaced by artificial intelligence? We argue that replacement is already underway-not as disappearance, but as a shift from researcher-as-creator to researcher-as-curator. As AI agents increasingly generate hypotheses, papers, and reviews, humans risk retaining responsibility while losing intellectual ownership. This article examines how AI is reshaping the scientific lifecycle and exposes the deeper danger: not that AI will fail to do science, but that humans may stop truly understanding it.

---

### From Prediction to Intervention: The Evolution of AI in Biomedicine

Authors: Andrew Feinberg, Aleksandr Sarachakov, Viktor Svekolkin, Alexander Bagaev, Ferran Prat, Michael Feinberg
Published: 2026-04-14
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2605.16293v2

Artificial intelligence has advanced rapidly in biomedicine through large-scale multimodal data integration, enabling increasingly accurate prediction of clinical outcomes and patient stratification. These systems, however, remain fundamentally observational: they learn statistical associations from historical data and operate within previously observed biological and clinical states, limiting their ability to generalize to novel therapies or unobserved interventions. We argue that AI in biomedicine is undergoing a structural transition. As biomedical decision-making increasingly depends on reasoning about intervention rather than extrapolation from past observations, predictive architectures become structurally insufficient. Systems that learn from historical data cannot, by construction, represent how biological systems evolve under perturbation, and therefore cannot reliably support decision-making in the presence of novel interventions. We introduce a conceptual framework distinguishing observational and interventional intelligence and define disease-level models as systems that explicitly represent the state, dynamics, and intervention response of biological processes. These models enable a shift from inference to simulation -- reasoning about what will happen under intervention rather than what is likely based on the past. This transition also implies a shift in where value is created: from data processing and prediction toward systems that support and define decision-making under intervention. It follows directly from the structure of biomedical decision-making and defines the next stage of AI in medicine. Systems that cannot model intervention will be structurally excluded from decision-making.

---

### Evidence of a Cognitive Shift in AI Education: How Students Are Rethinking Human Intelligence?

Authors: Islem Rekik
Published: 2026-04-14
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2605.16292v1

Perceptions of intelligence shape how learners evaluate and rely on artificial intelligence (AI) systems. Despite rapid advances in AI capabilities, the impact of sustained exposure to these tools on students' valuation of human intelligence (HI) relative to AI remains underexplored. This paper presents a longitudinal analysis of classroom poll responses collected between 2020 and 2026 in AI-focused undergraduate and MSc courses in computer science. Data from 471 students across technical courses (such as Machine Learning and Deep Graph Learning) and design-oriented courses (such as Design Thinking for AI) reveal four recurring phases: hype, distrust, trust, and dependency. While early responses in 2020 slightly favored AI, a consistent shift toward HI emerged from 2024 onward across all MSc cohorts. By 2026, preference for HI reached 65 percent in a technical course (a 12 percentage-point increase from 2025) and 90 percent in a design-oriented course (a 36 percentage-point increase). These findings suggest a gradual reappraisal of human intelligence as AI becomes a routine tool, with implications for learner autonomy and epistemic agency. We conclude by reflecting on this cognitive shift from favoring artificial intelligence toward prioritizing human intelligence.

---

### AI of the People, by the People, for the People: A Social Choice Approach to Collective Control of Artificial Intelligence

Authors: Paul Anton Bachmann, Niclas Boehmer, Lukas Daniel Klausner, Martin Lackner
Published: 2026-04-14
Categories: cs.CY, cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2605.16291v1

With the growing adoption of AI systems, reasoning about how society can exert control over AI becomes an increasingly urgent problem. Existing work on democratic control largely focuses on macro-level governance. In contrast, we propose a new approach grounded in social choice theory, which we term collective control of artificial intelligence. We argue that collective input can and should be incorporated at multiple points across the ML development pipeline, from data collection through objective design to alignment. We further demonstrate that social choice provides a well-suited modelling language for the treatment of collective input across all stages and that its axiomatic methodology yields principled criteria for evaluating various control mechanisms. Overall, our conceptual contribution provides a mathematically grounded framework to implement and analyse collective control of AI systems.

---

### BiSpikCLM: A Spiking Language Model integrating Softmax-Free Spiking Attention and Spike-Aware Alignment Distillation

Authors: Sihang Guo, Chenlin Zhou, Jiaqi Wang, Kehai Chen, Qingyan Meng, Zhengyu Ma
Published: 2026-04-14
Categories: cs.NE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.13859v1

Spiking Neural Networks (SNNs) offer promising energy-efficient alternatives to large language models (LLMs) due to their event-driven nature and ultra-low power consumption. However, to preserve capacity, most existing spiking LLMs still incur intensive floating-point matrix multiplication (MatMul) and nonlinearities, or training difficulties arising from the complex spatiotemporal dynamics. To address these challenges, we propose BiSpikCLM, the first fully binary spiking MatMul-free causal language model. BiSpikCLM introduces Softmax-Free Spiking Attention (SFSA), eliminating softmax and floating-point operations in autoregressive language modeling. For efficient training, we introduce Spike-Aware Alignment Distillation (SpAD), which aligns ANN teacher and SNN student across embeddings, attention maps, intermediate features, and output logits. SpAD framework allows BiSpikCLM to reach comparable performance to ANN counterparts using substantially fewer training tokens (e.g., only 5.6% of the tokens for the 1.3B model). As a result, BiSpikCLM achieves competitive performance at only 4.16% - 5.87% of the computational cost on natural language generation tasks. Our results highlight the feasibility and effectiveness of fully binary spike-driven LLMs and establish the distillation as a promising pathway for brain-inspired spiking NLP.

---

### Connecting online criminal behavior with machine learning: Using authorship attribution to analyze and link potential online traffickers

Authors: Vageesh Kumar Saxena
Published: 2026-04-14
Categories: cs.CL, cs.AI, cs.CV, cs.CY, cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2605.04080v1

This research investigated how online criminal activities can be better understood and connected using data-driven machine learning methods. Many illegal activities, such as human trafficking and illicit trade, have moved to online platforms where offenders hide behind anonymous accounts and frequently change identities. This makes it difficult for authorities to understand how large these networks are and how different online profiles may be linked. The research shows that people tend to maintain consistent patterns in how they write advertisements and present images online, even when they try to stay anonymous. By analysing these patterns across large collections of online advertisements, the research demonstrates how to link related accounts and identify repeated behaviour across illegal online markets. In addition, the research also addresses how such methods should be used responsibly. It proposes clear guidelines to ensure that privacy, fairness, and transparency are respected when these tools are applied. Overall, the research provides practical ways to support law enforcement investigations while emphasising careful and ethical use.

---

### Efficient Handwriting-Based Alzheimer,s Disease Diagnosis Using a Low-Rank Mixture of Experts Deep Learning Framework

Authors: Wu Wang, Yuang Cheng, Fouzi Harrou, Ying Sun
Published: 2026-04-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.04079v1

Early and reliable detection of Alzheimer's disease (AD) is crucial for timely clinical intervention and improved patient management. It also supports the evaluation of emerging therapeutic strategies. In this paper, we propose a Low-Rank Mixture of Experts (LoRA-MoE) deep learning framework for Alzheimer's disease diagnosis based on handwriting analysis. Handwriting signals provide a non-invasive and scalable digital biomarker that captures subtle cognitive-motor impairments associated with early AD progression. The proposed architecture allows multiple experts to specialize in different handwriting patterns while sharing a common base network. This design enables efficient learning of general representations while reducing interference between experts. Each expert is equipped with lightweight low-rank adapters. This mechanism significantly reduces the number of trainable parameters compared with standard Mixture of Experts (MoE) models and improves training stability. The proposed framework is evaluated on the Diagnosis AlzheimeR WIth haNdwriting (DARWIN) dataset. Extensive experiments are conducted, including ablation studies on key architectural parameters such as hidden dimension size, number of experts, and LoRA rank. The method is compared with multilayer perceptron (MLP) and conventional MoE architectures. In addition, stacking ensemble strategies (StackMean and StackMax) are investigated to improve robustness and predictive performance. Experimental results show that the LoRA-MoE framework achieves powerful diagnostic performance while activating significantly fewer parameters during inference. These results highlight the potential of the proposed approach as an accurate and computationally efficient solution for handwriting-based Alzheimer's disease screening and digital health applications.

---

### Validity-Calibrated Reasoning Distillation

Authors: Khouloud Saadi, Di Wang
Published: 2026-04-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.04078v2

Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies and frame distillation as trajectory imitation. This is misaligned with the structure of reasoning, where intermediate steps are often locally under-specified: global correctness constrains the final answer, but does not uniquely determine each intermediate move. We propose validity-calibrated reasoning distillation, a framework that treats reasoning distillation as a problem of local learning-signal allocation rather than path alignment. Instead of enforcing token-level imitation, we compare the student's and teacher's proposed next-step actions under the same prefix and use their relative local validity to modulate the strength of the distillation update. This yields a dynamic, context-dependent supervision mechanism that preserves the teacher's structural guidance while adapting update strength to local reasoning quality. Across mathematical reasoning, code generation, and instruction-following benchmarks, our method consistently outperforms strong distillation baselines. These results indicate that effective LLM reasoning distillation is governed not by rigid trajectory imitation, but by principled, locally calibrated allocation of learning signal.

---

### Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO

Authors: Zhiyuan Zeng, Jiameng Huang, Zhangyue Yin, Jiashuo Liu, Ziniu Li, Bingrui Li, Yuhao Wu, Yining Zheng, Ge Zhang, Wenhao Huang, Xipeng Qiu
Published: 2026-04-14
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.04077v1

Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is widely adopted for its simplicity and effectiveness. However, an important design choice remains underexplored: how token-level policy gradient terms are aggregated within each sampled group. Standard GRPO uses sequence aggregation, while recent work has advocated token aggregation as a better alternative. We show that these two rules induce different optimization biases: token aggregation introduces sign-length coupling, while sequence aggregation implicitly downweights longer responses through sequence-level equal weighting. To address this tension, we propose \textbf{Balanced Aggregation (BA)}, a simple drop-in replacement that computes token-level means separately within the positive and negative subsets and then combines them with sequence-count-based weights. Experiments with Qwen2.5-Math-7B and Qwen3-1.7B on DAPO-17k and Polaris, evaluated on six reasoning and coding benchmarks, show that BA consistently improves training stability and final performance over standard token and sequence aggregation. Our analysis further shows that the relative effectiveness of token and sequence aggregation is largely governed by response-length variation and the positive-negative length gap, highlighting aggregation as a critical design dimension in GRPO-style RLVR.

---

### A Regulatory Governance Framework for AI-Driven Financial Fraud Detection in U.S. Banking: Integrating OCC, SR 11-7, CFPB, and FinCEN Compliance Requirements for Model Development, Validation, and Monitoring Lifecycles

Authors: Mohammad Nasir Uddin
Published: 2026-04-14
Categories: cs.LG, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2605.04076v1

U.S. financial institutions deploying AI-based fraud detection face a fragmented compliance landscape spanning four regulatory frameworks -- OCC Bulletin 2011-12, SR 11-7, the CFPB AI circular, and FinCEN BSA/SAR requirements -- with no integrated governance life cycle connecting these requirements to model development, validation, and monitoring practice. This paper presents the Regulatory Governance Framework for AI-Driven Financial Fraud Detection (RGF-AFFD), a three-tier governance architecture empirically anchored in a multi-study empirical program. Using the IEEE-CIS dataset (590,540 transactions) and ULB benchmark (284,807 transactions), we benchmark six architectures including an LSTM+XGBoost ensemble, and conduct ablation, temporal drift, SHAP interpretability, and BISG fairness analyses. The LSTM+XGBoost ensemble achieves ROC-AUC of 0.9289 (F1: 0.6360) with a benefit-cost ratio of 6:1. XGBoost demonstrates the strongest temporal stability (delta-AUC = -0.0017 versus -0.0626 for LSTM). The RDT-FG Regulatory Digital Twin meta-model translates metrics into four regulator-specific health scores and a composite Regulatory Fitness Index for continuous compliance monitoring. The RGF-AFFD is the first integrated deployment blueprint to simultaneously satisfy OCC, SR 11-7, CFPB, and FinCEN requirements, supported by a community bank implementation vignette and four evidence-based policy recommendations.

---

### RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction

Authors: Sihao Liu, YuFan Xiong, Zhonghua Jiang, Zhaode Wang, chengfei lv Shengyu Zhang
Published: 2026-04-14
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.04075v1

Multimodal Large Language Models face severe challenges in computational efficiency and memory consumption due to the substantial expansion of the visual KV cache when processing long visual contexts. Existing KV cache compression methods typically rely on the "persistence of importance" hypothesis to prune tokens. However, this approach proves fragile in multimodal settings due to two key issues: 1) Visual tokens display "deferred importance," initially exhibiting low salience but becoming pivotal during later decoding, which can lead to premature eviction. 2) Discrete pruning disrupts the inherent spatial continuity of visual cues. To address these challenges, we propose RetentiveKV, an entropy-driven KV cache optimization method that reformulates KV eviction from "discrete context truncation" to "continuous memory evolution" based on State Space Models. Our method leverages information entropy to quantify the information potential of low-attention tokens and integrates tokens scheduled for eviction into a continuous state space through entropy-guided state transitions, enabling their dynamic reactivation when semantic relevance arises during subsequent decoding. Extensive experiments on multimodal benchmarks demonstrate that RetentiveKV achieves 5.0 times KV cache compression and 1.5 times decoding acceleration.

---

### A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers

Authors: Mohammad AlShaikh Saleh, Sanjay Chawla, Sertac Bayhan, Haitham Abu-Rub, Ali Ghrayeb
Published: 2026-04-14
Categories: cs.LG, cs.AI, cs.CE, cs.DC, cs.ET, cs.OS
arXiv: https://arxiv.org/abs/2605.04074v1

AI data centers experience rapid fluctuations in power demand due to the heterogeneity of computational tasks that they have to support. For example, the power profile of inference and training of large language models (LLMs) is quite distinct and big divergences can result in the instability of the underlying electricity grid. In this paper we propose, to the best of our knowledge, the first physics-informed DLinear time-series model that can accurately forecast power utilization of an AI data center 5-80 minutes (short-term forecasting) into the future. The physics, based on a multi-node lumped thermal resistance-capacitance (RC) network consistent with Newton's law of cooling, is captured using newly derived time-dependent ordinary differential equations (ODE) that separately models and interlinks power consumption with the GPU compute and memory utilization and temperature. The resulting model, that we refer to as PI-DLinear, trained and evaluated on a real AI data center dataset and is not only more accurate than the state-of-the-art (SOTA) models tested, but the forecast profile respects the underlying physics under power throttling and load transient events. Relative to the SOTA transformer-based and non-transformer-based models, improvements in forecasting accuracy (averaged across all look-back and prediction windows) range from 0.782%-39.08% for MSE, 0.993%-51.82% for MAE, and 0.370%-22.28% for RMSE.

---

### The Impact of AI-Generated Text on the Internet

Authors: Jonas Dolezal, Sawood Alam, Mark Graham, Maty Bohacek
Published: 2026-04-14
Categories: cs.CY, cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2604.26965v1

The proliferation of AI-generated and AI-assisted text on the internet is feared to contribute to a degradation in semantic and stylistic diversity, factual accuracy, and other negative developments (sometimes subsumed under the Dead Internet Theory). What has hindered answering these questions is that it has not been understood just how much of the internet is actually AI-generated or AI-edited. To this end, we construct a representative sample of websites published on the internet between 2022 and 2025 using the Internet Archive, and apply a state-of-the-art AI text detector on them. We find that by mid-2025, roughly 35% of newly published websites were classified as AI-generated or AI-assisted, up from zero before ChatGPT's launch in late 2022. We also find statistically significant evidence for some of the identified hypotheses; for example, that increases in AI-generated text on the internet correlate negatively with semantic diversity and positively with the prevalence of positive sentiment. We do not, however, find statistically significant evidence supporting the hypothesis that an increased rate of AI-generated text on the internet decreases factual accuracy or stylistic diversity. Notably, this diverges from public perception, which we measure in a user study, where the majority of US adults turned out to believe in all four of the above-mentioned hypotheses. Individuals who do not use AI or use it infrequently tend to believe in these negative impacts more than those who use it frequently; similarly, individuals who hold negative views of AI tend to believe in these hypotheses more than those with favorable views of the technology.

---

### Dont Just Teach, Explain! A Gamified 20Q Recommender for Cybersecurity Education

Authors: Mary Nusrat, Sarfuddin Bhuiyan, Gahangir Hossain
Published: 2026-04-14
Categories: cs.CY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.26964v2

The escalating complexity of modern cyber threats demands innovative approaches to security education that transcend traditional pedagogical methods. Conventional training paradigms often fail to engage learners meaningfully or develop the intuitive reasoning necessary for effective threat recognition. This paper introduces an interactive educational framework that reimagines cybersecurity awareness through the lens of a structured guessing game. Our approach integrates explainable artificial intelligence (XAI) principles with reinforcement learning to create a dynamic learning environment where users discover cybersecurity concepts through guided inquiry. The proposed system employs a policy-based reinforcement learning agent that assumes the role of a knowledgeable questioner, systematically narrowing down user-described security scenarios until it can both identify the underlying threat and provide transparent reasoning for its conclusion. By framing security education as an interactive dialogue, we transform passive knowledge acquisition into active discovery. We present the complete system architecture, detail the underlying algorithmic foundations, and demonstrate practical application through comprehensive case studies examining diverse attack vectors including the Cyber Kill Chain, phishing campaigns, ransomware outbreaks, and web application vulnerabilities. This work represents a significant departure from static security training methodologies, offering a personalized and game-based approach to cybersecurity education.

---

### Learning-to-Explain through 20Q Gaming: An Explainable Recommender for Cybersecurity Education

Authors: Mary Nusrat, Sarfuddin Bhuiyan, Gahangir Hossain
Published: 2026-04-14
Categories: cs.CY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.26964v1

The growing sophistication of contemporary cyber threats necessitates a more effective and adaptive approach to cybersecurity training. Intuitive and adaptive approaches to learning, which are often required, are not provided in traditional learning methods. In this article, we present a new educational framework, "Learning to Explain Cybersecurity with Q20 Game", based on explainable AI (XAI), an educational game to enhance interactivity in learning. We propose a novel, game-inspired framework - the Explainable Q20 Cybersecurity Recommender (EQ-20CR), that learns to elicit the minimal set of evidential facts needed to justify cybersecurity defensive action. By casting "Why should I execute this mitigation?" as a 20 questions (Q20) game, a policy-based reinforcement-learning (RL) agent actively queries an environment until it can both (i) recommend the optimal security education and (ii) explain that decision with a concise dialogue trace. The article draws from "Playing 20 Question Game with Policy-Based Reinforcement Learning" (1) and "Learning-to-Explain: Recommendation Reason Determination through Q20 Gaming" (2). The framework uses a policy-based reinforcement learning (RL) agent that leads the user through a sequence of questions to recognize and articulate a targeted cybersecurity concept, attack vector, or defense strategy. Furthermore, users are gradually exposed to informative questions by the system, revealing complicated, structured way at an adaptive difficulty level. In this paper, we design the architecture, its application to various concepts of cybersecurity through illustrative case studies, and its transformative potential on the training and awareness of cybersecurity recommendations.

---

### MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems

Authors: Yifei Wang, Hancheng Ye, Yechen Xu, Cong Guo, Chiyue Wei, Qinsi Wang, Dongting Li, Tingjun Chen, Hai "Helen" Li, Danyang Zhuo, Yiran Chen
Published: 2026-04-14
Categories: cs.OS, cs.DC, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2604.26963v2

Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators. Agentic workloads induce a temporal shift from single-turn inference to multi-turn LLM-tool loops, and a spatial shift from chat-scale, GPU-only execution to repository-scale, GPU-CPU co-located execution. Consequently, coordinating heterogeneous resource demands of agentic execution has emerged as a critical system challenge. We design and implement MARS, an efficient and adaptive co-scheduling system that globally coordinates heterogeneous agentic workloads under coupled GPU-CPU resource pressure. By establishing holistic visibility across GPU inference and CPU tool execution via a unified information stream, an external control plane in MARS decouples admission from execution to prevent heterogeneous resource oversubscription. An internal agent-centric scheduler further minimizes the end-to-end critical path by prioritizing latency-sensitive continuations and adaptively retaining KV cache state only when warm resumption yields a latency benefit. Our evaluations show that MARS reduces end-to-end latency by up to 5.94x while maintaining nearly maximal system throughput. We further integrate MARS as the serving backend for the OpenHands coding agent framework, demonstrating its real-world effectiveness by accelerating end-to-end task completion time by up to 1.87x. Our source code is publicly available at https://github.com/Afterglow231/MARS_preview .

---

### Representation Homogeneity and Systemic Instability in AI-Dominated Financial Markets: A Structural Approach

Authors: Yimeng Qiu, Qiwei Han
Published: 2026-04-14
Categories: q-fin.TR, cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2604.22818v1

This paper investigates how similarity in the informational representation of market states among Artificial Intelligence (AI) trading agents can generate systemic instability in financial markets. We construct a structural multi-agent market model calibrated using high-frequency microstructural moments. AI agents are modeled through a two-layer decision architecture consisting of a nonlinear representation layer and an adaptive linear readout layer. The representation layer maps raw market states into high-dimensional feature vectors, while the readout layer generates return forecasts that feed into a risk-controlled trading rule. This representation-based microfoundation separates two objects that are often conflated in the literature: representation homogeneity (the degree to which agents encode market states into similar feature spaces) and forecast overlap (the degree to which agents produce similar return predictions). We show theoretically that these two concepts are related but not equivalent, and that representation homogeneity can compress the effective space of forecast disagreement under stress even when predictions appear diverse in normal times. Through controlled factorial experiments that vary representation homogeneity while conditioning on alternative risk-aversion and learning-rate distributions, we hypothesize that increasing representation similarity amplifies synchronization in beliefs and positions, leading to volatility clustering, liquidity stress, and elevated tail risk. Our structural mechanisms suggest that low perceived volatility regimes can endogenously accumulate hidden leverage through position stickiness, which subsequently collapses when shocks trigger synchronized deleveraging. The results provide a structural foundation for macroprudential policies aimed at monitoring and preserving diversity in how AI systems represent and process market information.

---

### In-Sync: Adaptation of Speech Aware Large Language Models for ASR with Word Level Timestamp Predictions

Authors: Xulin Fan, Vishal Sunder, Samuel Thomas, Mark Hasegawa-Johnson, Brian Kingsbury, George Saon
Published: 2026-04-14
Categories: eess.AS, cs.CL, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2604.22817v1

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is critical for applications such as captioning, media search, and multimodal synchronization, yet it is often handled by external alignment tools. In this work, we extend an existing speech-aware language model to predict timestamps directly alongside transcripts. We introduce a set of novel lightweight training strategies that improve alignment robustness while preserving recognition quality. Experiments across multiple datasets show that these strategies not only enhance timestamp accuracy, but also yield gains in overall ASR performance. Together, they demonstrate an efficient and unified approach to speech recognition with precise timestamp prediction.

---

### Applied AI-Enhanced RF Interference Rejection

Authors: Rahul Jain, Pierre Trepagnier, Rick Gentile, Joey Botero, Alexia Schulz
Published: 2026-04-14
Categories: eess.SP, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.22816v1

AI-enhanced interference rejection in radio frequency (RF) transmissions has recently attracted interest because deep learning approaches trained on both the signal of interest (SOI) and the signal mixture (SOI plus interference) can outperform traditional approaches which only consider the SOI. The goal is to detect, demodulate, and decode signals over a range of signal-to-interference-plus-noise (SINR) levels without having a detailed, design-level knowledge of the interfering signal or the propagation conditions. Our present AI interference suppression results are based on Autoregressive Transformer Decoder models which exhibit orders of magnitude faster throughput at inference time than WaveNet models developed in earlier work. As a specific example, we investigate an analog FM "Walkie Talkie" radio signal of interest in the presence of an Orthogonal Frequency-Division Multiplexing (OFDM) interferer. This type of interferer is near-ubiquitous in the current RF landscape. Our results clearly show the benefits of transformer-based interference mitigation in tactical settings. We show that unintelligible transmissions become intelligible via metrics such as Perceptual Evaluation of Speech Quality (PESQ), while overall latency is kept to a minimum using readily available lightweight GPUs such as a Jetson AGX Orin. We believe these same techniques can also be applied to a broader set of national security scenarios, as well as having commercial applications.

---

### Cross-Course Generalizability of SRL-Aligned Predictive Models Using Digital Learning Traces

Authors: Jakob Schwerter, Loreen Sabel, Judith Bose, Matthew L. Bernacki, Di Xu, Marko Schmellenkamp, Thomas Zeume, Philipp Doebler
Published: 2026-04-14
Categories: cs.CY, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2604.22812v1

STEM dropout rates remain high at universities, particularly in computer science programs with theory-intensive courses. Digital learning environments now capture rich behavioral data that could help identify struggling students early, yet the generalizability of data-driven prediction models across courses and institutions remains uncertain. Guided by self-regulated learning (SRL) theory, this study analyzed multimodal digital-trace data from three undergraduate theoretical computer science courses (N1 = 137, N2 = 104, N3 = 148) at two universities. Weekly SRL-aligned digital-trace indicators were modeled using Elastic Net, Random Forest, and XGBoost to evaluate predictive performance over time and across settings, and model calibration both within and across courses. Early prediction of at-risk students was feasible, with SRL-related behaviors such as time management, effort regulation, and sustained engagement emerging as key predictors. While Random Forest achieved the highest in-sample accuracy, Elastic Net generalized more robustly across contexts. Out-of-sample accuracy and calibration declined between institutions with different base rates, underscoring the contextual nature of predictive analytics in higher education. These findings suggest that digital learning traces enable early identification of at-risk students within courses, but generalizing predictive models beyond their original context requires caution, particularly if the at-risk rates differ between contexts.

---

### FreqFormer: Hierarchical Frequency-Domain Attention with Adaptive Spectral Routing for Long-Sequence Video Diffusion Transformers

Authors: Haopeng Jin
Published: 2026-04-14
Categories: cs.CV, cs.AI, eess.IV
arXiv: https://arxiv.org/abs/2604.22808v1

Long-sequence video diffusion transformers hit a quadratic self-attention cost that dominates runtime and memory for very long token sequences. Most efficient attention methods use one approximation everywhere, yet video features are spectrally structured: low frequencies carry global layout and coarse motion; high frequencies carry texture and fine detail. We present FreqFormer, a frequency-aware heterogeneous attention framework. Token features are split into spectral bands with different operators: dense global attention on compressed low-frequency content, structured block-sparse attention on mid frequencies, and sliding-window local attention on high frequencies. A lightweight spectral routing network allocates heads across bands using layer statistics and the diffusion timestep, shifting compute toward global structure early in denoising and detail later. Cross-band summary tokens provide cheap residual exchange. FreqFormer is paired with a fused GPU execution plan that co-schedules dense, sparse, and local branches to cut kernel launches and memory traffic. We give a consistent complexity model, an orthonormal-decomposition view of approximation, and simulation-based systems numbers (throughput, arithmetic intensity, memory traffic, duration scaling). In simulations from 64K to 1M tokens, FreqFormer substantially reduces estimated attention FLOPs and KV-related memory traffic versus dense attention while keeping a hardware-friendly pattern, supporting spectrally structured heterogeneous attention as a practical direction for long-video diffusion transformers.

---

### Sliced Wasserstein Steering between Gaussian Measures

Authors: Kaito Ito, Anqi Dong
Published: 2026-04-14
Categories: math.OC, cs.LG, eess.SY, stat.ML
arXiv: https://arxiv.org/abs/2604.22807v1

Optimal transport with quadratic cost provides a geometric framework for steering an ensemble, modeled by a probability law, with minimal effort. Yet ambient-space formulations become unwieldy in high dimensions, and sensing or actuation in practice often reveals only linear views of the state -- camera silhouettes, LiDAR beams, tomographic slices. We develop a sliced feedback controller for distribution steering: the evolving law is projected onto one-dimensional directions on the sphere, the optimal one-dimensional velocity is synthesized in each projection, and these velocities are averaged to produce a feedback control in the ambient space. The construction reduces to the Benamou--Brenier problem in one dimension. In addition, it is invariant under orthogonal transforms, nonexpansive under projections, and well posed on $\mathcal{P}_2(\mathbb{R}^n)$. Computation proceeds by sampling directions on the sphere and solving independent one-dimensional subproblems, yielding a scalable method aligned with partial observations. In the Gaussian setting, we show that the developed sliced controller steers the law to the prescribed target. Furthermore, we derive an identity relating the energy consumption incurred by the controller to the sliced Wasserstein distance.

---

### See No Evil: Semantic Context-Aware Privacy Risk Detection for AR

Authors: Jialu Liu, Yao Li, Zhuoheng Li, Huining Li, Ying Chen
Published: 2026-04-14
Categories: cs.CV, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2604.22805v1

Augmented reality (AR) systems pose unique privacy risks due to their continuous capture of visual data. Existing AR privacy frameworks lack semantic understanding of visual content, limiting their effectiveness in detecting context-dependent privacy risks. We propose PrivAR, which leverages vision language models (VLMs) with chain-of-thought prompting for contextual privacy risk detection in AR environments. PrivAR uses visual scene cues to infer potential sensitive information types, such as identifying password notes in office environments through contextual reasoning. PrivAR detects and obfuscates textual content, preventing exposure of sensitive information while preserving contextual cues necessary for VLM inference. Additionally, we investigate contextually-informed warning interfaces to enhance user privacy awareness. Experiments on a real-world AR dataset show that PrivAR achieves superior accuracy (81.48%) and F1-score (84.62%) compared to baselines, while reducing privacy leakage rate to 17.58%. User studies evaluating contextually-informed warning interfaces provide insights into effective privacy-aware AR design.

---

### Skyline-First Traversal as a Control Mechanism for Multi-Criteria Graph Search

Authors: Nicolas Tacheny
Published: 2026-04-14
Categories: cs.AI, cs.DS
arXiv: https://arxiv.org/abs/2604.19807v1

In multi-criteria graph traversal, paths are compared via Pareto dominance, an ordering that identifies which paths are non-dominated, but says nothing about which path to expand next or when the search may stop. As a result, existing approaches rely on external mechanisms-heuristics, scalarization, or population-based exploration while Pareto dominance remains confined to passive roles such as pruning or ranking. This paper shows that, under constrained cost models, finite cost grids, Markovian transitions, and a nonzero progress measure, Pareto geometry alone is sufficient to drive both scheduling and termination. We show that extracting exclusively from the first Pareto layer, the skyline, induces a deterministic descent in a discrete completion potential, ensuring monotone progress toward solution completion. In parallel, a vector lower-bound certificate provides a stopping condition that guarantees dominance coverage of all remaining traversals without requiring a predefined number of solutions. Our analysis establishes deterministic potential descent, certified termination via dominance coverage, a uniform bound on layer width induced by cost-grid geometry, and greedy cost-space dispersion within the skyline. The resulting framework operates without scalarization, heuristic guidance, or probabilistic models, and repositions Pareto dominance from a passive filter to a deterministic driver of search.

---