# Research Papers — 2026-02 · bundle page 64 of 210

> Full-text markdown of papers #3151–3200 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/64
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/63.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/65.md)

### Leveraging Contrastive Learning for a Similarity-Guided Tampered Document Data Generation Pipeline

Authors: Mohamed Dhouib, Davide Buscaldi, Sonia Vanier, Aymen Shabou
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17322v1

Detecting tampered text in document images is a challenging task due to data scarcity. To address this, previous work has attempted to generate tampered documents using rule-based methods. However, the resulting documents often suffer from limited variety and poor visual quality, typically leaving highly visible artifacts that are rarely observed in real-world manipulations. This undermines the model's ability to learn robust, generalizable features and results in poor performance on real-world data. Motivated by this discrepancy, we propose a novel method for generating high-quality tampered document images. We first train an auxiliary network to compare text crops, leveraging contrastive learning with a novel strategy for defining positive pairs and their corresponding negatives. We also train a second auxiliary network to evaluate whether a crop tightly encloses the intended characters, without cutting off parts of characters or including parts of adjacent ones. Using a carefully designed generation pipeline that leverages both networks, we introduce a framework capable of producing diverse, high-quality tampered document images. We assess the effectiveness of our data generation pipeline by training multiple models on datasets derived from the same source images, generated using our method and existing approaches, under identical training protocols. Evaluating these models on various open-source datasets shows that our pipeline yields consistent performance improvements across architectures and datasets.

---

### The Sound of Death: Deep Learning Reveals Vascular Damage from Carotid Ultrasound

Authors: Christoph Balada, Aida Romano-Martinez, Payal Varshney, Vincent ten Cate, Katharina Geschke, Jonas Tesarz, Paul Claßen, Alexander K. Schuster, Dativa Tibyampansha, Karl-Patrik Kresoja, Philipp S. Wild, Sheraz Ahmed et al.
Published: 2026-02-19
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.17321v1

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, yet early risk detection is often limited by available diagnostics. Carotid ultrasound, a non-invasive and widely accessible modality, encodes rich structural and hemodynamic information that is largely untapped. Here, we present a machine learning (ML) framework that extracts clinically meaningful representations of vascular damage (VD) from carotid ultrasound videos, using hypertension as a weak proxy label. The model learns robust features that are biologically plausible, interpretable, and strongly associated with established cardiovascular risk factors, comorbidities, and laboratory measures. High VD stratifies individuals for myocardial infarction, cardiac death, and all-cause mortality, matching or outperforming conventional risk models such as SCORE2. Explainable AI analyses reveal that the model relies on vessel morphology and perivascular tissue characteristics, uncovering novel functional and anatomical signatures of vascular damage. This work demonstrates that routine carotid ultrasound contains far more prognostic information than previously recognized. Our approach provides a scalable, non-invasive, and cost-effective tool for population-wide cardiovascular risk assessment, enabling earlier and more personalized prevention strategies without reliance on laboratory tests or complex clinical inputs.

---

### Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation

Authors: Bogdan Kostić, Conor Fallon, Julian Risch, Alexander Löser
Published: 2026-02-19
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.17316v1

The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison. Yet, their reliability is increasingly questioned due to sensitivity to shallow variations in input prompts. This paper examines how controlled, truth-conditionally equivalent lexical and syntactic perturbations affect the absolute performance and relative ranking of 23 contemporary LLMs across three benchmarks: MMLU, SQuAD, and AMEGA. We employ two linguistically principled pipelines to generate meaning-preserving variations: one performing synonym substitution for lexical changes, and another using dependency parsing to determine applicable syntactic transformations. Results show that lexical perturbations consistently induce substantial, statistically significant performance degradation across nearly all models and tasks, while syntactic perturbations have more heterogeneous effects, occasionally improving results. Both perturbation types destabilize model leaderboards on complex tasks. Furthermore, model robustness did not consistently scale with model size, revealing strong task dependence. Overall, the findings suggest that LLMs rely more on surface-level lexical patterns than on abstract linguistic competence, underscoring the need for robustness testing as a standard component of LLM evaluation.

---

### Flickering Multi-Armed Bandits

Authors: Sourav Chakraborty, Amit Kiran Rege, Claire Monteleoni, Lijun Chen
Published: 2026-02-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.17315v3

We introduce Flickering Multi-Armed Bandits (FMAB) to model sequential decision-making in environments with changing action availability, where accessibility of the next action is restricted to a subset dependent on the agent's current choice. We formalize these constraints through stochastically evolving graphs where actions are limited to local neighborhoods. This mobility-constrained structure imposes a dual challenge: the statistical requirement of information acquisition and the physical overhead of navigation. We analyze FMAB under i.i.d. Erdős--R'enyi and Edge-Markovian process, proposing a two-phase lazy random walk algorithm for robust exploration. We establish high-probability sublinear regret bounds and prove near-optimality via a matching information-theoretic lower bound. Our results characterize the intrinsic cost of learning under local-move constraints, complemented by a robotic disaster-response simulation.

---

### Open Datasets in Learning Analytics: Trends, Challenges, and Best PRACTICE

Authors: Valdemar Švábenský, Brendan Flanagan, Erwin Daniel López Zapata, Atsushi Shimada
Published: 2026-02-19
Categories: cs.CY, cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2602.17314v2

Open datasets play a crucial role in three research domains that intersect data science and education: learning analytics, educational data mining, and artificial intelligence in education. Researchers in these domains apply computational methods to analyze data from educational contexts, aiming to better understand and improve teaching and learning. Providing open datasets alongside research papers supports reproducibility, collaboration, and trust in research findings. It also provides individual benefits for authors, such as greater visibility, credibility, and citation potential. Despite these advantages, the availability of open datasets and the associated practices within the learning analytics research communities, especially at their flagship conference venues, remain unclear. We surveyed available datasets published alongside research papers in learning analytics. We manually examined 1,125 papers from three flagship conferences (LAK, EDM, and AIED) over the past five years. We discovered, categorized, and analyzed 172 datasets used in 204 publications. Our study presents the most comprehensive collection and analysis of open educational datasets to date, along with the most detailed categorization. Of the 172 datasets identified, 143 were not captured in any prior survey of open data in learning analytics. We provide insights into the datasets' context, analytical methods, use, and other properties. Based on this survey, we summarize the current gaps in the field. Furthermore, we list practical recommendations, advice, and 8-item guidelines under the acronym PRACTICE with a checklist to help researchers publish their data. Lastly, we share our original dataset: an annotated inventory detailing the discovered datasets and the corresponding publications. We hope these findings will support further adoption of open data practices in learning analytics communities and beyond.

---

### LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy

Authors: Hsin-Jung Yang, Zhanhong Jiang, Prajwal Koirala, Qisai Liu, Cody Fleming, Soumik Sarkar
Published: 2026-02-19
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2602.17312v2

Offline safe reinforcement learning (RL) is increasingly important for cyber-physical systems (CPS), where safety violations during training are unacceptable and only pre-collected data are available. Existing offline safe RL methods typically balance reward-safety tradeoffs through constraint relaxation or joint optimization, but they often lack structural mechanisms to prevent safety drift. We propose LexiSafe, a lexicographic offline RL framework designed to preserve safety-aligned behavior. We first develop LexiSafe-SC, a single-cost formulation for standard offline safe RL, and derive safety-violation and performance-suboptimality bounds that together yield sample-complexity guarantees. We then extend the framework to hierarchical safety requirements with LexiSafe-MC, which supports multiple safety costs and admits its own sample-complexity analysis. Empirically, LexiSafe demonstrates reduced safety violations and improved task performance compared to constrained offline baselines. By unifying lexicographic prioritization with structural bias, LexiSafe offers a practical and theoretically grounded approach for safety-critical CPS decision-making.

---

### Attachment Anchors: A Novel Framework for Laparoscopic Grasping Point Prediction in Colorectal Surgery

Authors: Dennis N. Schneider, Lars Wagner, Daniel Rueckert, Dirk Wilhelm
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17310v1

Accurate grasping point prediction is a key challenge for autonomous tissue manipulation in minimally invasive surgery, particularly in complex and variable procedures such as colorectal interventions. Due to their complexity and prolonged duration, colorectal procedures have been underrepresented in current research. At the same time, they pose a particularly interesting learning environment due to repetitive tissue manipulation, making them a promising entry point for autonomous, machine learning-driven support. Therefore, in this work, we introduce attachment anchors, a structured representation that encodes the local geometric and mechanical relationships between tissue and its anatomical attachments in colorectal surgery. This representation reduces uncertainty in grasping point prediction by normalizing surgical scenes into a consistent local reference frame. We demonstrate that attachment anchors can be predicted from laparoscopic images and incorporated into a grasping framework based on machine learning. Experiments on a dataset of 90 colorectal surgeries demonstrate that attachment anchors improve grasping point prediction compared to image-only baselines. There are particularly strong gains in out-of-distribution settings, including unseen procedures and operating surgeons. These results suggest that attachment anchors are an effective intermediate representation for learning-based tissue manipulation in colorectal surgery.

---

### MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions

Authors: Hui Min Wong, Philip Heesen, Pascal Janetzky, Martin Bendszus, Stefan Feuerriegel
Published: 2026-02-19
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.17308v1

Large language models (LLMs) are increasingly used for diagnostic tasks in medicine. In clinical practice, the correct diagnosis can rarely be immediately inferred from the initial patient presentation alone. Rather, reaching a diagnosis often involves systematic history taking, during which clinicians reason over multiple potential conditions through iterative questioning to resolve uncertainty. This process requires considering differential diagnoses and actively excluding emergencies that demand immediate intervention. Yet, the ability of medical LLMs to generate informative follow-up questions and thus reason over differential diagnoses remains underexplored. Here, we introduce MedClarify, an AI agent for information-seeking that can generate follow-up questions for iterative reasoning to support diagnostic decision-making. Specifically, MedClarify computes a list of candidate diagnoses analogous to a differential diagnosis, and then proactively generates follow-up questions aimed at reducing diagnostic uncertainty. By selecting the question with the highest expected information gain, MedClarify enables targeted, uncertainty-aware reasoning to improve diagnostic performance. In our experiments, we first demonstrate the limitations of current LLMs in medical reasoning, which often yield multiple, similarly likely diagnoses, especially when patient cases are incomplete or relevant information for diagnosis is missing. We then show that our information-theoretic reasoning approach can generate effective follow-up questioning and thereby reduces diagnostic errors by ~27 percentage points (p.p.) compared to a standard single-shot LLM baseline. Altogether, MedClarify offers a path to improve medical LLMs through agentic information-seeking and to thus promote effective dialogues with medical LLMs that reflect the iterative and uncertain nature of real-world clinical reasoning.

---

### ArXiv-to-Model: A Practical Study of Scientific LM Training

Authors: Anuj Gupta
Published: 2026-02-19
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.17288v1

While frontier large language models demonstrate strong reasoning and mathematical capabilities, the practical process of training domain-specialized scientific language models from raw sources remains under-documented. In this work, we present a detailed case study of training a 1.36B-parameter scientific language model directly from raw arXiv LaTeX sources spanning mathematics, computer science, and theoretical physics. We describe an end-to-end pipeline covering metadata filtering, archive validation, LaTeX extraction, text normalization, domain-aware tokenization, and dense transformer training under constrained compute (2xA100 GPUs). Through 24 experimental runs, we analyze training stability, scaling behavior, data yield losses, and infrastructure bottlenecks. Our findings highlight how preprocessing decisions significantly affect usable token volume, how tokenization impacts symbolic stability, and how storage and I/O constraints can rival compute as limiting factors. We further analyze convergence dynamics and show stable training behavior in a data-rich regime (52B pretraining tokens). Rather than proposing a novel architecture, this work provides an engineering-grounded, transparent account of training a small scientific language model from scratch. We hope these insights support researchers operating under moderate compute budgets who seek to build domain-specialized models.

---

### Representation Collapse in Machine Translation Through the Lens of Angular Dispersion

Authors: Evgeniia Tokarchuk, Maya K. Nachesa, Sergey Troshin, Vlad Niculae
Published: 2026-02-19
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.17287v1

Modern neural translation models based on the Transformer architecture are known for their high performance, particularly when trained on high-resource datasets. A standard next-token prediction training strategy, while widely adopted in practice, may lead to overlooked artifacts such as representation collapse. Previous works have shown that this problem is especially pronounced in the representation of the deeper Transformer layers, where it often fails to efficiently utilize the geometric space. Representation collapse is even more evident in end-to-end training of continuous-output neural machine translation, where the trivial solution would be to set all vectors to the same value. In this work, we analyze the dynamics of representation collapse at different levels of discrete and continuous NMT transformers throughout training. We incorporate an existing regularization method based on angular dispersion and demonstrate empirically that it not only mitigates collapse but also improves translation quality. Furthermore, we show that quantized models exhibit similar collapse behavior and that the benefits of regularization are preserved even after quantization.

---

### Efficient privacy loss accounting for subsampling and random allocation

Authors: Vitaly Feldman, Moshe Shenfeld
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17284v2

We consider the privacy amplification properties of a sampling scheme in which a user's data isused in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps. This sampling scheme has been recently applied in the context of differentially private optimization (Chua et al., 2024a; Choquette-Choo et al., 2025) and communication-efficient high-dimensional private aggregation (Asi et al., 2026), where it was shown to have utility advantages over the standard Poisson sampling. Theoretical analyses of this sampling scheme (Feldman & Shenfeld, 2025; Dong et al., 2025) lead to bounds that are close to those of Poisson sampling, yet still have two significant shortcomings. First, in many practical settings, the resulting privacy parameters are not tight due to the approximation steps in the analysis. Second, the computed parameters are either the hockey stick or Renyi divergence, both of which introduce overheads when used in privacy loss accounting. In this work, we demonstrate that the privacy loss distribution (PLD) of random allocation applied to any differentially private algorithm can be computed efficiently. When applied to the Gaussian mechanism, our results demonstrate that the privacy-utility trade-off for random allocation is at least as good as that of Poisson subsampling. In particular, random allocation is better suited for training via DP-SGD. To support these computations, our work develops new tools for general privacy loss accounting based on a notion of PLD realization. This notion allows us to extend accurate privacy loss accounting to subsampling which previously required manual noise-mechanism-specific analysis.

---

### Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective

Authors: Yukun Chen, Xinyu Zhang, Boyi Deng, Jialong Tang, Yu Wan, Fei Huang, Yuxi Zhou, Baosong Yang, Yiming Li
Published: 2026-02-19
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.17283v2

As large language models (LLMs) are employed worldwide, existing evaluation paradigms for their multilingual capabilities primarily focus on factual task performance, neglecting the ability to judge content's deep-level values across multiple languages. To bridge this gap, we first reveal two primary challenges in constructing values judgment benchmarks, cultural diversity and disciplinary complexity, and propose a novel two-stage human-AI collaborative annotation framework to alleviate them. This framework identifies the issue scope and nature, establishes specific annotation criteria, and utilizes multiple LLMs for final review. Building upon this framework, we introduce \textbf{X-Value}, the first \textit{Cross-lingual Values Judgment Benchmark} designed to evaluate the capability of LLMs in judging deep-level values of content. X-Value comprises 4,750 Question-Answer pairs across 14 languages, covering 7 major global issue categories, and provides 12 granular annotation metadata to facilitate a rigorous evaluation of model performance. Systematic evaluations of X-Value are conducted across 17 LLMs using distinct prompting strategies. Multi-dimensional analysis of accuracy and F1-scores reveals their limitations in cross-lingual values judgment and indicates performance disparities across categories and languages. This work highlights the urgent need to improve the underlying, values-aware content judgment capability of LLMs.\footnote{Samples of X-Value are available at https://huggingface.co/datasets/Whitolf/X-Value.}

---

### Quantum Scrambling Born Machine

Authors: Marcin Płodzień
Published: 2026-02-19
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2602.17281v2

Quantum generative modeling, where the Born rule naturally defines probability distributions through measurement of parameterized quantum states, is a promising near-term application of quantum computing. We propose a Quantum Scrambling Born Machine in which a fixed entangling unitary -- acting as a scrambling reservoir -- provides multi-qubit entanglement, while only single-qubit rotations are optimized. We consider three entangling unitaries -- a Haar random unitary and two physically realizable approximations, a finite-depth brickwork random circuit and analog time evolution under nearest-neighbor spin-chain Hamiltonians -- and show that, for the benchmark distributions and system sizes considered, once the entangler produces near-Haar-typical entanglement the model learns the target distribution with weak sensitivity to the scrambler's microscopic origin. Finally, promoting the Hamiltonian couplings to trainable parameters casts the generative task as a variational Hamiltonian problem, with performance competitive with representative classical generative models at matched parameter count.

---

### Quantum Scrambling Born Machine

Authors: Marcin Płodzień
Published: 2026-02-19
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2602.17281v1

Quantum generative modeling, where the Born rule naturally defines probability distributions through measurement of parameterized quantum states, is a promising near-term application of quantum computing. We propose a Quantum Scrambling Born Machine in which a fixed entangling unitary -- acting as a scrambling reservoir -- provides multi-qubit entanglement, while only single-qubit rotations are optimized. We consider three entangling unitaries -- a Haar random unitary and two physically realizable approximations, a finite-depth brickwork random circuit and analog time evolution under nearest-neighbor spin-chain Hamiltonians -- and show that, for the benchmark distributions and system sizes considered, once the entangler produces near-Haar-typical entanglement the model learns the target distribution with weak sensitivity to the scrambler's microscopic origin. Finally, promoting the Hamiltonian couplings to trainable parameters casts the generative task as a variational Hamiltonian problem, with performance competitive with representative classical generative models at matched parameter count.

---

### Physics Encoded Spatial and Temporal Generative Adversarial Network for Tropical Cyclone Image Super-resolution

Authors: Ruoyi Zhang, Jiawei Yuan, Lujia Ye, Runling Yu, Liling Zhao
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17277v1

High-resolution satellite imagery is indispensable for tracking the genesis, intensification, and trajectory of tropical cyclones (TCs). However, existing deep learning-based super-resolution (SR) methods often treat satellite image sequences as generic videos, neglecting the underlying atmospheric physical laws governing cloud motion. To address this, we propose a Physics Encoded Spatial and Temporal Generative Adversarial Network (PESTGAN) for TC image super-resolution. Specifically, we design a disentangled generator architecture incorporating a PhyCell module, which approximates the vorticity equation via constrained convolutions and encodes the resulting approximate physical dynamics as implicit latent representations to separate physical dynamics from visual textures. Furthermore, a dual-discriminator framework is introduced, employing a temporal discriminator to enforce motion consistency alongside spatial realism. Experiments on the Digital Typhoon dataset for 4$\times$ upscaling demonstrate that PESTGAN establishes a better performance in structural fidelity and perceptual quality. While maintaining competitive pixel-wise accuracy compared to existing approaches, our method significantly excels in reconstructing meteorologically plausible cloud structures with superior physical fidelity.

---

### RLGT: A reinforcement learning framework for extremal graph theory

Authors: Ivan Damnjanović, Uroš Milivojević, Irena Đorđević, Dragan Stevanović
Published: 2026-02-19
Categories: cs.LG, math.CO
arXiv: https://arxiv.org/abs/2602.17276v2

Reinforcement learning (RL) is a subfield of machine learning that focuses on developing models that can autonomously learn optimal decision-making strategies over time. In a recent pioneering paper, Wagner demonstrated how the Deep Cross-Entropy RL method can be applied to tackle various problems from extremal graph theory by reformulating them as combinatorial optimization problems. Subsequently, many researchers became interested in refining and extending the framework introduced by Wagner, thereby creating various RL environments specialized for graph theory. Moreover, a number of problems from extremal graph theory were solved through the use of RL. In particular, several inequalities concerning the Laplacian spectral radius of graphs were refuted, new lower bounds were obtained for certain Ramsey numbers, and contributions were made to the Turán-type extremal problem in which the forbidden structures are cycles of length three and four. Here, we present Reinforcement Learning for Graph Theory (RLGT), a novel RL framework that systematizes the previous work and provides support for both undirected and directed graphs, with or without loops, and with an arbitrary number of edge colors. The framework efficiently represents graphs and aims to facilitate future RL-based research in extremal graph theory through optimized computational performance and a clean and modular design.

---

### Gaussian Surrogates for Poisson Imaging: Some Theoretical and Empirical Results

Authors: Alexandra Spitzer, Lorenzo Baldassari, Valentin Derbanot, Ivan Dokmanić
Published: 2026-02-19
Categories: eess.IV, stat.ML
arXiv: https://arxiv.org/abs/2602.17274v2

In imaging inverse problems with Poisson-distributed measurements, it is common to use objectives derived from the Poisson likelihood. But performance is often evaluated by mean squared error (MSE), which raises a practical question: how much does a Poisson objective matter for MSE, even at low dose? We analyze the MSE of Poisson and Gaussian surrogate reconstruction objectives under Poisson noise. In a stylized diagonal model, we show that the unregularized Poisson maximum-likelihood estimator can incur large MSE at low dose, while Poisson MAP mitigates this instability through regularization. We then study two Gaussian surrogate objectives: a heteroscedastic quadratic objective motivated by the normal approximation of Poisson data, and a homoscedastic quadratic objective that yields a simple linear estimator. We show that both surrogates can achieve MSE comparable to Poisson MAP in the low-dose regime, despite departing from the Poisson likelihood. Numerical computed tomography experiments indicate that these conclusions extend beyond the stylized setting of our theoretical analysis.

---

### Federated Latent Space Alignment for Multi-user Semantic Communications

Authors: Giuseppe Di Poce, Mario Edoardo Pandolfo, Emilio Calvanese Strinati, Paolo Di Lorenzo
Published: 2026-02-19
Categories: cs.IT, cs.AI
arXiv: https://arxiv.org/abs/2602.17271v1

Semantic communication aims to convey meaning for effective task execution, but differing latent representations in AI-native devices can cause semantic mismatches that hinder mutual understanding. This paper introduces a novel approach to mitigating latent space misalignment in multi-agent AI- native semantic communications. In a downlink scenario, we consider an access point (AP) communicating with multiple users to accomplish a specific AI-driven task. Our method implements a protocol that shares a semantic pre-equalizer at the AP and local semantic equalizers at user devices, fostering mutual understanding and task-oriented communication while considering power and complexity constraints. To achieve this, we employ a federated optimization for the decentralized training of the semantic equalizers at the AP and user sides. Numerical results validate the proposed approach in goal-oriented semantic communication, revealing key trade-offs among accuracy, com- munication overhead, complexity, and the semantic proximity of AI-native communication devices.

---

### Unified Latents (UL): How to train your latents

Authors: Jonathan Heek, Emiel Hoogeboom, Thomas Mensink, Tim Salimans
Published: 2026-02-19
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.17270v1

We present Unified Latents (UL), a framework for learning latent representations that are jointly regularized by a diffusion prior and decoded by a diffusion model. By linking the encoder's output noise to the prior's minimum noise level, we obtain a simple training objective that provides a tight upper bound on the latent bitrate. On ImageNet-512, our approach achieves competitive FID of 1.4, with high reconstruction quality (PSNR) while requiring fewer training FLOPs than models trained on Stable Diffusion latents. On Kinetics-600, we set a new state-of-the-art FVD of 1.3.

---

### Learning a Latent Pulse Shape Interface for Photoinjector Laser Systems

Authors: Alexander Klemps, Denis Ilia, Pradeep Kr. Banerjee, Ye Chen, Henrik Tünnermann, Nihat Ay
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17263v1

Controlling the longitudinal laser pulse shape in photoinjectors of Free-Electron Lasers is a powerful lever for optimizing electron beam quality, but systematic exploration of the vast design space is limited by the cost of brute-force pulse propagation simulations. We present a generative modeling framework based on Wasserstein Autoencoders to learn a differentiable latent interface between pulse shaping and downstream beam dynamics. Our empirical findings show that the learned latent space is continuous and interpretable while maintaining high-fidelity reconstructions. Pulse families such as higher-order Gaussians trace coherent trajectories, while standardizing the temporal pulse lengths shows a latent organization correlated with pulse energy. Analysis via principal components and Gaussian Mixture Models reveals a well behaved latent geometry, enabling smooth transitions between distinct pulse types via linear interpolation. The model generalizes from simulated data to real experimental pulse measurements, accurately reconstructing pulses and embedding them consistently into the learned manifold. Overall, the approach reduces reliance on expensive pulse-propagation simulations and facilitates downstream beam dynamics simulation and analysis.

---

### Quantifying and Mitigating Socially Desirable Responding in LLMs: A Desirability-Matched Graded Forced-Choice Psychometric Study

Authors: Kensuke Okada, Yui Furukawa, Kyosuke Bunji
Published: 2026-02-19
Categories: cs.CL, stat.ME
arXiv: https://arxiv.org/abs/2602.17262v2

Human self-report questionnaires are increasingly used in NLP to benchmark and audit large language models (LLMs), from persona consistency to safety and bias assessments. Yet these instruments presume honest responding; in evaluative contexts, LLMs can instead gravitate toward socially preferred answers-a form of socially desirable responding (SDR)-biasing questionnaire-derived scores and downstream conclusions. We propose a psychometric framework to quantify and mitigate SDR in questionnaire-based evaluation of LLMs. To quantify SDR, the same inventory is administered under HONEST versus FAKE-GOOD instructions, and SDR is computed as a direction-corrected standardized effect size from item response theory (IRT)-estimated latent scores. This enables comparisons across constructs and response formats, as well as against human instructed-faking benchmarks. For mitigation, we construct a graded forced-choice (GFC) Big Five inventory by selecting 30 cross-domain pairs from an item pool via constrained optimization to match desirability. Across nine instruction-following LLMs evaluated on synthetic personas with known target profiles, Likert-style questionnaires show consistently large SDR, whereas desirability-matched GFC substantially attenuates SDR while largely preserving the recovery of the intended persona profiles. These results highlight a model-dependent SDR-recovery trade-off and motivate SDR-aware reporting practices for questionnaire-based benchmarking and auditing of LLMs.

---

### EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection

Authors: Hung Mai, Loi Dinh, Duc Hai Nguyen, Dat Do, Luong Doan, Khanh Nguyen Quoc, Huan Vu, Naeem Ul Islam, Tuan Do
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17260v2

Recent advances in foundation video generators such as Sora2, Veo3, and other commercial systems have produced highly realistic synthetic videos, exposing the limitations of existing detection methods that rely on shallow embedding trajectories, image-based adaptation, or computationally heavy MLLMs. We propose EA-Swin, an Embedding-Agnostic Swin Transformer that models spatiotemporal dependencies directly on pretrained video embeddings via a factorized windowed attention design, making it compatible with generic ViT-style patch-based encoders. Moreover, we construct the EA-Video dataset, a benchmark dataset comprising 130K videos that integrates newly collected samples with curated existing datasets, covering diverse commercial and open-source generators and including unseen-generator splits for rigorous cross-distribution evaluation. Extensive experiments show that EA-Swin achieves 0.97-0.99 accuracy across major generators, outperforming prior SoTA methods (typically 0.8-0.9) by a margin of 5-20\%, while maintaining strong generalization to unseen distributions, establishing a scalable and robust solution for modern AI-generated video detection.

---

### A Multi-modal Detection System for Infrastructure-based Freight Signal Priority

Authors: Ziyan Zhang, Chuheng Wei, Xuanpeng Zhao, Siyan Li, Will Snyder, Mike Stas, Peng Hao, Kanok Boriboonsomsin, Guoyuan Wu
Published: 2026-02-19
Categories: cs.CV, eess.IV, eess.SY
arXiv: https://arxiv.org/abs/2602.17252v1

Freight vehicles approaching signalized intersections require reliable detection and motion estimation to support infrastructure-based Freight Signal Priority (FSP). Accurate and timely perception of vehicle type, position, and speed is essential for enabling effective priority control strategies. This paper presents the design, deployment, and evaluation of an infrastructure-based multi-modal freight vehicle detection system integrating LiDAR and camera sensors. A hybrid sensing architecture is adopted, consisting of an intersection-mounted subsystem and a midblock subsystem, connected via wireless communication for synchronized data transmission. The perception pipeline incorporates both clustering-based and deep learning-based detection methods with Kalman filter tracking to achieve stable real-time performance. LiDAR measurements are registered into geodetic reference frames to support lane-level localization and consistent vehicle tracking. Field evaluations demonstrate that the system can reliably monitor freight vehicle movements at high spatio-temporal resolution. The design and deployment provide practical insights for developing infrastructure-based sensing systems to support FSP applications.

---

### SCOPE: Structured Prototype-Guided Adaptation for EEG Foundation Models with Limited Labels

Authors: Jingying Ma, Feng Wu, Yucheng Xing, Qika Lin, Tianyu Liu, Chenyu Liu, Ziyu Jia, Mengling Feng
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17251v3

Electroencephalography (EEG) foundation models (EFMs) have shown strong potential for transferable representation learning, yet their adaptation in realistic settings remains challenging when only a few labeled subjects are available. We show that this challenge stems from a structural mismatch between noisy, limited supervision and the highly plastic parameter space of EFMs, reflected in three key failure modes: overconfident miscalibration, prediction collapse, and representation drift caused by unconstrained parameter updates. To address these challenges, we propose SCOPE, a Structured COnfidence-aware Prototype-guided framework for label-limited EFM adaptation. SCOPE first constructs cohort-level external supervision to provide persistent guidance and further derives confidence-aware pseudo-labels to select reliable unlabeled samples for adaptation. Building on the constructed external supervision, SCOPE introduces ProAdapter, a lightweight prototype-conditioned adapter that modulates frozen EFMs to preserve pretrained representations. Experiments across 50 label-limited adaptation settings, covering 6 EEG tasks, 5 EFM backbones, and 5%-50% training labeled-subject ratios, show that SCOPE consistently achieves strong performance and efficiency.

---

### Inferring Height from Earth Embeddings: First insights using Google AlphaEarth

Authors: Alireza Hamoudzadeh, Valeria Belloni, Roberta Ravanelli
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17250v1

This study investigates whether the geospatial and multimodal features encoded in \textit{Earth Embeddings} can effectively guide deep learning (DL) regression models for regional surface height mapping. In particular, we focused on AlphaEarth Embeddings at 10 m spatial resolution and evaluated their capability to support terrain height inference using a high-quality Digital Surface Model (DSM) as reference. U-Net and U-Net++ architectures were thus employed as lightweight convolutional decoders to assess how well the geospatial information distilled in the embeddings can be translated into accurate surface height estimates. Both architectures achieved strong training performance (both with $R^2 = 0.97$), confirming that the embeddings encode informative and decodable height-related signals. On the test set, performance decreased due to distribution shifts in height frequency between training and testing areas. Nevertheless, U-Net++ shows better generalization ($R^2 = 0.84$, median difference = -2.62 m) compared with the standard U-Net ($R^2 = 0.78$, median difference = -7.22 m), suggesting enhanced robustness to distribution mismatch. While the testing RMSE (approximately 16 m for U-Net++) and residual bias highlight remaining challenges in generalization, strong correlations indicate that the embeddings capture transferable topographic patterns. Overall, the results demonstrate the promising potential of AlphaEarth Embeddings to guide DL-based height mapping workflows, particularly when combined with spatially aware convolutional architectures, while emphasizing the need to address bias for improved regional transferability.

---

### Web Agents Should Use Typed Actions Instead of Click-Based Browsing

Authors: Linxi Jiang, Rui Xi, Zhijie Liu, Shuo Chen, Zhiqiang Lin, Suman Nath
Published: 2026-02-19
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.17245v2

This position paper argues that building a reliable agentic Web requires shifting from low-level interaction primitives to typed actions supported by a semantic layer. Today's web agents primarily operate through clicks, keystrokes, and DOM manipulation, which leads to brittle long-horizon behavior, high execution cost, and limited auditability. We propose web verbs as a concrete design for this layer. A verb exposes a web operation as a typed function with structured inputs, structured outputs, and documented behavior, whether it is backed by a server-side Web API or a maintained client-side workflow. Verb calls can carry preconditions, postconditions, policy tags, and logging hooks, allowing agents to synthesize concise programs with explicit control flow and data flow and to produce checkable execution traces. Using representative case studies, we illustrate how verb-level composition can produce correct, reproducible outcomes, while browser agents using low-level interaction primitives may produce brittle behavior or incorrect reasoning. We conclude with a call to action on standardization, developer tooling, and community processes needed to make this semantic layer deployable and trustworthy at web scale.

---

### CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations

Authors: Oleksii Furman, Patryk Marszałek, Jan Masłowski, Piotr Gaiński, Maciej Zięba, Marek Śmieja
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17244v1

Counterfactual explanations (CFs) provide human-interpretable insights into model's predictions by identifying minimal changes to input features that would alter the model's output. However, existing methods struggle to generate multiple high-quality explanations that (1) affect only a small portion of the features, (2) can be applied to tabular data with heterogeneous features, and (3) are consistent with the user-defined constraints. We propose CounterFlowNet, a generative approach that formulates CF generation as sequential feature modification using conditional Generative Flow Networks (GFlowNet). CounterFlowNet is trained to sample CFs proportionally to a user-specified reward function that can encode key CF desiderata: validity, sparsity, proximity and plausibility, encouraging high-quality explanations. The sequential formulation yields highly sparse edits, while a unified action space seamlessly supports continuous and categorical features. Moreover, actionability constraints, such as immutability and monotonicity of features, can be enforced at inference time via action masking, without retraining. Experiments on eight datasets under two evaluation protocols demonstrate that CounterFlowNet achieves superior trade-offs between validity, sparsity, plausibility, and diversity with full satisfaction of the given constraints.

---

### TAPO-Structured Description Logic for Information Behavior: Procedural and Oracle-Based Extensions

Authors: Takao Inoué
Published: 2026-02-19
Categories: cs.LO, cs.AI
arXiv: https://arxiv.org/abs/2602.17242v1

We introduce \emph{TAPO-Structured Description Logic} (TAPO--DL), a formal extension of classical description logic designed to model \emph{information behavior} as a structured, dynamic process. TAPO--DL extends the standard T--Box/A--Box architecture with two additional layers: a \emph{Procedural Box} (P--Box), which supports concept-driven, imperative-style programs such as conditional and iterative actions, and an \emph{Oracle Box} (O--Box), which formalizes controlled interaction with external information sources. While the terminological and assertional components capture static conceptual and factual knowledge, the procedural and oracle-based components enable the explicit representation of information-generating actions and external validation. We provide a unified semantic framework for TAPO--DL based on a co-generative, sheaf-theoretic interpretation, in which local informational states are modeled as sections and informational stability corresponds to the existence of coherent global structures. Within this setting, informational truth is characterized as stability under repeated agentive interaction rather than correspondence to a fixed global state. By integrating description logic with procedural dynamics, oracle-based reasoning, and sheaf-theoretic semantics, TAPO--DL offers a principled formal framework for analyzing information behavior in contexts involving interaction, uncertainty, and contextuality.

---

### All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection and Mitigation in LLM Backtesting

Authors: Zeyu Zhang, Ryan Chen, Bradly C. Stadie
Published: 2026-02-19
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.17234v2

Backtesting LLMs on resolved events assumes models reason only from pre-cutoff knowledge, yet pretrained models inevitably leak post-cutoff knowledge. We introduce a claim-level evaluation framework that decomposes prediction rationales into atomic claims and applies Shapley values to quantify each claim's decision impact, yielding \textbf{Shapley-DCLR} (\textbf{Shapley}-weighted \textbf{D}ecision-\textbf{C}ritical \textbf{L}eakage \textbf{R}ate) -- an interpretable metric measuring what fraction of decision-driving reasoning is contaminated. We further propose \textbf{TimeSPEC} (\textbf{Time}-\textbf{S}upervised \textbf{P}rediction with \textbf{E}xtracted \textbf{C}laims), an inference-time architecture that interleaves temporally-filtered retrieval with claim-level supervision, producing predictions grounded entirely in pre-cutoff evidence. Across three LLMs, the ablation experiments confirm retrieval and supervision are jointly necessary; and a three-task probe further illstrates that the performance cost of temporal enforcement scales with each task's reliance on post-cutoff information.

---

### HiMAP: History-aware Map-occupancy Prediction with Fallback

Authors: Yiming Xu, Yi Yang, Hao Cheng, Monika Sester
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17231v1

Accurate motion forecasting is critical for autonomous driving, yet most predictors rely on multi-object tracking (MOT) with identity association, assuming that objects are correctly and continuously tracked. When tracking fails due to, e.g., occlusion, identity switches, or missed detections, prediction quality degrades and safety risks increase. We present \textbf{HiMAP}, a tracking-free, trajectory prediction framework that remains reliable under MOT failures. HiMAP converts past detections into spatiotemporally invariant historical occupancy maps and introduces a historical query module that conditions on the current agent state to iteratively retrieve agent-specific history from unlabeled occupancy representations. The retrieved history is summarized by a temporal map embedding and, together with the final query and map context, drives a DETR-style decoder to produce multi-modal future trajectories. This design lifts identity reliance, supports streaming inference via reusable encodings, and serves as a robust fallback when tracking is unavailable. On Argoverse~2, HiMAP achieves performance comparable to tracking-based methods while operating without IDs, and it substantially outperforms strong baselines in the no-tracking setting, yielding relative gains of 11\% in FDE, 12\% in ADE, and a 4\% reduction in MR over a fine-tuned QCNet. Beyond aggregate metrics, HiMAP delivers stable forecasts for all agents simultaneously without waiting for tracking to recover, highlighting its practical value for safety-critical autonomy. The code is available under: https://github.com/XuYiMing83/HiMAP.

---

### Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy

Authors: Bianca Raimondi, Maurizio Gabbrielli
Published: 2026-02-19
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.17229v2

The black-box nature of Large Language Models necessitates novel evaluation frameworks that transcend surface-level performance metrics. This study investigates the internal neural representations of cognitive complexity using Bloom's Taxonomy as a hierarchical lens. By analyzing high-dimensional activation vectors from different LLMs, we probe whether different cognitive levels, ranging from basic recall (Remember) to abstract synthesis (Create), are linearly separable within the model's residual streams. Our results demonstrate that linear classifiers achieve approximately 95% mean accuracy across all Bloom levels, providing strong evidence that cognitive level is encoded in a linearly accessible subspace of the model's representations. These findings provide evidence that the model resolves the cognitive difficulty of a prompt early in the forward pass, with representations becoming increasingly separable across layers.

---

### Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs

Authors: Arka Pal, Louai Zahran, William Gvozdjak, Akilesh Potti, Micah Goldblum
Published: 2026-02-19
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.17223v1

As large language models (LLMs) continue to grow in size, fewer users are able to host and run models locally. This has led to increased use of third-party hosting services. However, in this setting, there is a lack of guarantees on the computation performed by the inference provider. For example, a dishonest provider may replace an expensive large model with a cheaper-to-run weaker model and return the results from the weaker model to the user. Existing tools to verify inference typically rely on methods from cryptography such as zero-knowledge proofs (ZKPs), but these add significant computational overhead, and remain infeasible for use for large models. In this work, we develop a new insight -- that given a method for performing private LLM inference, one can obtain forms of verified inference at marginal extra cost. Specifically, we propose two new protocols which leverage privacy-preserving LLM inference in order to provide guarantees over the inference that was carried out. Our approaches are cheap, requiring the addition of a few extra tokens of computation, and have little to no downstream impact. As the fastest privacy-preserving inference methods are typically faster than ZK methods, the proposed protocols also improve verification runtime. Our work provides novel insights into the connections between privacy and verifiability in LLM inference.

---

### Decoding the Human Factor: High Fidelity Behavioral Prediction for Strategic Foresight

Authors: Ben Yellin, Ehud Ezra, Mark Foreman, Shula Grinapol
Published: 2026-02-19
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.17222v1

Predicting human decision-making in high-stakes environments remains a central challenge for artificial intelligence. While large language models (LLMs) demonstrate strong general reasoning, they often struggle to generate consistent, individual-specific behavior, particularly when accurate prediction depends on complex interactions between psychological traits and situational constraints. Prompting-based approaches can be brittle in this setting, exhibiting identity drift and limited ability to leverage increasingly detailed persona descriptions. To address these limitations, we introduce the Large Behavioral Model (LBM), a behavioral foundation model fine-tuned to predict individual strategic choices with high fidelity. LBM shifts from transient persona prompting to behavioral embedding by conditioning on a structured, high-dimensional trait profile derived from a comprehensive psychometric battery. Trained on a proprietary dataset linking stable dispositions, motivational states, and situational constraints to observed choices, LBM learns to map rich psychological profiles to discrete actions across diverse strategic dilemmas. In a held-out scenario evaluation, LBM fine-tuning improves behavioral prediction relative to the unadapted Llama-3.1-8B-Instruct backbone and performs comparably to frontier baselines when conditioned on Big Five traits. Moreover, we find that while prompting-based baselines exhibit a complexity ceiling, LBM continues to benefit from increasingly dense trait profiles, with performance improving as additional trait dimensions are provided. Together, these results establish LBM as a scalable approach for high-fidelity behavioral simulation, enabling applications in strategic foresight, negotiation analysis, cognitive security, and decision support.

---

### From Labor to Collaboration: A Methodological Experiment Using AI Agents to Augment Research Perspectives in Taiwan's Humanities and Social Sciences

Authors: Yi-Chih Huang
Published: 2026-02-19
Categories: cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2602.17221v1

Generative AI is reshaping knowledge work, yet existing research focuses predominantly on software engineering and the natural sciences, with limited methodological exploration for the humanities and social sciences. Positioned as a "methodological experiment," this study proposes an AI Agent-based collaborative research workflow (Agentic Workflow) for humanities and social science research. Taiwan's Claude.ai usage data (N = 7,729 conversations, November 2025) from the Anthropic Economic Index (AEI) serves as the empirical vehicle for validating the feasibility of this methodology. This study operates on two levels: the primary level is the design and validation of a methodological framework - a seven-stage modular workflow grounded in three principles: task modularization, human-AI division of labor, and verifiability, with each stage delineating clear roles for human researchers (research judgment and ethical decisions) and AI Agents (information retrieval and text generation); the secondary level is the empirical analysis of AEI Taiwan data - serving as an operational demonstration of the workflow's application to secondary data research, showcasing both the process and output quality (see Appendix A). This study contributes by proposing a replicable AI collaboration framework for humanities and social science researchers, and identifying three operational modes of human-AI collaboration - direct execution, iterative refinement, and human-led - through reflexive documentation of the operational process. This taxonomy reveals the irreplaceability of human judgment in research question formulation, theoretical interpretation, contextualized reasoning, and ethical reflection. Limitations including single-platform data, cross-sectional design, and AI reliability risks are acknowledged.

---

### Continual learning and refinement of causal models through dynamic predicate invention

Authors: Enrique Crespo-Fernandez, Oliver Ray, Telmo de Menezes e Silva Filho, Peter Flach
Published: 2026-02-19
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.17217v1

Efficiently navigating complex environments requires agents to internalize the underlying logic of their world, yet standard world modelling methods often struggle with sample inefficiency, lack of transparency, and poor scalability. We propose a framework for constructing symbolic causal world models entirely online by integrating continuous model learning and repair into the agent's decision loop, by leveraging the power of Meta-Interpretive Learning and predicate invention to find semantically meaningful and reusable abstractions, allowing an agent to construct a hierarchy of disentangled, high-quality concepts from its observations. We demonstrate that our lifted inference approach scales to domains with complex relational dynamics, where propositional methods suffer from combinatorial explosion, while achieving sample-efficiency orders of magnitude higher than the established PPO neural-network-based baseline.

---

### Extending quantum theory with AI-assisted deterministic game theory

Authors: Florian Pauschitz, Ben Moseley, Ghislain Fourny
Published: 2026-02-19
Categories: quant-ph, cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2602.17213v1

We present an AI-assisted framework for predicting individual runs of complex quantum experiments, including contextuality and causality (adaptive measurements), within our long-term programme of discovering a local hidden-variable theory that extends quantum theory. In order to circumvent impossibility theorems, we replace the assumption of free choice (measurement independence and parameter independence) with a weaker, compatibilistic version called contingent free choice. Our framework is based on interpreting complex quantum experiments as a Chess-like game between observers and the universe, which is seen as an economic agent minimizing action. The game structures corresponding to generic experiments such as fixed-causal-order process matrices or causal contextuality scenarios, together with a deterministic non-Nashian resolution algorithm that abandons unilateral deviation assumptions (free choice) and assumes Perfect Prediction instead, were described in previous work. In this new research, we learn the reward functions of the game, which contain a hidden variable, using neural networks. The cost function is the Kullback-Leibler divergence between the frequency histograms obtained through many deterministic runs of the game and the predictions of the extended Born rule. Using our framework on the specific case of the EPR 2-2-2 experiment acts as a proof-of-concept and a toy local-realist hidden-variable model that non-Nashian quantum theory is a promising avenue towards a local hidden-variable theory. Our framework constitutes a solid foundation, which can be further expanded in order to fully discover a complete quantum theory.

---

### MGD: Moment Guided Diffusion for Maximum Entropy Generation

Authors: Etienne Lempereur, Nathanaël Cuvelle--Magar, Florentin Coeurdoux, Stéphane Mallat, Eric Vanden-Eijnden
Published: 2026-02-19
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.17211v2

Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from moment constraints but require sampling via MCMC or Langevin dynamics, which typically exhibit exponential slowdown in high dimensions. In contrast, generative models based on diffusion and flow matching efficiently transport noise to data but offer limited theoretical guarantees and can overfit when data is scarce. We introduce Moment Guided Diffusion (MGD), which combines elements of both approaches. Building on the stochastic interpolant framework, MGD samples maximum entropy distributions by solving a stochastic differential equation that guides moments toward prescribed values in finite time, thereby avoiding slow mixing in equilibrium-based methods. We formally obtain, in the large-volatility limit, convergence of MGD to the maximum entropy distribution and derive a tractable estimator of the resulting entropy computed directly from the dynamics. Applications to financial time series, turbulent flows, and cosmological fields using wavelet scattering moments yield estimates of negentropy for high-dimensional multiscale processes.

---

### MGD: Moment Guided Diffusion for Maximum Entropy Generation

Authors: Etienne Lempereur, Nathanaël Cuvelle--Magar, Florentin Coeurdoux, Stéphane Mallat, Eric Vanden-Eijnden
Published: 2026-02-19
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.17211v1

Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from moment constraints but require sampling via MCMC or Langevin dynamics, which typically exhibit exponential slowdown in high dimensions. In contrast, generative models based on diffusion and flow matching efficiently transport noise to data but offer limited theoretical guarantees and can overfit when data is scarce. We introduce Moment Guided Diffusion (MGD), which combines elements of both approaches. Building on the stochastic interpolant framework, MGD samples maximum entropy distributions by solving a stochastic differential equation that guides moments toward prescribed values in finite time, thereby avoiding slow mixing in equilibrium-based methods. We formally obtain, in the large-volatility limit, convergence of MGD to the maximum entropy distribution and derive a tractable estimator of the resulting entropy computed directly from the dynamics. Applications to financial time series, turbulent flows, and cosmological fields using wavelet scattering moments yield estimates of negentropy for high-dimensional multiscale processes.

---

### SoftDTW-CUDA-Torch: Memory-Efficient GPU-Accelerated Soft Dynamic Time Warping for PyTorch

Authors: Ron Shapira Weber, Oren Freifeld
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17206v1

We present softdtw-cuda-torch, an open-source PyTorch library for computing Soft Dynamic Time Warping (SoftDTW) on GPUs. Our implementation addresses three key limitations of existing GPU implementations of SoftDTW: a hard sequence-length cap of 1024, numerical instability in the backward pass for small smoothing parameters, and excessive GPU memory consumption from materializing pairwise distance tensors. We introduce (1) tiled anti-diagonal kernel execution that removes the sequence-length constraint, (2) a log-space back-ward pass that prevents floating-point overflow, and (3) a fused distance-computation mode that eliminates the O(BN M ) intermediate distance tensor, achieving up to 98% memory reduction compared to prior work. The library supports arbitrary sequence lengths, full PyTorch autograd integration, and Soft-DTW Barycenter computation. Code is available at https://github.com/BGU-CS-VIL/sdtw-cuda-torch.

---

### Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising

Authors: Yuduo Guo, Hao Zhang, Mingyu Li, Fujiang Yu, Yunjing Wu, Yuhan Hao, Song Huang, Yongming Liang, Xiaojing Lin, Xinyang Li, Jiamin Wu, Zheng Cai et al.
Published: 2026-02-19
Categories: astro-ph.IM, astro-ph.CO, astro-ph.GA, cs.AI
arXiv: https://arxiv.org/abs/2602.17205v2

The detection limit of astronomical imaging observations is limited by several noise sources. Some of that noise is correlated between neighbouring image pixels and exposures, so in principle could be learned and corrected. We present an astronomical self-supervised transformer-based denoising algorithm (ASTERIS), that integrates spatiotemporal information across multiple exposures. Benchmarking on mock data indicates that ASTERIS improves detection limits by 1.0 magnitude at 90% completeness and purity, while preserving the point spread function and photometric accuracy. Observational validation using data from the James Webb Space Telescope (JWST) and Subaru telescope identifies previously undetectable features, including low-surface-brightness galaxy structures and gravitationally-lensed arcs. Applied to deep JWST images, ASTERIS identifies three times more redshift > 9 galaxy candidates, with rest-frame ultraviolet luminosity 1.0 magnitude fainter, than previous methods.

---

### GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation

Authors: Ye Zhu, Kaleb S. Newman, Johannes F. Lutzeyer, Adriana Romero-Soriano, Michal Drozdzal, Olga Russakovsky
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17200v2

Despite high semantic alignment, modern text-to-image (T2I) generative models still struggle to synthesize diverse images from a given prompt. In this work, we enhance the T2I diversity through a geometric lens. Unlike most existing methods that rely primarily on entropy-based guidance to increase sample dissimilarity, we introduce Geometry-Aware Spherical Sampling (GASS) to enhance diversity by explicitly controlling both prompt-dependent and prompt-independent sources of variation. Specifically, we decompose the diversity measure in CLIP embeddings using two orthogonal directions: the text embedding, which captures semantic variation related to the prompt, and an identified orthogonal direction that captures prompt-independent variation (e.g., backgrounds). Based on this decomposition, GASS increases the geometric projection spread of generated image embeddings along both axes and guides the T2I sampling process via expanded predictions along the generation trajectory. Our experiments on different frozen T2I backbones (U-Net and DiT, diffusion and flow) and benchmarks demonstrate the effectiveness of disentangled diversity enhancement with minimal impact on image fidelity and semantic alignment.

---

### EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models

Authors: Yahong Wang, Juncheng Wu, Zhangkai Ni, Chengmei Yang, Yihang Liu, Longzhen Yang, Yuyin Zhou, Ying Wen, Lianghua He
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17196v2

Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective for accelerating inference, determining when and where to prune remains largely heuristic. Existing approaches typically rely on static, empirically selected layers, which limit interpretability and transferability across models. In this work, we introduce a matrix-entropy perspective and identify an "Entropy Collapse Layer" (ECL), where the information content of visual representations exhibits a sharp and consistent drop, which provides a principled criterion for selecting the pruning stage. Building on this observation, we propose EntropyPrune, a novel matrix-entropy-guided token pruning framework that quantifies the information value of individual visual tokens and prunes redundant ones without relying on attention maps. Moreover, to enable efficient computation, we exploit the spectral equivalence of dual Gram matrices, reducing the complexity of entropy computation and yielding up to a 64x theoretical speedup. Extensive experiments on diverse multimodal benchmarks demonstrate that EntropyPrune consistently outperforms state-of-the-art pruning methods in both accuracy and efficiency. On LLaVA-1.5-7B, our method achieves a 68.2% reduction in FLOPs while preserving 96.0% of the original performance. Furthermore, EntropyPrune generalizes effectively to high-resolution and video-based models, highlighting the strong robustness and scalability in practical MLLM acceleration. The code will be publicly available at https://github.com/YahongWang1/EntropyPrune.

---

### EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models

Authors: Yahong Wang, Juncheng Wu, Zhangkai Ni, Chengmei Yang, Yihang Liu, Longzhen Yang, Yuyin Zhou, Ying Wen, Lianghua He
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17196v1

Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective for accelerating inference, determining when and where to prune remains largely heuristic. Existing approaches typically rely on static, empirically selected layers, which limit interpretability and transferability across models. In this work, we introduce a matrix-entropy perspective and identify an "Entropy Collapse Layer" (ECL), where the information content of visual representations exhibits a sharp and consistent drop, which provides a principled criterion for selecting the pruning stage. Building on this observation, we propose EntropyPrune, a novel matrix-entropy-guided token pruning framework that quantifies the information value of individual visual tokens and prunes redundant ones without relying on attention maps. Moreover, to enable efficient computation, we exploit the spectral equivalence of dual Gram matrices, reducing the complexity of entropy computation and yielding up to a 64x theoretical speedup. Extensive experiments on diverse multimodal benchmarks demonstrate that EntropyPrune consistently outperforms state-of-the-art pruning methods in both accuracy and efficiency. On LLaVA-1.5-7B, our method achieves a 68.2% reduction in FLOPs while preserving 96.0% of the original performance. Furthermore, EntropyPrune generalizes effectively to high-resolution and video-based models, highlighting the strong robustness and scalability in practical MLLM acceleration. The code will be publicly available at https://github.com/YahongWang1/EntropyPrune.

---

### What Makes a Good Doctor Response? A Study on Text-Based Telemedicine

Authors: Adrian Cosma, Cosmin Dumitrache, Emilian Radoi
Published: 2026-02-19
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.17194v3

Text-based telemedicine has become an increasingly used mode of care, requiring clinicians to deliver medical advice clearly and effectively in writing. As platforms increasingly rely on patient ratings and feedback, clinicians face growing pressure to maintain satisfaction scores, even though these evaluations often reflect communication quality more than clinical accuracy. We analyse patient satisfaction signals in Romanian text-based telemedicine. Using a sample of anonymised text-based telemedicine consultations, we model feedback as a binary outcome, treating thumbs-up responses as positive and grouping negative or absent feedback into the other class. We extract from doctor responses interpretable, predominantly language-agnostic features (e.g., length, structural characteristics, readability proxies), along with Romanian LIWC psycholinguistic features and politeness/hedging markers where available. We train a classifier with a time-based split and perform SHAP-based analyses, which indicate that metadata dominates prediction, functioning as a strong prior, while characteristics of the response text provide a smaller but actionable signal. In subgroup correlation analyses, politeness and hedging are consistently associated with positive patient feedback, whereas lexical diversity shows a negative association.

---

### Texo: Formula Recognition within 20M Parameters

Authors: Sicheng Mao
Published: 2026-02-19
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.17189v1

In this paper we present Texo, a minimalist yet highperformance formula recognition model that contains only 20 million parameters. By attentive design, distillation and transfer of the vocabulary and the tokenizer, Texo achieves comparable performance to state-of-the-art models such as UniMERNet-T and PPFormulaNet-S, while reducing the model size by 80% and 65%, respectively. This enables real-time inference on consumer-grade hardware and even in-browser deployment. We also developed a web application to demonstrate the model capabilities and facilitate its usage for end users.

---

### Anti-causal domain generalization: Leveraging unlabeled data

Authors: Sorawit Saengkyongam, Juan L. Gamella, Andrew C. Miller, Jonas Peters, Nicolai Meinshausen, Christina Heinze-Deml
Published: 2026-02-19
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.17187v2

The problem of domain generalization concerns learning predictive models that are robust to distribution shifts when deployed in new, previously unseen environments. Existing methods typically require labeled data from multiple training environments, limiting their applicability when labeled data are scarce. In this work, we study domain generalization in an anti-causal setting, where the outcome causes the observed covariates. Under this structure, environment perturbations that affect the covariates do not propagate to the outcome, which motivates regularizing the model's sensitivity to these perturbations. Crucially, estimating these perturbation directions does not require labels, enabling us to leverage unlabeled data from multiple environments. We propose two methods that penalize the model's sensitivity to variations in the mean and covariance of the covariates across environments, respectively, and prove that these methods have worst-case optimality guarantees under certain classes of environments. Finally, we demonstrate the empirical performance of our approach on a controlled physical system and a physiological signal dataset.

---

### Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain

Authors: Seulbi Lee, Sangheum Hwang
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17186v2

Large Vision Language Models (LVLMs) have achieved remarkable progress, yet they often suffer from language bias, producing answers without relying on visual evidence. While prior work attempts to mitigate this issue through decoding strategies, architectural modifications, or curated instruction data, they typically lack a quantitative measure of how much individual training samples or tokens actually benefit from the image. In this work, we introduce Visual Information Gain (VIG), a perplexity-based metric that measures the reduction in prediction uncertainty provided by visual input. VIG enables fine-grained analysis at both sample and token levels, effectively highlighting visually grounded elements such as colors, spatial relations, and attributes. Leveraging this, we propose a VIG-guided selective training scheme that prioritizes high-VIG samples and tokens. This approach improves visual grounding and mitigates language bias, achieving superior performance with significantly reduced supervision by focusing exclusively on visually informative samples and tokens.

---

### The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions

Authors: Uğur Genç, Heng Gu, Chadha Degachi, Evangelos Niforatos, Senthil Chandrasegaran, Himanshu Verma
Published: 2026-02-19
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2602.17185v1

Large Language Model-powered conversational agents (CAs) are increasingly capable of projecting sophisticated personalities through language, but how these projections affect users is unclear. We thus examine how CA personalities expressed linguistically affect user decisions and perceptions in the context of charitable giving. In a crowdsourced study, 360 participants interacted with one of eight CAs, each projecting a personality composed of three linguistic aspects: attitude (optimistic/pessimistic), authority (authoritative/submissive), and reasoning (emotional/rational). While the CA's composite personality did not affect participants' decisions, it did affect their perceptions and emotional responses. Particularly, participants interacting with pessimistic CAs felt lower emotional state and lower affinity towards the cause, perceived the CA as less trustworthy and less competent, and yet tended to donate more toward the charity. Perceptions of trust, competence, and situational empathy significantly predicted donation decisions. Our findings emphasize the risks CAs pose as instruments of manipulation, subtly influencing user perceptions and decisions.

---

### Robustness and Reasoning Fidelity of Large Language Models in Long-Context Code Question Answering

Authors: Kishan Maharaj, Nandakishore Menon, Ashita Saxena, Srikanth Tamilselvam
Published: 2026-02-19
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.17183v1

Large language models (LLMs) increasingly assist software engineering tasks that require reasoning over long code contexts, yet their robustness under varying input conditions remains unclear. We conduct a systematic study of long-context code question answering using controlled ablations that test sensitivity to answer format, distractors, and context scale. Extending LongCodeBench Python dataset with new COBOL and Java question-answer sets, we evaluate state-of-the-art models under three settings: (i) shuffled multiple-choice options, (ii) open-ended questions and (iii) needle-in-a-haystack contexts containing relevant and adversarially irrelevant information. Results show substantial performance drops in both shuffled multiple-choice options and open-ended questions, and brittle behavior in the presence of irrelevant cues. Our findings highlight limitations of current long-context evaluations and provide a broader benchmark for assessing code reasoning in both legacy and modern systems.

---

### NRGS-SLAM: Monocular Non-Rigid SLAM for Endoscopy via Deformation-Aware 3D Gaussian Splatting

Authors: Jiwei Shan, Zeyu Cai, Yirui Li, Yongbo Chen, Lijun Han, Yun-hui Liu, Hesheng Wang, Shing Shin Cheng
Published: 2026-02-19
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.17182v1

Visual simultaneous localization and mapping (V-SLAM) is a fundamental capability for autonomous perception and navigation. However, endoscopic scenes violate the rigidity assumption due to persistent soft-tissue deformations, creating a strong coupling ambiguity between camera ego-motion and intrinsic deformation. Although recent monocular non-rigid SLAM methods have made notable progress, they often lack effective decoupling mechanisms and rely on sparse or low-fidelity scene representations, which leads to tracking drift and limited reconstruction quality. To address these limitations, we propose NRGS-SLAM, a monocular non-rigid SLAM system for endoscopy based on 3D Gaussian Splatting. To resolve the coupling ambiguity, we introduce a deformation-aware 3D Gaussian map that augments each Gaussian primitive with a learnable deformation probability, optimized via a Bayesian self-supervision strategy without requiring external non-rigidity labels. Building on this representation, we design a deformable tracking module that performs robust coarse-to-fine pose estimation by prioritizing low-deformation regions, followed by efficient per-frame deformation updates. A carefully designed deformable mapping module progressively expands and refines the map, balancing representational capacity and computational efficiency. In addition, a unified robust geometric loss incorporates external geometric priors to mitigate the inherent ill-posedness of monocular non-rigid SLAM. Extensive experiments on multiple public endoscopic datasets demonstrate that NRGS-SLAM achieves more accurate camera pose estimation (up to 50\% reduction in RMSE) and higher-quality photo-realistic reconstructions than state-of-the-art methods. Comprehensive ablation studies further validate the effectiveness of our key design choices. Source code will be publicly available upon paper acceptance.

---