# Research Papers — 2026-02 · bundle page 75 of 210 > Full-text markdown of papers #3701–3750 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/75 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/74.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/76.md) ### ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization Authors: Junbo Jacob Lian, Yujun Sun, Huiling Chen, Chaoyu Zhang, Hanzhang Qin, Chung-Piaw Teo Published: 2026-02-17 Categories: cs.SE, cs.AI, cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.15983v4 Large language models (LLMs) can translate natural-language problem descriptions into optimization code, but the code is prone to silent failures: it executes and returns a solver-feasible solution while encoding a semantically incorrect formulation. On compositional problems, the resulting feasibility-correctness gap reaches 90 percentage points. We introduce ReLoop, which combines two mechanisms. Structured generation decomposes code production into a four-stage reasoning chain (understand, formalize, synthesize, verify) to reduce formulation errors during generation. Behavioral verification detects the errors that remain by testing whether the formulation responds correctly to solver-based parameter perturbation, a signal that comes from the solver rather than from LLM self-review and requires no ground truth. The two mechanisms address different error structures: structured generation gives the largest gain on compositional problems (+8.5pp accuracy on RetailOpt-190 with Claude Opus 4.6), and behavioral verification gives its largest gain on localized defects (+4.4pp on MAMO-ComplexLP). With diagnostic execution recovery, ReLoop reaches 100% executable code on Claude Opus 4.6, and relative to direct generation it raises or preserves every reported metric of the three chat-tuned foundation models on all three benchmarks. For the narrowly fine-tuned SFT model we test, the chain-of-thought prompt conflicts with its learned output format and lowers its accuracy on MAMO-ComplexLP; we document and analyze this interaction. We release RetailOpt-190, 190 compositional retail optimization scenarios in which several constraints interact. --- ### ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization Authors: Junbo Jacob Lian, Yujun Sun, Huiling Chen, Chaoyu Zhang, Hanzhang Qin, Chung-Piaw Teo Published: 2026-02-17 Categories: cs.SE, cs.AI, cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.15983v2 Large language models (LLMs) can translate natural language into optimization code, but silent failures pose a critical risk: code that executes and returns solver-feasible solutions may encode semantically incorrect formulations -- a feasibility-correctness gap reaching 90 percentage points on compositional problems. We introduce ReLoop, which addresses this gap through two complementary mechanisms. Structured generation decomposes code production into a four-stage reasoning chain (understand, formalize, synthesize, verify), preventing formulation errors at their source. Behavioral verification detects errors that survive generation by testing whether the formulation responds correctly to solver-based parameter perturbation -- an external semantic signal that bypasses LLM self-review and requires no ground truth. The two mechanisms are complementary by error structure: structured generation drives the largest gains on compositional problems (+8.5pp accuracy on RetailOpt-190 with Claude Opus 4.6), while behavioral verification dominates on localized defects (+4.4pp on MAMO-ComplexLP, its largest contribution across benchmarks). Combined with diagnostic execution recovery, ReLoop reaches 100% executable code on Claude Opus 4.6 and consistently improves accuracy on chat-tuned foundation models across three benchmarks; we further identify a known limitation of narrowly-tuned SFT models, whose learned output formats are brittle to chain-of-thought prompts -- an interaction we document and analyze. We release RetailOpt-190, 190 compositional retail optimization scenarios targeting the multi-constraint interactions where LLMs most frequently fail. --- ### LAND: A Longitudinal Analysis of Neuromorphic Datasets Authors: Gregory Cohen, Alexandre Marcireau Published: 2026-02-17 Categories: cs.CV, cs.DB arXiv: https://arxiv.org/abs/2602.15973v1 Neuromorphic engineering has a data problem. Despite the meteoric rise in the number of neuromorphic datasets published over the past ten years, the conclusion of a significant portion of neuromorphic research papers still states that there is a need for yet more data and even larger datasets. Whilst this need is driven in part by the sheer volume of data required by modern deep learning approaches, it is also fuelled by the current state of the available neuromorphic datasets and the difficulties in finding them, understanding their purpose, and determining the nature of their underlying task. This is further compounded by practical difficulties in downloading and using these datasets. This review starts by capturing a snapshot of the existing neuromorphic datasets, covering over 423 datasets, and then explores the nature of their tasks and the underlying structure of the presented data. Analysing these datasets shows the difficulties arising from their size, the lack of standardisation, and difficulties in accessing the actual data. This paper also highlights the growth in the size of individual datasets and the complexities involved in working with the data. However, a more important concern is the rise of synthetic datasets, created by either simulation or video-to-events methods. This review explores the benefits of simulated data for testing existing algorithms and applications, highlighting the potential pitfalls for exploring new applications of neuromorphic technologies. This review also introduces the concepts of meta-datasets, created from existing datasets, as a way of both reducing the need for more data, and to remove potential bias arising from defining both the dataset and the task. --- ### Fast Online Learning with Gaussian Prior-Driven Hierarchical Unimodal Thompson Sampling Authors: Tianchi Zhao, He Liu, Hongyin Shi, Jinliang Li Published: 2026-02-17 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.15972v1 We study a type of Multi-Armed Bandit (MAB) problems in which arms with a Gaussian reward feedback are clustered. Such an arm setting finds applications in many real-world problems, for example, mmWave communications and portfolio management with risky assets, as a result of the universality of the Gaussian distribution. Based on the Thompson Sampling algorithm with Gaussian prior (TSG) algorithm for the selection of the optimal arm, we propose our Thompson Sampling with Clustered arms under Gaussian prior (TSCG) specific to the 2-level hierarchical structure. We prove that by utilizing the 2-level structure, we can achieve a lower regret bound than we do with ordinary TSG. In addition, when the reward is Unimodal, we can reach an even lower bound on the regret by our Unimodal Thompson Sampling algorithm with Clustered Arms under Gaussian prior (UTSCG). Each of our proposed algorithms are accompanied by theoretical evaluation of the upper regret bound, and our numerical experiments confirm the advantage of our proposed algorithms. --- ### B-DENSE: Branching For Dense Ensemble Network Supervision Efficiency Authors: Cherish Puniani, Tushar Kumar, Arnav Bendre, Gaurav Kumar, Shree Singhi Published: 2026-02-17 Categories: cs.LG, cs.AI, cs.CV, cs.NE arXiv: https://arxiv.org/abs/2602.15971v2 Inspired by non-equilibrium thermodynamics, diffusion models have achieved state-of-the-art performance in generative modeling. However, their iterative sampling nature results in high inference latency. While recent distillation techniques accelerate sampling, they discard intermediate trajectory steps. This sparse supervision leads to a loss of structural information and introduces significant discretization errors. To mitigate this, we propose B-DENSE, a novel framework that leverages multi-branch trajectory alignment. We modify the student architecture to output $K$-fold expanded channels, where each subset corresponds to a specific branch representing a discrete intermediate step in the teacher's trajectory. By training these branches to simultaneously map to the entire sequence of the teacher's target timesteps, we enforce dense intermediate trajectory alignment. Consequently, the student model learns to navigate the solution space from the earliest stages of training, demonstrating superior image generation quality compared to baseline distillation frameworks. --- ### From Reflection to Repair: A Scoping Review of Dataset Documentation Tools Authors: Pedro Reynolds-Cuéllar, Marisol Wong-Villacres, Adriana Alvarado Garcia, Heila Precel Published: 2026-02-17 Categories: cs.SE, cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2602.15968v1 Dataset documentation is widely recognized as essential for the responsible development of automated systems. Despite growing efforts to support documentation through different kinds of artifacts, little is known about the motivations shaping documentation tool design or the factors hindering their adoption. We present a systematic review supported by mixed-methods analysis of 59 dataset documentation publications to examine the motivations behind building documentation tools, how authors conceptualize documentation practices, and how these tools connect to existing systems, regulations, and cultural norms. Our analysis shows four persistent patterns in dataset documentation conceptualization that potentially impede adoption and standardization: unclear operationalizations of documentation's value, decontextualized designs, unaddressed labor demands, and a tendency to treat integration as future work. Building on these findings, we propose a shift in Responsible AI tool design toward institutional rather than individual solutions, and outline actions the HCI community can take to enable sustainable documentation practices. --- ### Non-Contact Physiological Monitoring in Pediatric Intensive Care Units via Adaptive Masking and Self-Supervised Learning Authors: Mohamed Khalil Ben Salah, Philippe Jouvet, Rita Noumeir Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15967v1 Continuous monitoring of vital signs in Pediatric Intensive Care Units (PICUs) is essential for early detection of clinical deterioration and effective clinical decision-making. However, contact-based sensors such as pulse oximeters may cause skin irritation, increase infection risk, and lead to patient discomfort. Remote photoplethysmography (rPPG) offers a contactless alternative to monitor heart rate using facial video, but remains underutilized in PICUs due to motion artifacts, occlusions, variable lighting, and domain shifts between laboratory and clinical data. We introduce a self-supervised pretraining framework for rPPG estimation in the PICU setting, based on a progressive curriculum strategy. The approach leverages the VisionMamba architecture and integrates an adaptive masking mechanism, where a lightweight Mamba-based controller assigns spatiotemporal importance scores to guide probabilistic patch sampling. This strategy dynamically increases reconstruction difficulty while preserving physiological relevance. To address the lack of labeled clinical data, we adopt a teacher-student distillation setup. A supervised expert model, trained on public datasets, provides latent physiological guidance to the student. The curriculum progresses through three stages: clean public videos, synthetic occlusion scenarios, and unlabeled videos from 500 pediatric patients. Our framework achieves a 42% reduction in mean absolute error relative to standard masked autoencoders and outperforms PhysFormer by 31%, reaching a final MAE of 3.2 bpm. Without explicit region-of-interest extraction, the model consistently attends to pulse-rich areas and demonstrates robustness under clinical occlusions and noise. --- ### Automated Re-Identification of Holstein-Friesian Cattle in Dense Crowds Authors: Phoenix Yu, Tilo Burghardt, Andrew W Dowsey, Neill W Campbell Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15962v1 Holstein-Friesian detection and re-identification (Re-ID) methods capture individuals well when targets are spatially separate. However, existing approaches, including YOLO-based species detection, break down when cows group closely together. This is particularly prevalent for species which have outline-breaking coat patterns. To boost both effectiveness and transferability in this setting, we propose a new detect-segment-identify pipeline that leverages the Open-Vocabulary Weight-free Localisation and the Segment Anything models as pre-processing stages alongside Re-ID networks. To evaluate our approach, we publish a collection of nine days CCTV data filmed on a working dairy farm. Our methodology overcomes detection breakdown in dense animal groupings, resulting in a 98.93% accuracy. This significantly outperforms current oriented bounding box-driven, as well as SAM species detection baselines with accuracy improvements of 47.52% and 27.13%, respectively. We show that unsupervised contrastive learning can build on this to yield 94.82% Re-ID accuracy on our test data. Our work demonstrates that Re-ID in crowded scenarios is both practical as well as reliable in working farm settings with no manual intervention. Code and dataset are provided for reproducibility. --- ### R$^2$Energy: A Large-Scale Benchmark for Robust Renewable Energy Forecasting under Diverse and Extreme Conditions Authors: Zhi Sheng, Yuan Yuan, Guozhen Zhang, Yong Li Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15961v1 The rapid expansion of renewable energy, particularly wind and solar power, has made reliable forecasting critical for power system operations. While recent deep learning models have achieved strong average accuracy, the increasing frequency and intensity of climate-driven extreme weather events pose severe threats to grid stability and operational security. Consequently, developing robust forecasting models that can withstand volatile conditions has become a paramount challenge. In this paper, we present R$^2$Energy, a large-scale benchmark for NWP-assisted renewable energy forecasting. It comprises over 10.7 million high-fidelity hourly records from 902 wind and solar stations across four provinces in China, providing the diverse meteorological conditions necessary to capture the wide-ranging variability of renewable generation. We further establish a standardized, leakage-free forecasting paradigm that grants all models identical access to future Numerical Weather Prediction (NWP) signals, enabling fair and reproducible comparison across state-of-the-art representative forecasting architectures. Beyond aggregate accuracy, we incorporate regime-wise evaluation with expert-aligned extreme weather annotations, uncovering a critical ``robustness gap'' typically obscured by average metrics. This gap reveals a stark robustness-complexity trade-off: under extreme conditions, a model's reliability is driven by its meteorological integration strategy rather than its architectural complexity. R$^2$Energy provides a principled foundation for evaluating and developing forecasting models for safety-critical power system applications. --- ### Deformation-Free Cross-Domain Image Registration via Position-Encoded Temporal Attention Authors: Yiwen Wang, Jiahao Qin Published: 2026-02-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.15959v2 We address the problem of cross-domain image registration, where paired images exhibit coupled geometric misalignment and domain-specific appearance shift. We formalize this as a factorization problem: decomposing each image into a domain-invariant scene representation and a global appearance statistic, such that registration reduces to recombining the scene structure of the moving image with the appearance of the fixed image via Adaptive Instance Normalization (AdaIN). This factorization eliminates the need for explicit deformation field estimation. To exploit temporal coherence in sequential acquisitions, we introduce a position-encoded cross-frame attention mechanism that fuses learnable and sinusoidal position embeddings with multi-head attention over a sliding window of neighboring frames, enriching the scene representation with inter-frame context. We instantiate this framework as GPEReg-Net and evaluate on two benchmarks: FIRE-Reg-256 (retinal fundus, semi-rigid) and HPatches-Reg-256 (synthetic textured patches, affine). GPEReg-Net achieves state-of-the-art performance on both benchmarks (FIRE: SSIM = 0.928, PSNR = 33.47 dB; HPatches: SSIM = 0.450, PSNR = 21.01 dB), surpassing all baselines, including deformation-based methods, while running 1.87x faster than SAS-Net. Code: https://github.com/JiahaoQin/GPEReg-Net. --- ### DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting Authors: Md Mofijul Islam, Md Sirajus Salekin, Nivedha Balakrishnan, Vincil C. Bishop, Niharika Jain, Spencer Romo, Bob Strahan, Boyi Xie, Diego A. Socolinsky Published: 2026-02-17 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.15958v1 Document understanding in real-world applications often requires processing heterogeneous, multi-page document packets containing multiple documents stitched together. Despite recent advances in visual document understanding, the fundamental task of document packet splitting, which involves separating a document packet into individual units, remains largely unaddressed. We present the first comprehensive benchmark dataset, DocSplit, along with novel evaluation metrics for assessing the document packet splitting capabilities of large language models. DocSplit comprises five datasets of varying complexity, covering diverse document types, layouts, and multimodal settings. We formalize the DocSplit task, which requires models to identify document boundaries, classify document types, and maintain correct page ordering within a document packet. The benchmark addresses real-world challenges, including out-of-order pages, interleaved documents, and documents lacking clear demarcations. We conduct extensive experiments evaluating multimodal LLMs on our datasets, revealing significant performance gaps in current models' ability to handle complex document splitting tasks. The DocSplit benchmark datasets and proposed novel evaluation metrics provide a systematic framework for advancing document understanding capabilities essential for legal, financial, healthcare, and other document-intensive domains. We release the datasets to facilitate future research in document packet processing. --- ### Evolutionary Systems Thinking: From Equilibrium Models to Open-Ended Adaptive Dynamics Authors: Dan Adler Published: 2026-02-17 Categories: q-bio.PE, cs.NE, econ.TH arXiv: https://arxiv.org/abs/2602.15957v2 Complex change is often described as ``evolutionary'' in economics, policy, technology, and organizations, yet many system dynamics models represent behavior within a fixed set of stocks, flows, relationships, and transition rules. Such models can generate nonlinear, oscillatory, path-dependent, or chaotic behavior, but structural novelty must ordinarily be specified in advance. This paper argues that evolutionary dynamics should be treated as a core systems-thinking problem rather than as a biological metaphor. We introduce Stability-Driven Assembly (SDA), a minimal non-equilibrium framework in which stochastic interactions and differential persistence generate endogenous selection without genes, template-based replication, or an externally specified fitness function. Longer-lived configurations accumulate in the population and therefore become more likely to participate in subsequent interactions. This creates feedback among persistence, population composition, and future pattern formation. The resulting abundance-weighted sampling is equivalent to fitness-proportional selection, allowing SDA to be interpreted as a natural genetic algorithm driven by persistence-weighted population dynamics. SDA provides a conceptual basis for distinguishing fixed-state-space dynamics from evolving possibility spaces, in which persistent structures can reshape future flows, interactions, and available configurations. It also suggests that equilibrium should be treated as provisional: a quasi-stable regime may be reorganized when a more persistent configuration emerges. We conclude by outlining two ways to extend system dynamics practice: constructing an SDA-style population model alongside a stock-flow model, and using SDA perturbation analysis to examine the vulnerability of an existing regime to structural innovation. --- ### Evolutionary Systems Thinking -- From Equilibrium Models to Open-Ended Adaptive Dynamics Authors: Dan Adler Published: 2026-02-17 Categories: q-bio.PE, cs.NE, econ.TH arXiv: https://arxiv.org/abs/2602.15957v1 Complex change is often described as "evolutionary" in economics, policy, and technology, yet most system dynamics models remain constrained to fixed state spaces and equilibrium-seeking behavior. This paper argues that evolutionary dynamics should be treated as a core system-thinking problem rather than as a biological metaphor. We introduce Stability-Driven Assembly (SDA) as a minimal, non-equilibrium framework in which stochastic interactions combined with differential persistence generate endogenous selection without genes, replication, or predefined fitness functions. In SDA, longer-lived patterns accumulate in the population, biasing future interactions and creating feedback between population composition and system dynamics. This feedback yields fitness-proportional sampling as an emergent property, realizing a natural genetic algorithm driven solely by stability. Using SDA, we demonstrate why equilibrium-constrained models, even when simulated numerically, cannot exhibit open-ended evolution: evolutionary systems require population-dependent, non-stationary dynamics in which structure and dynamics co-evolve. We conclude by discussing implications for system dynamics, economics, and policy modeling, and outline how agent-based and AI-enabled approaches may support evolutionary models capable of sustained novelty and structural emergence. --- ### Adaptive Semi-Supervised Training of P300 ERP-BCI Speller System with Minimum Calibration Effort Authors: Shumeng Chen, Jane E. Huggins, Tianwen Ma Published: 2026-02-17 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2602.15955v1 A P300 ERP-based Brain-Computer Interface (BCI) speller is an assistive communication tool. It searches for the P300 event-related potential (ERP) elicited by target stimuli, distinguishing it from the neural responses to non-target stimuli embedded in electroencephalogram (EEG) signals. Conventional methods require a lengthy calibration procedure to construct the binary classifier, which reduced overall efficiency. Thus, we proposed a unified framework with minimum calibration effort such that, given a small amount of labeled calibration data, we employed an adaptive semi-supervised EM-GMM algorithm to update the binary classifier. We evaluated our method based on character-level prediction accuracy, information transfer rate (ITR), and BCI utility. We applied calibration on training data and reported results on testing data. Our results indicate that, out of 15 participants, 9 participants exceed the minimum character-level accuracy of 0.7 using either on our adaptive method or the benchmark, and 7 out of these 9 participants showed that our adaptive method performed better than the benchmark. The proposed semi-supervised learning framework provides a practical and efficient alternative to improve the overall spelling efficiency in the real-time BCI speller system, particularly in contexts with limited labeled data. --- ### Hybrid Model Predictive Control with Physics-Informed Neural Network for Satellite Attitude Control Authors: Carlo Cena, Mauro Martini, Marcello Chiaberge Published: 2026-02-17 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.15954v1 Reliable spacecraft attitude control depends on accurate prediction of attitude dynamics, particularly when model-based strategies such as Model Predictive Control (MPC) are employed, where performance is limited by the quality of the internal system model. For spacecraft with complex dynamics, obtaining accurate physics-based models can be difficult, time-consuming, or computationally heavy. Learning-based system identification presents a compelling alternative; however, models trained exclusively on data frequently exhibit fragile stability properties and limited extrapolation capability. This work explores Physics-Informed Neural Networks (PINNs) for modeling spacecraft attitude dynamics and contrasts it with a conventional data-driven approach. A comprehensive dataset is generated using high-fidelity numerical simulations, and two learning methodologies are investigated: a purely data-driven pipeline and a physics-regularized approach that incorporates prior knowledge into the optimization process. The results indicate that embedding physical constraints during training leads to substantial improvements in predictive reliability, achieving a 68.17% decrease in mean relative error relative. When deployed within an MPC architecture, the physics-informed models yield superior closed-loop tracking performance and improved robustness to uncertainty. Furthermore, a hybrid control formulation that merges the learned nonlinear dynamics with a nominal linear model enables consistent steady-state convergence and significantly faster response, reducing settling times by 61.52%-76.42% under measurement noise and reaction wheel friction. --- ### MadEvolve: Evolutionary Optimization of Cosmological Algorithms with Large Language Models Authors: Tianyi Li, Shihui Zang, Moritz Münchmeyer Published: 2026-02-17 Categories: astro-ph.CO, cs.LG arXiv: https://arxiv.org/abs/2602.15951v1 We develop a general framework to discover scientific algorithms and apply it to three problems in computational cosmology. Our code, MadEvolve, is similar to Google's AlphaEvolve, but places a stronger emphasis on free parameters and their optimization. Our code starts with a baseline human algorithm implementation, and then optimizes its performance metrics by making iterative changes to its code. As a further convenient feature, MadEvolve automatically generates a report that compares the input algorithm with the evolved algorithm, describes the algorithmic innovations and lists the free parameters and their function. Our code supports both auto-differentiable, gradient-based parameter optimization and gradient-free optimization methods. We apply MadEvolve to the reconstruction of cosmological initial conditions, 21cm foreground contamination reconstruction and effective baryonic physics in N-body simulations. In all cases, we find substantial improvements over the base algorithm. We make MadEvolve and our three tasks publicly available at madevolve.org. --- ### Can Vision-Language Models See Squares? Text-Recognition Mediates Spatial Reasoning Across Three Model Families Authors: Yuval Levental Published: 2026-02-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.15950v2 We present a simple experiment that exposes a fundamental limitation in vision-language models (VLMs): the inability to accurately localize filled cells in binary grids when those cells lack textual identity. We generate fifteen 15x15 grids with varying density (10.7%-41.8% filled cells) and render each as two image types -- text symbols (. and #) and filled squares without gridlines -- then ask three frontier VLMs (Claude Opus, ChatGPT 5.2, and Gemini 3 Thinking) to transcribe them. In the text-symbol condition, Claude and ChatGPT achieve approximately 91% cell accuracy and 84% F1, while Gemini achieves 84% accuracy and 63% F1. In the filled-squares condition, all three models collapse to 60-73% accuracy and 29-39% F1. Critically, all conditions pass through the same visual encoder -- the text symbols are images, not tokenized text. The text-vs-squares F1 gap ranges from 34 to 54 points across models, demonstrating that VLMs behave as if they possess a high-fidelity text-recognition pathway for spatial reasoning that dramatically outperforms their native visual pathway. Each model exhibits a distinct failure mode in the squares condition -- systematic under-counting (Claude), massive over-counting (ChatGPT), and template hallucination (Gemini) -- but all share the same underlying deficit: severely degraded spatial localization for non-textual visual elements. --- ### From Tool Orchestration to Code Execution: A Study of MCP Design Choices Authors: Yuval Felendler, Parth A. Gandhi, Idan Habler, Yuval Elovici, Asaf Shabtai Published: 2026-02-17 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.15945v1 Model Context Protocols (MCPs) provide a unified platform for agent systems to discover, select, and orchestrate tools across heterogeneous execution environments. As MCP-based systems scale to incorporate larger tool catalogs and multiple concurrently connected MCP servers, traditional tool-by-tool invocation increases coordination overhead, fragments state management, and limits support for wide-context operations. To address these scalability challenges, recent MCP designs have incorporated code execution as a first-class capability, an approach called Code Execution MCP (CE-MCP). This enables agents to consolidate complex workflows, such as SQL querying, file analysis, and multi-step data transformations, into a single program that executes within an isolated runtime environment. In this work, we formalize the architectural distinction between context-coupled (traditional) and context-decoupled (CE-MCP) models, analyzing their fundamental scalability trade-offs. Using the MCP-Bench framework across 10 representative servers, we empirically evaluate task behavior, tool utilization patterns, execution latency, and protocol efficiency as the scale of connected MCP servers and available tools increases, demonstrating that while CE-MCP significantly reduces token usage and execution latency, it introduces a vastly expanded attack surface. We address this security gap by applying the MAESTRO framework, identifying sixteen attack classes across five execution phases-including specific code execution threats such as exception-mediated code injection and unsafe capability synthesis. We validate these vulnerabilities through adversarial scenarios across multiple LLMs and propose a layered defense architecture comprising containerized sandboxing and semantic gating. Our findings provide a rigorous roadmap for balancing scalability and security in production-ready executable agent workflows. --- ### Visual Memory Injection Attacks for Multi-Turn Conversations Authors: Christian Schlarmann, Matthias Hein Published: 2026-02-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.15927v1 Generative large vision-language models (LVLMs) have recently achieved impressive performance gains, and their user base is growing rapidly. However, the security of LVLMs, in particular in a long-context multi-turn setting, is largely underexplored. In this paper, we consider the realistic scenario in which an attacker uploads a manipulated image to the web/social media. A benign user downloads this image and uses it as input to the LVLM. Our novel stealthy Visual Memory Injection (VMI) attack is designed such that on normal prompts the LVLM exhibits nominal behavior, but once the user gives a triggering prompt, the LVLM outputs a specific prescribed target message to manipulate the user, e.g. for adversarial marketing or political persuasion. Compared to previous work that focused on single-turn attacks, VMI is effective even after a long multi-turn conversation with the user. We demonstrate our attack on several recent open-weight LVLMs. This article thereby shows that large-scale manipulation of users is feasible with perturbed images in multi-turn conversation settings, calling for better robustness of LVLMs against these attacks. We release the source code at https://github.com/chs20/visual-memory-injection --- ### A Study on Real-time Object Detection using Deep Learning Authors: Ankita Bose, Jayasravani Bhumireddy, Naveen N Published: 2026-02-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.15926v1 Object detection has compelling applications over a range of domains, including human-computer interfaces, security and video surveillance, navigation and road traffic monitoring, transportation systems, industrial automation healthcare, the world of Augmented Reality (AR) and Virtual Reality (VR), environment monitoring and activity identification. Applications of real time object detection in all these areas provide dynamic analysis of the visual information that helps in immediate decision making. Furthermore, advanced deep learning algorithms leverage the progress in the field of object detection providing more accurate and efficient solutions. There are some outstanding deep learning algorithms for object detection which includes, Faster R CNN(Region-based Convolutional Neural Network),Mask R-CNN, Cascade R-CNN, YOLO (You Only Look Once), SSD (Single Shot Multibox Detector), RetinaNet etc. This article goes into great detail on how deep learning algorithms are used to enhance real time object recognition. It provides information on the different object detection models available, open benchmark datasets, and studies on the use of object detection models in a range of applications. Additionally, controlled studies are provided to compare various strategies and produce some illuminating findings. Last but not least, a number of encouraging challenges and approaches are offered as suggestions for further investigation in both relevant deep learning approaches and object recognition. --- ### Robust Stochastic Gradient Posterior Sampling with Lattice Based Discretisation Authors: Zier Mensch, Lars Holdijk, Samuel Duffield, Maxwell Aifer, Patrick J. Coles, Max Welling, Miranda C. N. Cheng Published: 2026-02-17 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.15925v1 Stochastic-gradient MCMC methods enable scalable Bayesian posterior sampling but often suffer from sensitivity to minibatch size and gradient noise. To address this, we propose Stochastic Gradient Lattice Random Walk (SGLRW), an extension of the Lattice Random Walk discretization. Unlike conventional Stochastic Gradient Langevin Dynamics (SGLD), SGLRW introduces stochastic noise only through the off-diagonal elements of the update covariance; this yields greater robustness to minibatch size while retaining asymptotic correctness. Furthermore, as comparison we analyze a natural analogue of SGLD utilizing gradient clipping. Experimental validation on Bayesian regression and classification demonstrates that SGLRW remains stable in regimes where SGLD fails, including in the presence of heavy-tailed gradient noise, and matches or improves predictive performance. --- ### A fully differentiable framework for training proxy Exchange Correlation Functionals for periodic systems Authors: Rakshit Kumar Singh, Aryan Amit Barsainyan, Bharath Ramsundar Published: 2026-02-17 Categories: cond-mat.mtrl-sci, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.15923v1 Density Functional Theory (DFT) is widely used for first-principles simulations in chemistry and materials science, but its computational cost remains a key limitation for large systems. Motivated by recent advances in ML-based exchange-correlation (XC) functionals, this paper introduces a differentiable framework that integrates machine learning models into density functional theory (DFT) for solids and other periodic systems. The framework defines a clean API for neural network models that can act as drop in replacements for conventional exchange-correlation (XC) functionals and enables gradients to flow through the full self-consistent DFT workflow. The framework is implemented in Python using a PyTorch backend, making it fully differentiable and easy to use with standard deep learning tools. We integrate the implementation with the DeepChem library to promote the reuse of established models and to lower the barrier for experimentation. In initial benchmarks against established electronic structure packages (GPAW and PySCF), our models achieve relative errors on the order of 5-10%. --- ### World Action Models are Zero-shot Policies Authors: Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng, Shenyuan Gao, Sihyun Yu, George Kurian, Suneel Indupuru, You Liang Tan, Chuning Zhu, Jiannan Xiang, Ayaan Malik, Kyungmin Lee et al. Published: 2026-02-17 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.15922v1 State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce DreamZero, a World Action Model (WAM) built upon a pretrained video diffusion backbone. Unlike VLAs, WAMs learn physical dynamics by predicting future world states and actions, using video as a dense representation of how the world evolves. By jointly modeling video and action, DreamZero learns diverse skills effectively from heterogeneous robot data without relying on repetitive demonstrations. This results in over 2x improvement in generalization to new tasks and environments compared to state-of-the-art VLAs in real robot experiments. Crucially, through model and system optimizations, we enable a 14B autoregressive video diffusion model to perform real-time closed-loop control at 7Hz. Finally, we demonstrate two forms of cross-embodiment transfer: video-only demonstrations from other robots or humans yield a relative improvement of over 42% on unseen task performance with just 10-20 minutes of data. More surprisingly, DreamZero enables few-shot embodiment adaptation, transferring to a new embodiment with only 30 minutes of play data while retaining zero-shot generalization. --- ### Including Node Textual Metadata in Laplacian-constrained Gaussian Graphical Models Authors: Jianhua Wang, Killian Cressant, Pedro Braconnot Velloso, Arnaud Breloy Published: 2026-02-17 Categories: stat.ML, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2602.15920v1 This paper addresses graph learning in Gaussian Graphical Models (GGMs). In this context, data matrices often come with auxiliary metadata (e.g., textual descriptions associated with each node) that is usually ignored in traditional graph estimation processes. To fill this gap, we propose a graph learning approach based on Laplacian-constrained GGMs that jointly leverages the node signals and such metadata. The resulting formulation yields an optimization problem, for which we develop an efficient majorization-minimization (MM) algorithm with closed-form updates at each iteration. Experimental results on a real-world financial dataset demonstrate that the proposed method significantly improves graph clustering performance compared to state-of-the-art approaches that use either signals or metadata alone, thus illustrating the interest of fusing both sources of information. --- ### Assessing Per-Sample Membership Inference Vulnerability without Retraining Authors: Valentin Dorseuil, Jamal Atif, Olivier Cappé Published: 2026-02-17 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.15919v2 Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted approaches by a wide margin. Motivated by this observation, we address the following question: can the privacy vulnerability of individual training points be assessed without training shadow models? We show that per-sample exposure to MIA is governed not only by a point's loss, but also by a data-dependent geometric measure. In the linear setting, we derive a closed-form decomposition of individual black-box MIA vulnerability into a population leverage score and a residual loss term, making explicit how sample-dependent geometry translates into privacy exposure. Since the final layer of most modern architectures is linear, we extend this framework to deep networks and propose a surrogate score operating on last-layer representations that requires only a single trained model and no shadow models. Empirical evaluations across diverse datasets and architectures show that our score outperforms loss and gradient-norm baselines at identifying the highest-risk points under state-of-the-art attacks, providing a computationally efficient and theoretically grounded tool for per-sample privacy risk assessment. --- ### EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery Authors: Zelin Xu, Yupu Zhang, Saugat Adhikari, Saiful Islam, Tingsong Xiao, Zibo Liu, Shigang Chen, Da Yan, Zhe Jiang Published: 2026-02-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.15918v1 Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical world. However, spatial reasoning on Earth imagery has lagged behind, as it uniquely involves grounding objects in georeferenced images and quantitatively reasoning about distances, directions, and topological relations using both visual cues and vector geometry coordinates (e.g., 2D bounding boxes, polylines, and polygons). Existing benchmarks for Earth imagery primarily focus on 2D spatial grounding, image captioning, and coarse spatial relations (e.g., simple directional or proximity cues). They lack support for quantitative direction and distance reasoning, systematic topological relations, and complex object geometries beyond bounding boxes. To fill this gap, we propose \textbf{EarthSpatialBench}, a comprehensive benchmark for evaluating spatial reasoning in MLLMs on Earth imagery. The benchmark contains over 325K question-answer pairs spanning: (1) qualitative and quantitative reasoning about spatial distance and direction; (2) systematic topological relations; (3) single-object queries, object-pair queries, and compositional aggregate group queries; and (4) object references expressed via textual descriptions, visual overlays, and explicit geometry coordinates, including 2D bounding boxes, polylines, and polygons. We conducted extensive experiments on both open-source and proprietary models to identify limitations in the spatial reasoning of MLLMs. --- ### ROIX-Comp: Optimizing X-ray Computed Tomography Imaging Strategy for Data Reduction and Reconstruction Authors: Amarjit Singh, Kento Sato, Kohei Yoshida, Kentaro Uesugi, Yasumasa Joti, Takaki Hatsui, Andrès Rubio Proaño Published: 2026-02-17 Categories: eess.IV, cs.CV, cs.DC, cs.IT arXiv: https://arxiv.org/abs/2602.15917v1 In high-performance computing (HPC) environments, particularly in synchrotron radiation facilities, vast amounts of X-ray images are generated. Processing large-scale X-ray Computed Tomography (X-CT) datasets presents significant computational and storage challenges due to their high dimensionality and data volume. Traditional approaches often require extensive storage capacity and high transmission bandwidth, limiting real-time processing capabilities and workflow efficiency. To address these constraints, we introduce a region-of-interest (ROI)-driven extraction framework (ROIX-Comp) that intelligently compresses X-CT data by identifying and retaining only essential features. Our work reduces data volume while preserving critical information for downstream processing tasks. At pre-processing stage, we utilize error-bounded quantization to reduce the amount of data to be processed and therefore improve computational efficiencies. At the compression stage, our methodology combines object extraction with multiple state-of-the-art lossless and lossy compressors, resulting in significantly improved compression ratios. We evaluated this framework against seven X-CT datasets and observed a relative compression ratio improvement of 12.34x compared to the standard compression. --- ### Nonparametric Identification and Inference for Counterfactual Distributions with Confounding Authors: Jianle Sun, Kun Zhang Published: 2026-02-17 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2602.15916v1 We propose nonparametric identification and semiparametric estimation of joint potential outcome distributions in the presence of confounding. First, in settings with observed confounding, we derive tighter, covariate-informed bounds on the joint distribution by leveraging conditional copulas. To overcome the non-differentiability of bounding min/max operators, we establish the asymptotic properties for both a direct estimator with polynomial margin condition and a smooth approximation with log-sum-exp operator, facilitating valid inference for individual-level effects under the canonical rank-preserving assumption. Second, we tackle the challenge of unmeasured confounding by introducing a causal representation learning framework. By utilizing instrumental variables, we prove the nonparametric identifiability of the latent confounding subspace under injectivity and completeness conditions. We develop a ``triple machine learning" estimator that employs cross-fitting scheme to sequentially handle the learned representation, nuisance parameters, and target functional. We characterize the asymptotic distribution with variance inflation induced by representation learning error, and provide conditions for semiparametric efficiency. We also propose a practical VAE-based algorithm for confounding representation learning. Simulations and real-world analysis validate the effectiveness of proposed methods. By bridging classical semiparametric theory with modern representation learning, this work provides a robust statistical foundation for distributional and counterfactual inference in complex causal systems. --- ### MaS-VQA: A Mask-and-Select Framework for Knowledge-Based Visual Question Answering Authors: Xianwei Mao, Kai Ye, Sheng Zhou, Nan Zhang, Haikuan Huang, Bin Li, Jiajun Bu Published: 2026-02-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.15915v1 Knowledge-based Visual Question Answering (KB-VQA) requires models to answer questions by integrating visual information with external knowledge. However, retrieved knowledge is often noisy, partially irrelevant, or misaligned with the visual content, while internal model knowledge is difficult to control and interpret. Naive aggregation of these sources limits reasoning effectiveness and reduces answer accuracy. To address this, we propose MaS-VQA, a selection-driven framework that tightly couples explicit knowledge filtering with implicit knowledge reasoning. MaS-VQA first retrieves candidate passages and applies a Mask-and-Select mechanism to jointly prune irrelevant image regions and weakly relevant knowledge fragments, producing compact, high-signal multimodal knowledge . This filtered knowledge then guides the activation of internal knowledge in a constrained semantic space, enabling complementary co-modeling of explicit and implicit knowledge for robust answer prediction. Experiments on Encyclopedic-VQA and InfoSeek demonstrate consistent performance gains across multiple MLLM backbones, and ablations verify that the selection mechanism effectively reduces noise and enhances knowledge utilization. --- ### Steering Dynamical Regimes of Diffusion Models by Breaking Detailed Balance Authors: Haiqi Lu, Ying Tang Published: 2026-02-17 Categories: cond-mat.stat-mech, cs.LG arXiv: https://arxiv.org/abs/2602.15914v1 We show that deliberately breaking detailed balance in generative diffusion processes can accelerate the reverse process without changing the stationary distribution. Considering the Ornstein--Uhlenbeck process, we decompose the dynamics into a symmetric component and a non-reversible anti-symmetric component that generates rotational probability currents. We then construct an exponentially optimal non-reversible perturbation that improves the long-time relaxation rate while preserving the stationary target. We analyze how such non-reversible control reshapes the macroscopic dynamical regimes of the phase transitions recently identified in generative diffusion models. We derive a general criterion for the speciation time and show that suitable non-reversible perturbations can accelerate speciation. In contrast, the collapse transition is governed by a trace-controlled phase-space contraction mechanism that is fixed by the symmetric component, and the corresponding collapse time remains unchanged under anti-symmetric perturbations. Numerical experiments on Gaussian mixture models support these findings. --- ### Foundation Models for Medical Imaging: Status, Challenges, and Directions Authors: Chuang Niu, Pengwei Wu, Bruno De Man, Ge Wang Published: 2026-02-17 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.15913v1 Foundation models (FMs) are rapidly reshaping medical imaging, shifting the field from narrowly trained, task-specific networks toward large, general-purpose models that can be adapted across modalities, anatomies, and clinical tasks. In this review, we synthesize the emerging landscape of medical imaging FMs along three major axes: principles of FM design, applications of FMs, and forward-looking challenges and opportunities. Taken together, this review provides a technically grounded, clinically aware, and future-facing roadmap for developing FMs that are not only powerful and versatile but also trustworthy and ready for responsible translation into clinical practice. --- ### Ensemble-size-dependence of deep-learning post-processing methods that minimize an (un)fair score: motivating examples and a proof-of-concept solution Authors: Christopher David Roberts Published: 2026-02-17 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2602.15830v1 Fair scores reward ensemble forecast members that behave like samples from the same distribution as the verifying observations. They are therefore an attractive choice as loss functions to train data-driven ensemble forecasts or post-processing methods when large training ensembles are either unavailable or computationally prohibitive. The adjusted continuous ranked probability score (aCRPS) is fair and unbiased with respect to ensemble size, provided forecast members are exchangeable and interpretable as conditionally independent draws from an underlying predictive distribution. However, distribution-aware post-processing methods that introduce structural dependency between members can violate this assumption, rendering aCRPS unfair. We demonstrate this effect using two approaches designed to minimize the expected aCRPS of a finite ensemble: (1) a linear member-by-member calibration, which couples members through a common dependency on the sample ensemble mean, and (2) a deep-learning method, which couples members via transformer self-attention across the ensemble dimension. In both cases, the results are sensitive to ensemble size and apparent gains in aCRPS can correspond to systematic unreliability characterized by over-dispersion. We introduce trajectory transformers as a proof-of-concept that ensemble-size independence can be achieved. This approach is an adaptation of the Post-processing Ensembles with Transformers (PoET) framework and applies self-attention over lead time while preserving the conditional independence required by aCRPS. When applied to weekly mean $T_{2m}$ forecasts from the ECMWF subseasonal forecasting system, this approach successfully reduces systematic model biases whilst also improving or maintaining forecast reliability regardless of the ensemble size used in training (3 vs 9 members) or real-time forecasts (9 vs 100 members). --- ### Operationalising the Superficial Alignment Hypothesis via Task Complexity Authors: Tomás Vergara-Browne, Darshan Patil, Ivan Titov, Siva Reddy, Tiago Pimentel, Marius Mosbach Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15829v2 The superficial alignment hypothesis (SAH) posits that large language models learn most of their knowledge during pre-training, and that post-training merely surfaces this knowledge. The SAH, however, lacks a precise definition, which has led to (i) different and seemingly orthogonal arguments supporting it, and (ii) important critiques to it. We propose a new metric called task complexity: the length of the shortest program that achieves a target performance on a task. In this framework, the SAH simply claims that pre-trained models drastically reduce the complexity of achieving high performance on many tasks. Our definition unifies prior arguments supporting the SAH, interpreting them as different strategies to find such short programs. Experimentally, we estimate the task complexity of mathematical reasoning, machine translation, and instruction following; we then show that these complexities can be remarkably low when conditioned on a pre-trained model. Further, we find that pre-training enables access to strong performances on our tasks, but it can require programs of gigabytes of length to access them. Post-training, on the other hand, collapses the complexity of reaching this same performance by several orders of magnitude. Overall, our results highlight that task adaptation often requires surprisingly little information -- often just a few kilobytes. --- ### Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation Authors: Yuxuan Kuang, Sungjae Park, Katerina Fragkiadaki, Shubham Tulsiani Published: 2026-02-17 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.15828v1 Learning generalist policies capable of accomplishing a plethora of everyday tasks remains an open challenge in dexterous manipulation. In particular, collecting large-scale manipulation data via real-world teleoperation is expensive and difficult to scale. While learning in simulation provides a feasible alternative, designing multiple task-specific environments and rewards for training is similarly challenging. We propose Dex4D, a framework that instead leverages simulation for learning task-agnostic dexterous skills that can be flexibly recomposed to perform diverse real-world manipulation tasks. Specifically, Dex4D learns a domain-agnostic 3D point track conditioned policy capable of manipulating any object to any desired pose. We train this 'Anypose-to-Anypose' policy in simulation across thousands of objects with diverse pose configurations, covering a broad space of robot-object interactions that can be composed at test time. At deployment, this policy can be zero-shot transferred to real-world tasks without finetuning, simply by prompting it with desired object-centric point tracks extracted from generated videos. During execution, Dex4D uses online point tracking for closed-loop perception and control. Extensive experiments in simulation and on real robots show that our method enables zero-shot deployment for diverse dexterous manipulation tasks and yields consistent improvements over prior baselines. Furthermore, we demonstrate strong generalization to novel objects, scene layouts, backgrounds, and trajectories, highlighting the robustness and scalability of the proposed framework. --- ### Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching Authors: Zhen Wu, Xiaoyu Huang, Lujie Yang, Yuanhang Zhang, Xi Chen, Pieter Abbeel, Rocky Duan, Angjoo Kanazawa, Carmelo Sferrazza, Guanya Shi, C. Karen Liu Published: 2026-02-17 Categories: cs.RO, cs.AI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2602.15827v2 While recent advances in humanoid locomotion have achieved stable walking on varied terrains, capturing the agility and adaptivity of highly dynamic human motions remains an open challenge. In particular, agile parkour in complex environments demands not only low-level robustness, but also human-like motion expressiveness, long-horizon skill composition, and perception-driven decision-making. In this paper, we present Perceptive Humanoid Parkour (PHP), a modular framework that enables humanoid robots to autonomously perform long-horizon, vision-based parkour across challenging obstacle courses. Our approach first leverages motion matching, formulated as nearest-neighbor search in a feature space, to compose retargeted atomic human skills into long-horizon kinematic trajectories. This framework enables the flexible composition and smooth transition of complex skill chains while preserving the elegance and fluidity of dynamic human motions. Next, we train motion-tracking reinforcement learning (RL) expert policies for these composed motions, and distill them into a single depth-based, multi-skill student policy, using a combination of DAgger and RL. Crucially, the combination of perception and skill composition enables autonomous, context-aware decision-making: using only onboard depth sensing and a discrete 2D velocity command, the robot selects and executes whether to step over, climb onto, vault or roll off obstacles of varying geometries and heights. We validate our framework with extensive real-world experiments on a Unitree G1 humanoid robot, demonstrating highly dynamic parkour skills such as climbing tall obstacles up to 1.25m (96% robot height), as well as long-horizon multi-obstacle traversal with closed-loop adaptation to real-time obstacle perturbations. --- ### CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing Authors: Zarif Ikram, Arad Firouzkouhi, Stephen Tu, Mahdi Soltanolkotabi, Paria Rashidinejad Published: 2026-02-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.15823v2 A central challenge in large language model (LLM) editing is capability preservation: methods that successfully change targeted behavior can quietly game the editing proxy and corrupt general capabilities, producing degenerate behaviors reminiscent of proxy/reward hacking. We present CrispEdit, a scalable and principled second-order editing algorithm that treats capability preservation as an explicit constraint, unifying and generalizing several existing editing approaches. CrispEdit formulates editing as constrained optimization and enforces the constraint by projecting edit updates onto the low-curvature subspace of the capability-loss landscape. At the crux of CrispEdit is expressing capability constraint via Bregman divergence, whose quadratic form yields the Gauss-Newton Hessian exactly and even when the base model is not trained to convergence. We make this second-order procedure efficient at the LLM scale using Kronecker-factored approximate curvature (K-FAC) and a novel matrix-free projector that exploits Kronecker structure to avoid constructing massive projection matrices. Across standard model-editing benchmarks, CrispEdit achieves high edit success while keeping capability degradation below 1% on average across datasets, significantly improving over prior editors. --- ### Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statistics Authors: Anna Zimmel, Paul Setinek, Gianluca Galletti, Johannes Brandstetter, Werner Zellinger Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15820v1 Machine learning surrogates are increasingly used in engineering to accelerate costly simulations, yet distribution shifts between training and deployment often cause severe performance degradation (e.g., unseen geometries or configurations). Test-Time Adaptation (TTA) can mitigate such shifts, but existing methods are largely developed for lower-dimensional classification with structured outputs and visually aligned input-output relationships, making them unstable for the high-dimensional, unstructured and regression problems common in simulation. We address this challenge by proposing a TTA framework based on storing maximally informative (D-optimal) statistics, which jointly enables stable adaptation and principled parameter selection at test time. When applied to pretrained simulation surrogates, our method yields up to 7% out-of-distribution improvements at negligible computational cost. To the best of our knowledge, this is the first systematic demonstration of effective TTA for high-dimensional simulation regression and generative design optimization, validated on the SIMSHIFT and EngiBench benchmarks. --- ### VideoSketcher: Sequential Sketch Generation Using Video Model Priors Authors: Hui Ren, Yuval Alaluf, Omer Bar Tal, Alexander Schwing, Antonio Torralba, Yael Vinker Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15819v2 Sketching is inherently sequential: strokes are drawn progressively to explore and refine ideas. Yet most generative approaches treat sketches as static images, ignoring the temporal process underlying creative exploration. Modeling this sequential structure remains challenging: prior methods either rely on large-scale human-drawn datasets with limited diversity, or use large language models (LLMs) to produce drawing instructions, often at the cost of visual fidelity. We present VideoSketcher, a method for generating high-quality sketching processes by adapting pretrained text-to-video diffusion models to the sparse, continuous nature of sketch formation. Our key insight is that LLMs and video diffusion models offer complementary strengths: LLMs act as semantic planners that decompose concepts into step-by-step instructions, while video diffusion models serve as powerful "renderers" that translate them into temporally coherent sketch sequences. We introduce a two-stage fine-tuning strategy that decouples temporal structure from visual appearance: stroke ordering is learned from synthetic shape compositions, while style is distilled from as few as seven hand-drawn examples. Despite minimal supervision, our method can generate diverse, high-quality sequential sketches that faithfully follow specified drawing orders. Our framework naturally extends to brush style control and autoregressive generation, supporting artistic applications. --- ### Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning Authors: Oswin So, Eric Yang Yu, Songyuan Zhang, Matthew Cleaveland, Mitchell Black, Chuchu Fan Published: 2026-02-17 Categories: cs.LG, cs.RO, math.OC arXiv: https://arxiv.org/abs/2602.15817v1 Recent advances in deep reinforcement learning (RL) have achieved strong results on high-dimensional control tasks, but applying RL to reachability problems raises a fundamental mismatch: reachability seeks to maximize the set of states from which a system remains safe indefinitely, while RL optimizes expected returns over a user-specified distribution. This mismatch can result in policies that perform poorly on low-probability states that are still within the safe set. A natural alternative is to frame the problem as a robust optimization over a set of initial conditions that specify the initial state, dynamics and safe set, but whether this problem has a solution depends on the feasibility of the specified set, which is unknown a priori. We propose Feasibility-Guided Exploration (FGE), a method that simultaneously identifies a subset of feasible initial conditions under which a safe policy exists, and learns a policy to solve the reachability problem over this set of initial conditions. Empirical results demonstrate that FGE learns policies with over 50% more coverage than the best existing method for challenging initial conditions across tasks in the MuJoCo simulator and the Kinetix simulator with pixel observations. --- ### Developing AI Agents with Simulated Data: Why, what, and how? Authors: Xiaoran Liu, Istvan David Published: 2026-02-17 Categories: cs.AI, cs.ET arXiv: https://arxiv.org/abs/2602.15816v1 As insufficient data volume and quality remain the key impediments to the adoption of modern subsymbolic AI, techniques of synthetic data generation are in high demand. Simulation offers an apt, systematic approach to generating diverse synthetic data. This chapter introduces the reader to the key concepts, benefits, and challenges of simulation-based synthetic data generation for AI training purposes, and to a reference framework to describe, design, and analyze digital twin-based AI simulation solutions. --- ### Avey-B Authors: Devang Acharya, Mohammad Hammoud Published: 2026-02-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.15814v1 Compact pretrained bidirectional encoders remain the backbone of industrial NLP under tight compute and memory budgets. Their effectiveness stems from self-attention's ability to deliver high-quality bidirectional contextualization with sequence-level parallelism, as popularized by BERT-style architectures. Recently, Avey was introduced as an autoregressive, attention-free alternative that naturally admits an encoder-only adaptation. In this paper, we reformulate Avey for the encoder-only paradigm and propose several innovations to its architecture, including decoupled static and dynamic parameterizations, stability-oriented normalization, and neural compression. Results show that this reformulated architecture compares favorably to four widely used Transformer-based encoders, consistently outperforming them on standard token-classification and information-retrieval benchmarks while scaling more efficiently to long contexts. --- ### CARL-CXR: Continual Adapter-Based Routing for Task-Unknown Chest Radiograph Classification Authors: Muthu Subash Kavitha, Anas Zafar, Amgad Muneer, Jia Wu Published: 2026-02-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.15811v2 Clinical deployment of chest radiograph classifiers requires models that can be updated as new datasets become available without retraining on previously observed data or degrading validated performance. We study a task-incremental continual learning setting for chest radiograph classification under task-unknown inference, where heterogeneous chest X-ray datasets arrive sequentially and task identity is unavailable at deployment time. We propose CARL-CXR, a continual adapter-based routing framework that maintains a fixed high-capacity backbone while incrementally introducing lightweight task-specific adapters and classifier heads. A latent task selector operates on adapter-conditioned features to dynamically route each input to the most relevant task pathway, leveraging compact task prototypes and feature-level experience replay to preserve task identity across sequential updates without storing raw images. Experiments on MIMIC-CXR and CheXpert two large-scale datasets with distinct patient populations, imaging devices, and annotation pipelines demonstrate that CARL-CXR achieves minimal catastrophic forgetting (0.012 AUROC drop), representing a 6X and 11X reduction over established continual learning baselines LwF and EWC respectively, while maintaining competitive diagnostic performance (AUROC 0.74). Under task unknown deployment, CARL-CXR outperforms joint training by 12.5 points in routing accuracy (75.0% vs. 62.5%): unlike LwF and EWC, which require explicit task identifiers at inference and provide no routing mechanism. --- ### Decision Quality Evaluation Framework at Pinterest Authors: Yuqi Tian, Robert Paine, Attila Dobi, Kevin O'Sullivan, Aravindh Manickavasagam, Faisal Farooq Published: 2026-02-17 Categories: stat.AP, cs.AI arXiv: https://arxiv.org/abs/2602.15809v1 Online platforms require robust systems to enforce content safety policies at scale. A critical component of these systems is the ability to evaluate the quality of moderation decisions made by both human agents and Large Language Models (LLMs). However, this evaluation is challenging due to the inherent trade-offs between cost, scale, and trustworthiness, along with the complexity of evolving policies. To address this, we present a comprehensive Decision Quality Evaluation Framework developed and deployed at Pinterest. The framework is centered on a high-trust Golden Set (GDS) curated by subject matter experts (SMEs), which serves as a ground truth benchmark. We introduce an automated intelligent sampling pipeline that uses propensity scores to efficiently expand dataset coverage. We demonstrate the framework's practical application in several key areas: benchmarking the cost-performance trade-offs of various LLM agents, establishing a rigorous methodology for data-driven prompt optimization, managing complex policy evolution, and ensuring the integrity of policy content prevalence metrics via continuous validation. The framework enables a shift from subjective assessments to a data-driven and quantitative practice for managing content safety systems. --- ### The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety Authors: Max Springer, Chung Peng Lee, Blossom Metevier, Jane Castleman, Bohdan Turbal, Hayoung Jung, Zeyu Shen, Aleksandra Korolova Published: 2026-02-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.15799v1 Fine-tuning aligned language models on benign tasks unpredictably degrades safety guardrails, even when training data contains no harmful content and developers have no adversarial intent. We show that the prevailing explanation, that fine-tuning updates should be orthogonal to safety-critical directions in high-dimensional parameter space, offers false reassurance: we show this orthogonality is structurally unstable and collapses under the dynamics of gradient descent. We then resolve this through a novel geometric analysis, proving that alignment concentrates in low-dimensional subspaces with sharp curvature, creating a brittle structure that first-order methods cannot detect or defend. While initial fine-tuning updates may indeed avoid these subspaces, the curvature of the fine-tuning loss generates second-order acceleration that systematically steers trajectories into alignment-sensitive regions. We formalize this mechanism through the Alignment Instability Condition, three geometric properties that, when jointly satisfied, lead to safety degradation. Our main result establishes a quartic scaling law: alignment loss grows with the fourth power of training time, governed by the sharpness of alignment geometry and the strength of curvature coupling between the fine-tuning task and safety-critical parameters. These results expose a structural blind spot in the current safety paradigm. The dominant approaches to safe fine-tuning address only the initial snapshot of a fundamentally dynamic problem. Alignment fragility is not a bug to be patched; it is an intrinsic geometric property of gradient descent on curved manifolds. Our results motivate the development of curvature-aware methods, and we hope will further enable a shift in alignment safety analysis from reactive red-teaming to predictive diagnostics for open-weight model deployment. --- ### Enhancing Building Semantics Preservation in AI Model Training with Large Language Model Encodings Authors: Suhyung Jang, Ghang Lee, Jaekun Lee, Hyunjun Lee Published: 2026-02-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.15791v1 Accurate representation of building semantics, encompassing both generic object types and specific subtypes, is essential for effective AI model training in the architecture, engineering, construction, and operation (AECO) industry. Conventional encoding methods (e.g., one-hot) often fail to convey the nuanced relationships among closely related subtypes, limiting AI's semantic comprehension. To address this limitation, this study proposes a novel training approach that employs large language model (LLM) embeddings (e.g., OpenAI GPT and Meta LLaMA) as encodings to preserve finer distinctions in building semantics. We evaluated the proposed method by training GraphSAGE models to classify 42 building object subtypes across five high-rise residential building information models (BIMs). Various embedding dimensions were tested, including original high-dimensional LLM embeddings (1,536, 3,072, or 4,096) and 1,024-dimensional compacted embeddings generated via the Matryoshka representation model. Experimental results demonstrated that LLM encodings outperformed the conventional one-hot baseline, with the llama-3 (compacted) embedding achieving a weighted average F1-score of 0.8766, compared to 0.8475 for one-hot encoding. The results underscore the promise of leveraging LLM-based encodings to enhance AI's ability to interpret complex, domain-specific building semantics. As the capabilities of LLMs and dimensionality reduction techniques continue to evolve, this approach holds considerable potential for broad application in semantic elaboration tasks throughout the AECO industry. --- ### This human study did not involve human subjects: Validating LLM simulations as behavioral evidence Authors: Jessica Hullman, David Broska, Huaman Sun, Aaron Shaw Published: 2026-02-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.15785v1 A growing literature uses large language models (LLMs) as synthetic participants to generate cost-effective and nearly instantaneous responses in social science experiments. However, there is limited guidance on when such simulations support valid inference about human behavior. We contrast two strategies for obtaining valid estimates of causal effects and clarify the assumptions under which each is suitable for exploratory versus confirmatory research. Heuristic approaches seek to establish that simulated and observed human behavior are interchangeable through prompt engineering, model fine-tuning, and other repair strategies designed to reduce LLM-induced inaccuracies. While useful for many exploratory tasks, heuristic approaches lack the formal statistical guarantees typically required for confirmatory research. In contrast, statistical calibration combines auxiliary human data with statistical adjustments to account for discrepancies between observed and simulated responses. Under explicit assumptions, statistical calibration preserves validity and provides more precise estimates of causal effects at lower cost than experiments that rely solely on human participants. Yet the potential of both approaches depends on how well LLMs approximate the relevant populations. We consider what opportunities are overlooked when researchers focus myopically on substituting LLMs for human participants in a study. --- ### Context-aware Skin Cancer Epithelial Cell Classification with Scalable Graph Transformers Authors: Lucas Sancéré, Noémie Moreau, Katarzyna Bozek Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15783v2 Whole-slide images (WSIs) from cancer patients contain rich information that can be used for medical diagnosis or to follow treatment progress. To automate their analysis, numerous deep learning methods based on convolutional neural networks and Vision Transformers have been developed and have achieved strong performance in segmentation and classification tasks. However, due to the large size and complex cellular organization of WSIs, these models rely on patch-based representations, losing vital tissue-level context. We propose using scalable Graph Transformers on a full-WSI cell graph for classification. We evaluate this methodology on a challenging task: the classification of healthy versus tumor epithelial cells in cutaneous squamous cell carcinoma (cSCC), where both cell types exhibit very similar morphologies and are therefore difficult to differentiate for image-based approaches. We first compared image-based and graph-based methods on a single WSI. Graph Transformer models SGFormer and DIFFormer achieved balanced accuracies of $85.2 \pm 1.5$ ($\pm$ standard error) and $85.1 \pm 2.5$ in 3-fold cross-validation, respectively, whereas the best image-based method reached $81.2 \pm 3.0$. By evaluating several node feature configurations, we found that the most informative representation combined morphological and texture features as well as the cell classes of non-epithelial cells, highlighting the importance of the surrounding cellular context. We then extended our work to train on several WSIs from several patients. To address the computational constraints of image-based models, we extracted four $2560 \times 2560$ pixel patches from each image and converted them into graphs. In this setting, DIFFormer achieved a balanced accuracy of $83.6 \pm 1.9$ (3-fold cross-validation), while the state-of-the-art image-based model CellViT256 reached $78.1 \pm 0.5$. --- ### Context-aware Skin Cancer Epithelial Cell Classification with Scalable Graph Transformers Authors: Lucas Sancéré, Noémie Moreau, Katarzyna Bozek Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15783v1 Whole-slide images (WSIs) from cancer patients contain rich information that can be used for medical diagnosis or to follow treatment progress. To automate their analysis, numerous deep learning methods based on convolutional neural networks and Vision Transformers have been developed and have achieved strong performance in segmentation and classification tasks. However, due to the large size and complex cellular organization of WSIs, these models rely on patch-based representations, losing vital tissue-level context. We propose using scalable Graph Transformers on a full-WSI cell graph for classification. We evaluate this methodology on a challenging task: the classification of healthy versus tumor epithelial cells in cutaneous squamous cell carcinoma (cSCC), where both cell types exhibit very similar morphologies and are therefore difficult to differentiate for image-based approaches. We first compared image-based and graph-based methods on a single WSI. Graph Transformer models SGFormer and DIFFormer achieved balanced accuracies of $85.2 \pm 1.5$ ($\pm$ standard error) and $85.1 \pm 2.5$ in 3-fold cross-validation, respectively, whereas the best image-based method reached $81.2 \pm 3.0$. By evaluating several node feature configurations, we found that the most informative representation combined morphological and texture features as well as the cell classes of non-epithelial cells, highlighting the importance of the surrounding cellular context. We then extended our work to train on several WSIs from several patients. To address the computational constraints of image-based models, we extracted four $2560 \times 2560$ pixel patches from each image and converted them into graphs. In this setting, DIFFormer achieved a balanced accuracy of $83.6 \pm 1.9$ (3-fold cross-validation), while the state-of-the-art image-based model CellViT256 reached $78.1 \pm 0.5$. --- ### Meteorological data and Sky Images meets Neural Models for Photovoltaic Power Forecasting Authors: Ines Montoya-Espinagosa, Antonio Agudo Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15782v1 Due to the rise in the use of renewable energies as an alternative to traditional ones, and especially solar energy, there is increasing interest in studying how to address photovoltaic forecasting in the face of the challenge of variability in photovoltaic energy production, using different methodologies. This work develops a hybrid approach for short and long-term forecasting based on two studies with the same purpose. A multimodal approach that combines images of the sky and photovoltaic energy history with meteorological data is proposed. The main goal is to improve the accuracy of ramp event prediction, increase the robustness of forecasts in cloudy conditions, and extend capabilities beyond nowcasting, to support more efficient operation of the power grid and better management of solar variability. Deep neural models are used for both nowcasting and forecasting solutions, incorporating individual and multiple meteorological variables, as well as an analytical solar position. The results demonstrate that the inclusion of meteorological data, particularly the surface long-wave, radiation downwards, and the combination of wind and solar position, significantly improves current predictions in both nowcasting and forecasting tasks, especially on cloudy days. This study highlights the importance of integrating diverse data sources to improve the reliability and interpretability of solar energy prediction models. --- ### Neural Scaling Laws for Boosted Jet Tagging Authors: Matthias Vigl, Nicole Hartman, Michael Kagan, Lukas Heinrich Published: 2026-02-17 Categories: hep-ex, cs.LG, hep-ph, physics.data-an arXiv: https://arxiv.org/abs/2602.15781v1 The success of Large Language Models (LLMs) has established that scaling compute, through joint increases in model capacity and dataset size, is the primary driver of performance in modern machine learning. While machine learning has long been an integral component of High Energy Physics (HEP) data analysis workflows, the compute used to train state-of-the-art HEP models remains orders of magnitude below that of industry foundation models. With scaling laws only beginning to be studied in the field, we investigate neural scaling laws for boosted jet classification using the public JetClass dataset. We derive compute optimal scaling laws and identify an effective performance limit that can be consistently approached through increased compute. We study how data repetition, common in HEP where simulation is expensive, modifies the scaling yielding a quantifiable effective dataset size gain. We then study how the scaling coefficients and asymptotic performance limits vary with the choice of input features and particle multiplicity, demonstrating that increased compute reliably drives performance toward an asymptotic limit, and that more expressive, lower-level features can raise the performance limit and improve results at fixed dataset size. ---