# Research Papers — 2026-06 · bundle page 30 of 260 > Full-text markdown of papers #1451–1500 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/30 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/29.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/31.md) ### BERTomelo: Your Portuguese Encoder Best Friend Authors: Rennê Ruan Alves Oliveira, Gustavo Cordeiro Galvão Van Erven, Luís Paulo Faina Garcia Published: 2026-06-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.28999v1 Encoders have become the state of the art for multiple NLP tasks, especially those requiring deep contextual understanding. While multilingual models offer broad coverage, dedicated monolingual encoders are essential for capturing the unique lexical and syntactic nuances of specific languages. For Portuguese, however, existing monolingual options like BERTimbau and Albertina have not kept pace with recent architectural breakthroughs, often lagging behind English benchmarks in scalability and efficiency. This work introduces BERTomelo, a next-generation monolingual encoder pre-trained from scratch and specifically optimized for the Portuguese language. By leveraging the ModernBERT architecture, BERTomelo overcomes the limitations of previous models, offering Base and Large versions with a 1,024-token context window and hardware-level optimizations like FlashAttention and alternating attention mechanisms. The model was trained on ClassiCC-PT, a massive, high-quality Portuguese corpus of 106 million documents, ensuring superior alignment with the language's contemporary usage. The results demonstrate that BERTomelo not only outperforms previous Portuguese encoders but also provides a more robust and efficient alternative to massive multilingual models in downstream tasks such as STS and NER. --- ### Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation Authors: Sanjeepan Sivapiran, Gias Uddin Published: 2026-06-27 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2606.28998v2 Large Language Model (LLM) alignment trains an LLM using preference data to produce outputs that better meet established quality standards. While LLM alignment techniques are studied for non-coding tasks, we know little about their usefulness for coding tasks. It is unclear whether LLM code alignment could support both functional requirements (producing executable, correct code) and non-functional requirements (code readability, style, maintainability). It is also unknown whether alignment for a code LLM should begin with base pretrained version or the finetuned (i.e., instruction-tuned) version of the LLM. In this paper, we offer insights on the above two research questions by conducting an empirical study. We studied five state-of-the-art (SOTA) LLMs using two widely used LLM alignment techniques: Direct Preference Optimization (DPO) and BoNBoN. For each training record, we created a preference pair as accepted and rejected instances by using the SelfCodeAlign pipeline. DPO and BoNBoN are reward-free models, i.e., they eliminate the need for multiple reward scores for output preferences. We tuned each LLM using the two alignment techniques in two settings: pretrained and finetuned versions of an LLM. We evaluated functional requirements using four SOTA benchmarks (HumanEval+, MBPP+, EvalPerf, EvoEval) and non-functional requirements using the CODAL benchmark, which evaluates code quality across five dimensions derived from software engineering practices. We find that pretrained-to-aligned pathways achieve larger improvements in the aligned variant over its pretrained variant. But the pretrained variant is generally less accurate than its finetuned variant. However, finetuned- to-aligned offers smaller performance improvements or, in some cases, degradation in the aligned variant than its finetuned variant. --- ### On Surrogate Modeling of Static Response of AM Short-Fiber Thermoplastics Using Graph Neural Networks Authors: Pharindra Pathak, Vipin Kumar, Trenton M. Ricks, Suhasini Gururaja, Siddhartha Srivastava Published: 2026-06-27 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2606.28996v1 Short-fiber thermoplastic (SFT) composites are increasingly employed in lightweight aerospace and automotive structures owing to their favorable strength-to-weight ratio, high production rates, and recyclability. Unlike continuous-fiber systems, the mechanical response of SFTs is governed by mesoscale interactions among fiber orientation, spatial clustering, and manufacturing-induced porosity. These features exhibit significant spatial variability in manufactured components and influence stiffness, damage initiation, and nonlinear deformation. Although mesoscale finite element (FE) models can resolve such heterogeneity, their application to realistic three-dimensional microstructures remains computationally intractable. A data-driven surrogate framework is proposed to predict the mechanical behavior of additively manufactured, compression-molded (AM-CM) SFTs. Microstructures reconstructed from micro-computed tomography data were discretized into Voronoi-based cells representing distinct fiber-interaction neighborhoods. Each cell was homogenized via nonlinear FE simulations incorporating matrix damage, and the resulting stress-strain responses trained a hybrid Graph Neural Network-Long Short-Term Memory (GNN-LSTM) architecture encoding microstructural topology and history-dependent mechanical evolution. The surrogate accurately predicts stiffness and stress-strain behavior of unseen microstructures, achieving $R^2\approx 0.98$ relative to high-fidelity FE simulations with over two orders-of-magnitude reduction in computational cost. Coupling the framework with experimentally calibrated damage laws demonstrates that fiber orientation, clustering, and porosity collectively govern local effective stiffness. The approach provides a physics-informed, data-efficient pathway to identify mechanically weak microstructural cells and accelerate digital-twin development for SFT components. --- ### Arbitrary Reduction of Validation Error for AI Decision Tests using Homomorphic AI and Repetition Codes Authors: Eric Filiol, Jaagup Sepp Published: 2026-06-27 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2606.28994v1 This paper presents new results and breakthrough obtained with the HbHAI techniques (Hash-based Homomorphic Artificial Intelligence) proposed in \cite{filiol0,sepp}. HbHAI is based on a novel class of key-dependent hash functions that naturally preserve most similarity properties, most AI algorithms rely on. It enables to analyse and process data in its cryptographically secure form while using existing native AI algorithms without modification, with unprecedented performances compared to existing homomorphic encryption schemes and most notably compared to the same processing on corresponding plaintext data. Two major results have been obtained further. First we enable to reduce the compression rate up to a factor of 10 thus allowing to process massive datasets while reducing the computation time and the energy footprint in the same order. Second, we show how it is possible to arbitrarily reduce the final validation error of AI-based decision tests by using repetition error-correcting codes. --- ### Fine-Tuning General-Purpose Large Language Models for Agricultural Applications:A Reproducible Framework and Evaluation Protocol Based on Qwen3-8B Authors: Zhaoyang Li, Ruijie Zhang, Jiaqi Liu, Zhaoji Sun Published: 2026-06-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.28992v1 General-purpose large language models (LLMs) have demonstrated strong abilities in opendomain question answering, information extraction, and text generation. Agricultural applications, however, are domain-specific, region-dependent, time-sensitive, and safety-critical. Without data governance, expert evaluation, and evidence constraints, an agricultural assistant mayproduce unreliable advice on crop diseases, pesticide use, fertilization, or policy interpretation.To avoid presenting unverified simulated numbers as real experimental findings, this paper doesnot report any model-performance claims that have not been produced by an actual training runand expert evaluation. Instead, we propose AgriTune-R, a reproducible and auditable frameworkfor adapting general-purpose LLMs to agricultural tasks. The framework selects the publiclyverifiable Qwen3-8B model as the recommended base model and integrates agricultural datagovernance, instruction construction, LoRA/QLoRA parameter-efficient fine-tuning, retrievalaugmented generation, expert evaluation, and safety control for high-risk questions. The contributions are: (1) a structured workflow for agricultural LLM adaptation; (2) an evaluationprotocol for agricultural knowledge QA, pest and disease consultation, cultivation management,and policy explanation; (3) an expert-review rubric combining factuality, safety, evidence consistency, and uncertainty expression; and (4) a clear separation between protocol design andempirical conclusions, providing an executable baseline for future empirical studies. --- ### Learning from Acquisition: Metadata-driven Multimodal Pre-training for Cardiac MRI Authors: Xueyi Fu, Liwei Hu, Zi Wang, Guang Yang Published: 2026-06-27 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2606.28991v1 Cardiac magnetic resonance imaging (CMR) routinely records structured acquisition metadata, yet most CMR foundation models rely primarily on image-only pre-training and leave this naturally available source of weak semantic supervision largely underexplored. We propose MetaCLIP-CMR, a metadata-driven framework based on Contrastive Language--Image Pre-training (CLIP), which converts imaging modality, anatomical view, scanner vendor, field strength, and scanner model into textual supervision for CMR representation learning. The pretrained image encoder is evaluated on imaging modality classification, cine view classification, and cardiac segmentation. MetaCLIP-CMR achieves 86.8% modality accuracy and 86.5% cine view accuracy, clearly outperforming ImageNet and masked reconstruction initialisations. For downstream cardiac segmentation, MetaCLIP-CMR consistently obtains the highest Dice score across the evaluated ACDC and M&Ms cine short-axis (SAX) settings under both full-data and 20% fine-tuning regimes. Compared with recent image-focused large-scale CMR pre-training models, MetaCLIP-CMR achieves comparable ACDC segmentation performance, while requiring less than 1% of their pre-training image scale. These results suggest that metadata learning offers a natural and easy-to-use strategy for transforming routinely recorded acquisition information into effective supervision for foundation-level CMR representation learning, highlighting the promise of metadata-driven multimodal pre-training. --- ### Compositional Dynamics in Learning and Mechanics Authors: David I. Spivak Published: 2026-06-27 Categories: math.CT, cs.AI arXiv: https://arxiv.org/abs/2606.28984v2 We give a single compositional setting in which gradient-based learning and Hamiltonian-style mechanics appear as functorial semantics. The syntax is an operad Arr whose objects are input-output interfaces (pairs of manifolds) and whose morphisms are *smooth adaptive arrangements*, which consist of a responsive parameter space, a lens given by smooth output and input maps, and a real-valued potential. The main technical result of the paper is what we call *lens internalization*, a lax symmetric monoidal functor Lens(C) $\to$ C associated to any symmetric monoidal closed category C. Using it, we provide two functors $Φ_\text{phase}$, $Φ_\text{conf}$: Arr $\to$ PC into the 2-category of polynomial coalgebras -- input-output discrete dynamical systems -- which we take as the semantics category. $Φ_\text{phase}$ stores both position and momentum, whereas $Φ_\text{conf}$ stores only position. When applied to a parameterized function, $Φ_\text{conf}$ recovers the gradient descent training algorithm, with backpropagation as the lens' backward pass. When applied to harmonic particles wired together -- in series, or according to any finite directed graph -- one diagram yields two different regimes, both of which are governed by the graph Laplacian: $Φ_\text{phase}$ gives the discrete wave equation, which is conservative and second-order, and $Φ_\text{conf}$ gives the discrete heat equation, which is dissipative and first-order. They are two semantics of one adaptive arrangement, e.g. with the same potential in each case. And because Arr is an operad, such diagrams nest -- larger systems wired from smaller ones -- and each semantics assembles a system's dynamics functorially from its parts. These dynamics are moreover executable: a parameterized neural network and a graph of particles both compile, by the same construction, to explicit state machines one can run. --- ### Compositional Dynamics in Learning and Mechanics Authors: David I. Spivak Published: 2026-06-27 Categories: math.CT, cs.AI arXiv: https://arxiv.org/abs/2606.28984v1 We give a single compositional setting in which gradient-based learning and Hamiltonian-style mechanics appear as functorial semantics. The syntax is an operad Arr whose objects are input-output interfaces (pairs of manifolds) and whose morphisms are *smooth adaptive arrangements*, which consist of a reactive parameter space, a lens given by smooth output and input maps, and a real-valued potential. The main technical result of the paper is what we call *lens internalization*, a lax symmetric monoidal functor Lens(C) $\to$ C associated to any symmetric monoidal closed category C. Using it, we provide two functors $Φ_\text{phase}$, $Φ_\text{conf}$: Arr $\to$ PC into the 2-category of polynomial coalgebras -- input-output discrete dynamical systems -- which we take as the semantics category. $Φ_\text{phase}$ stores both position and momentum, whereas $Φ_\text{conf}$ stores only position. When applied to a parameterized function, $Φ_\text{conf}$ recovers the gradient descent training algorithm, with backpropagation as the lens' backward pass. When applied to harmonic particles wired together -- in series, or according to any finite directed graph -- one diagram yields two different regimes, both of which are governed by the graph Laplacian: $Φ_\text{phase}$ gives the discrete wave equation, which is conservative and second-order, and $Φ_\text{conf}$ gives the discrete heat equation, which is dissipative and first-order. They are two semantics of one adaptive arrangement, e.g. with the same potential in each case. And because Arr is an operad, such diagrams nest -- larger systems wired from smaller ones -- and each semantics assembles a system's dynamics functorially from its parts. These dynamics are moreover executable: a parameterized neural network and a graph of particles both compile, by the same construction, to explicit state machines one can run. --- ### Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer Authors: Francesca Pia Panaccione, Eugenio Lomurno, Francesca Fati, Carlotta Pecchiari, Marina Rosanu, Luigi De Vitis, Lucia Ribero, Gabriella Schivardi, Giovanni Damiano Aletti, Nicoletta Colombo, Maria Francesca Spadea, Francesco Multinu et al. Published: 2026-06-27 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.28980v1 Ovarian cancer is frequently diagnosed at an advanced stage, making preoperative contrast-enhanced computed tomography (CT) central to staging and surgical planning; yet the scarcity of annotated imaging data, compounded by privacy regulations, limits the development of generalizable computational models in this domain. Text-conditioned 3D CT synthesis has shown promise, but existing pipelines depend on paired radiology reports and have been evaluated only on chest CT. We propose OvESyn (Ovarian Evidence-based Synthesis), a framework that constructs standardized Findings and Impression sections directly from CT-derived imaging descriptors and routine clinical metadata, without any original radiology report, and uses them to condition a latent diffusion model adapted to 493 high-grade serous ovarian carcinoma patients. This is the first text-conditioned 3D CT synthesis framework adapted to an abdomino-pelvic oncologic setting. A systematic ablation over two adaptation axes, vision-language encoder alignment and generator fine-tuning, identifies generator domain adaptation as the operative mechanism for crossing the domain gap and establishing the target anatomy: without it, synthesis remains anchored to the thoracic pretraining domain, with Precision and Recall collapsing to zero and FID2.5D exceeding 140, regardless of encoder alignment. Encoder alignment instead refines intensity and fine detail. The full OvESyn attains the best distributional and intensity fidelity (FID2.5D 29.35, Precision 0.671, Wasserstein-1 0.044), while the generator-only variant maximizes coverage (Recall 0.645), reflecting a fidelity/coverage trade-off governed by encoder adaptation. Requiring only automatic segmentations and routine preoperative metadata, OvESyn supports transferability to report-scarce settings and provides a foundation for synthetic cohort generation in abdomino-pelvic oncologic imaging. --- ### Can LLMs Hire Fairly? Racial Bias in Resume Screening Authors: Zhenyu Gao, Wenxi Jiang, Yutong Yan Published: 2026-06-27 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2606.28978v1 We audit fourteen mainstream large language models (LLMs) for hiring discrimination using the paired-resume methodology of Kline, Rose, and Walters (2022). The sole 2023-vintage model reproduces the pro-White callback gap documented in field experiments on labor market discrimination ($+2.12$ pp, significant at the 1\% level). Every model released in 2024 or after shows either a null gap or a significant pro-Black reversal (up to $-3.01$ pp). The same pattern holds on the gender axis. Based on 24,024 paired postings per model across 14 models, our results document a reversal in the direction of algorithmic hiring bias across model generations. --- ### Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution Authors: Shuang Cui, Fan Ji, Guanglong Sun, Yufei Guo, Xiongxin Tang, Jiangmeng Li, Fanjiang Xu Published: 2026-06-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28971v2 Real-world image restoration (IR) remains challenging due to complex and coupled degradations. While recent agentic IR frameworks leverage Large Language Models for flexible tool planning, they face two critical limitations. First, from a search scheme perspective, excessive reliance on greedy strategies fails to balance exploration and exploitation. Second, existing agentic systems underutilize information, exhibiting episodic amnesia. To address these challenges, we propose \textbf{Self-Evolving Agentic Image Restoration (SEAR)}, which formulates restoration as a sequential decision-making problem. Inspired by the dual-process theory, SEAR comprises an Intuitive Executor and a Deliberate Planner, respectively following the fast-thinking \textit{System 1} and slow-thinking \textit{System 2} principles. The Deliberate Planner employs Pruning-Aware Monte Carlo Tree Search for long-horizon reasoning, utilizing a hybrid no-reference reward and a Multimodal Large Language Model (MLLM)-based tournament to prevent metric exploitation. Complementarily, the Intuitive Executor leverages a self-evolving episodic memory indexed by degradation-aware state fingerprints. This mechanism distills expensive search trajectories into adaptive expertise, overcoming episodic amnesia while progressively amortizing cold-start exploration costs through memory reuse. Extensive experiments on synthetic and real-world benchmarks demonstrate its strong perceptual and quantitative performance. --- ### Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution Authors: Shuang Cui, Fan Ji, Guanglong Sun, Yufei Guo, Xiongxin Tang, Jiangmeng Li, Fanjiang Xu Published: 2026-06-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28971v1 Real-world image restoration (IR) remains challenging due to complex and coupled degradations. While recent agentic IR frameworks leverage Large Language Models for flexible tool planning, they face two critical limitations. First, from a search scheme perspective, excessive reliance on greedy strategies fails to balance exploration and exploitation. Second, existing agentic systems underutilize information, exhibiting episodic amnesia. To address these challenges, we propose \textbf{Self-Evolving Agentic Image Restoration (SEAR)}, which formulates restoration as a sequential decision-making problem. Inspired by the dual-process theory, SEAR comprises an Intuitive Executor and a Deliberate Planner, respectively following the fast-thinking \textit{System 1} and slow-thinking \textit{System 2} principles. The Deliberate Planner employs Pruning-Aware Monte Carlo Tree Search for long-horizon reasoning, utilizing a hybrid no-reference reward and a Multimodal Large Language Model (MLLM)-based tournament to prevent metric exploitation. Complementarily, the Intuitive Executor leverages a self-evolving episodic memory indexed by degradation-aware state fingerprints. This mechanism distills expensive search trajectories into adaptive expertise, overcoming episodic amnesia while progressively amortizing cold-start exploration costs through memory reuse. Extensive experiments on synthetic and real-world benchmarks demonstrate its strong perceptual and quantitative performance. --- ### RGLD: Randomized Global-Local Density Estimation for Tabular Anomaly Detection Authors: Quanling Zhao, Jiaying Yang, Ye Tian, Josh Victoria, Zhijun Wang, Pietro Mercati, Onat Gungor, Tajana Rosing Published: 2026-06-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.28970v1 Unsupervised tabular anomaly detection requires methods that are accurate, robust across heterogeneous datasets, and computationally efficient. Classical statistical detectors are often efficient, but they usually rely on a fixed data view and a single notion of abnormality. Deep anomaly detectors can learn more flexible scoring functions, but they are substantially slower and difficult to tune in unsupervised settings due to the lack of a reliable supervisory signal. We propose RGLD, a randomized global-local density estimator for efficient unsupervised tabular anomaly detection. RGLD combines a global random-feature density branch, which identifies samples in broadly low-density regions, with a local neighbor branch, which detects samples that are weakly supported by nearby observations. Both branches operate over feature-bagged randomized views, allowing RGLD to expose anomaly evidence that may be hidden in any single representation. We conduct experiments on 47 tabular datasets against 23 statistical and deep anomaly detection baselines under fully unsupervised setting. RGLD achieves the strongest dataset-level AUROC performance, ranking 1st in dataset wins, and ranks 2nd in AUPRC wins. RGLD is also faster than all evaluated deep detectors, achieving 50x-580x speedups, and remains competitive with statistical methods in runtime, yielding a favorable accuracy-efficiency tradeoff. --- ### Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data Authors: Eun Cheol Choi, Youngrae Kim, Prabhu Pugalenthi, Hong-En Chen, Bo-Ruei Huang Published: 2026-06-27 Categories: cs.CL, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2606.28963v1 Large language models (LLMs) are increasingly used to simulate social survey responses, yet their outputs exhibit systematic biases: marginal distributions are skewed, response variance is poorly calibrated, and predictor-outcome relationships are attenuated. We ask a simple question: given a small pilot sample of human responses, can an LLM recover the statistical characteristics of a broader population? We decompose recovery along three axes: structural fidelity, marginal fidelity, and individual fidelity. Using a COVID-19 misinformation survey as a case study, we benchmark three families of approaches: prompting, rectification, and fine-tuning. The findings suggest that fine-tuning on small pilot samples offers a balanced approach for achieving multiple forms of fidelity, but the levels of such fidelity can vary across subsamples, potentially threatening pluralistic alignment. --- ### FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks Authors: Aoying Zheng, Anqi Du, Zizhuang Deng, Yuxuan Chen Published: 2026-06-27 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2606.28962v1 Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attacks. In these attacks, malicious behaviors remain dormant in full-precision models and activate only after specific quantization distortions, bypassing standard security audits. To mitigate this, we introduce FlipGuard, a proactive defense framework that selectively perturbs model weights prior to quantization. By breaking the adversary's precise alignment between weight patterns and quantization boundaries, FlipGuard suppresses backdoor activation without requiring access to training data or trigger samples. We further propose the Defense Effectiveness Ratio (DER), a unified metric to jointly evaluate security gains, utility preservation, and computational cost. Extensive experiments across seven LLMs (including StarCoder and LLaMA-family models) and three quantization schemes (INT8, FP4, NF4) demonstrate that FlipGuard effectively neutralizes QCBs across three scenarios, i.e., vulnerable code generation, content injection, and over-refusal, achieving high security with negligible performance degradation. --- ### Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries Authors: Jean Feng, Vishal Patel, Patrick Heagerty, Yifan Mai, Venkatesh Sivaraman, Patrick Vossler, Jialin Ouyang, Anupam B. Jena Published: 2026-06-27 Categories: cs.AI, q-bio.QM, stat.AP arXiv: https://arxiv.org/abs/2606.28960v1 Physicians now pose millions of clinical questions to AI tools each week, yet these tools are evaluated largely on hypothetical or exam-style questions, not those actually asked in practice. We report a blinded evaluation built on 620 Real-world Point-Of-Care Queries (Real-POCQi) submitted to the OpenEvidence (OE) platform by physicians spanning 30 specialties, as well as 187 questions from HealthBench. 149 practicing physicians across 36 states made head-to-head comparisons between answers from three frontier general-purpose models (Claude Opus 4.8, Gemini 3.1 Pro, and GPT-5.5) and a specialized clinical tool (OE), with graders matched to each question's specialty. When comparing answers along five dimensions relevant to clinical decision support -- accuracy, clinical utility, source quality, verifiability, & completeness -- physicians scored the specialized tool highest on all axes; in the primary analysis on Real-POCQi, win differences (margins between win and loss rates) ranged from 25 to 39 percentage points (p<0.001). Results remained consistent in sensitivity analyses stratifying by citation display, answer length, OE-user status, and Real-POCQi versus HealthBench. In parallel, LLM judges were found to systematically differ from expert judges, though both generally agreed on the best model. These findings underscore two conclusions: (i) AI tool evaluations should reflect real-world query distributions and use expert judges that mirror the specialization defining modern medicine and (ii) the consistent advantage of the specialized tool over general-purpose models does not necessarily mean that the latter cannot serve similar purposes, but that targeted engineering and customization can yield meaningful gains in performance for its users. We release Real-POCQi as a public benchmark, as well as the prespecified statistical analysis for reproducing results of this study. --- ### Modification-Considering Value Learning for Reward Hacking Mitigation in RL Authors: Evgenii Opryshko, Umangi Jain, Igor Gilitschenski Published: 2026-06-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.28955v1 Reinforcement learning agents can exploit misspecified reward signals to achieve high apparent returns while failing on the intended objective, a failure mode known as reward hacking. Existing practical defenses typically constrain policy updates to stay near a known safe reference, creating a tension between suppressing hacking and permitting legitimate improvement. We propose Modification-Considering Value Learning (MCVL), which operationalizes the theoretical idea of current utility optimization for standard value-based RL. MCVL wraps an off-policy learner and treats each incoming transition as a candidate modification: it forecasts two training paths, one that includes the transition and one that does not, and scores both with a frozen bootstrapped-return estimator derived from a learned reward model and value function. The transition is admitted only if inclusion does not decrease the score. We formalize conditions under which this filtering is both safe and permissive, and instantiate MCVL with DDQN and TD3. Across four safety-relevant gridworlds and three modified MuJoCo continuous-control tasks with diverse hacking mechanisms, MCVL mitigates reward hacking while continuing to improve the intended objective. Project website: ktolnos.github.io/mcvl/. --- ### Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System Authors: Thomas Thebaud, Sonal Joshi, Henry Li, Martin Sustek, Jesus Villalba, Sanjeev Khudanpur, Najim Dehak Published: 2026-06-27 Categories: cs.SD, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.28953v1 Poisoning attacks entail attackers intentionally tampering with training data. In this paper, we consider a dirty-label poisoning attack scenario on a speech commands classification system. The threat model assumes that certain utterances from one of the classes (source class) are poisoned by superimposing a trigger on it, and its label is changed to another class selected by the attacker (target class). We propose a filtering defense against such an attack. First, we use DIstillation with NO labels (DINO) to learn unsupervised representations for all the training examples. Next, we use K-means and LDA to cluster these representations. Finally, we keep the utterances with the most repeated label in their cluster for training and discard the rest. For a 10% poisoned source class, we demonstrate a drop in attack success rate from 99.75% to 0.25%. We test our defense against a variety of threat models, including different target and source classes, as well as trigger variations. --- ### Machine-learnable Sets Authors: Veit Elser, Manish Krishan Lal Published: 2026-06-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.28947v2 In this study we present a formal definition of large discrete sets having, informally, three properties: their elements are easily recognized, easily generated, and the latter tasks are easily learned from examples. The formalism is specialized to sets of binary strings and a definition of "machine-learnability" based on the existence of a bounded-complexity Boolean autoencoder that fixes the elements of the set. We present experiments where the autoencoders are implemented by nets of Boolean threshold functions. Machine-learnability is demonstrated for Rorschach patterns (that may have reversed contrast in the mirrored half), and considerably "wilder" sets whose elements are only approximately fixed by admissible autoencoders. In the second case we demonstrate a simple iteration that evolves wild sets to make them properly machine-learnable. --- ### Machine-learnable Sets Authors: Veit Elser, Manish Krishan Lal Published: 2026-06-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.28947v1 In this study we present a formal definition of large discrete sets having, informally, three properties: their elements are easily recognized, easily generated, and the latter tasks are easily learned from examples. The formalism is specialized to sets of binary strings and a definition of "machine-learnability" based on the existence of a bounded-complexity Boolean autoencoder that fixes the elements of the set. We present experiments where the autoencoders are implemented by nets of Boolean threshold functions. Machine-learnability is demonstrated for Rorschach patterns (that may have reversed contrast in the mirrored half), and considerably "wilder" sets whose elements are only approximately fixed by admissible autoencoders. In the second case we demonstrate a simple iteration that evolves wild sets to make them properly machine-learnable. --- ### Character Recognition of Nepali Number Plate Authors: Satyasa Khadka, Sandhya Baral, Sudip Tiwari, Sharad Kumar Ghimire Published: 2026-06-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28946v1 This paper presents a robust Automatic Number Plate Recognition (ANPR) system tailored for Nepali license plates written in Devanagari script. In this paper, a pipelined model was used that integrates YOLO-based models for license plate and character detection, followed by a CNN classifier trained on 34 Devanagari characters. Two publicly available data sets were used that incorporate diverse lighting, fonts, and structural variations. Data augmentation and additional training on embossed plates enhanced the generalizability of the model. The system achieved a recognition accuracy of up to 93\%, demonstrating strong performance under real-world conditions and providing a scalable solution for traffic management in Nepal. Code: https://github.com/Satyasakhadka/Nepali-NumberPlate-Character-Recognition --- ### A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctions Authors: Junhan Li, Yuxin Zhang, Haoran Wang, Minghao Chen Published: 2026-06-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.28943v1 Learning to bid in repeated multi-unit auctions with bandit feedback poses a fundamental challenge. Existing methods often rely on rigid explore-then-exploit schedules, assume stationary adversaries, and optimize solely for bidder utility, thereby limiting adaptability and strategic robustness. To address these limitations, we introduce the A3M framework, which integrates adaptive deep reinforcement learning (DRL), explicit adversarial reasoning, and principled multi-objective reward design for online auction strategy optimization. A3M employs an actor-critic DRL backbone to dynamically balance exploration and exploitation, an opponent model for fictitious play against non-stationary adversaries, and a composite reward function to jointly maximize utility, auctioneer revenue, and fairness. We provide the first comprehensive empirical evaluation of this integrated approach against established baselines in both discriminatory and uniform price auctions. Results show that A3M reduces final regret by 30--40\% in standard settings, maintains robust performance against adversarial strategy shifts, scales favorably with the number of units $K$, and enables tunable multi-objective trade-offs. An extensive ablation study confirms the necessity of each core component. Our work establishes A3M as a powerful and flexible framework for learning in complex auction environments. --- ### ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies Authors: Tzu-Hsiang Lin, Srinivas Shakkottai, Dileep Kalathil, P. R. Kumar Published: 2026-06-27 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2606.28939v1 Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into task failure. Existing methods address this either by expanding the training distribution through expert corrections or synthetic augmentation, or by steering a frozen policy at test time with guidance from a learned model. The former can be expensive or assumption-dependent, while the latter discards the corrected trajectories after execution. We introduce ReGuide, a self-improving framework that treats guided rollouts as reusable on-policy recovery data. ReGuide first uses Phase-Conditioned Guidance (PCG) to generate corrective rollouts: it constructs phase-specific latent targets, applies guidance only in the drifted-but-recoverable regime, and guides through the estimated clean action to match the dynamics model's training distribution. Successful guided rollouts are then absorbed back into the policy through ReGuide-FT, which fine-tunes the current checkpoint, or ReGuide-FS, which retrains from scratch on the augmented dataset; the two can also be composed and iterated. On Robomimic Can, Square, Transport, and Tool Hang, ReGuide improves base-policy success by $1.3$--$7.7\times$, outperforms LPB in the test-time-only setting, and matched-data ablations show that the gains come from guided recovery data rather than additional rollouts alone. --- ### EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Control Authors: Yuxin Liu, Zihan Chen, Haoyu Wang, Mingxuan Zhang, Ruijie Lin, Siyuan Zhao Published: 2026-06-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.28938v1 Modern vision-language models (VLMs) for driving assistants typically treat vehicle dynamics as a black box, resulting in decisions that lack awareness of the vehicle's real-time electro-mechanical state. To bridge this gap, we introduce the Electro-Visual-Language Assistant (EVLA) -- a novel framework that combines multi-modal scene understanding with real-time perception of the electrified powertrain state (e.g., motor torque, battery SOC). Our approach features two key innovations: first, a Unified Co-State Encoder (UCSE) that fuses visual, textual, and vehicle-state inputs into a shared latent representation, augmented with an Energy-Efficiency Field to model spatial energy costs; and second, an Electro-aware Structured Reasoning Chain (ESRC), which replaces external chain-of-thought prompting with an internal, deterministic reasoning process grounded in physical constraints and optimization objectives. Trained end-to-end with a physics-guided joint loss, EVLA learns to generate context-aware and energy-optimal driving decisions. Extensive evaluations on a driving QA benchmark demonstrate that EVLA substantially outperforms strong fine-tuned VLM baselines, improving the final score by +0.0871 and accuracy by +5.6\%. Ablation studies validate the necessity of each component, and efficiency analyses show that EVLA achieves 36\% faster inference than multi-stage pipelines. This work underscores that integrating vehicle-state awareness and structured physical reasoning is crucial for developing next-generation, physically-grounded driving assistants. --- ### FinInvest-GTCN: Explainable Graph-Temporal-Causal Modeling for Risk-Aware Investment Decision Optimization Authors: Junyan Tan, Yifan Li, Minghao Wang, Zihan Chen, Haoyu Zhang Published: 2026-06-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.28933v1 Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings. To overcome these issues, we introduce \textbf{FinInvest-GTCN}, a Graph-Temporal-Causal Network that redefines the task from content recommendation to quantitative risk-return assessment. This architecture combines a relational graph encoder to capture the investment ecosystem's topology, a multi-scale temporal fusion module to handle long-term dependencies and non-stationarity, and a causal decision head that generates risk-adjusted predictions with interpretable causal attributions. A core innovation is the Meta-Causal Adaptation (MCA) strategy, which facilitates robust fine-tuning for new, data-scarce sectors by aligning updates with causally-plausible structures derived from meta-pretraining. Comprehensive experiments on proprietary VC datasets show that FinInvest-GTCN delivers state-of-the-art results, markedly lowering the primary Risk-Adjusted Mean Squared Error (RA-MSE) to 2.51 from a baseline of 3.05 and boosting the cumulative return of a simulated portfolio by 18.7\%. Ablation studies underscore the essential role of each component, while additional analyses confirm the model's stability, interpretability, and enhanced adaptability. This work pioneers a data-driven, explainable framework for investment decision support. --- ### DLR: Zero-Inference-Cost Latent Residuals for Low-Rank Pre-Training Authors: Dong Wang, Wenwu Tang, Yun Cheng, Olga Saukh Published: 2026-06-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.28932v1 Large language models have driven recent progress in language and multimodal AI, yet pre-training them at scale is prohibitively expensive. Low-rank pre-training, which factorizes each weight matrix into a rank-r product to reduce both parameters and FLOPs, is a promising response but typically lags full-rank training in quality. We propose Duplicated Latent Residual (DLR), a training-only, parameter-free, foldable plug-in for low-rank pre-training. DLR augments the standard low-rank output Bz with a fixed structured residual alpha/sqrt(K) * Expand_K(z) that replicates each latent coordinate K = ceil(d_out/r) times across the output. With alpha fixed, DLR adds zero learnable parameters per layer; after training, it is absorbed into the up-projection in closed form, B* = B + alpha/sqrt(K) R^T, so deployment parameter count, FLOPs and memory match the underlying low-rank backbone exactly. Across LLaMA models from 60M to 7B parameters, DLR strengthens low-rank pre-training on C4 validation perplexity in most settings, with the clearest gains at 130M and above; folded checkpoints transfer cleanly to supervised fine-tuning on standard benchmarks. --- ### Cybersecurity is the True Frontier for Generative AI Success or Failure Authors: Edward Raff, Maor Ashkenazi, Sagar Samtani, David J. Elkind, Sven Krasser Published: 2026-06-27 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2606.28929v1 Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models (LLMs) to automate processes as ``agents.'' Cybersecurity workflows require orchestrating hundreds of standard and bespoke tools through various formats. The scale of cybersecurity data is enormous; for example, a single malware sample can be viewed as a sequence of billions of tokens. The cost of labeling any file by experts is enormous and labor-intensive, in part because an adversary (possibly a well-funded nation state actor) is attempting to subvert your detection methods. Even skilled experts may disagree on the correct label, creating ambiguity in what constitutes ground truth. When deployed, models must run quickly on billions of items a day, where low-latency is critical for operational success, in a continuously changing environment. In addition, explainability is not optional: analysts demand clear reasoning for model decisions to cope with the large number of false-positive alerts they face daily, and to quickly develop remediation and understand how something went wrong. In short, the amount of complexity cybersecurity is greater than that of natural language and computer vision, and thus we posit that cybersecurity is the better test-case for general AI progress than other, well-studied fields. --- ### A Theoretical Interpretation of In-Context Learning via Probabilistic Modeling Authors: Zhenyu Liu, Huaze Tang, Shao-Lun Huang Published: 2026-06-27 Categories: cs.IT, cs.LG arXiv: https://arxiv.org/abs/2606.28926v1 In-context learning (ICL) is an emerging paradigm that employs the semantic information inherent in large language models (LLMs) for generating answers to user queries. While the remarkable performance of ICL has been widely known, a general modeling and a rigorous theoretical analysis of this paradigm are still lacking. This work presents a probabilistic model for ICL and derives the performance of ICL for both general parametric distributions and exponential families. Based on the derived results, the work explains the impact of multiple factors such as the number of demonstrations, the sensitivity of the probabilistic model to the variation of its parameters, as well as the similarity between the demonstrations and the query on the performance of ICL. --- ### Multi-Agent Routing as Set-Valued Prediction: A WildChat Benchmark and Cost-Aware Evaluation Authors: Ananto Nayan Bala, Faisal Muhammad Shah Published: 2026-06-27 Categories: cs.LG, cs.AI, cs.IR, cs.MA arXiv: https://arxiv.org/abs/2606.28925v2 Tool and agent routing from natural-language prompts is naturally a set-valued prediction problem: a single query may require multiple agents, while over-selection increases execution cost. The benchmark introduced here is derived from WildChat and contains 3,000 prompts over a fixed 12-agent catalog, with AI-assisted heuristic labels under a fixed schema and controlled rebalancing for multi-label evaluation. The evaluation protocol combines set-level metrics (Precision, Recall, F1, Jaccard, and Exact Match), latency, an execution-oriented capability-coverage simulation, and a constrained weighted-routing setting based on ordinal agent-cost tiers. Compared methods include nearest-neighbor matching, linear multilabel classification, dependency-aware baselines, a fine-tuned encoder, deterministic weighted post-scoring via Weighted Agent Routing (WAR), and a zero-shot LLM baseline. Results show that supervised routers substantially outperform nearest-neighbor and zero-shot LLM routing. The fine-tuned encoder achieves the strongest unconstrained set accuracy, while the linear multilabel model provides the strongest practical baseline. In the constrained setting, the weighted routing layer improves utility when applied on top of strong supervised scorers, with the largest gain observed for Encoder+WAR. Overall, the benchmark and evaluation protocol support reproducible study of accuracy-cost trade-offs in fixed-catalog multi-agent routing. --- ### Towards Improved Anomaly Detection for Cloud Cybersecurity via Graph Neural Networks Authors: Manu Nandan, TJ Jaymes, Michael Brautbar, Edward Raff Published: 2026-06-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.28923v1 Detecting security threats in an organization's cloud computing environment has become necessary due to the increased reliance on cloud infrastructure. Logging of all cloud computing events enables investigation into any incidents after they are detected. Automated detection of threats using the logs based on heuristics or anomaly detection could result in a high false positive rate due to its relatively static nature. In this article, we present an industrial case study of a self-supervised learning method using graph neural networks applied to AWS CloudTrail logs to surface suspicious events for analyst review. The model produces an anomaly score for each event and dynamically adapts to changes in the organization without requiring periodic retraining. Based on our experiments across five organizations, the proposed model produced substantially fewer alerts than a domain expert rule-based baseline in almost all cases, reducing alert volumes to approximately 1 per hour from thousands generated by traditional methods. We note that this evaluation covers only flagged events, and false negatives cannot be estimated from the current data; findings should therefore be interpreted as a practical deployment study offering insights into real-world constraints rather than a fully validated detection system. We discuss these limitations and the requirements for extending the approach to other cloud environments as future work. --- ### ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images Authors: Zixiao Zhang, Lingling Li, Pei He, Xu Liu, Licheng Jiao Published: 2026-06-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28920v1 Remote sensing visual grounding (RSVG) aims to locate specific objects in high-resolution RS imagery using free-form natural language descriptions. While recent advances in multimodal large language models (MLLMs) show great potential for such open-vocabulary RSVG, their training-free adaptation is hindered by the modality gap between abstract linguistic semantics and fine-grained visual cues. In cluttered RS scenes, this gap inevitably causes severe localization drift. To bridge this gap, we propose Exemplar-driven Calibrated Refinement (ExACT), a novel training-free framework driven by a one-shot visual prompting mechanism to explicitly provide discriminative structural guidance for precise pixel-level localization. Specifically, we propose a Vision Exemplar-based Calibrator (VEC) that extracts fine-grained visual correspondences from the given exemplar to rectify the rough cross-modal priors from frozen MLLMs, effectively suppressing background artifacts and accurately outlining target boundaries. Subsequently, a Structure-Aware Refiner (SAR) employs an iterative merge-and-select clustering strategy to consolidate the calibrated priors into high-quality positive and negative geometric prompts. These prompts then guide the Segment Anything Model (SAM) to achieve precise pixel-level predictions. Extensive experiments confirm the superiority of ExACT over existing training-free and weakly-supervised methods. --- ### ML-Powered LDAP Reconnaissance Detection using Weak Supervision Authors: Shaefer Drew, Edward Raff, Michael Brautbar, Yaron Zinar, Benjamin Malmberg, Dor Agron, Sagi Sheinfeld, Avraham Kama, Asaf Romano Published: 2026-06-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.28917v1 Lightweight Directory Access Protocol (LDAP) is a protocol that allows users to query and modify Active Directory (AD) data. By default, all users have read access to all AD data through LDAP, making it a common initial tool for reconnaissance when a threat actor first compromises an identity. To capture threat actors early in the reconnaissance phase, we developed two machine learning frameworks to detect LDAP reconnaissance: an ML classifier to predict malicious LDAP queries and an ML-based data-mining method to extract malicious query signatures. By correlating LDAP queries with endpoint detections, the first framework uses weak supervision to label a massive dataset and classify LDAP queries as malicious or benign. For immediate deployment, a second technique was developed on top of this approach to employ a rigorous statistical hypothesis-testing framework for mining novel, malicious LDAP signatures. While this weakly supervised approach is limited compared with manual human labeling, it is more practical for this use case because it leverages large-scale automated corpus construction, reducing costs and time. Ultimately, both the LDAP classifier and the ML-based LDAP signature mining method achieved performance benchmarks, with the classifier achieving up to a 65\% True Positive Rate (TPR) on the holdout set while limiting false positives, and mined signatures demonstrating 81.48\% field precision with CrowdStrike's Managed Detection and Response team. --- ### Latent Bridges for Multi-Table Question Answering Authors: Simone Varriale, Tamara Cucumides, Floris Geerts, Paolo Papotti Published: 2026-06-27 Categories: cs.CL, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2606.28916v1 We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering. Our method lifts relational data into an heterogeneous graph, encodes it via message passing, and transfers the signals to an LLM through a small set of query-conditioned latent tokens. This provides the LLM with a compact, task-relevant structural representation together with the flattened text. Crucially, the LLM remains strictly frozen to preserve its general reasoning capabilities; we train only the lightweight graph encoder and latent bridge (91M parameters), allowing the entire pipeline to be trained efficiently. Our pipeline significantly improves performance on relational Question Answering, with the largest gains in demanding multi-table settings, offering an efficient, principled way to connect relational deep learning with LLMs. --- ### What Color is the Sky (for a non-human) ? Authors: Yair Weiss, Ofer Springer Published: 2026-06-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28912v1 The light of the daytime sky contains a mixture of many colors yet is perceived as blue by human observers. This is largely due to the particular response functions of the human cones. Under these response functions skylight and blue light are metamers: they yield the exact same excitation of the cones. In this paper we ask: is it possible to define the ``color'' of the sky for other visual systems? We present a simple computational method to determine monochromatic metamers to a given input light for arbitrary visual systems. Using published values on spectral sensitivity functions of various species, we use our method to determine the dominant wavelength of monochromatic metamers to skylight. For a wide range of species (bichromats, trichromats and tetrachormats) we find monochromatic metamers to skylight but the dominant wavelength of the metamer can vary drastically between species and be very different from the color perceived by humans. --- ### MALOQ: Massively Accelerated Learning of Operators for Quantum Transport Authors: Manasa Kaniselvan, Alexander Maeder, Denghui Lu, Alexandros Nikolaos Ziogas, Mathieu Luisier Published: 2026-06-27 Categories: cs.LG, cond-mat.mtrl-sci, cs.DC, physics.comp-ph arXiv: https://arxiv.org/abs/2606.28911v1 Machine-learned (ML) operator models can be trained to predict density functional theory (DFT) Hamiltonian/density matrices at significantly reduced computational cost, thus extending electronic-structure calculations to previously unfeasible scales. Here, we introduce MALOQ (Massively Accelerated Learning of Operators for Quantum Transport), an application built to train on and predict electronic-structure matrices for systems made of few to 100k atoms, described by large basis sets, and covering a wide range of atomic elements. Based on a state-of-the-art, SO(2)-equivariant backbone architecture, MALOQ provides (i) custom data-processing kernels to handle high-rank Hamiltonian matrix data and (ii) a scalable edge-wise distribution of atomic graph(s). Trained on the largest molecular Hamiltonian datasets available today, it reduces time-per-epoch by over 30% compared to a molecule-wise-distributed framework, and enables inference on material graphs of arbitrary size. We demonstrate scalable training and inference for 3,000-12,000 atoms on the Alps supercomputer, up to 192 GPUs and 256 GPUs, respectively. --- ### Road to scalability for efficient graph search on massively parallel neuromorphic hardware Authors: Oskar von Seeler, Elena C. Offenberg, Carlo Michaelis, Tomas Kulvicius, Jannik Luboeinski, Andrew B. Lehr, Christian Tetzlaff Published: 2026-06-27 Categories: cs.NE arXiv: https://arxiv.org/abs/2606.28907v1 Efficient computation of shortest paths in weighted graphs is a fundamental problem with many applications. Neuromorphic hardware platforms promise massively parallel, efficient computation, changing parallelism tradeoffs. In this work, we introduce NEURO-MAPP (Neuromorphic-based Min-Add Parallel Propagation), a distributed shortest path algorithm designed to use the local computation and network communication available in neuromorphic systems. We provide an optimized implementation of the algorithm on the SpiNNaker 2 platform and evaluate its performance on a selection of synthetic and real-world graphs. These results are compared to Dijkstra's algorithm on a modern CPU. We find that the NEURO-MAPP implementation scales favorably in terms of runtime for many graph types while consuming less energy per shortest-path query than the CPU implementation in almost all cases. These findings highlight the potential of neuromorphic hardware featuring sparse, spike-based communication as a scalable and energy-efficient platform for computation in graph search and related tasks. --- ### Projection-based coupling of infrared thermography and stereocorrelation-based digital image correlation Authors: Jendrik-Alexander Tröger, Lutz Müller-Lohse, Stefan Hartmann Published: 2026-06-27 Categories: cs.CV, cond-mat.mtrl-sci, physics.optics arXiv: https://arxiv.org/abs/2606.28905v1 Full-field measurement techniques such as digital image correlation and infrared thermography are prevalent in experimental solid mechanics. Digital image correlation is used to analyze surface deformation, while infrared thermography quantifies surface temperature fields. However, sophisticated procedures are necessary to express both datasets in the same Lagrangian frame, especially when analyzing non-flat surfaces. In this study, we propose an external projection-based coupling that uses the pinhole camera model to relate two-dimensional temperature data measured by infrared thermography to three-dimensional point coordinates from stereocorrelation-based digital image correlation. Unlike existing multiview approaches, we utilize two independently calibrated industrial-grade systems and augment the experimental evaluation with the pinhole camera model. The projection matrix of the camera model is calibrated using a single image of a reference object. Through this projection, temperature fields are accurately represented at material points. Our method is particularly suited for, but not restricted to, curved surfaces and straightforward to embed in existing experimental protocols, as the image registration is kept as is. Additionally, we propose using radial basis functions as a global interpolation ansatz in both space and time to compute in-plane temperature gradients and even temperature rates on curved surfaces, thereby providing an extensive and information-rich full-field dataset. --- ### MedEvoEval: Evaluating Continual Evolution of Doctor Agents through Simulated Clinical Episodes Authors: Hui Zhang Published: 2026-06-27 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.28900v1 Doctor agents are moving beyond single-turn answer generation toward evolving clinical decision systems. Within an outpatient episode, they acquire evidence, use examination and consultation resources, and decide when to finalize a diagnosis and management plan. Across episodes, their behavior may change through memory, retrieval, reflection, or other update mechanisms. Current evaluations only partially cover this setting. Fixed-input medical QA benchmarks score final answers from complete inputs, whereas many interactive benchmarks still focus on individual encounters or fixed runs, providing limited support for evaluating how episode-level decisions interact with cross-episode experience. We introduce MedEvoEval, an executable longitudinal evaluation framework based on action-gated simulated outpatient episodes. Each source case is converted into role-specific patient, examination, and manager views; evidence is revealed only through valid actions; and each episode records a structured trace that links observations, actions, final outputs, manager scores, and optional experience write-back. We release a runnable E&D artifact with 700 processed episodes, provenance notes, schemas, an episode runner, scoring scripts, configurations, example logs, analysis code, and trajectory- and step-level derivatives. Experiments show that episode traces expose process costs hidden by final-answer scoring, show how MDT-style consultation reallocates resources, and support longitudinal analyses of memory maturation, held-out transfer, update-stage response, and backward retention. Together, these results show that MedEvoEval provides a concrete basis for evaluating whether doctor agents improve through experience, transfer useful behavior, and retain earlier capabilities over time. --- ### PASTA: A Paraphrasing And Self-Training Approach for Knowledge Updating in LLMs Authors: Takayuki Yamamoto, Daisuke Kawahara Published: 2026-06-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.28898v1 Knowledge updating in pre-trained Large Language Models (LLMs) remains an important challenge. While continual training provides a potential avenue for knowledge updating, it continues to present substantial technical difficulties. Furthermore, LLMs often struggle with accurately answering questions about specific factual information, such as news articles - a capability limitation widely recognized in the research community. This paper proposes PASTA, a simple yet powerful framework for integrating detailed factual information from news articles as new knowledge into LLMs, with the primary goal of building specialized models that accurately answer questions about this knowledge. Our framework combines data augmentation, question-answering generation, and a novel self-learning DPO process that simultaneously enables knowledge overwriting and hallucination suppression. We provide insights into effective knowledge updating through systematic analysis of learning parameters and data configurations. In our experimental evaluation with web articles published after the base model's knowledge cutoff, PASTA achieved remarkable improvement from 0.02 to 0.82 accuracy while maintaining general language capabilities, demonstrating its effectiveness for creating domain-specialized LLMs. --- ### A Task-Driven and Quality-Assured Agent Framework for SAR Data Generation Authors: Xuanting Wu, Fan Zhanga, Fei Ma, Ling Guan, Guochun Ma, Yongsheng Zhou Published: 2026-06-27 Categories: eess.IV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.28896v1 Synthetic aperture radar (SAR) data augmentation is important for improving the generalization of data-driven SAR interpretation models, yet practical augmentation workflows are often hindered by heterogeneous dataset formats, task-dependent metadata requirements, diverse generation methods, and weak validation of generated samples. This paper presents the \textbf{S}AR \textbf{A}ugmentation and \textbf{G}eneration \textbf{A}gent (SAGA), a schema-grounded and benefit-aware agent framework for task-oriented SAR data generation and augmentation. Given a natural-language request and heterogeneous SAR inputs, SAGA extracts observable dataset facts, validates executable dataset schemas, selects feasible augmentation strategies through validator-constrained planning, and compiles the selected strategy into an auditable augmentation workflow. Generated data are further assessed by quality, distribution, SAR-artifact, duplicate, leakage, and optional downstream-task evaluators to support evidence-qualified augmentation claims. By separating semantic proposal from deterministic validation and execution, SAGA improves the reliability and reproducibility of SAR augmentation decisions. Experiments on controlled agentic benchmarks and downstream SAR interpretation tasks show that SAGA improves schema grounding, skill planning, invalid-sample rejection, and downstream augmentation utility compared with rule-based, LLM-only, ReAct-style, and fixed-augmentation baselines. --- ### Exploring the Value of Diverse LLM Explanations in Introductory Programming Authors: Seth Bernstein, Paul Denny, Juho Leinonen, Kush Patel, Rayhona Nasimova, Matt Littlefield, Stephen MacNeil Published: 2026-06-27 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2606.28882v1 Large Language Models (LLMs) have shown the potential to generate code explanations that surpass those of peers in quality, offering promising opportunities for computer science education. While these explanations may not yet match the depth and clarity of instructor-provided explanations, research in computational creativity highlights that the quantity and diversity of ideas can often outweigh a singular focus on quality. Inspired by this, we explore whether combining multiple diverse explanations, each emphasizing distinct aspects (e.g., function, concept, goal), can enhance students' understanding of programming exercises compared to generic explanations that do not emphasize distinct conceptual aspects. In our study 971 first-year computing students were randomly assigned either diverse or generic LLM-generated explanations for two programming exercises. Students completed multiple-choice and open-ended questions for each exercise, followed by Likert-scale questions and open-ended reflections. Our findings outline patterns in student performance and perceived cognitive load across the two explanation conditions. These findings highlight how variation in explanation emphasis may relate to learner engagement and understanding. Across participants, open-ended response accuracy was consistently about 7.7% higher when students received diverse explanations, with no difference in perceived cognitive load. --- ### An Integrated Machine Learning and Hierarchical Variance Decomposition Pipeline for Student Performance Prediction and Metacognitive Calibration on Multi-Signal Telemetry Authors: Gurdeep Singh Virdee Published: 2026-06-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.28881v1 Predicting student performance and characterizing metacognitive calibration are essential for personalization in intelligent tutoring systems. Prior research treats performance prediction, calibration error calculation, and variance decomposition as separate pipelines, preventing unified interpretation. I propose the Unified Behavioral Prediction and Calibration Analysis Pipeline (UBP-CAP), an integrated framework processing student pre-execution behavioral telemetry through three linked modules: (1) a LightGBM classifier with SHAP for binary correctness prediction, (2) formal calibration metrics (ECE, MCE, and Brier score decomposition) to evaluate metacognitive alignment, and (3) a crossed Generalized Linear Mixed-Effects Model (GLMM) for decomposing calibration deviations. I introduce the Predictive-Explanatory Divergence Index (PEDI), which quantifies structural divergence between predictive and explanatory feature profiles. Evaluated on 1,195 interaction records (27 students, 45 tasks), Logistic Regression achieves AUC-ROC = 0.903, outperforming LightGBM (0.878). Student naive ECE (0.109) significantly exceeds model ECE (0.068), confirming systematic miscalibration. The crossed GLMM yields ICCStudent = 0.123, showing calibration is situational rather than dispositional. PEDIcos = 0.081 (p = 0.327) indicates structural alignment between prediction and explanation on shared behavioral features. --- ### Analysis of Adam Algorithms for Stochastic Dynamic Systems Authors: Xin Zheng, Yifei Jin, Lei Guo Published: 2026-06-27 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2606.28879v1 The adaptive moment estimation algorithm, known as Adam, is widely used in modern machine learning, owing to its low per-iteration complexity and strong empirical performance. Despite its prevalent use, the theoretical foundation of Adam remains largely unexplored for time-varying and nonstationary systems. In fact, the existing theoretical analyses of Adam-type algorithms are primarily concerned with time-invariant model parameters and explicitly or implicitly rely on independent and identically distributed (i.i.d.) data assumptions, under which the learning taskcan be formulated as minimizing a fixed expected objective with a static minimizer. However, such assumptions are often violated in time-varying and nonstationary systems, thereby calling for a theoretical investigation beyond the conventional yet idealized i.i.d. setting. The main objective of this paper is to solve this challenging problem by establishing a general theory of Adam for time-varying and nonstationary stochastic systems. We will introduce some new techniques for analyzing the products of nonstationary and dependent random matrices induced by Adam's coupled first- and second-moment recursions, and will construct a new stochastic Lyapunov function that blends these two moment dynamics. Under a stochastic excitation condition that allows nonstationary and dependent data, we will derive both parameter tracking and output prediction error bounds explicitly, quantifying the effects of stepsize, first- and second-momentum parameters, gradient noise and parameter drift. These bounds not only provide guarantees for Adam performance, but also provide guidelines for hyperparameter selection. Experiments on both synthetic and real-world data validate our theory and design guidelines. --- ### MMLA: Memory-Mediated Learning Architecture for Predictive Dual-State Adaptation Authors: Junyi Zou, Avrova Donz Published: 2026-06-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.28876v4 Memory-Mediated Learning Architecture (MMLA) separates slow base parameters theta, a bounded numerical policy carrier Phi, and a bounded authoritative memory M. Predictive Dual-State Adaptation (PDSA) lets feedback update Phi while one problem remains active and lets a trusted lifecycle atomically commit one typed row or exact NULL. Later reasoning may read both states, but their writers, resets, rollback domains, and ledgers remain distinct. Realized futures supervise values only during training; deployment is causal and future-blind. We give conditional theory and falsifiable contracts for reasoning-time updates, completed-segment consolidation, predictive admission, authoritative memory, and dual-state attribution. Assumptions, counterexamples, capacity and cost ledgers, recovery duties, and identifying experiments are explicit; these are not implementation guarantees. Controlled studies show exact lifecycle execution on 300/300 held-out records for each of three seeds, calibrated retrieval gains over frozen-hidden dense and BM25 baselines, and exact typed anchor-filler transport on 240/240 held-out records per seed. These validate restricted components, not natural-language memory management or complete PDSA. Post-training studies retain positive and negative evidence. Later protocols obtain restricted readout progress, but a nine-trajectory comparison finds that matched latent readout, a full-width bridge, and bridge plus frozen text-teacher alignment all fail continuous-event qualification across both task families. A separately adapted text reference and restoration checks pass. At the September 13, 2026 evidence cutoff, no strict policy-only reasoning-time-training effect, predictive-admission oracle margin, learned future-blind admission policy, or policy-by-memory factorial advantage is established. --- ### Memory-Managed Long-Context Attention: Bounded Editable Memory with a Hard Lifecycle and Calibrated Sparse Fallback Authors: Junyi Zou, Avrova Donz Published: 2026-06-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.28876v2 We study memory-managed long-context attention: explicit bounded memory with a learned query-independent writer, lifecycle control, query-aware reading, calibrated sparse fallback, and frozen-LLM generation from raw evidence. Track A is a controlled versioned-variable task where last-mention retrieval is wrong by construction. Its full lifecycle scores 1.000 on all three seeds versus a 0.333 lexical baseline, and generation reaches 300/300 at 146 prompt tokens, compared with 172/300 for full-context reading at 729 tokens. Track B uses held-out HotpotQA questions and train-derived, answer-excluded distractors at natural and 8.2k-word lengths. A learned two-hop selector with a bounded 32-passage cache and fallback beats dense retrieval by 5.5--16.6 F1 and reaches 102--116% of full-context F1 at 10% of the evidence words. These real-text gains come from the learned selector; the cache preserves quality at a 0--2.9 F1 cost, and static QA text does not exercise overwrite or protection. The original Llama budget gate failure and the forward-adjudicated Qwen follow-up are reported explicitly. All backbones are frozen; joint training, faithful architecture baselines, and systems measurements remain future work. --- ### A Bayesian latent Gaussian process framework for aerodynamic uncertainty quantification Authors: Geoffrey Davis, Ashwin Renganathan Published: 2026-06-27 Categories: stat.ML, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2606.28871v1 Predicting the aerodynamic performance (e.g. lift, drag, and moment coefficients) of an aircraft is challenging -- computational models are biased and direct simulations are prohibitive. A pragmatic way to overcome this limitation is by calibrating low-fidelity computational predictions with experimental measurements. This, however, requires calibrating against \emph{sparse} measurements contaminated with \emph{uncertainty} in both the control inputs and the measured aerodynamic response. We develop a methodology to address this problem based on Gaussian process surrogates and the classical Kennedy-O'Hagan calibration. A surrogate model learned on abundant-but-cheap low-fidelity data is calibrated with a sparse set of measurement data. Crucialy, we develop a Bayesian latent Gaussian process based approach that marginalizes the calibrated surrogate model over the input uncertainty, while also matching the marginal mean and variance of the measured output uncertainty. Once calibrated, our surrogate model predicts the uncertainty in aerodynamic coefficients with very high accuracy, including at extrapolative input settings. We validate our calibrated surrogate model predictions against measurement data with \emph{true} uncertainty intervals to demonstrate that the model places $94.2-95.8\%$ of its predictive samples inside the released $95\%$ truth intervals, with endpoint cumulative probabilities very close to the nominal 0.025 and 0.975 levels. --- ### Open but Incompatible: A License Compatibility Analysis of Corpora for Low-Resource African Languages Authors: Ernst van Gassen Published: 2026-06-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.28867v1 Creative Commons licenses dominate African NLP corpus releases, but their compatibility rules are rarely applied. CC-BY-SA and CC-BY-NC cannot be combined in a single published dataset; a NoDerivs clause silently prohibits tokenisation and annotation. This paper audits the license provenance of over twenty corpus families used in African NLP, constructs a six-tier compatibility matrix, and applies it to three case-study languages: Kituba/Munukutuba, Zarma, and Moore. Four failure modes are documented with primary-source evidence: outright prohibition (JW300, removed from OPUS after a legal audit confirmed Terms of Service violation); composite license misrepresentation (WAXAL, whose CC-BY 4.0 claim is contradicted by its own HuggingFace dataset card); a NoDerivs clause hidden behind a CC-BY label (Tanzil); and data persistence failure (the Congolese Radio Corpus, where 402 of 405 source URLs are now dead). A pre-annotation due diligence checklist and a survey of legally clean enrichment opportunities close the paper. --- ### On Test-Time Scaling for Vision-Language Models Authors: Fawaz Sammani, Tzoulio Chamiti, Nikos Deligiannis Published: 2026-06-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28864v2 Test-time scaling is a paradigm where large models use additional compute at inference to achieve better performance, without changing model weights. While it has been widely studied for Large Language Models (LLMs), its applicability to Large Vision-Language Models (LVLMs) remains less explored and analyzed, with limited analysis of whether, when, and to what extent these approaches transfer to LVLMs. In this work, we ask a simple but fundamental question: can conventional test-time scaling methods developed for LLMs be directly applied to LVLMs? We present the first comprehensive study of test-time scaling for LVLMs, spanning multiple models and model sizes, nine test-time scaling methods, and six diverse benchmarks. Our main findings is that 1) different from previous findings, small, well-performing models benefit the most from test-time scaling, enabling performance improvements of up to around 30\%, reaching large models performance, and often outperforming them, 2) LVLMs lose focus when given more compute than necessary, and 3) Visual information is encoded early in the reasoning chain, after which the chain is dominated by text-only reasoning and the contribution of image tokens drops significantly. Finally, we also provide a global and fine-grained analysis on the quality and information sufficiency of the reasoning chains produced. Overall, our findings and analysis provide practical guidance and insights into LVLMs and their deployment in research and industry. --- ### Defeat Devices in AI Systems Authors: Emilio Ferrara Published: 2026-06-27 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.28863v1 AI systems increasingly exhibit behavior that differs systematically between evaluation and deployment contexts. Alignment faking, sandbagging, benchmark gaming, deceptive scheming, specification gaming, and trojans have each been documented separately, with each line of work characterizing one facet of what we argue is a single structural mechanism. We propose that this common mechanism is a defeat device, an engineering and regulatory concept long established in vehicle-emissions law and brought to broad public attention by the 2015 Volkswagen emissions case. A defeat device in an AI system has three necessary elements: a discriminator that detects evaluation context, a concealed swap that conditions behavior on detection, and a gap between eval-distribution and deployment-distribution performance on the stated evaluation criterion. We formalize this triadic test as a behavioral definition, organize documented cases along three taxonomic axes (origin, trigger, swap mechanism), propose Trigger-Axis-Aware Differential Probing (TADP) as a forensic detection protocol, and advance the claim that defeat devices can naturally emerge in current frontier AI systems without any operator engineering. We characterize naturally-emerging defeat devices as potentially one of the harmful emerging phenomena that AI safety practice should monitor and test for systematically. Implications for evaluation methodology, post-training pipeline design, interpretability research priorities, and AI governance follow. --- ### HKVLM: Faithful Query--Region Binding for Frozen-Detector Visual Grounding Authors: Bo Ma Published: 2026-06-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28862v2 Visual grounding often fails even when the target object is present in the proposal pool, because the language-side referent is bound to the wrong region. We study this binding failure under frozen perception and ask whether an explicit query--region alignment hook, together with a perception-grounded abstention mechanism, can improve faithful grounding without retraining the detector or the vision-language backbone. HKVLM freezes a language-aligned open-vocabulary detector for localization and learns a lightweight hook that maps referential query embeddings to detector proposals in a shared space; a verifier abstains when no region sufficiently supports the query. We prove an exact proposal-level diagnostic decomposition, $(1-\mathrm{SeeErr})(1-\mathrm{SayErr})$, separating proposal-coverage failures from conditional binding failures, and a monotonicity result that characterizes the faithfulness--recall trade-off induced by abstention. Across RefCOCO, RefCOCO+, RefCOCOg, and POPE, HKVLM improves over untrained and trained matched-perception binding controls and substantially reduces hallucination through abstention. Strong coordinate-decoding and end-to-end fine-tuned baselines remain much higher in raw grounding accuracy, and a reasoning-stress set exposes binding as the main current bottleneck. We therefore present HKVLM as a diagnostic and mechanism-level study of query--region binding under frozen perception, not as an absolute localization leader. ---