# Research Papers — 2026-02 · bundle page 41 of 210 > Full-text markdown of papers #2001–2050 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/41 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/40.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/42.md) ### Inspectorch: Efficient rare event exploration in solar observations Authors: C. J. Díaz Baso, I. J. Soler Poquet, C. Kuckein, M. van Noort, N. Poirier Published: 2026-02-23 Categories: astro-ph.SR, cs.CV arXiv: https://arxiv.org/abs/2602.20316v2 The Sun is observed in unprecedented detail, enabling studies of its activity on very small spatiotemporal scales. However, the large volume of data collected by our telescopes cannot be fully analyzed with conventional methods. Popular machine learning methods identify general trends from observations, but tend to overlook unusual events due to their low frequency of occurrence. We study the applicability of unsupervised probabilistic methods to efficiently identify rare events in multidimensional solar observations and optimize our computational resources to the study of these extreme phenomena. We introduce Inspectorch, an open-source framework that utilizes flow-based models: flexible density estimators capable of learning the multidimensional distribution of solar observations. Once optimized, it assigns a probability to each sample, allowing us to identify unusual events. We apply this approach by applying it to observations from the Hinode Spectro-Polarimeter, the Interface Region Imaging Spectrograph, the Microlensed Hyperspectral Imager at Swedish 1-m Solar Telescope, the Atmospheric Imaging Assembly on board the Solar Dynamics Observatory and the Extreme Ultraviolet Imager on board Solar Orbiter. We find that the algorithm assigns consistently lower probabilities to spectra that exhibit unusual features. For example, it identifies profiles with very strong Doppler shifts, uncommon broadening, and temporal dynamics associated with small-scale reconnection events, among others. As a result, Inspectorch demonstrates that density estimation using flow-based models offers a powerful approach to identifying rare events in large solar datasets. The resulting probabilistic anomaly scores allow computational resources to be focused on the most informative and physically relevant events. We make our Python package publicly available at https://github.com/cdiazbas/inspectorch. --- ### N4MC: Neural 4D Mesh Compression Authors: Guodong Chen, Huanshuo Dong, Mallesham Dasari Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20312v1 We present N4MC, the first 4D neural compression framework to efficiently compress time-varying mesh sequences by exploiting their temporal redundancy. Unlike prior neural mesh compression methods that treat each mesh frame independently, N4MC takes inspiration from inter-frame compression in 2D video codecs, and learns motion compensation in long mesh sequences. Specifically, N4MC converts consecutive irregular mesh frames into regular 4D tensors to provide a uniform and compact representation. These tensors are then condensed using an auto-decoder, which captures both spatial and temporal correlations for redundancy removal. To enhance temporal coherence, we introduce a transformer-based interpolation model that predicts intermediate mesh frames conditioned on latent embeddings derived from tracked volume centers, eliminating motion ambiguities. Extensive evaluations show that N4MC outperforms state-of-the-art in rate-distortion performance, while enabling real-time decoding of 4D mesh sequences. The implementation of our method is available at: https://github.com/frozzzen3/N4MC. --- ### QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models Authors: Jingxuan Zhang, Yunta Hsieh, Zhongwei Wan, Haokun Lin, Xin Wang, Ziqi Wang, Yingtie Lei, Mi Zhang Published: 2026-02-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.20309v4 Vision-language-action (VLA) models unify perception, language, and control for embodied agents but face significant challenges in practical deployment due to rapidly increasing compute and memory demands, especially as models scale to longer horizons and larger backbones. To address these bottlenecks, we introduce QuantVLA, a training-free post-training quantization (PTQ) framework that, to our knowledge, is the first PTQ approach for VLA systems and the first to successfully quantize a diffusion transformer (DiT) action head. QuantVLA incorporates three scale-calibrated components: (1) a selective quantization layout that integerizes all linear layers in both the language backbone and the DiT while keeping attention projections in floating point to preserve the original operator schedule; (2) attention temperature matching, a lightweight per-head scaling mechanism that stabilizes attention logits and is folded into the dequantization scales at inference; and (3) output head balancing, a per-layer residual interface calibration that mitigates post-projection energy drift. The framework requires no additional training, uses only a small unlabeled calibration buffer, and supports integer kernels for low-bit weights and activations while leaving the architecture unchanged. Across representative VLA models on LIBERO, QuantVLA exceeds the task success rates of full-precision baselines, achieves about 70% relative memory savings on the quantized components, providing a practical pathway toward scalable low-bit embodied intelligence under strict compute, memory, and power constraints. --- ### In-context Pre-trained Time-Series Foundation Models adapt to Unseen Tasks Authors: Shangqing Xu, Harshavardhan Kamarthi, Haoxin Liu, B. Aditya Prakash Published: 2026-02-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.20307v1 Time-series foundation models (TSFMs) have demonstrated strong generalization capabilities across diverse datasets and tasks. However, existing foundation models are typically pre-trained to enhance performance on specific tasks and often struggle to generalize to unseen tasks without fine-tuning. To address this limitation, we propose augmenting TSFMs with In-Context Learning (ICL) capabilities, enabling them to perform test-time inference by dynamically adapting to input-output relationships provided within the context. Our framework, In-Context Time-series Pre-training (ICTP), restructures the original pre-training data to equip the backbone TSFM with ICL capabilities, enabling adaptation to unseen tasks. Experiments demonstrate that ICT improves the performance of state-of-the-art TSFMs by approximately 11.4% on unseen tasks without requiring fine-tuning. --- ### Shape-informed cardiac mechanics surrogates in data-scarce regimes via geometric encoding and generative augmentation Authors: Davide Carrara, Marc Hirschvogel, Francesca Bonizzoni, Stefano Pagani, Simone Pezzuto, Francesco Regazzoni Published: 2026-02-23 Categories: cs.LG, cs.AI, math.NA arXiv: https://arxiv.org/abs/2602.20306v1 High-fidelity computational models of cardiac mechanics provide mechanistic insight into the heart function but are computationally prohibitive for routine clinical use. Surrogate models can accelerate simulations, but generalization across diverse anatomies is challenging, particularly in data-scarce settings. We propose a two-step framework that decouples geometric representation from learning the physics response, to enable shape-informed surrogate modeling under data-scarce conditions. First, a shape model learns a compact latent representation of left ventricular geometries. The learned latent space effectively encodes anatomies and enables synthetic geometries generation for data augmentation. Second, a neural field-based surrogate model, conditioned on this geometric encoding, is trained to predict ventricular displacement under external loading. The proposed architecture performs positional encoding by using universal ventricular coordinates, which improves generalization across diverse anatomies. Geometric variability is encoded using two alternative strategies, which are systematically compared: a PCA-based approach suitable for working with point cloud representations of geometries, and a DeepSDF-based implicit neural representation learned directly from point clouds. Overall, our results, obtained on idealized and patient-specific datasets, show that the proposed approaches allow for accurate predictions and generalization to unseen geometries, and robustness to noisy or sparsely sampled inputs. --- ### Multilevel Determinants of Overweight and Obesity Among U.S. Children Aged 10-17: Comparative Evaluation of Statistical and Machine Learning Approaches Using the 2021 National Survey of Children's Health Authors: Joyanta Jyoti Mondal Published: 2026-02-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.20303v1 Background: Childhood and adolescent overweight and obesity remain major public health concerns in the United States and are shaped by behavioral, household, and community factors. Their joint predictive structure at the population level remains incompletely characterized. Objectives: The study aims to identify multilevel predictors of overweight and obesity among U.S. adolescents and compare the predictive performance, calibration, and subgroup equity of statistical, machine-learning, and deep-learning models. Data and Methods: We analyze 18,792 children aged 10-17 years from the 2021 National Survey of Children's Health. Overweight/obesity is defined using BMI categories. Predictors included diet, physical activity, sleep, parental stress, socioeconomic conditions, adverse experiences, and neighborhood characteristics. Models include logistic regression, random forest, gradient boosting, XGBoost, LightGBM, multilayer perceptron, and TabNet. Performance is evaluated using AUC, accuracy, precision, recall, F1 score, and Brier score. Results: Discrimination range from 0.66 to 0.79. Logistic regression, gradient boosting, and MLP showed the most stable balance of discrimination and calibration. Boosting and deep learning modestly improve recall and F1 score. No model was uniformly superior. Performance disparities across race and poverty groups persist across algorithms. Conclusion: Increased model complexity yields limited gains over logistic regression. Predictors consistently span behavioral, household, and neighborhood domains. Persistent subgroup disparities indicate the need for improved data quality and equity-focused surveillance rather than greater algorithmic complexity. --- ### What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance Authors: William Watson, Nicole Cho, Sumitra Ganesh, Manuela Veloso Published: 2026-02-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.20300v1 Large Language Model (LLM) hallucinations are usually treated as defects of the model or its decoding strategy. Drawing on classical linguistics, we argue that a query's form can also shape a listener's (and model's) response. We operationalize this insight by constructing a 22-dimension query feature vector covering clause complexity, lexical rarity, and anaphora, negation, answerability, and intention grounding, all known to affect human comprehension. Using 369,837 real-world queries, we ask: Are there certain types of queries that make hallucination more likely? A large-scale analysis reveals a consistent "risk landscape": certain features such as deep clause nesting and underspecification align with higher hallucination propensity. In contrast, clear intention grounding and answerability align with lower hallucination rates. Others, including domain specificity, show mixed, dataset- and model-dependent effects. Thus, these findings establish an empirically observable query-feature representation correlated with hallucination risk, paving the way for guided query rewriting and future intervention studies. --- ### Gap-Dependent Bounds for Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation Authors: Haochen Zhang, Zhong Zheng, Lingzhou Xue Published: 2026-02-23 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.20297v1 We study gap-dependent performance guarantees for nearly minimax-optimal algorithms in reinforcement learning with linear function approximation. While prior works have established gap-dependent regret bounds in this setting, existing analyses do not apply to algorithms that achieve the nearly minimax-optimal worst-case regret bound $\tilde{O}(d\sqrt{H^3K})$, where $d$ is the feature dimension, $H$ is the horizon length, and $K$ is the number of episodes. We bridge this gap by providing the first gap-dependent regret bound for the nearly minimax-optimal algorithm LSVI-UCB++ (He et al., 2023). Our analysis yields improved dependencies on both $d$ and $H$ compared to previous gap-dependent results. Moreover, leveraging the low policy-switching property of LSVI-UCB++, we introduce a concurrent variant that enables efficient parallel exploration across multiple agents and establish the first gap-dependent sample complexity upper bound for online multi-agent RL with linear function approximation, achieving linear speedup with respect to the number of agents. --- ### Learning to Solve Complex Problems via Dataset Decomposition Authors: Wanru Zhao, Lucas Caccia, Zhengyan Shi, Minseon Kim, Weijia Xu, Alessandro Sordoni Published: 2026-02-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.20296v1 Curriculum learning is a class of training strategies that organizes the data being exposed to a model by difficulty, gradually from simpler to more complex examples. This research explores a reverse curriculum generation approach that recursively decomposes complex datasets into simpler, more learnable components. We propose a teacher-student framework where the teacher is equipped with the ability to reason step-by-step, which is used to recursively generate easier versions of examples, enabling the student model to progressively master difficult tasks. We propose a novel scoring system to measure data difficulty based on its structural complexity and conceptual depth, allowing curriculum construction over decomposed data. Experiments on math datasets (MATH and AIME) and code generation datasets demonstrate that models trained with curricula generated by our approach exhibit superior performance compared to standard training on original datasets. --- ### InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation Authors: Yu Li, Pranav Narayanan Venkit, Yada Pruksachatkun, Chien-Sheng Wu Published: 2026-02-23 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.20294v1 Simulating real personalities with large language models requires grounding generation in authentic personal data. Existing evaluation approaches rely on demographic surveys, personality questionnaires, or short AI-led interviews as proxies, but lack direct assessment against what individuals actually said. We address this gap with an interview-grounded evaluation framework for personality simulation at a large scale. We extract over 671,000 question-answer pairs from 23,000 verified interview transcripts across 1,000 public personalities, each with an average of 11.5 hours of interview content. We propose a multi-dimensional evaluation framework with four complementary metrics measuring content similarity, factual consistency, personality alignment, and factual knowledge retention. Through systematic comparison, we demonstrate that methods grounded in real interview data substantially outperform those relying solely on biographical profiles or the model's parametric knowledge. We further reveal a trade-off in how interview data is best utilized: retrieval-augmented methods excel at capturing personality style and response quality, while chronological-based methods better preserve factual consistency and knowledge retention. Our evaluation framework enables principled method selection based on application requirements, and our empirical findings provide actionable insights for advancing personality simulation research. --- ### Discrete Diffusion with Sample-Efficient Estimators for Conditionals Authors: Karthik Elamvazhuthi, Abhijith Jayakumar, Andrey Y. Lokhov Published: 2026-02-23 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.20293v3 We study a discrete denoising diffusion framework that integrates a sample-efficient estimator of single-site conditionals with round-robin noising and denoising dynamics for generative modeling over discrete state spaces. Rather than approximating a discrete analog of a score function, our formulation treats single-site conditional probabilities as the fundamental objects that parameterize the reverse diffusion process. We employ a sample-efficient method known as Neural Interaction Screening Estimator (NeurISE) to estimate these conditionals in the diffusion dynamics. Controlled experiments on synthetic Ising models, MNIST, and scientific data sets produced by a D-Wave quantum annealer, synthetic Potts model and one dimensional quantum systems demonstrate the proposed approach. On the binary data sets, these experiments demonstrate that the proposed approach outperforms popular existing methods including ratio-based approaches, achieving improved performance in total variation, cross-correlations, and kernel density estimation metrics. --- ### Quantifying the Expectation-Realisation Gap for Agentic AI Systems Authors: Sebastian Lobentanzer Published: 2026-02-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.20292v2 Agentic AI systems are deployed with expectations of substantial productivity gains, yet rigorous empirical evidence reveals systematic discrepancies between pre-deployment expectations and post-deployment outcomes. We review controlled trials and independent validations across software engineering, clinical documentation, and clinical decision support to quantify this expectation-realisation gap. In software development, experienced developers expected a 24% speedup from AI tools but were slowed by 19% -- a 43 percentage-point calibration error. In clinical documentation, vendor claims of multi-minute time savings contrast with measured reductions of less than one minute per note, and one widely deployed tool showed no statistically significant effect. In clinical decision support, externally validated performance falls substantially below developer-reported metrics. These shortfalls are driven by workflow integration friction, verification burden, measurement construct mismatches, and systematic variation in who benefits and who does not. The evidence motivates structured planning frameworks that require explicit, quantified benefit expectations with human oversight costs factored in. --- ### De-rendering, Reasoning, and Repairing Charts with Vision-Language Models Authors: Valentin Bonas, Martin Sinnona, Viviana Siless, Emmanuel Iarussi Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20291v1 Data visualizations are central to scientific communication, journalism, and everyday decision-making, yet they are frequently prone to errors that can distort interpretation or mislead audiences. Rule-based visualization linters can flag violations, but they miss context and do not suggest meaningful design changes. Directly querying general-purpose LLMs about visualization quality is unreliable: lacking training to follow visualization design principles, they often produce inconsistent or incorrect feedback. In this work, we introduce a framework that combines chart de-rendering, automated analysis, and iterative improvement to deliver actionable, interpretable feedback on visualization design. Our system reconstructs the structure of a chart from an image, identifies design flaws using vision-language reasoning, and proposes concrete modifications supported by established principles in visualization research. Users can selectively apply these improvements and re-render updated figures, creating a feedback loop that promotes both higher-quality visualizations and the development of visualization literacy. In our evaluation on 1,000 charts from the Chart2Code benchmark, the system generated 10,452 design recommendations, which clustered into 10 coherent categories (e.g., axis formatting, color accessibility, legend consistency). These results highlight the promise of LLM-driven recommendation systems for delivering structured, principle-based feedback on visualization design, opening the door to more intelligent and accessible authoring tools. --- ### The Sim-to-Real Gap in MRS Quantification: A Systematic Deep Learning Validation for GABA Authors: Zien Ma, S. M. Shermer, Oktay Karakuş, Frank C. Langbein Published: 2026-02-23 Categories: eess.SP, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2602.20289v1 Magnetic resonance spectroscopy (MRS) is used to quantify metabolites in vivo and estimate biomarkers for conditions ranging from neurological disorders to cancers. Quantifying low-concentration metabolites such as GABA ($γ$-aminobutyric acid) is challenging due to low signal-to-noise ratio (SNR) and spectral overlap. We investigate and validate deep learning for quantifying complex, low-SNR, overlapping signals from MEGA-PRESS spectra, devise a convolutional neural network (CNN) and a Y-shaped autoencoder (YAE), and select the best models via Bayesian optimisation on 10,000 simulated spectra from slice-profile-aware MEGA-PRESS simulations. The selected models are trained on 100,000 simulated spectra. We validate their performance on 144 spectra from 112 experimental phantoms containing five metabolites of interest (GABA, Glu, Gln, NAA, Cr) with known ground truth concentrations across solution and gel series acquired at 3 T under varied bandwidths and implementations. These models are further assessed against the widely used LCModel quantification tool. On simulations, both models achieve near-perfect agreement (small MAEs; regression slopes $\approx 1.00$, $R^2 \approx 1.00$). On experimental phantom data, errors initially increased substantially. However, modelling variable linewidths in the training data significantly reduced this gap. The best augmented deep learning models achieved a mean MAE for GABA over all phantom spectra of 0.151 (YAE) and 0.160 (FCNN) in max-normalised relative concentrations, outperforming the conventional baseline LCModel (0.220). A sim-to-real gap remains, but physics-informed data augmentation substantially reduced it. Phantom ground truth is needed to judge whether a method will perform reliably on real data. --- ### The Truthfulness Spectrum Hypothesis Authors: Zhuofan Josh Ying, Shauli Ravfogel, Nikolaus Kriegeskorte, Peter Hase Published: 2026-02-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.20273v1 Large language models (LLMs) have been reported to linearly encode truthfulness, yet recent work questions this finding's generality. We reconcile these views with the truthfulness spectrum hypothesis: the representational space contains directions ranging from broadly domain-general to narrowly domain-specific. To test this hypothesis, we systematically evaluate probe generalization across five truth types (definitional, empirical, logical, fictional, and ethical), sycophantic and expectation-inverted lying, and existing honesty benchmarks. Linear probes generalize well across most domains but fail on sycophantic and expectation-inverted lying. Yet training on all domains jointly recovers strong performance, confirming that domain-general directions exist despite poor pairwise transfer. The geometry of probe directions explains these patterns: Mahalanobis cosine similarity between probes near-perfectly predicts cross-domain generalization (R^2=0.98). Concept-erasure methods further isolate truth directions that are (1) domain-general, (2) domain-specific, or (3) shared only across particular domain subsets. Causal interventions reveal that domain-specific directions steer more effectively than domain-general ones. Finally, post-training reshapes truth geometry, pushing sycophantic lying further from other truth types, suggesting a representational basis for chat models' sycophantic tendencies. Together, our results support the truthfulness spectrum hypothesis: truth directions of varying generality coexist in representational space, with post-training reshaping their geometry. Code for all experiments is provided in https://github.com/zfying/truth_spec. --- ### Uncertainty-Aware Delivery Delay Duration Prediction via Multi-Task Deep Learning Authors: Stefan Faulkner, Reza Zandehshahvar, Vahid Eghbal Akhlaghi, Sebastien Ouellet, Carsten Jordan, Pascal Van Hentenryck Published: 2026-02-23 Categories: cs.LG, cs.AI, math.OC, stat.AP arXiv: https://arxiv.org/abs/2602.20271v1 Accurate delivery delay prediction is critical for maintaining operational efficiency and customer satisfaction across modern supply chains. Yet the increasing complexity of logistics networks, spanning multimodal transportation, cross-country routing, and pronounced regional variability, makes this prediction task inherently challenging. This paper introduces a multi-task deep learning model for delivery delay duration prediction in the presence of significant imbalanced data, where delayed shipments are rare but operationally consequential. The model embeds high-dimensional shipment features with dedicated embedding layers for tabular data, and then uses a classification-then-regression strategy to predict the delivery delay duration for on-time and delayed shipments. Unlike sequential pipelines, this approach enables end-to-end training, improves the detection of delayed cases, and supports probabilistic forecasting for uncertainty-aware decision making. The proposed approach is evaluated on a large-scale real-world dataset from an industrial partner, comprising more than 10 million historical shipment records across four major source locations with distinct regional characteristics. The proposed model is compared with traditional machine learning methods. Experimental results show that the proposed method achieves a mean absolute error of 0.67-0.91 days for delayed-shipment predictions, outperforming single-step tree-based regression baselines by 41-64% and two-step classify-then-regress tree-based models by 15-35%. These gains demonstrate the effectiveness of the proposed model in operational delivery delay forecasting under highly imbalanced and heterogeneous conditions. --- ### Coupled Cluster con MōLe: Molecular Orbital Learning for Neural Wavefunctions Authors: Luca Thiede, Abdulrahman Aldossary, Andreas Burger, Jorge Arturo Campos-Gonzalez-Angulo, Ning Wang, Alexander Zook, Melisa Alkan, Kouhei Nakaji, Taylor Lee Patti, Jérôme Florian Gonthier, Mohammad Ghazi Vakili, Alán Aspuru-Guzik Published: 2026-02-23 Categories: cs.LG, physics.chem-ph arXiv: https://arxiv.org/abs/2602.20232v1 Density functional theory (DFT) is the most widely used method for calculating molecular properties; however, its accuracy is often insufficient for quantitative predictions. Coupled-cluster (CC) theory is the most successful method for achieving accuracy beyond DFT and for predicting properties that closely align with experiment. It is known as the ''gold standard'' of quantum chemistry. Unfortunately, the high computational cost of CC limits its widespread applicability. In this work, we present the Molecular Orbital Learning (MōLe) architecture, an equivariant machine learning model that directly predicts CC's core mathematical objects, the excitation amplitudes, from the mean-field Hartree-Fock molecular orbitals as inputs. We test various aspects of our model and demonstrate its remarkable data efficiency and out-of-distribution generalization to larger molecules and off-equilibrium geometries, despite being trained only on small equilibrium geometries. Finally, we also examine its ability to reduce the number of cycles required to converge CC calculations. MōLe can set the foundations for high-accuracy wavefunction-based ML architectures to accelerate molecular design and complement force-field approaches. --- ### UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models Authors: Manish Kumar Govind, Dominick Reilly, Pu Wang, Srijan Das Published: 2026-02-23 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.20231v2 Latent action representations learned from unlabeled videos have recently emerged as a promising paradigm for pretraining vision-language-action (VLA) models without explicit robot action supervision. However, latent actions derived solely from RGB observations primarily encode appearance-driven dynamics and lack explicit 3D geometric structure, which is essential for precise and contact-rich manipulation. To address this limitation, we introduce UniLACT, a transformer-based VLA model that incorporates geometric structure through depth-aware latent pretraining, enabling downstream policies to inherit stronger spatial priors. To facilitate this process, we propose UniLARN, a unified latent action learning framework based on inverse and forward dynamics objectives that learns a shared embedding space for RGB and depth while explicitly modeling their cross-modal interactions. This formulation produces modality-specific and unified latent action representations that serve as pseudo-labels for the depth-aware pretraining of UniLACT. Extensive experiments in both simulation and real-world settings demonstrate the effectiveness of depth-aware unified latent action representations. UniLACT consistently outperforms RGB-based latent action baselines under in-domain and out-of-domain pretraining regimes, as well as on both seen and unseen manipulation tasks.The project page is at https://manishgovind.github.io/unilact-vla/ --- ### Exploring Anti-Aging Literature via ConvexTopics and Large Language Models Authors: Lana E. Yeganova, Won G. Kim, Shubo Tian, Natalie Xie, Donald C. Comeau, W. John Wilbur, Zhiyong Lu Published: 2026-02-23 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.20224v1 The rapid expansion of biomedical publications creates challenges for organizing knowledge and detecting emerging trends, underscoring the need for scalable and interpretable methods. Common clustering and topic modeling approaches such as K-means or LDA remain sensitive to initialization and prone to local optima, limiting reproducibility and evaluation. We propose a reformulation of a convex optimization based clustering algorithm that produces stable, fine-grained topics by selecting exemplars from the data and guaranteeing a global optimum. Applied to about 12,000 PubMed articles on aging and longevity, our method uncovers topics validated by medical experts. It yields interpretable topics spanning from molecular mechanisms to dietary supplements, physical activity, and gut microbiota. The method performs favorably, and most importantly, its reproducibility and interpretability distinguish it from common clustering approaches, including K-means, LDA, and BERTopic. This work provides a basis for developing scalable, web-accessible tools for knowledge discovery. --- ### MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning Authors: Wall Kim, Chaeyoung Song, Hanul Kim Published: 2026-02-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.20223v3 Recently, TabPFN has gained attention as a foundation model for tabular data. However, it struggles to integrate heterogeneous modalities such as images and text, which are common in domains like healthcare and marketing, thereby limiting its applicability. To address this, we present the Multi-Modal Prior-data Fitted Network (MMPFN), which extends TabPFN to handle tabular and non-tabular modalities in a unified manner. MMPFN comprises per-modality encoders, modality projectors, and pre-trained foundation models. The modality projectors serve as the critical bridge, transforming non-tabular embeddings into tabular-compatible tokens for unified processing. To this end, we introduce a multi-head gated MLP and a cross-attention pooler that extract richer context from non-tabular inputs while mitigates attention imbalance issue in multimodal learning. Extensive experiments on medical and general-purpose multimodal datasets demonstrate that MMPFN consistently outperforms competitive state-of-the-art methods and effectively exploits non-tabular modalities alongside tabular features. These results highlight the promise of extending prior-data fitted networks to the multimodal setting, offering a scalable and effective framework for heterogeneous data learning. The source code is available at https://github.com/too-z/MultiModalPFN. --- ### What Matters for Simulation to Online Reinforcement Learning on Real Robots Authors: Yarden As, Dhruva Tirumala, René Zurbrügg, Chenhao Li, Stelian Coros, Andreas Krause, Markus Wulfmeier Published: 2026-02-23 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.20220v2 We investigate what specific design choices enable successful online reinforcement learning (RL) on physical robots. Across 100 real-world training runs on three distinct robotic platforms, we systematically ablate algorithmic, systems, and experimental decisions that are typically left implicit in prior work. We find that some widely used defaults can be harmful, while a set of robust, readily adopted design choices within standard RL practice yield stable learning across tasks and hardware. These results provide the first large-sample empirical study of such design choices, enabling practitioners to deploy online RL with lower engineering effort. --- ### An Approach to Combining Video and Speech with Large Language Models in Human-Robot Interaction Authors: Guanting Shen, Zi Tian Published: 2026-02-23 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.20219v1 Interpreting human intent accurately is a central challenge in human-robot interaction (HRI) and a key requirement for achieving more natural and intuitive collaboration between humans and machines. This work presents a novel multimodal HRI framework that combines advanced vision-language models, speech processing, and fuzzy logic to enable precise and adaptive control of a Dobot Magician robotic arm. The proposed system integrates Florence-2 for object detection, Llama 3.1 for natural language understanding, and Whisper for speech recognition, providing users with a seamless and intuitive interface for object manipulation through spoken commands. By jointly addressing scene perception and action planning, the approach enhances the reliability of command interpretation and execution. Experimental evaluations conducted on consumer-grade hardware demonstrate a command execution accuracy of 75\%, highlighting both the robustness and adaptability of the system. Beyond its current performance, the proposed architecture serves as a flexible and extensible foundation for future HRI research, offering a practical pathway toward more sophisticated and natural human-robot collaboration through tightly coupled speech and vision-language processing. --- ### KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem Authors: Seongjin Cha, Gyuwan Kim, Dongsu Han, Tao Yang, Insu Han Published: 2026-02-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.20217v2 Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore the dynamic computational overhead of attention in long-context scenarios. We propose KnapSpec, a training-free framework that reformulates draft model selection as a knapsack problem to maximize tokens-per-time throughput. By decoupling Attention and MLP layers and modeling their hardware-specific latencies as functions of context length, KnapSpec adaptively identifies optimal draft configurations on the fly via a parallel dynamic programming algorithm. Furthermore, we provide the first rigorous theoretical analysis establishing cosine similarity between hidden states as a mathematically sound proxy for the token acceptance rate. This foundation allows our method to maintain high drafting faithfulness while navigating the shifting bottlenecks of real-world hardware. Our experiments on Qwen3 and Llama3 demonstrate that KnapSpec consistently outperforms state-of-the-art SSD baselines, achieving up to 1.47x wall-clock speedup across various benchmarks. Our plug-and-play approach ensures high-speed inference for long sequences without requiring additional training or compromising the target model's output distribution. --- ### Right to History: A Sovereignty Kernel for Verifiable AI Agent Execution Authors: Jing Zhang Published: 2026-02-23 Categories: cs.CR, cs.AI, cs.OS arXiv: https://arxiv.org/abs/2602.20214v1 AI agents increasingly act on behalf of humans, yet no existing system provides a tamper-evident, independently verifiable record of what they did. As regulations such as the EU AI Act begin mandating automatic logging for high-risk AI systems, this gap carries concrete consequences -- especially for agents running on personal hardware, where no centralized provider controls the log. Extending Floridi's informational rights framework from data about individuals to actions performed on their behalf, this paper proposes the Right to History: the principle that individuals are entitled to a complete, verifiable record of every AI agent action on their own hardware. The paper formalizes this principle through five system invariants with structured proof sketches, and implements it in PunkGo, a Rust sovereignty kernel that unifies RFC 6962 Merkle tree audit logs, capability-based isolation, energy-budget governance, and a human-approval mechanism. Adversarial testing confirms all five invariants hold. Performance evaluation shows sub-1.3 ms median action latency, ~400 actions/sec throughput, and 448-byte Merkle inclusion proofs at 10,000 log entries. --- ### CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions Authors: Jingwei Shi, Xinxiang Yin, Jing Huang, Jinman Zhao, Shengyu Tao Published: 2026-02-23 Categories: cs.SE, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.20213v2 The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases. However, existing benchmarks often lack coverage for subtle corner cases, allowing incorrect solutions to pass. To bridge this gap, we propose CodeHacker, an automated agent framework dedicated to generating targeted adversarial test cases that expose latent vulnerabilities in program submissions. Mimicking the hack mechanism in competitive programming, CodeHacker employs a multi-strategy approach, including stress testing, anti-hash attacks, and logic-specific targeting to break specific code submissions. To ensure the validity and reliability of these attacks, we introduce a Calibration Phase, where the agent iteratively refines its own Validator and Checker via self-generated adversarial probes before evaluating contestant code.Experiments demonstrate that CodeHacker significantly improves the True Negative Rate (TNR) of existing datasets, effectively filtering out incorrect solutions that were previously accepted. Furthermore, generated adversarial cases prove to be superior training data, boosting the performance of RL-trained models on benchmarks like LiveCodeBench. --- ### Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling Authors: Kiyoung Seong, Sungsoo Ahn, Sehui Han, Changyoung Park Published: 2026-02-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.20210v3 Crystal modeling spans a family of conditional and unconditional generation tasks, including crystal structure prediction (CSP) and de novo generation (DNG). While recent deep generative models have shown promising performance, they remain largely task-specific, lacking a unified framework that shares crystal representations across tasks. To address this limitation, we propose Multimodal Crystal Flow (MCFlow), a unified multimodal flow model that realizes multiple crystal generation tasks as distinct inference trajectories via independent time variables for atom types and crystal structures. To enable multimodal flow in a standard transformer model, we introduce a composition- and symmetry-aware atom ordering with hierarchical permutation augmentation, injecting compositional and crystallographic priors without explicit structural templates. Experiments on the MP-20 and MPTS-52 benchmarks show that a single MCFlow model is competitive with task-specific baselines across CSP, DNG, and structure-conditioned atom type generation. --- ### Regressor-guided Diffusion Model for De Novo Peptide Sequencing with Explicit Mass Control Authors: Shaorong Chen, Jingbo Zhou, Jun Xia Published: 2026-02-23 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2602.20209v1 The discovery of novel proteins relies on sensitive protein identification, for which de novo peptide sequencing (DNPS) from mass spectra is a crucial approach. While deep learning has advanced DNPS, existing models inadequately enforce the fundamental mass consistency constraint, that a predicted peptide's mass must match the experimental measured precursor mass. Previous DNPS methods often treat this critical information as a simple input feature or use it in post-processing, leading to numerous implausible predictions that do not adhere to this fundamental physical property. To address this limitation, we introduce DiffuNovo, a novel regressor-guided diffusion model for de novo peptide sequencing that provides explicit peptide-level mass control. Our approach integrates the mass constraint at two critical stages: during training, a novel peptide-level mass loss guides model optimization, while at inference, regressor-based guidance from gradient-based updates in the latent space steers the generation to compel the predicted peptide adheres to the mass constraint. Comprehensive evaluations on established benchmarks demonstrate that DiffuNovo surpasses state-of-the-art methods in DNPS accuracy. Additionally, as the first DNPS model to employ a diffusion model as its core backbone, DiffuNovo leverages the powerful controllability of diffusion architecture and achieves a significant reduction in mass error, thereby producing much more physically plausible peptides. These innovations represent a substantial advancement toward robust and broadly applicable DNPS. The source code is available in the supplementary material. --- ### Model Merging in the Essential Subspace Authors: Longhua Li, Lei Qi, Qi Tian, Xin Geng Published: 2026-02-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.20208v2 Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model without additional training. Despite extensive research, task interference remains a major obstacle that often undermines the performance of merged models. In this paper, we propose ESM (Essential Subspace Merging) , a robust framework for effective model merging. We begin by performing Principal Component Analysis (PCA) on feature shifts induced by parameter updates. The resulting principal directions span an essential subspace that dominantly influences feature representations. Each task's parameter update matrix is projected onto its respective essential subspace for low-rank decomposition before merging. This methodology mitigates inter-task interference while preserving core task-specific functionality. Furthermore, we introduce a multi-level polarized scaling strategy that amplifies parameters containing critical knowledge and suppresses redundant ones, preventing essential knowledge from being overwhelmed during fusion. Extensive experiments across multiple task sets and model scales demonstrate that our method achieves state-of-the-art performance in multi-task model merging. Code is available at https://github.com/kiddo127/ESM. --- ### Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device Authors: Abdelrahman Shaker, Ahmed Heakl, Jaseel Muhammad, Ritesh Thawkar, Omkar Thawakar, Senmao Li, Hisham Cholakkal, Ian Reid, Eric P. Xing, Salman Khan, Fahad Shahbaz Khan Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20161v2 Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and too heavy for deployment on edge devices. We present Mobile-O, a compact vision-language-diffusion model that brings unified multimodal intelligence to a mobile device. Its core module, the Mobile Conditioning Projector (MCP), fuses vision-language features with a diffusion generator using depthwise-separable convolutions and layerwise alignment. This design enables efficient cross-modal conditioning with minimal computational cost. Trained on only a few million samples and post-trained in a novel quadruplet format (generation prompt, image, question, answer), Mobile-O jointly enhances both visual understanding and generation capabilities. Despite its efficiency, Mobile-O attains competitive or superior performance compared to other unified models, achieving 74% on GenEval and outperforming Show-O and JanusFlow by 5% and 11%, while running 6x and 11x faster, respectively. For visual understanding, Mobile-O surpasses them by 15.3% and 5.1% averaged across seven benchmarks. Running in only ~3s per 512x512 image on an iPhone, Mobile-O establishes the first practical framework for real-time unified multimodal understanding and generation on edge devices. We hope Mobile-O will ease future research in real-time unified multimodal intelligence running entirely on-device with no cloud dependency. Our code, models, datasets, and mobile application are publicly available at https://amshaker.github.io/Mobile-O/ --- ### tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction Authors: Chen Wang, Hao Tan, Wang Yifan, Zhiqin Chen, Yuheng Liu, Kalyan Sunkavalli, Sai Bi, Lingjie Liu, Yiwei Hu Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20160v2 We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear computational complexity, further scaling the model's capability. Our framework efficiently compresses multiple image observations into the fast weights of the TTT layer, forming an implicit 3D representation in the latent space that can be decoded into various explicit formats, such as Gaussian Splats (GS) for downstream applications. The online learning variant of our model supports progressive 3D reconstruction and refinement from streaming observations. We demonstrate that pretraining on novel view synthesis tasks effectively transfers to explicit 3D modeling, resulting in improved reconstruction quality and faster convergence. Extensive experiments show that our method achieves superior performance in feedforward 3D Gaussian reconstruction compared to state-of-the-art approaches on both objects and scenes. --- ### A Very Big Video Reasoning Suite Authors: Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thaddäus Wiedemer, Qingying Gao, Dezhi Luo, Yaoyao Qian, Lianyu Huang, Zelong Hong, Jiahui Ge, Qianli Ma et al. Published: 2026-02-23 Categories: cs.CV, cs.AI, cs.LG, cs.MM, cs.RO arXiv: https://arxiv.org/abs/2602.20159v4 Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over spatiotemporal structure such as continuity, interaction, and causality. However, systematically studying video reasoning and its scaling behavior is hindered by the lack of large-scale training data. To address this gap, we introduce the Very Big Video Reasoning (VBVR) Dataset, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets. We further present VBVR-Bench, a verifiable evaluation framework that moves beyond model-based judging by incorporating rule-based, human-aligned scorers, enabling reproducible and interpretable diagnosis of video reasoning capabilities. Leveraging the VBVR suite, we conduct one of the first large-scale scaling studies of video reasoning and observe early signs of emergent generalization to unseen reasoning tasks. Together, VBVR lays a foundation for the next stage of research in generalizable video reasoning. The data, benchmark toolkit, and models are publicly available at https://video-reason.com/?v=vbvr . --- ### A Very Big Video Reasoning Suite Authors: Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thaddäus Wiedemer, Qingying Gao, Dezhi Luo, Yaoyao Qian, Lianyu Huang, Zelong Hong, Jiahui Ge, Qianli Ma et al. Published: 2026-02-23 Categories: cs.CV, cs.AI, cs.LG, cs.MM, cs.RO arXiv: https://arxiv.org/abs/2602.20159v2 Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over spatiotemporal structure such as continuity, interaction, and causality. However, systematically studying video reasoning and its scaling behavior is hindered by the lack of large-scale training data. To address this gap, we introduce the Very Big Video Reasoning (VBVR) Dataset, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets. We further present VBVR-Bench, a verifiable evaluation framework that moves beyond model-based judging by incorporating rule-based, human-aligned scorers, enabling reproducible and interpretable diagnosis of video reasoning capabilities. Leveraging the VBVR suite, we conduct one of the first large-scale scaling studies of video reasoning and observe early signs of emergent generalization to unseen reasoning tasks. Together, VBVR lays a foundation for the next stage of research in generalizable video reasoning. The data, benchmark toolkit, and models are publicly available at https://video-reason.com/ . --- ### Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning Authors: Zhongxiao Cong, Qitao Zhao, Minsik Jeon, Shubham Tulsiani Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20157v1 Current feed-forward 3D/4D reconstruction systems rely on dense geometry and pose supervision -- expensive to obtain at scale and particularly scarce for dynamic real-world scenes. We present Flow3r, a framework that augments visual geometry learning with dense 2D correspondences (`flow') as supervision, enabling scalable training from unlabeled monocular videos. Our key insight is that the flow prediction module should be factored: predicting flow between two images using geometry latents from one and pose latents from the other. This factorization directly guides the learning of both scene geometry and camera motion, and naturally extends to dynamic scenes. In controlled experiments, we show that factored flow prediction outperforms alternative designs and that performance scales consistently with unlabeled data. Integrating factored flow into existing visual geometry architectures and training with ${\sim}800$K unlabeled videos, Flow3r achieves state-of-the-art results across eight benchmarks spanning static and dynamic scenes, with its largest gains on in-the-wild dynamic videos where labeled data is most scarce. --- ### Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks Authors: David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi, Maksym Andriushchenko Published: 2026-02-23 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2602.20156v3 LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this can extend agent capabilities to new domains, it creates an increasingly complex agent supply chain, offering new surfaces for prompt injection attacks. We identify skill-based prompt injection as a significant threat and introduce SkillInject, a benchmark evaluating the susceptibility of widely-used LLM agents to injections through skill files. SkillInject contains 202 injection-task pairs with attacks ranging from obviously malicious injections to subtle, context-dependent attacks hidden in otherwise legitimate instructions. We evaluate frontier LLMs on SkillInject, measuring both security in terms of harmful instruction avoidance and utility in terms of legitimate instruction compliance. Our results show that today's agents are highly vulnerable with up to 80% attack success rate with frontier models, often executing extremely harmful instructions including data exfiltration, destructive action, and ransomware-like behavior. They furthermore suggest that this problem will not be solved through model scaling or simple input filtering, but that robust agent security will require context-aware authorization frameworks. Our benchmark is available at https://www.skill-inject.com/. --- ### JUCAL: Jointly Calibrating Aleatoric and Epistemic Uncertainty in Classification Tasks Authors: Jakob Heiss, Sören Lambrecht, Jakob Weissteiner, Hanna Wutte, Žan Žurič, Josef Teichmann, Bin Yu Published: 2026-02-23 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2602.20153v1 We study post-calibration uncertainty for trained ensembles of classifiers. Specifically, we consider both aleatoric (label noise) and epistemic (model) uncertainty. Among the most popular and widely used calibration methods in classification are temperature scaling (i.e., pool-then-calibrate) and conformal methods. However, the main shortcoming of these calibration methods is that they do not balance the proportion of aleatoric and epistemic uncertainty. Not balancing these uncertainties can severely misrepresent predictive uncertainty, leading to overconfident predictions in some input regions while being underconfident in others. To address this shortcoming, we present a simple but powerful calibration algorithm Joint Uncertainty Calibration (JUCAL) that jointly calibrates aleatoric and epistemic uncertainty. JUCAL jointly calibrates two constants to weight and scale epistemic and aleatoric uncertainties by optimizing the negative log-likelihood (NLL) on the validation/calibration dataset. JUCAL can be applied to any trained ensemble of classifiers (e.g., transformers, CNNs, or tree-based methods), with minimal computational overhead, without requiring access to the models' internal parameters. We experimentally evaluate JUCAL on various text classification tasks, for ensembles of varying sizes and with different ensembling strategies. Our experiments show that JUCAL significantly outperforms SOTA calibration methods across all considered classification tasks, reducing NLL and predictive set size by up to 15% and 20%, respectively. Interestingly, even applying JUCAL to an ensemble of size 5 can outperform temperature-scaled ensembles of size up to 50 in terms of NLL and predictive set size, resulting in up to 10 times smaller inference costs. Thus, we propose JUCAL as a new go-to method for calibrating ensembles in classification. --- ### Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data Authors: Zhenyao Ma, Yue Liang, Dongxu Li Published: 2026-02-23 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.20152v1 Inspired by behavioral science, we propose Behavior Learning (BL), a novel general-purpose machine learning framework that learns interpretable and identifiable optimization structures from data, ranging from single optimization problems to hierarchical compositions. It unifies predictive performance, intrinsic interpretability, and identifiability, with broad applicability to scientific domains involving optimization. BL parameterizes a compositional utility function built from intrinsically interpretable modular blocks, which induces a data distribution for prediction and generation. Each block represents and can be written in symbolic form as a utility maximization problem (UMP), a foundational paradigm in behavioral science and a universal framework of optimization. BL supports architectures ranging from a single UMP to hierarchical compositions, the latter modeling hierarchical optimization structures. Its smooth and monotone variant (IBL) guarantees identifiability. Theoretically, we establish the universal approximation property of BL, and analyze the M-estimation properties of IBL. Empirically, BL demonstrates strong predictive performance, intrinsic interpretability and scalability to high-dimensional data. Code: https://github.com/MoonYLiang/Behavior-Learning ; install via pip install blnetwork. --- ### Conformal Risk Control for Non-Monotonic Losses Authors: Anastasios N. Angelopoulos Published: 2026-02-23 Categories: stat.ME, cs.LG, math.ST, stat.ML arXiv: https://arxiv.org/abs/2602.20151v1 Conformal risk control is an extension of conformal prediction for controlling risk functions beyond miscoverage. The original algorithm controls the expected value of a loss that is monotonic in a one-dimensional parameter. Here, we present risk control guarantees for generic algorithms applied to possibly non-monotonic losses with multidimensional parameters. The guarantees depend on the stability of the algorithm -- unstable algorithms have looser guarantees. We give applications of this technique to selective image classification, FDR and IOU control of tumor segmentations, and multigroup debiasing of recidivism predictions across overlapping race and sex groups using empirical risk minimization. --- ### Simulation-Ready Cluttered Scene Estimation via Physics-aware Joint Shape and Pose Optimization Authors: Wei-Cheng Huang, Jiaheng Han, Xiaohan Ye, Zherong Pan, Kris Hauser Published: 2026-02-23 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.20150v3 Estimating simulation-ready scenes from real-world observations is crucial for downstream planning and policy learning tasks. Regretfully, existing methods struggle in cluttered environments, often exhibiting prohibitive computational cost, poor robustness, and restricted generality when scaling to multiple interacting objects. We propose a unified optimization-based formulation for real-to-sim scene estimation that jointly recovers the shapes and poses of multiple rigid objects under physical constraints. Our method is built on two key technical innovations. First, we leverage the recently introduced shape-differentiable contact model, whose global differentiability permits joint optimization over object geometry and pose while modeling inter-object contacts. Second, we exploit the structured sparsity of the augmented Lagrangian Hessian to derive an efficient linear system solver whose computational cost scales favorably with scene complexity. Building on this formulation, we develop an end-to-end Simulation-ready Physics-Aware Reconstruction for Cluttered Scenes (SPARCS) pipeline, which integrates learning-based object initialization, physics-constrained joint shape-pose optimization, and differentiable texture refinement. Experiments on cluttered scenes with up to 5 objects and 22 convex hulls demonstrate that our approach robustly reconstructs physically valid, simulation-ready object shapes and poses. Project webpage: https://rory-weicheng.github.io/SPARCS/. --- ### Agentic AI for Scalable and Robust Optical Systems Control Authors: Zehao Wang, Mingzhe Han, Wei Cheng, Yue-Kai Huang, Philip Ji, Denton Wu, Mahdi Safari, Flemming Holtorf, Kenaish AlQubaisi, Norbert M. Linke, Danyang Zhuo, Yiran Chen et al. Published: 2026-02-23 Categories: eess.SY, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2602.20144v2 We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interprets natural language tasks and executes protocol-compliant actions on heterogeneous optical devices through a structured tool abstraction layer. We implement 64 standardized MCP tools across 8 representative optical devices and construct a 410-task benchmark to evaluate request understanding, role-aware responses, multi-step coordination, robustness to linguistic variation, and error handling. We assess two deployment configurations--commercial online LLMs and locally hosted open-source LLMs--and compare them with LLM-based code generation baselines. AgentOptics achieves 87.7%--99.0% average task success rates, significantly outperforming code-generation approaches, which reach up to 50% success. We further demonstrate broader applicability through five case studies extending beyond device-level control to system orchestration, monitoring, and closed-loop optimization. These include DWDM link provisioning and coordinated monitoring of coherent 400 GbE and analog radio-over-fiber (ARoF) channels; autonomous characterization and bias optimization of a wideband ARoF link carrying 5G fronthaul traffic; multi-span channel provisioning with launch power optimization; closed-loop fiber polarization stabilization; and distributed acoustic sensing (DAS)-based fiber monitoring with LLM-assisted event detection. These results establish AgentOptics as a scalable, robust paradigm for autonomous control and orchestration of heterogeneous optical systems. --- ### Agentic AI for Scalable and Robust Optical Systems Control Authors: Zehao Wang, Mingzhe Han, Wei Cheng, Yue-Kai Huang, Philip Ji, Denton Wu, Mahdi Safari, Flemming Holtorf, Kenaish AlQubaisi, Norbert M. Linke, Danyang Zhuo, Yiran Chen et al. Published: 2026-02-23 Categories: eess.SY, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2602.20144v1 We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interprets natural language tasks and executes protocol-compliant actions on heterogeneous optical devices through a structured tool abstraction layer. We implement 64 standardized MCP tools across 8 representative optical devices and construct a 410-task benchmark to evaluate request understanding, role-aware responses, multi-step coordination, robustness to linguistic variation, and error handling. We assess two deployment configurations--commercial online LLMs and locally hosted open-source LLMs--and compare them with LLM-based code generation baselines. AgentOptics achieves 87.7%--99.0% average task success rates, significantly outperforming code-generation approaches, which reach up to 50% success. We further demonstrate broader applicability through five case studies extending beyond device-level control to system orchestration, monitoring, and closed-loop optimization. These include DWDM link provisioning and coordinated monitoring of coherent 400 GbE and analog radio-over-fiber (ARoF) channels; autonomous characterization and bias optimization of a wideband ARoF link carrying 5G fronthaul traffic; multi-span channel provisioning with launch power optimization; closed-loop fiber polarization stabilization; and distributed acoustic sensing (DAS)-based fiber monitoring with LLM-assisted event detection. These results establish AgentOptics as a scalable, robust paradigm for autonomous control and orchestration of heterogeneous optical systems. --- ### Recurrent Structural Policy Gradient for Partially Observable Mean Field Games Authors: Clarisse Wibault, Johannes Forkel, Sebastian Towers, Tiphaine Wibault, Juan Duque, George Whittle, Andreas Schaab, Yucheng Yang, Chiyuan Wang, Maike Osborne, Benjamin Moll, Jakob Foerster Published: 2026-02-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.20141v2 Mean Field Games (MFGs) provide a principled framework for modelling interactions in large population systems. However, algorithmic progress has been limited since model-free methods are high variance and exact methods scale poorly. Recent Hybrid Structural Methods (HSMs) reduce variance while maintaining tractability by leveraging low-dimensional individual state and action spaces and known transition dynamics to compute the exact expected return conditioned on Monte Carlo rollouts of common noise. However, HSMs have not been extended to partially observable settings. We propose Recurrent Structural Policy Gradient (RSPG), the first history-aware HSM for MFGs with public partial information. RSPG achieves an order-of-magnitude faster convergence than model-free RL methods while learning history-aware behaviour, unlike current HSMs. To facilitate research into MFGs, we also introduce MFAX, our JAX-based framework for MFGs that supports both analytic and sample-based mean-field updates. MFAX and usage examples can be found at https://clarisse-wibault.github.io/rspg/. --- ### Do Large Language Models Understand Data Visualization Rules? Authors: Martin Sinnona, Valentin Bonas, Emmanuel Iarussi, Viviana Siless Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20137v1 Data visualization rules-derived from decades of research in design and perception-ensure trustworthy chart communication. While prior work has shown that large language models (LLMs) can generate charts or flag misleading figures, it remains unclear whether they can reason about and enforce visualization rules directly. Constraint-based systems such as Draco encode these rules as logical constraints for precise automated checks, but maintaining symbolic encodings requires expert effort, motivating the use of LLMs as flexible rule validators. In this paper, we present the first systematic evaluation of LLMs against visualization rules using hard-verification ground truth derived from Answer Set Programming (ASP). We translated a subset of Draco's constraints into natural-language statements and generated a controlled dataset of 2,000 Vega-Lite specifications annotated with explicit rule violations. LLMs were evaluated on both accuracy in detecting violations and prompt adherence, which measures whether outputs follow the required structured format. Results show that frontier models achieve high adherence (Gemma 3 4B / 27B: 100%, GPT-oss 20B: 98%) and reliably detect common violations (F1 up to 0.82),yet performance drops for subtler perceptual rules (F1 < 0.15 for some categories) and for outputs generated from technical ASP formulations.Translating constraints into natural language improved performance by up to 150% for smaller models. These findings demonstrate the potential of LLMs as flexible, language-driven validators while highlighting their current limitations compared to symbolic solvers. --- ### KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration Authors: Mohammad Amanlou, Erfan Shafiee Moghaddam, Yasaman Amou Jafari, Mahdi Noori, Farhan Farsi, Behnam Bahrak Published: 2026-02-23 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2602.20135v1 With the rise of large language models (LLMs), they have become instrumental in applications such as Retrieval-Augmented Generation (RAG). Yet evaluating these systems remains bottlenecked by the time and cost of building specialized assessment datasets. We introduce KNIGHT, an LLM-based, knowledge-graph-driven framework for generating multiple-choice question (MCQ) datasets from external sources. KNIGHT constructs a topic-specific knowledge graph, a structured and parsimonious summary of entities and relations, that can be reused to generate instructor-controlled difficulty levels, including multi-hop questions, without repeatedly re-feeding the full source text. This knowledge graph acts as a compressed, reusable state, making question generation a cheap read over the graph. We instantiate KNIGHT on Wikipedia/Wikidata while keeping the framework domain- and ontology-agnostic. As a case study, KNIGHT produces six MCQ datasets in History, Biology, and Mathematics. We evaluate quality on five criteria: fluency, unambiguity (single correct answer), topic relevance, option uniqueness, and answerability given the provided sources (as a proxy for hallucination). Results show that KNIGHT enables token- and cost-efficient generation from a reusable graph representation, achieves high quality across these criteria, and yields model rankings aligned with MMLU-style benchmarks, while supporting topic-specific and difficulty-controlled evaluation. --- ### Adversarial Data Modeling in Epidemiology Authors: Yiqi Su, Christo Kurisummoottil Thomas, Walid Saad, Sanmay Das, Bud Mishra, Naren Ramakrishnan Published: 2026-02-23 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2602.20134v2 Epidemiological models increasingly rely on crowdsourced, self-reported behavioral data such as vaccination status, mask usage, and social distancing adherence. This data, however, is not passively sampled but instead strategically reported, making it a canonical case of adversarial input to a data mining pipeline. Individuals misreport for various reasons, e.g., to avoid penalties, to access benefits, or to express distrust in public health authorities. We introduce a data-modeling framework that casts the interaction between the population and a public health authority as a signaling game. This approach provides both a generative model of strategically-corrupted behavioral data and a mechanism for the receiver to recover reliable signal from it. Individuals (senders) choose how to report their behaviors, while the public health authority (receiver) updates their epidemiological model(s) based on potentially distorted signals, and modifies its trust in incoming reports accordingly. Focusing on deception around masking and vaccination, we characterize analytically game equilibrium outcomes as distinct regimes of data corruption, and evaluate the degree to which deception can be tolerated while maintaining epidemic control through policy interventions. In large scale simulations, our results show that even under pervasive dishonesty in pooling equilibria, well-designed sender and receiver strategies can still maintain effective epidemic control. Real-world validation further shows that behavioral distortions often exhibit structured patterns rather than arbitrary noise. This work advances the understanding of adversarial data in epidemiology and offers tools for designing more robust public health models in the presence of strategic user behavior. --- ### Modeling Epidemiological Dynamics Under Adversarial Data and User Deception Authors: Yiqi Su, Christo Kurisummoottil Thomas, Walid Saad, Bud Mishra, Naren Ramakrishnan Published: 2026-02-23 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2602.20134v1 Epidemiological models increasingly rely on self-reported behavioral data such as vaccination status, mask usage, and social distancing adherence to forecast disease transmission and assess the impact of non-pharmaceutical interventions (NPIs). While such data provide valuable real-time insights, they are often subject to strategic misreporting, driven by individual incentives to avoid penalties, access benefits, or express distrust in public health authorities. To account for such human behavior, in this paper, we introduce a game-theoretic framework that models the interaction between the population and a public health authority as a signaling game. Individuals (senders) choose how to report their behaviors, while the public health authority (receiver) updates their epidemiological model(s) based on potentially distorted signals. Focusing on deception around masking and vaccination, we characterize analytically game equilibrium outcomes and evaluate the degree to which deception can be tolerated while maintaining epidemic control through policy interventions. Our results show that separating equilibria-with minimal deception-drive infections to near zero over time. Remarkably, even under pervasive dishonesty in pooling equilibria, well-designed sender and receiver strategies can still maintain effective epidemic control. This work advances the understanding of adversarial data in epidemiology and offers tools for designing more robust public health models in the presence of strategic user behavior. --- ### AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization Authors: Mert Cemri, Shubham Agrawal, Akshat Gupta, Shu Liu, Audrey Cheng, Qiuyang Mang, Ashwin Naren, Lutfi Eren Erdogan, Koushik Sen, Matei Zaharia, Alex Dimakis, Ion Stoica Published: 2026-02-23 Categories: cs.NE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.20133v1 The paradigm of automated program generation is shifting from one-shot generation to inference-time search, where Large Language Models (LLMs) function as semantic mutation operators within evolutionary loops. While effective, these systems are currently governed by static schedules that fail to account for the non-stationary dynamics of the search process. This rigidity results in substantial computational waste, as resources are indiscriminately allocated to stagnating populations while promising frontiers remain under-exploited. We introduce AdaEvolve, a framework that reformulates LLM-driven evolution as a hierarchical adaptive optimization problem. AdaEvolve uses an "accumulated improvement signal" to unify decisions across three levels: Local Adaptation, which dynamically modulates the exploration intensity within a population of solution candidates; Global Adaptation, which routes the global resource budget via bandit-based scheduling across different solution candidate populations; and Meta-Guidance which generates novel solution tactics based on the previously generated solutions and their corresponding improvements when the progress stalls. We demonstrate that AdaEvolve consistently outperforms the open-sourced baselines across 185 different open-ended optimization problems including combinatorial, systems optimization and algorithm design problems. --- ### LAD: Learning Advantage Distribution for Reasoning Authors: Wendi Li, Sharon Li Published: 2026-02-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.20132v1 Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to dominant reward signals, while neglecting alternative yet valid reasoning trajectories, thereby limiting diversity and exploration. To address this issue, we introduce Learning Advantage Distributions (LAD), a distribution-matching framework that replaces advantage maximization with learning the advantage-induced distribution. By establishing the equivalence between the optimal policy update and an advantage-based target distribution, we derive a practical LAD objective formulated as minimizing an $f$-divergence between the policy-induced and advantage-induced distributions. This yields a gradient update that increases likelihood for high-advantage responses while suppressing over-confident probability growth, preventing collapse without requiring auxiliary entropy regularization. LAD incurs no extra training cost compared to GRPO and scales naturally to LLM post-training. In a controlled bandit setting, LAD faithfully recovers the multimodal advantage distribution, validating the theoretical formulation. Experiments on math and code reasoning tasks across several LLM backbones show that LAD reliably improves both accuracy and generative diversity. --- ### To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering Authors: Zaifu Zhan, Min Zeng, Shuang Zhou, Yiran Song, Xiaoyi Chen, Yu Hou, Yifan Wu, Yang Ruan, Rui Zhang Published: 2026-02-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.20130v1 Objective: To improve the efficiency of medical question answering (MedQA) with large language models (LLMs) by avoiding unnecessary reasoning while maintaining accuracy. Methods: We propose Selective Chain-of-Thought (Selective CoT), an inference-time strategy that first predicts whether a question requires reasoning and generates a rationale only when needed. Two open-source LLMs (Llama-3.1-8B and Qwen-2.5-7B) were evaluated on four biomedical QA benchmarks-HeadQA, MedQA-USMLE, MedMCQA, and PubMedQA. Metrics included accuracy, total generated tokens, and inference time. Results: Selective CoT reduced inference time by 13-45% and token usage by 8-47% with minimal accuracy loss ($\leq$4\%). In some model-task pairs, it achieved both higher accuracy and greater efficiency than standard CoT. Compared with fixed-length CoT, Selective CoT reached similar or superior accuracy at substantially lower computational cost. Discussion: Selective CoT dynamically balances reasoning depth and efficiency by invoking explicit reasoning only when beneficial, reducing redundancy on recall-type questions while preserving interpretability. Conclusion: Selective CoT provides a simple, model-agnostic, and cost-effective approach for medical QA, aligning reasoning effort with question complexity to enhance real-world deployability of LLM-based clinical systems. --- ### Adaptation to Intrinsic Dependence in Diffusion Language Models Authors: Yunxiao Zhao, Changxiao Cai Published: 2026-02-23 Categories: cs.LG, cs.IT, math.ST, stat.ML arXiv: https://arxiv.org/abs/2602.20126v1 Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive (AR) approaches, enabling parallel token generation beyond a rigid left-to-right order. Despite growing empirical success, the theoretical understanding of how unmasking schedules -- which specify the order and size of unmasked tokens during sampling -- affect generation quality remains limited. In this work, we introduce a distribution-agnostic unmasking schedule for DLMs that adapts to the (unknown) dependence structure of the target data distribution, without requiring any prior knowledge or hyperparameter tuning. In contrast to prior deterministic procedures that fix unmasking sizes, our method randomizes the number of tokens revealed at each iteration. We show that, for two specific parameter choices, the sampling convergence guarantees -- measured by Kullback-Leibler (KL) divergence -- scale as $\widetilde O(\mathsf{TC}/K)$ and $\widetilde O(\mathsf{DTC}/K)$ respectively. Here, $K$ is the number of iterations, and $\mathsf{TC}$ and $\mathsf{DTC}$ are the total correlation and dual total correlation of the target distribution, capturing the intrinsic dependence structure underlying the data. Importantly, our guarantees hold in the practically relevant parallel-sampling regime $K<L$ where $L$ is the token sequence length. These results significantly improve upon prior convergence theories and yield substantial sampling acceleration for low-complexity distributions. Overall, our findings unveil the adaptivity of DLMs to intrinsic data structures and shed light on the benefit of randomized unmasking sizes in inference schedule design. --- ### NanoKnow: How to Know What Your Language Model Knows Authors: Lingwei Gu, Nour Jedidi, Jimmy Lin Published: 2026-02-23 Categories: cs.CL, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2602.20122v2 How do large language models (LLMs) know what they know? Answering this question has been difficult because pre-training data is often a "black box" - unknown or inaccessible. The recent release of nanochat - a family of small LLMs with fully open pre-training data - addresses this as it provides a transparent view into where a model's parametric knowledge comes from. Towards the goal of understanding how knowledge is encoded by LLMs, we release NanoKnow, a benchmark dataset that partitions questions from Natural Questions and SQuAD into splits based on whether their answers are present in nanochat's pre-training corpus. Using these splits, we can now properly disentangle the sources of knowledge that LLMs rely on when producing an output. To demonstrate NanoKnow's utility, we conduct experiments using eight nanochat checkpoints. Our findings show: (1) closed-book accuracy is strongly influenced by answer frequency in the pre-training data, (2) providing external evidence can mitigate this frequency dependence, (3) even with external evidence, models are more accurate when answers were seen during pre-training, demonstrating that parametric and external knowledge are complementary, and (4) non-relevant information is harmful, with accuracy decreasing based on both the position and the number of non-relevant contexts. We release all NanoKnow artifacts at https://github.com/castorini/NanoKnow. ---