# Research Papers — 2026-02 · bundle page 115 of 210 > Full-text markdown of papers #5701–5750 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/115 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/114.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/116.md) ### Semi-Supervised Cross-Domain Imitation Learning Authors: Li-Min Chu, Kai-Siang Ma, Ming-Hong Chen, Ping-Chun Hsieh Published: 2026-02-11 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2602.10793v1 Cross-domain imitation learning (CDIL) accelerates policy learning by transferring expert knowledge across domains, which is valuable in applications where the collection of expert data is costly. Existing methods are either supervised, relying on proxy tasks and explicit alignment, or unsupervised, aligning distributions without paired data, but often unstable. We introduce the Semi-Supervised CDIL (SS-CDIL) setting and propose the first algorithm for SS-CDIL with theoretical justification. Our method uses only offline data, including a small number of target expert demonstrations and some unlabeled imperfect trajectories. To handle domain discrepancy, we propose a novel cross-domain loss function for learning inter-domain state-action mappings and design an adaptive weight function to balance the source and target knowledge. Experiments on MuJoCo and Robosuite show consistent gains over the baselines, demonstrating that our approach achieves stable and data-efficient policy learning with minimal supervision. Our code is available at~ https://github.com/NYCU-RL-Bandits-Lab/CDIL. --- ### Bayesian Signal Component Decomposition via Diffusion-within-Gibbs Sampling Authors: Yi Zhang, Rui Guo, Yonina C. Eldar Published: 2026-02-11 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2602.10792v2 In signal processing, the data collected from sensing devices is often a noisy linear superposition of multiple components, and the estimation of components of interest constitutes a crucial pre-processing step. In this work, we develop a Bayesian framework for signal component decomposition, which combines Gibbs sampling with plug-and-play (PnP) diffusion priors to draw component samples from the posterior distribution. Unlike many existing methods, our framework supports incorporating component-wise model-driven and data-driven priors into diffusion models in a unified manner. Moreover, the proposed posterior sampler allows component priors to be learned separately and flexibly combined for different decomposition tasks at inference time. Under suitable assumptions, the proposed Diffusion-within-Gibbs (DiG) sampler provably produces samples from the posterior distribution. We also show that DiG can be interpreted as an extension of a class of recently proposed diffusion-based samplers, and that, for suitable classes of sensing operators, DiG better exploits the structure of the measurement model. Numerical experiments demonstrate the superior performance of our method over existing approaches. --- ### VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection Authors: Samal Mukhtar, Yinghua Yao, Zhu Sun, Mustafa Mustafa, Yew Soon Ong, Youcheng Sun Published: 2026-02-11 Categories: cs.SE, cs.AI, cs.CR, cs.IR arXiv: https://arxiv.org/abs/2602.10787v1 Software vulnerability detection (SVD) is a critical challenge in modern systems. Large language models (LLMs) offer natural-language explanations alongside predictions, but most work focuses on binary evaluation, and explanations often lack semantic consistency with Common Weakness Enumeration (CWE) categories. We propose VulReaD, a knowledge-graph-guided approach for vulnerability reasoning and detection that moves beyond binary classification toward CWE-level reasoning. VulReaD leverages a security knowledge graph (KG) as a semantic backbone and uses a strong teacher LLM to generate CWE-consistent contrastive reasoning supervision, enabling student model training without manual annotations. Students are fine-tuned with Odds Ratio Preference Optimization (ORPO) to encourage taxonomy-aligned reasoning while suppressing unsupported explanations. Across three real-world datasets, VulReaD improves binary F1 by 8-10% and multi-class classification by 30% Macro-F1 and 18% Micro-F1 compared to state-of-the-art baselines. Results show that LLMs outperform deep learning baselines in binary detection and that KG-guided reasoning enhances CWE coverage and interpretability. --- ### Kill it with FIRE: On Leveraging Latent Space Directions for Runtime Backdoor Mitigation in Deep Neural Networks Authors: Enrico Ahlers, Daniel Passon, Yannic Noller, Lars Grunske Published: 2026-02-11 Categories: cs.LG, cs.AI, cs.CR, cs.CV arXiv: https://arxiv.org/abs/2602.10780v1 Machine learning models are increasingly present in our everyday lives; as a result, they become targets of adversarial attackers seeking to manipulate the systems we interact with. A well-known vulnerability is a backdoor introduced into a neural network by poisoned training data or a malicious training process. Backdoors can be used to induce unwanted behavior by including a certain trigger in the input. Existing mitigations filter training data, modify the model, or perform expensive input modifications on samples. If a vulnerable model has already been deployed, however, those strategies are either ineffective or inefficient. To address this gap, we propose our inference-time backdoor mitigation approach called FIRE (Feature-space Inference-time REpair). We hypothesize that a trigger induces structured and repeatable changes in the model's internal representation. We view the trigger as directions in the latent spaces between layers that can be applied in reverse to correct the inference mechanism. Therefore, we turn the backdoored model against itself by manipulating its latent representations and moving a poisoned sample's features along the backdoor directions to neutralize the trigger. Our evaluation shows that FIRE has low computational overhead and outperforms current runtime mitigations on image benchmarks across various attacks, datasets, and network architectures. --- ### From Steering to Pedalling: Do Autonomous Driving VLMs Generalize to Cyclist-Assistive Spatial Perception and Planning? Authors: Krishna Kanth Nakka, Vedasri Nakka Published: 2026-02-11 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.10771v1 Cyclists often encounter safety-critical situations in urban traffic, highlighting the need for assistive systems that support safe and informed decision-making. Recently, vision-language models (VLMs) have demonstrated strong performance on autonomous driving benchmarks, suggesting their potential for general traffic understanding and navigation-related reasoning. However, existing evaluations are predominantly vehicle-centric and fail to assess perception and reasoning from a cyclist-centric viewpoint. To address this gap, we introduce CyclingVQA, a diagnostic benchmark designed to probe perception, spatio-temporal understanding, and traffic-rule-to-lane reasoning from a cyclist's perspective. Evaluating 31+ recent VLMs spanning general-purpose, spatially enhanced, and autonomous-driving-specialized models, we find that current models demonstrate encouraging capabilities, while also revealing clear areas for improvement in cyclist-centric perception and reasoning, particularly in interpreting cyclist-specific traffic cues and associating signs with the correct navigational lanes. Notably, several driving-specialized models underperform strong generalist VLMs, indicating limited transfer from vehicle-centric training to cyclist-assistive scenarios. Finally, through systematic error analysis, we identify recurring failure modes to guide the development of more effective cyclist-assistive intelligent systems. --- ### LOREN: Low Rank-Based Code-Rate Adaptation in Neural Receivers Authors: Bram Van Bolderik, Vlado Menkovski, Sonia Heemstra de Groot, Manil Dev Gomony Published: 2026-02-11 Categories: cs.LG, cs.AI, cs.AR, eess.SP arXiv: https://arxiv.org/abs/2602.10770v1 Neural network based receivers have recently demonstrated superior system-level performance compared to traditional receivers. However, their practicality is limited by high memory and power requirements, as separate weight sets must be stored for each code rate. To address this challenge, we propose LOREN, a Low Rank-Based Code-Rate Adaptation Neural Receiver that achieves adaptability with minimal overhead. LOREN integrates lightweight low rank adaptation adapters (LOREN adapters) into convolutional layers, freezing a shared base network while training only small adapters per code rate. An end-to-end training framework over 3GPP CDL channels ensures robustness across realistic wireless environments. LOREN achieves comparable or superior performance relative to fully retrained base neural receivers. The hardware implementation of LOREN in 22nm technology shows more than 65% savings in silicon area and up to 15% power reduction when supporting three code rates. --- ### Collaborative Threshold Watermarking Authors: Tameem Bakr, Anish Ambreth, Nils Lukas Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.10765v2 In federated learning (FL), $K$ clients jointly train a model without sharing raw data. Because each participant invests data and compute, clients need mechanisms to later prove the provenance of a jointly trained model. Model watermarking embeds a hidden signal in the weights, but naive approaches either do not scale with many clients as per-client watermarks dilute as $K$ grows, or give any individual client the ability to verify and potentially remove the watermark. We introduce $(t,K)$-threshold watermarking: clients collaboratively embed a shared watermark during training, while only coalitions of at least $t$ clients can reconstruct the watermark key and verify a suspect model. We secret-share the watermark key $τ$ so that coalitions of fewer than $t$ clients cannot reconstruct it, and verification can be performed without revealing $τ$ in the clear. We instantiate our protocol in the white-box setting and evaluate it on image classification tasks on both IID and non-IID partitions, as well as language models fine-tuning setting. Our watermark remains detectable at scale ($K=128$) with minimal accuracy loss and stays above the detection threshold ($z\ge 4$) under attacks including adaptive fine-tuning using up to 20% of the training data. Code is available at https://github.com/tameemalaa/collaborative-threshold-watermark. --- ### Dual-End Consistency Model Authors: Linwei Dong, Ruoyu Guo, Ge Bai, Zehuan Yuan, Yawei Luo, Changqing Zou Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.10764v3 The slow iterative sampling nature remains a major bottleneck for the practical deployment of diffusion and flow-based generative models. While consistency models (CMs) represent a state-of-the-art distillation-based approach for efficient generation, their large-scale application is still limited by two key issues: training instability and inflexible sampling. Existing methods seek to mitigate these problems through architectural adjustments or regularized objectives, yet overlook the critical reliance on trajectory selection. In this work, we first conduct an analysis on these two limitations: training instability originates from loss divergence induced by unstable self-supervised term, whereas sampling inflexibility arises from error accumulation. Based on these insights and analysis, we propose the Dual-End Consistency Model (DE-CM) that selects vital sub-trajectory clusters to achieve stable and effective training. DE-CM decomposes the PF-ODE trajectory and selects three critical sub-trajectories as optimization targets. Specifically, our approach leverages continuous-time CMs objectives to achieve few-step distillation and utilizes flow matching as a boundary regularizer to stabilize the training process. Furthermore, we propose a novel noise-to-noisy (N2N) mapping that can map noise to any point, thereby alleviating the error accumulation in the first step. Extensive experimental results show the effectiveness of our method: it achieves a state-of-the-art FID score of 1.70 in one-step generation on the ImageNet 256x256 dataset, outperforming existing CM-based one-step approaches. --- ### Amortized Inference of Neuron Parameters on Analog Neuromorphic Hardware Authors: Jakob Kaiser, Eric Müller, Johannes Schemmel Published: 2026-02-11 Categories: cs.NE arXiv: https://arxiv.org/abs/2602.10763v2 Our work utilized a non-sequential simulation-based inference algorithm to provide an amortized neural density estimator, which approximates the posterior distribution for seven parameters of the adaptive exponential integrate-and-fire neuron model of the analog neuromorphic BrainScaleS-2 substrate. We constrained the large parameter space by training a binary classifier to predict parameter combinations yielding observations in regimes of interest, i.e. moderate spike counts. We compared two neural density estimators: one using handcrafted summary statistics and one using a summary network trained in combination with the neural density estimator. The summary network yielded a more focused posterior and generated posterior predictive traces that accurately captured the membrane potential dynamics. When using handcrafted summary statistics, posterior predictive traces match the included features but show deviations in the exact dynamics. The posteriors showed signs of bias and miscalibration but were still able to yield posterior predictive samples that were close to the target observations on which the posteriors were constrained. Our results validate amortized simulation-based inference as a tool for parameterizing analog neuron circuits. --- ### Text-to-Vector Conversion for Residential Plan Design Authors: Egor Bazhenov, Stepan Kasai, Viacheslav Shalamov, Valeria Efimova Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.10757v1 Computer graphics, comprising both raster and vector components, is a fundamental part of modern science, industry, and digital communication. While raster graphics offer ease of use, its pixel-based structure limits scalability. Vector graphics, defined by mathematical primitives, provides scalability without quality loss, however, it is more complex to produce. For design and architecture, the versatility of vector graphics is paramount, despite its computational demands. This paper introduces a novel method for generating vector residential plans from textual descriptions. Our approach surpasses existing solutions by approximately 5% in CLIPScore-based visual quality, benefiting from its inherent handling of right angles and flexible settings. Additionally, we present a new algorithm for vectorizing raster plans into structured vector images. Such images have a better CLIPscore compared to others by about 4%. --- ### Exploring the impact of adaptive rewiring in Graph Neural Networks Authors: Charlotte Cambier van Nooten, Christos Aronis, Yuliya Shapovalova, Lucia Cavallaro Published: 2026-02-11 Categories: cs.LG, cs.AI, eess.SY, stat.ML arXiv: https://arxiv.org/abs/2602.10754v1 This paper explores sparsification methods as a form of regularization in Graph Neural Networks (GNNs) to address high memory usage and computational costs in large-scale graph applications. Using techniques from Network Science and Machine Learning, including Erdős-Rényi for model sparsification, we enhance the efficiency of GNNs for real-world applications. We demonstrate our approach on N-1 contingency assessment in electrical grids, a critical task for ensuring grid reliability. We apply our methods to three datasets of varying sizes, exploring Graph Convolutional Networks (GCN) and Graph Isomorphism Networks (GIN) with different degrees of sparsification and rewiring. Comparison across sparsification levels shows the potential of combining insights from both research fields to improve GNN performance and scalability. Our experiments highlight the importance of tuning sparsity parameters: while sparsity can improve generalization, excessive sparsity may hinder learning of complex patterns. Our adaptive rewiring approach, particularly when combined with early stopping, proves promising by allowing the model to adapt its connectivity structure during training. This research contributes to understanding how sparsity can be effectively leveraged in GNNs for critical applications like power grid reliability analysis. --- ### Predicting integers from continuous parameters Authors: Bas Maat, Peter Bloem Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.10751v3 We study the problem of predicting numeric labels that are constrained to the integers or to a subrange of the integers. For example, the number of up-votes on social media posts, or the number of bicycles available at a public rental station. While it is possible to model these as continuous values, and to apply traditional regression, this approach changes the underlying distribution on the labels from discrete to continuous. Discrete distributions have certain benefits, which leads us to the question whether such integer labels can be modeled directly by a discrete distribution, whose parameters are predicted from the features of a given instance. Moreover, we focus on the use case of output distributions of neural networks, which adds the requirement that the parameters of the distribution be continuous so that backpropagation and gradient descent may be used to learn the weights of the network. We investigate several options for such distributions, some existing and some novel, and test them on a range of tasks, including tabular learning, sequential prediction and image generation. We find that overall the best performance comes from two distributions: Bitwise, which represents the target integer in bits and places a Bernoulli distribution on each, and a discrete analogue of the Laplace distribution, which uses a distribution with exponentially decaying tails around a continuous mean. --- ### SecureScan: An AI-Driven Multi-Layer Framework for Malware and Phishing Detection Using Logistic Regression and Threat Intelligence Integration Authors: Rumman Firdos, Aman Dangi Published: 2026-02-11 Categories: cs.CR, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.10750v2 The growing sophistication of modern malware and phishing campaigns has diminished the effectiveness of traditional signature-based intrusion detection systems. This work presents SecureScan, an AI-driven, triple-layer detection framework that integrates logistic regression-based classification, heuristic analysis, and external threat intelligence via the VirusTotal API for comprehensive triage of URLs, file hashes, and binaries. The proposed architecture prioritizes efficiency by filtering known threats through heuristics, classifying uncertain samples using machine learning, and validating borderline cases with third-party intelligence. On benchmark datasets, SecureScan achieves 93.1 percent accuracy with balanced precision (0.87) and recall (0.92), demonstrating strong generalization and reduced overfitting through threshold-based decision calibration. A calibrated threshold and gray-zone logic (0.45-0.55) were introduced to minimize false positives and enhance real-world stability. Experimental results indicate that a lightweight statistical model, when augmented with calibrated verification and external intelligence, can achieve reliability and performance comparable to more complex deep learning systems. --- ### Spectral-Spatial Contrastive Learning Framework for Regression on Hyperspectral Data Authors: Mohamad Dhaini, Paul Honeine, Maxime Berar, Antonin Van Exem Published: 2026-02-11 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.10745v1 Contrastive learning has demonstrated great success in representation learning, especially for image classification tasks. However, there is still a shortage in studies targeting regression tasks, and more specifically applications on hyperspectral data. In this paper, we propose a spectral-spatial contrastive learning framework for regression tasks for hyperspectral data, in a model-agnostic design allowing to enhance backbones such as 3D convolutional and transformer-based networks. Moreover, we provide a collection of transformations relevant for augmenting hyperspectral data. Experiments on synthetic and real datasets show that the proposed framework and transformations significantly improve the performance of all studied backbone models. --- ### Self-Supervised Image Super-Resolution Quality Assessment based on Content-Free Multi-Model Oriented Representation Learning Authors: Kian Majlessi, Amir Masoud Soltani, Mohammad Ebrahim Mahdavi, Aurelien Gourrier, Peyman Adibi Published: 2026-02-11 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.10744v1 Super-resolution (SR) applied to real-world low-resolution (LR) images often results in complex, irregular degradations that stem from the inherent complexity of natural scene acquisition. In contrast to SR artifacts arising from synthetic LR images created under well-defined scenarios, those distortions are highly unpredictable and vary significantly across different real-life contexts. Consequently, assessing the quality of SR images (SR-IQA) obtained from realistic LR, remains a challenging and underexplored problem. In this work, we introduce a no-reference SR-IQA approach tailored for such highly ill-posed realistic settings. The proposed method enables domain-adaptive IQA for real-world SR applications, particularly in data-scarce domains. We hypothesize that degradations in super-resolved images are strongly dependent on the underlying SR algorithms, rather than being solely determined by image content. To this end, we introduce a self-supervised learning (SSL) strategy that first pretrains multiple SR model oriented representations in a pretext stage. Our contrastive learning framework forms positive pairs from images produced by the same SR model and negative pairs from those generated by different methods, independent of image content. The proposed approach S3 RIQA, further incorporates targeted preprocessing to extract complementary quality information and an auxiliary task to better handle the various degradation profiles associated with different SR scaling factors. To this end, we constructed a new dataset, SRMORSS, to support unsupervised pretext training; it includes a wide range of SR algorithms applied to numerous real LR images, which addresses a gap in existing datasets. Experiments on real SR-IQA benchmarks demonstrate that S3 RIQA consistently outperforms most state-of-the-art relevant metrics. --- ### Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Tracking Authors: Vaisakh Shaj, Cameron Barker, Aidan Scannell, Andras Szecsenyi, Elliot J. Crowley, Amos Storkey Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.10743v2 State-space language models such as Mamba and gated linear attention (GLA) offer linear-complexity, parallelisable alternatives to transformers, but their linear state updates limit expressivity and robust state tracking. We close this gap from a probabilistic angle, casting sequence mixing as exact Bayesian filtering with the Kalman filter as the core primitive. Classical Kalman filters give principled state and uncertainty estimates but are viewed as inherently sequential; we show that reparameterising them in information form turns their updates into an associative scan - so the per-token recurrent update is non-linear (a Möbius/precision recursion) yet remains temporally parallel. The resulting Kalman Linear Attention (KLA) layer is a drop-in sequence mixer that performs time-parallel probabilistic inference, carries an explicit belief-state uncertainty, and is strictly more expressive than GLA-style linear updates at the same computational cost. This expressivity translates directly into stronger state tracking: KLA solves permutation-composition ($A_5$) tasks that linear SSMs and attention cannot, while staying scan-parallel. As a drop-in primitive it also matches or improves on modern SSMs and GLAs across synthetic token-manipulation and zero-shot commonsense benchmarks, and is among the first stacked Bayesian-filtering primitives trained at the billion-token scale. --- ### Reinforced Curriculum Pre-Alignment for Domain-Adaptive VLMs Authors: Yuming Yan, Shuo Yang, Kai Tang, Sihong Chen, Yang Zhang, Ke Xu, Dan Hu, Qun Yu, Pengfei Hu, Edith C. H. Ngai Published: 2026-02-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.10740v1 Vision-Language Models (VLMs) demonstrate remarkable general-purpose capabilities but often fall short in specialized domains such as medical imaging or geometric problem-solving. Supervised Fine-Tuning (SFT) can enhance performance within a target domain, but it typically causes catastrophic forgetting, limiting its generalization. The central challenge, therefore, is to adapt VLMs to new domains while preserving their general-purpose capabilities. Continual pretraining is effective for expanding knowledge in Large Language Models (LLMs), but it is less feasible for VLMs due to prohibitive computational costs and the unavailability of pretraining data for most open-source models. This necessitates efficient post-training adaptation methods. Reinforcement learning (RL)-based approaches such as Group Relative Policy Optimization (GRPO) have shown promise in preserving general abilities, yet they often fail in domain adaptation scenarios where the model initially lacks sufficient domain knowledge, leading to optimization collapse. To bridge this gap, we propose Reinforced Curriculum Pre-Alignment (RCPA), a novel post-training paradigm that introduces a curriculum-aware progressive modulation mechanism. In the early phase, RCPA applies partial output constraints to safely expose the model to new domain concepts. As the model's domain familiarity increases, training gradually transitions to full generation optimization, refining responses and aligning them with domain-specific preferences. This staged adaptation balances domain knowledge acquisition with the preservation of general multimodal capabilities. Extensive experiments across specialized domains and general benchmarks validate the effectiveness of RCPA, establishing a practical pathway toward building high-performing and domain-adaptive VLMs. --- ### Calliope: A TTS-based Narrated E-book Creator Ensuring Exact Synchronization, Privacy, and Layout Fidelity Authors: Hugo L. Hammer, Vajira Thambawita, Pål Halvorsen Published: 2026-02-11 Categories: cs.SD, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.10735v1 A narrated e-book combines synchronized audio with digital text, highlighting the currently spoken word or sentence during playback. This format supports early literacy and assists individuals with reading challenges, while also allowing general readers to seamlessly switch between reading and listening. With the emergence of natural-sounding neural Text-to-Speech (TTS) technology, several commercial services have been developed to leverage these technology for converting standard text e-books into high-quality narrated e-books. However, no open-source solutions currently exist to perform this task. In this paper, we present Calliope, an open-source framework designed to fill this gap. Our method leverages state-of-the-art open-source TTS to convert a text e-book into a narrated e-book in the EPUB 3 Media Overlay format. The method offers several innovative steps: audio timestamps are captured directly during TTS, ensuring exact synchronization between narration and text highlighting; the publisher's original typography, styling, and embedded media are strictly preserved; and the entire pipeline operates offline. This offline capability eliminates recurring API costs, mitigates privacy concerns, and avoids copyright compliance issues associated with cloud-based services. The framework currently supports the state-of-the-art open-source TTS systems XTTS-v2 and Chatterbox. A potential alternative approach involves first generating narration via TTS and subsequently synchronizing it with the text using forced alignment. However, while our method ensures exact synchronization, our experiments show that forced alignment introduces drift between the audio and text highlighting significant enough to degrade the reading experience. Source code and usage instructions are available at https://github.com/hugohammer/TTS-Narrated-Ebook-Creator.git. --- ### Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling Authors: Alaa Elsetohy, Sama Hadhoud, Haryo Akbarianto Wibowo, Chenxi Whitehouse, Genta Indra Winata, Fajri Koto, Alham Fikri Aji Published: 2026-02-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.10732v2 Multilingual benchmarks rarely test reasoning over culturally grounded premises: translated datasets keep English-centric scenarios, while culture-first datasets often lack control over the reasoning required. We propose Macaron, a template-first benchmark that factorizes reasoning type and cultural aspect across question languages. Using 100 language-agnostic templates that cover 7 reasoning types, 22 cultural aspects, native annotators create scenario-aligned English and local-language multiple-choice questions, and systematically derived True/False questions. Macaron contains 11,862 instances spanning 20 countries/cultural contexts, 10 scripts, and 20 languages and dialects (including low-resource ones like Amharic, Yoruba, Zulu, Kyrgyz, and some Arabic dialects). In zero-shot evaluation of 21 multilingual LLMs, reasoning-mode models achieve the strongest performance (80.8% overall) and near-parity between English and local languages, while open-weight models degrade substantially in local languages and often approach chance on T/F tasks. Culture-grounded mathematical and counting templates are consistently the hardest. The data can be accessed here https://huggingface.co/datasets/AlaaAhmed2444/Macaron. --- ### OccFace: Unified Occlusion-Aware Facial Landmark Detection with Per-Point Visibility Authors: Xinhao Xiang, Zhengxin Li, Saurav Dhakad, Theo Bancroft, Jiawei Zhang, Weiyang Li Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.10728v1 Accurate facial landmark detection under occlusion remains challenging, especially for human-like faces with large appearance variation and rotation-driven self-occlusion. Existing detectors typically localize landmarks while handling occlusion implicitly, without predicting per-point visibility that downstream applications can benefits. We present OccFace, an occlusion-aware framework for universal human-like faces, including humans, stylized characters, and other non-human designs. OccFace adopts a unified dense 100-point layout and a heatmap-based backbone, and adds an occlusion module that jointly predicts landmark coordinates and per-point visibility by combining local evidence with cross-landmark context. Visibility supervision mixes manual labels with landmark-aware masking that derives pseudo visibility from mask-heatmap overlap. We also create an occlusion-aware evaluation suite reporting NME on visible vs. occluded landmarks and benchmarking visibility with Occ AP, F1@0.5, and ROC-AUC, together with a dataset annotated with 100-point landmarks and per-point visibility. Experiments show improved robustness under external occlusion and large head rotations, especially on occluded regions, while preserving accuracy on visible landmarks. --- ### Rising Multi-Armed Bandits with Known Horizons Authors: Seockbean Song, Chenyu Gan, Youngsik Yoon, Siwei Wang, Wei Chen, Jungseul Ok Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.10727v2 The Rising Multi-Armed Bandit (RMAB) framework models environments where expected rewards of arms increase with plays, which models practical scenarios where performance of each option improves with the repeated usage, such as in robotics and hyperparameter tuning. For instance, in hyperparameter tuning, the validation accuracy of a model configuration (arm) typically increases with each training epoch. A defining characteristic of RMAB is em horizon-dependent optimality: unlike standard settings, the optimal strategy here shifts dramatically depending on the available budget $T$. This implies that knowledge of $T$ yields significantly greater utility in RMAB, empowering the learner to align its decision-making with this shifting optimality. However, the horizon-aware setting remains underexplored. To address this, we propose a novel CUmulative Reward Estimation UCB (CURE-UCB) that explicitly integrates the horizon. We provide a rigorous analysis establishing a new regret upper bound and prove that our method strictly outperforms horizon-agnostic strategies in structured environments like ``linear-then-flat'' instances. Extensive experiments demonstrate its significant superiority over baselines. --- ### A Diffusion-Based Generative Prior Approach to Sparse-view Computed Tomography Authors: Davide Evangelista, Pasquale Cascarano, Elena Loli Piccolomini Published: 2026-02-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.10722v1 The reconstruction of X-rays CT images from sparse or limited-angle geometries is a highly challenging task. The lack of data typically results in artifacts in the reconstructed image and may even lead to object distortions. For this reason, the use of deep generative models in this context has great interest and potential success. In the Deep Generative Prior (DGP) framework, the use of diffusion-based generative models is combined with an iterative optimization algorithm for the reconstruction of CT images from sinograms acquired under sparse geometries, to maintain the explainability of a model-based approach while introducing the generative power of a neural network. There are therefore several aspects that can be further investigated within these frameworks to improve reconstruction quality, such as image generation, the model, and the iterative algorithm used to solve the minimization problem, for which we propose modifications with respect to existing approaches. The results obtained even under highly sparse geometries are very promising, although further research is clearly needed in this direction. --- ### Ecological mapping with geospatial foundation models Authors: Craig Mahlasi, Gciniwe S. Baloyi, Zaheed Gaffoor, Levente Klein, Anne Jones, Etienne Vos, Michal Muszynski, Geoffrey Dawson, Campbell Watson Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.10720v2 The value of Earth observation foundation models for high-impact ecological applications remains insufficiently characterized. This study is one of the first to systematically evaluate the performance, limitations and practical considerations across three common ecological use cases: forest functional trait estimation, land use and land cover mapping and peatland detection. We fine-tune two pretrained models (Prithvi-EO-2.0 and TerraMind) and benchmark them against a ResNet-101 baseline using datasets collected from open sources. Across all tasks, Prithvi-EO-2.0 and TerraMind consistently outperform the ResNet baseline, demonstrating improved generalization and transfer across ecological domains. TerraMind marginally exceeds Prithvi-EO-2.0 in unimodal settings and shows substantial gains when additional modalities are incorporated. However, performance is sensitive to divergence between downstream inputs and pretraining modalities, underscoring the need for careful dataset alignment. Results also indicate that higher-resolution inputs and more accurate pixel-level labels remain critical for capturing fine-scale ecological dynamics. --- ### From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving Authors: Sining Ang, Yuguang Yang, Chenxu Dang, Canyu Chen, Cheng Chi, Haiyan Liu, Xuanyao Mao, Jason Bao, Xuliang, Bingchuan Sun, Yan Wang Published: 2026-02-11 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.10719v2 Vision-Language-Action (VLA) driving augments end-to-end (E2E) planning with language-enabled visual backbones, yet it remains unclear how vision-language models (VLMs) differ from standard vision-only encoders and whether these differences survive policy learning. We study this question under a unified VLM-hidden + diffusion-policy paradigm, comparing multiple VLM families/scales (e.g., InternVL3 and Qwen3VL) with vision-only encoders (e.g., ResNet, ViT, and EVA-CLIP). We ask three questions: how similar are their representations, do residual differences induce meaningful behavioral differences, and how can they improve accuracy-cost trade-offs? We find that VLM and vision-only policies share a substantial common subspace after policy learning, yet both retain non-transferable residual subspaces. Using a Shared-Unique SAE, we show that these residual factors are behaviorally relevant: vision-only encoders are stronger in simple, geometry-dominant scenarios, whereas VLMs are stronger in long-tail, semantically complex, and interaction-heavy cases. The two policy families also exhibit distinct driving styles, with vision-only models being more conservative on average and VLMs more assertive. Exploiting the complementarity between a VLM branch and a ViT branch yields an oracle upper bound of 93.58 PDMS on NAVSIM. We introduce HybridDriveVLA, which runs both branches and uses a learned trajectory scorer for selection, improving PDMS to 92.10 (+1.30 over the VLM baseline), and DualDriveVLA, a fast-slow variant that invokes the VLM in only 15% of scenarios, achieving 91.00 PDMS (+0.20) with about a 1.9x latency speedup over the VLM baseline. Code will be released. --- ### SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Authors: Yifan Zhang, Zunhai Su, Shuhao Hu, Rui Yang, Wei Wu, Yulei Qian, Yuchen Xie, Xunliang Cai Published: 2026-02-11 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.10718v3 While FP8 attention has shown substantial promise in innovations like FlashAttention-3, its integration into the decoding phase of the DeepSeek Multi-head Latent Attention (MLA) architecture presents notable challenges. These challenges include numerical heterogeneity arising from the decoupling of positional embeddings, misalignment of quantization scales in FP8 PV GEMM, and the need for optimized system-level support. In this paper, we introduce SnapMLA, an FP8 MLA decoding framework optimized to improve long-context efficiency through the following hardware-aware algorithm-kernel co-optimization techniques: (i) RoPE-Aware Per-Token KV Quantization: Motivated by our analysis of the heterogeneous quantization sensitivity inherent to the MLA KV cache, this approach preserves the RoPE part in high precision. Furthermore, per-token granularity is employed to align with the autoregressive decoding process and maintain quantization accuracy. (ii) Quantized PV Computation Pipeline Reconstruction: Addresses the misalignment of quantization scales in FP8 PV computation caused by the shared KV structure of the MLA. (iii) End-to-End Dataflow Optimization: Establishes an efficient data read-and-write workflow using specialized kernels, ensuring streamlined data flow and improved performance. Extensive experiments on state-of-the-art MLA LLMs show that SnapMLA achieves up to a 1.91x improvement in throughput on long-output decoding workloads while maintaining near-parity benchmark quality compared with the BF16 baseline on the evaluated reasoning and code-generation benchmarks. Code is available at https://github.com/meituan-longcat/SGLang-FluentLLM. --- ### RE-LLM: Refining Empathetic Speech-LLM Responses by Integrating Emotion Nuance Authors: Jing-Han Chen, Bo-Hao Su, Ya-Tse Wu, Chi-Chun Lee Published: 2026-02-11 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2602.10716v1 With generative AI advancing, empathy in human-AI interaction is essential. While prior work focuses on emotional reflection, emotional exploration, key to deeper engagement, remains overlooked. Existing LLMs rely on text which captures limited emotion nuances. To address this, we propose RE-LLM, a speech-LLM integrating dimensional emotion embeddings and auxiliary learning. Experiments show statistically significant gains in empathy metrics across three datasets. RE-LLM relatively improves the Emotional Reaction score by 14.79% and 6.76% compared to text-only and speech-LLM baselines on ESD. Notably, it raises the Exploration score by 35.42% and 3.91% on IEMOCAP, 139.28% and 9.83% on ESD, and 60.95% and 22.64% on MSP-PODCAST. It also boosts unweighted accuracy by 5.4% on IEMOCAP, 2.3% on ESD, and 6.9% on MSP-PODCAST in speech emotion recognition. These results highlight the enriched emotional understanding and improved empathetic response generation of RE-LLM. --- ### Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents Authors: Yifei Li, Weidong Guo, Lingling Zhang, Rongman Xu, Muye Huang, Hui Liu, Lijiao Xu, Yu Xu, Jun Liu Published: 2026-02-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.10715v1 Long-term conversational memory is a core capability for LLM-based dialogue systems, yet existing benchmarks and evaluation protocols primarily focus on surface-level factual recall. In realistic interactions, appropriate responses often depend on implicit constraints such as user state, goals, or values that are not explicitly queried later. To evaluate this setting, we introduce \textbf{LoCoMo-Plus}, a benchmark for assessing cognitive memory under cue--trigger semantic disconnect, where models must retain and apply latent constraints across long conversational contexts. We further show that conventional string-matching metrics and explicit task-type prompting are misaligned with such scenarios, and propose a unified evaluation framework based on constraint consistency. Experiments across diverse backbone models, retrieval-based methods, and memory systems demonstrate that cognitive memory remains challenging and reveals failures not captured by existing benchmarks. Our code and evaluation framework are publicly available at: https://github.com/xjtuleeyf/Locomo-Plus. --- ### A Non-asymptotic Analysis for Learning and Applying a Preconditioner in MCMC Authors: Max Hird, Florian Maire, Jeffrey Negrea Published: 2026-02-11 Categories: stat.CO, stat.ML arXiv: https://arxiv.org/abs/2602.10714v3 Preconditioning is a common method applied to modify Markov chain Monte Carlo algorithms with the goal of making them more efficient. In practice it is often extremely effective, even when the preconditioner is learned from the chain. We analyse and compare the finite-time computational costs of schemes which learn a preconditioner based on the target covariance or the expected Hessian of the target potential with that of a corresponding scheme that does not use preconditioning. We apply our results to various algorithms including the Unadjusted Langevin Algorithm (ULA) and the proximal sampler for an appropriately regular target, establishing non-asymptotic guarantees for versions of these algorithms that learn and use preconditioners. To do so, we establish non-asymptotic guarantees on the time taken to collect $N$ approximately independent samples from the target for schemes that learn their preconditioners under the assumption that the underlying Markov chain satisfies a contraction in the Wasserstein-2 distance. This approximate independence condition, that we formalize, allows us to bridge the non-asymptotic bounds of modern MCMC theory and classical heuristics of effective sample size and mixing time, and is needed to amortise the costs of learning a preconditioner across the samples it will help to produce. --- ### A Non-asymptotic Analysis for Learning and Applying a Preconditioner in MCMC Authors: Max Hird, Florian Maire, Jeffrey Negrea Published: 2026-02-11 Categories: stat.CO, stat.ML arXiv: https://arxiv.org/abs/2602.10714v2 Preconditioning is a common method applied to modify Markov chain Monte Carlo algorithms with the goal of making them more efficient. In practice it is often extremely effective, even when the preconditioner is learned from the chain. We analyse and compare the finite-time computational costs of schemes which learn a preconditioner based on the target covariance or the expected Hessian of the target potential with that of a corresponding scheme that does not use preconditioning. We apply our results to various algorithms including the Unadjusted Langevin Algorithm (ULA) and the proximal sampler for an appropriately regular target, establishing non-asymptotic guarantees for versions of these algorithms that learn and use preconditioners. To do so, we establish non-asymptotic guarantees on the time taken to collect $N$ approximately independent samples from the target for schemes that learn their preconditioners under the assumption that the underlying Markov chain satisfies a contraction condition in the Wasserstein-2 distance. This approximate independence condition, that we formalize, allows us to bridge the non-asymptotic bounds of modern MCMC theory and classical heuristics of effective sample size and mixing time, and is needed to amortise the costs of learning a preconditioner across the many samples it will be used to produce. --- ### Cross-Sectional Asset Retrieval via Future-Aligned Soft Contrastive Learning Authors: Hyeongmin Lee, Chanyeol Choi, Jihoon Kwon, Yoon Kim, Alejandro Lopez-Lira, Wonbin Ahn, Justin Xu, Srijan Sood, Qingsong Wen, Chun-Li Yang, Yongjae Lee Published: 2026-02-11 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2602.10711v2 Asset retrieval (finding similar assets in a financial universe) is central to quantitative investment decision-making. Existing approaches define similarity through historical price patterns or sector classifications, but such backward-looking criteria provide no guarantee about future behavior. We argue that effective asset retrieval should be future-aligned: the retrieved assets should be those most likely to exhibit correlated future returns. To this end, we propose Future-Aligned Soft Contrastive Learning (FASCL), a representation learning framework whose soft contrastive loss uses pairwise future return correlations as continuous supervision targets. We further introduce an evaluation protocol designed to directly assess whether retrieved assets share similar future trajectories. Experiments on 5,631 US-listed securities against 14 baselines show that FASCL attains the best future return correlation at every retrieval depth and the best rank information coefficient at every depth and horizon, leads on trend consistency in 13 of 16 cells, and gives the highest gross Sharpe ratio in a spread trading backtest at every basket size. Code is available at https://github.com/HyeongminLEE/fascl . --- ### Cross-Sectional Asset Retrieval via Future-Aligned Soft Contrastive Learning Authors: Hyeongmin Lee, Chanyeol Choi, Jihoon Kwon, Yoon Kim, Alejandro Lopez-Lira, Wonbin Ahn, Yongjae Lee Published: 2026-02-11 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2602.10711v1 Asset retrieval--finding similar assets in a financial universe--is central to quantitative investment decision-making. Existing approaches define similarity through historical price patterns or sector classifications, but such backward-looking criteria provide no guarantee about future behavior. We argue that effective asset retrieval should be future-aligned: the retrieved assets should be those most likely to exhibit correlated future returns. To this end, we propose Future-Aligned Soft Contrastive Learning (FASCL), a representation learning framework whose soft contrastive loss uses pairwise future return correlations as continuous supervision targets. We further introduce an evaluation protocol designed to directly assess whether retrieved assets share similar future trajectories. Experiments on 4,229 US equities demonstrate that FASCL consistently outperforms 13 baselines across all future-behavior metrics. The source code will be available soon. --- ### FGAA-FPN: Foreground-Guided Angle-Aware Feature Pyramid Network for Oriented Object Detection Authors: Jialin Ma Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.10710v2 With the increasing availability of high-resolution remote sensing and aerial imagery, oriented object detection has become a key capability for geographic information updating, maritime surveillance, and disaster response. However, it remains challenging due to cluttered backgrounds, severe scale variation, and large orientation changes. Existing approaches largely improve performance through multi-scale feature fusion with feature pyramid networks or contextual modeling with attention, but they often lack explicit foreground modeling and do not leverage geometric orientation priors, which limits feature discriminability. To overcome these limitations, we propose FGAA-FPN, a Foreground-Guided Angle-Aware Feature Pyramid Network for oriented object detection. FGAA-FPN is built on a hierarchical functional decomposition that accounts for the distinct spatial resolution and semantic abstraction across pyramid levels, thereby strengthening multi-scale representations. Concretely, a Foreground-Guided Feature Modulation module learns foreground saliency under weak supervision to enhance object regions and suppress background interference in low-level features. In parallel, an Angle-Aware Multi-Head Attention module encodes relative orientation relationships to guide global interactions among high-level semantic features. Extensive experiments on DOTA v1.0 and DOTA v1.5 demonstrate that FGAA-FPN achieves state-of-the-art results, reaching 75.5% and 68.3% mAP, respectively. --- ### Interpretable Graph-Level Anomaly Detection via Contrast with Normal Prototypes Authors: Qiuran Zhao, Kai Ming Ting, Xinpeng Li Published: 2026-02-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.10708v1 The task of graph-level anomaly detection (GLAD) is to identify anomalous graphs that deviate significantly from the majority of graphs in a dataset. While deep GLAD methods have shown promising performance, their black-box nature limits their reliability and deployment in real-world applications. Although some recent methods have made attempts to provide explanations for anomaly detection results, they either provide explanations without referencing normal graphs, or rely on abstract latent vectors as prototypes rather than concrete graphs from the dataset. To address these limitations, we propose Prototype-based Graph-Level Anomaly Detection (ProtoGLAD), an interpretable unsupervised framework that provides explanation for each detected anomaly by explicitly contrasting with its nearest normal prototype graph. It employs a point-set kernel to iteratively discover multiple normal prototype graphs and their associated clusters from the dataset, then identifying graphs distant from all discovered normal clusters as anomalies. Extensive experiments on multiple real-world datasets demonstrate that ProtoGLAD achieves competitive anomaly detection performance compared to state-of-the-art GLAD methods while providing better human-interpretable prototype-based explanations. --- ### Reducing Estimation Uncertainty Using Normalizing Flows and Stratification Authors: Paweł Lorek, Rafał Nowak, Rafał Topolnicki, Tomasz Trzciński, Maciej Zięba, Aleksandra Krystecka Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.10706v3 Estimating the expectation of a real-valued function of a random variable from sample data is a critical aspect of statistical analysis, with far-reaching implications in various applications. Current methodologies typically assume (semi-)parametric distributions such as Gaussian or mixed Gaussian, leading to significant estimation uncertainty if these assumptions do not hold. We propose a flow-based model, integrated with stratified sampling, that leverages a parametrized neural network to offer greater flexibility in modeling unknown data distributions, thereby mitigating this limitation. Our model shows a marked reduction in estimation uncertainty across multiple datasets, including high-dimensional (30 and 128) ones, outperforming crude Monte Carlo estimators and Gaussian mixture models. Reproducible code is available at https://github.com/rnoxy/flowstrat. --- ### (MGS)$^2$-Net: Unifying Micro-Geometric Scale and Macro-Geometric Structure for Cross-View Geo-Localization Authors: Minglei Li, Mengfan He, Chunyu Li, Chao Chen, Xingyu Shao, Ziyang Meng Published: 2026-02-11 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.10704v2 Cross-view geo-localization (CVGL) is pivotal for GNSS-denied UAV navigation but remains brittle under the drastic geometric misalignment between oblique aerial views and orthographic satellite references. Existing methods predominantly operate within a 2D manifold, neglecting the underlying 3D geometry where view-dependent vertical facades (macro-structure) and scale variations (micro-scale) severely corrupt feature alignment. To bridge this gap, we propose (MGS)$^2$, a geometry-grounded framework. The core of our innovation is the Macro-Geometric Structure Filtering (MGSF) module. Unlike pixel-wise matching sensitive to noise, MGSF leverages dilated geometric gradients to physically filter out high-frequency facade artifacts while enhancing the view-invariant horizontal plane, directly addressing the domain shift. To guarantee robust input for this structural filtering, we explicitly incorporate a Micro-Geometric Scale Adaptation (MGSA) module. MGSA utilizes depth priors to dynamically rectify scale discrepancies via multi-branch feature fusion. Furthermore, a Geometric-Appearance Contrastive Distillation (GACD) loss is designed to strictly discriminate against oblique occlusions. Extensive experiments demonstrate that (MGS)$^2$ achieves state-of-the-art performance, recording a Recall@1 of 97.5\% on University-1652 and 97.02\% on SUES-200. Furthermore, the framework exhibits superior cross-dataset generalization against geometric ambiguity. The code is available at: \href{https://github.com/GabrielLi1473/MGS-Net}{https://github.com/GabrielLi1473/MGS-Net}. --- ### A Unified Experimental Architecture for Informative Path Planning: from Simulation to Deployment with GuadalPlanner Authors: Alejandro Mendoza Barrionuevo, Dame Seck Diop, Alejandro Casado Pérez, Daniel Gutiérrez Reina, Sergio L. Toral Marín, Samuel Yanes Luis Published: 2026-02-11 Categories: cs.RO, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2602.10702v1 The evaluation of informative path planning algorithms for autonomous vehicles is often hindered by fragmented execution pipelines and limited transferability between simulation and real-world deployment. This paper introduces a unified architecture that decouples high-level decision-making from vehicle-specific control, enabling algorithms to be evaluated consistently across different abstraction levels without modification. The proposed architecture is realized through GuadalPlanner, which defines standardized interfaces between planning, sensing, and vehicle execution. It is an open and extensible research tool that supports discrete graph-based environments and interchangeable planning strategies, and is built upon widely adopted robotics technologies, including ROS2, MAVLink, and MQTT. Its design allows the same algorithmic logic to be deployed in fully simulated environments, software-in-the-loop configurations, and physical autonomous vehicles using an identical execution pipeline. The approach is validated through a set of experiments, including real-world deployment on an autonomous surface vehicle performing water quality monitoring with real-time sensor feedback. --- ### Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation Authors: Jie Jiang, Yangru Huang, Zeyu Wang, Changping Wang, Yuling Xiong, Jun Zhang, Huan Yu Published: 2026-02-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.10699v2 Generative recommendation via autoregressive models has unified retrieval and ranking into a single conditional generation framework. However, fine-tuning these models with Reinforcement Learning (RL) often suffers from a fundamental probability-reward mismatch. Conventional likelihood-dominated decoding (e.g., beam search) exhibits a myopic bias toward locally probable prefixes, which causes two critical failures: (1) insufficient exploration, where high-reward items in low-probability branches are prematurely pruned and rarely sampled, and (2) advantage compression, where trajectories sharing high-probability prefixes receive highly correlated rewards with low within-group variance, yielding a weak comparative signal for RL. To address these challenges, we propose V-STAR, a Value-guided Sampling and Tree-structured Advantage Reinforcement framework. V-STAR forms a self-evolving loop via two synergistic components. First, a Value-Guided Efficient Decoding (VED) is developed to identify decisive nodes and selectively deepen high-potential prefixes. This improves exploration efficiency without exhaustive tree search. Second, we propose Sibling-GRPO, which exploits the induced tree topology to compute sibling-relative advantages and concentrates learning signals on decisive branching decisions. Extensive experiments on both offline and online datasets demonstrate that V-STAR outperforms state-of-the-art baselines, delivering superior accuracy and candidate-set diversity under strict latency constraints. --- ### AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models Authors: Zhifeng Rao, Wenlong Chen, Lei Xie, Xia Hua, Dongfu Yin, Zhen Tian, F. Richard Yu Published: 2026-02-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.10698v1 Vision-Language-Action (VLA) models have recently achieved remarkable progress in robotic perception and control, yet most existing approaches primarily rely on VLM trained using 2D images, which limits their spatial understanding and action grounding in complex 3D environments. To address this limitation, we propose a novel framework that integrates depth estimation into VLA models to enrich 3D feature representations. Specifically, we employ a depth estimation baseline called VGGT to extract geometry-aware 3D cues from standard RGB inputs, enabling efficient utilization of existing large-scale 2D datasets while implicitly recovering 3D structural information. To further enhance the reliability of these depth-derived features, we introduce a new module called action assistant, which constrains the learned 3D representations with action priors and ensures their consistency with downstream control tasks. By fusing the enhanced 3D features with conventional 2D visual tokens, our approach significantly improves the generalization ability and robustness of VLA models. Experimental results demonstrate that the proposed method not only strengthens perception in geometrically ambiguous scenarios but also leads to superior action prediction accuracy. This work highlights the potential of depth-driven data augmentation and auxiliary expert supervision for bridging the gap between 2D observations and 3D-aware decision-making in robotic systems. --- ### Fast and Large-Scale Unbalanced Optimal Transport via its Semi-Dual and Adaptive Gradient Methods Authors: Ferdinand Genans Published: 2026-02-11 Categories: math.OC, stat.ML arXiv: https://arxiv.org/abs/2602.10697v1 Unbalanced Optimal Transport (UOT) has emerged as a robust relaxation of standard Optimal Transport, particularly effective for handling outliers and mass variations. However, scalable algorithms for UOT, specifically those based on Gradient Descent (SGD), remain largely underexplored. In this work, we address this gap by analyzing the semi-dual formulation of Entropic UOT and demonstrating its suitability for adaptive gradient methods. While the semi-dual is a standard tool for large-scale balanced OT, its geometry in the unbalanced setting appears ill-conditioned under standard analysis. Specifically, worst-case bounds on the marginal penalties using $χ^2$ divergence suggest a condition number scaling with $n/\varepsilon$, implying poor scalability. In contrast, we show that the local condition number actually scales as $\mathcal{O}(1/\varepsilon)$, effectively removing the ill-conditioned dependence on $n$. Exploiting this property, we prove that SGD methods adapt to this local curvature, achieving a convergence rate of $\mathcal{O}(n/\varepsilon T)$ in the stochastic and online regimes, making it suitable for large-scale and semi-discrete applications. Finally, for the full batch discrete setting, we derive a nearly tight upper bound on local smoothness depending solely on the gradient. Using it to adapt step sizes, we propose a modified Adaptive Nesterov Accelerated Gradient (ANAG) method on the semi-dual functional and prove that it achieves a local complexity of $\mathcal{O}(n^2\sqrt{1/\varepsilon}\ln(1/δ))$. --- ### Robust Assortment Optimization from Observational Data Authors: Miao Lu, Yuxuan Han, Han Zhong, Zhengyuan Zhou, Jose Blanchet Published: 2026-02-11 Categories: stat.ML, cs.LG, math.OC, math.ST arXiv: https://arxiv.org/abs/2602.10696v3 Assortment optimization is a fundamental challenge in modern retail and recommendation systems, where the goal is to select a subset of products that maximizes expected revenue under complex customer choice behaviors. While recent advances in data-driven methods have leveraged historical data to learn and optimize assortments, these approaches typically rely on strong assumptions -- namely, the stability of customer preferences and the correctness of the underlying choice models. However, such assumptions frequently break in real-world scenarios due to preference shifts and model misspecification, leading to poor generalization and revenue loss. Motivated by this limitation, we propose a robust framework for data-driven assortment optimization that accounts for potential distributional shifts in customer choice behavior. Our approach models potential preference shift from a nominal choice model that generates data and seeks to maximize worst-case expected revenue. We first establish the computational tractability of robust assortment planning when the nominal model is known, then advance to the data-driven setting, where we design statistically optimal algorithms that minimize the data requirements while maintaining robustness. Our theoretical analysis provides both upper bounds and matching lower bounds on the sample complexity, offering theoretical guarantees for robust generalization. Notably, we uncover and identify the notion of ``robust item-wise coverage'' as the minimal data requirement to enable sample-efficient robust assortment learning. Our work bridges the gap between robustness and statistical efficiency in assortment learning, contributing new insights and tools for reliable assortment optimization under uncertainty. --- ### Robust Assortment Optimization from Observational Data Authors: Miao Lu, Yuxuan Han, Han Zhong, Zhengyuan Zhou, Jose Blanchet Published: 2026-02-11 Categories: stat.ML, cs.LG, math.OC, math.ST arXiv: https://arxiv.org/abs/2602.10696v2 Assortment optimization is a fundamental challenge in modern retail and recommendation systems, where the goal is to select a subset of products that maximizes expected revenue under complex customer choice behaviors. While recent advances in data-driven methods have leveraged historical data to learn and optimize assortments, these approaches typically rely on strong assumptions -- namely, the stability of customer preferences and the correctness of the underlying choice models. However, such assumptions frequently break in real-world scenarios due to preference shifts and model misspecification, leading to poor generalization and revenue loss. Motivated by this limitation, we propose a robust framework for data-driven assortment optimization that accounts for potential distributional shifts in customer choice behavior. Our approach models potential preference shift from a nominal choice model that generates data and seeks to maximize worst-case expected revenue. We first establish the computational tractability of robust assortment planning when the nominal model is known, then advance to the data-driven setting, where we design statistically optimal algorithms that minimize the data requirements while maintaining robustness. Our theoretical analysis provides both upper bounds and matching lower bounds on the sample complexity, offering theoretical guarantees for robust generalization. Notably, we uncover and identify the notion of ``robust item-wise coverage'' as the minimal data requirement to enable sample-efficient robust assortment learning. Our work bridges the gap between robustness and statistical efficiency in assortment learning, contributing new insights and tools for reliable assortment optimization under uncertainty. --- ### VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training Authors: Guobin Shen, Chenxiao Zhao, Xiang Cheng, Lei Huang, Xing Yu Published: 2026-02-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.10693v3 Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between training and inference engines. Naive importance sampling gives an unbiased correction but suffers from high variance, which is amplified by unbounded ratios and autoregressive generation. Prior remedies either rely on scenario-specific engineering, or trade bias for variance via token-level clipping or sequence-level normalization, yet these approaches remain largely heuristic. We propose Variational sEquence-level Soft Policy Optimization (VESPO). By explicitly incorporating variance reduction into a variational formulation, we derive a principled closed-form reshaping kernel that operates directly on sequence-level importance weights, avoids token-level approximation and length normalization, and admits an explicit variance bound for the deployed kernel. Experiments on math reasoning and code generation show that VESPO maintains stable training under severe off-policy conditions (staleness up to 64x) and delivers consistent gains across both dense and Mixture-of-Experts (MoE) models, outperforming recent reshaping baselines under matched setup. Code is available at https://github.com/FloyedShen/VESPO. --- ### Convergence Rates for Distribution Matching with Sliced Optimal Transport Authors: Gauthier Thurin, Claire Boyer, Kimia Nadjahi Published: 2026-02-11 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.10691v2 We study the slice-matching scheme, an efficient iterative method for distribution matching based on sliced optimal transport. We investigate convergence to the target distribution and derive quantitative non-asymptotic rates. To this end, we establish Lojasiewicz-type inequalities for the Sliced-Wasserstein objective. A key challenge is to control along the trajectory the constants in these inequalities. We show that this becomes tractable for Gaussian distributions. Specifically, eigenvalues are controlled when matching along random orthonormal bases at each iteration. We complement our theory with numerical experiments and illustrate the predicted dependence on dimension and step-size, as well as the stabilizing effect of orthonormal-basis sampling. --- ### OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL Authors: Jinjie Shen, Jing Wu, Yaxiong Wang, Lechao Cheng, Shengeng Tang, Tianrui Hui, Nan Pu, Zhun Zhong Published: 2026-02-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.10687v3 Existing forgery detection methods are often limited to uni-modal or bi-modal settings, failing to handle the interleaved text, images, and videos prevalent in real-world misinformation. To bridge this gap, this paper targets to develop a unified framework for omnibus vision-language forgery detection and grounding. In this unified setting, the {interplay} between diverse modalities and the dual requirements of simultaneous detection and localization pose a critical ``difficulty bias`` problem: the simpler veracity classification task tends to dominate the gradients, leading to suboptimal performance in fine-grained grounding during multi-task optimization. To address this challenge, we propose \textbf{OmniVL-Guard}, a balanced reinforcement learning framework for omnibus vision-language forgery detection and grounding. Particularly, OmniVL-Guard comprises two core designs: Self-Evolving CoT Generatio and Adaptive Reward Scaling Policy Optimization (ARSPO). {Self-Evolving CoT Generation} synthesizes high-quality reasoning paths, effectively overcoming the cold-start challenge. Building upon this, {Adaptive Reward Scaling Policy Optimization (ARSPO)} dynamically modulates reward scales and task weights, ensuring a balanced joint optimization. Extensive experiments demonstrate that OmniVL-Guard significantly outperforms state-of-the-art methods and exhibits zero-shot robust generalization across out-of-domain scenarios. The dataset and code are publicly available at https://github.com/shen8424/OmniVL-Guard. --- ### Beyond Task Performance: A Metric-Based Analysis of Sequential Cooperation in Heterogeneous Multi-Agent Destructive Foraging Authors: Alejandro Mendoza Barrionuevo, Samuel Yanes Luis, Daniel Gutiérrez Reina, Sergio L. Toral Marín Published: 2026-02-11 Categories: cs.MA, cs.LG arXiv: https://arxiv.org/abs/2602.10685v1 This work addresses the problem of analyzing cooperation in heterogeneous multi-agent systems which operate under partial observability and temporal role dependency, framed within a destructive multi-agent foraging setting. Unlike most previous studies, which focus primarily on algorithmic performance with respect to task completion, this article proposes a systematic set of general-purpose cooperation metrics aimed at characterizing not only efficiency, but also coordination and dependency between teams and agents, fairness, and sensitivity. These metrics are designed to be transferable to different multi-agent sequential domains similar to foraging. The proposed suite of metrics is structured into three main categories that jointly provide a multilevel characterization of cooperation: primary metrics, inter-team metrics, and intra-team metrics. They have been validated in a realistic destructive foraging scenario inspired by dynamic aquatic surface cleaning using heterogeneous autonomous vehicles. It involves two specialized teams with sequential dependencies: one focused on the search of resources, and another on their destruction. Several representative approaches have been evaluated, covering both learning-based algorithms and classical heuristic paradigms. --- ### A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization Authors: Vicente Conde Mendes, Lorenzo Bardone, Cédric Koller, Jorge Medina Moreira, Vittorio Erba, Emanuele Troiani, Lenka Zdeborová Published: 2026-02-11 Categories: stat.ML, cond-mat.dis-nn, cs.LG arXiv: https://arxiv.org/abs/2602.10680v2 Many real-world datasets contain hidden structure that cannot be detected by simple linear correlations between input features. For example, latent factors may influence the data in a coordinated way, even though their effect is invisible to covariance-based methods such as PCA. In practice, nonlinear neural networks often succeed in extracting such hidden structure in unsupervised and self-supervised learning. However, constructing a minimal high-dimensional model where this advantage can be rigorously analyzed has remained an open theoretical challenge. We introduce a tractable high-dimensional spiked model with two latent factors: one visible to covariance, and one statistically dependent yet uncorrelated, appearing only in higher-order moments. PCA and linear autoencoders fail to recover the latter, while a minimal nonlinear autoencoder provably extracts both. We analyze both the population risk, and empirical risk minimization. Our model also provides a tractable example where self-supervised test loss is poorly aligned with representation quality: nonlinear autoencoders recover latent structure that linear methods miss, even though their reconstruction loss is higher. --- ### A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization Authors: Vicente Conde Mendes, Lorenzo Bardone, Cédric Koller, Jorge Medina Moreira, Vittorio Erba, Emanuele Troiani, Lenka Zdeborová Published: 2026-02-11 Categories: stat.ML, cond-mat.dis-nn, cs.LG arXiv: https://arxiv.org/abs/2602.10680v1 Many real-world datasets contain hidden structure that cannot be detected by simple linear correlations between input features. For example, latent factors may influence the data in a coordinated way, even though their effect is invisible to covariance-based methods such as PCA. In practice, nonlinear neural networks often succeed in extracting such hidden structure in unsupervised and self-supervised learning. However, constructing a minimal high-dimensional model where this advantage can be rigorously analyzed has remained an open theoretical challenge. We introduce a tractable high-dimensional spiked model with two latent factors: one visible to covariance, and one statistically dependent yet uncorrelated, appearing only in higher-order moments. PCA and linear autoencoders fail to recover the latter, while a minimal nonlinear autoencoder provably extracts both. We analyze both the population risk, and empirical risk minimization. Our model also provides a tractable example where self-supervised test loss is poorly aligned with representation quality: nonlinear autoencoders recover latent structure that linear methods miss, even though their reconstruction loss is higher. --- ### TwiFF (Think With Future Frames): A Large-Scale Dataset for Dynamic Visual Reasoning Authors: Junhua Liu, Zhangcheng Wang, Zhike Han, Ningli Wang, Guotao Liang, Kun Kuang Published: 2026-02-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.10675v1 Visual Chain-of-Thought (VCoT) has emerged as a promising paradigm for enhancing multimodal reasoning by integrating visual perception into intermediate reasoning steps. However, existing VCoT approaches are largely confined to static scenarios and struggle to capture the temporal dynamics essential for tasks such as instruction, prediction, and camera motion. To bridge this gap, we propose TwiFF-2.7M, the first large-scale, temporally grounded VCoT dataset derived from $2.7$ million video clips, explicitly designed for dynamic visual question and answer. Accompanying this, we introduce TwiFF-Bench, a high-quality evaluation benchmark of $1,078$ samples that assesses both the plausibility of reasoning trajectories and the correctness of final answers in open-ended dynamic settings. Building on these foundations, we propose the TwiFF model, a unified modal that synergistically leverages pre-trained video generation and image comprehension capabilities to produce temporally coherent visual reasoning cues-iteratively generating future action frames and textual reasoning. Extensive experiments demonstrate that TwiFF significantly outperforms existing VCoT methods and Textual Chain-of-Thought baselines on dynamic reasoning tasks, which fully validates the effectiveness for visual question answering in dynamic scenarios. Our code and data is available at https://github.com/LiuJunhua02/TwiFF. --- ### Domain Knowledge Guided Bayesian Optimization For Autonomous Alignment Of Complex Scientific Instruments Authors: Aashwin Mishra, Matt Seaberg, Ryan Roussel, Daniel Ratner, Apurva Mehta Published: 2026-02-11 Categories: cs.LG, math-ph arXiv: https://arxiv.org/abs/2602.10670v1 Bayesian Optimization (BO) is a powerful tool for optimizing complex non-linear systems. However, its performance degrades in high-dimensional problems with tightly coupled parameters and highly asymmetric objective landscapes, where rewards are sparse. In such needle-in-a-haystack scenarios, even advanced methods like trust-region BO (TurBO) often lead to unsatisfactory results. We propose a domain knowledge guided Bayesian Optimization approach, which leverages physical insight to fundamentally simplify the search problem by transforming coordinates to decouple input features and align the active subspaces with the primary search axes. We demonstrate this approach's efficacy on a challenging 12-dimensional, 6-crystal Split-and-Delay optical system, where conventional approaches, including standard BO, TuRBO and multi-objective BO, consistently led to unsatisfactory results. When combined with an reverse annealing exploration strategy, this approach reliably converges to the global optimum. The coordinate transformation itself is the key to this success, significantly accelerating the search by aligning input co-ordinate axes with the problem's active subspaces. As increasingly complex scientific instruments, from large telescopes to new spectrometers at X-ray Free Electron Lasers are deployed, the demand for robust high-dimensional optimization grows. Our results demonstrate a generalizable paradigm: leveraging physical insight to transform high-dimensional, coupled optimization problems into simpler representations can enable rapid and robust automated tuning for consistent high performance while still retaining current optimization algorithms. --- ### From Diet to Free Lunch: Estimating Auxiliary Signal Properties using Dynamic Pruning Masks in Speech Enhancement Networks Authors: Riccardo Miccini, Clément Laroche, Tobias Piechowiak, Xenofon Fafoutis, Luca Pezzarossa Published: 2026-02-11 Categories: eess.AS, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2602.10666v1 Speech Enhancement (SE) in audio devices is often supported by auxiliary modules for Voice Activity Detection (VAD), SNR estimation, or Acoustic Scene Classification to ensure robust context-aware behavior and seamless user experience. Just like SE, these tasks often employ deep learning; however, deploying additional models on-device is computationally impractical, whereas cloud-based inference would introduce additional latency and compromise privacy. Prior work on SE employed Dynamic Channel Pruning (DynCP) to reduce computation by adaptively disabling specific channels based on the current input. In this work, we investigate whether useful signal properties can be estimated from these internal pruning masks, thus removing the need for separate models. We show that simple, interpretable predictors achieve up to 93% accuracy on VAD, 84% on noise classification, and an R2 of 0.86 on F0 estimation. With binary masks, predictions reduce to weighted sums, inducing negligible overhead. Our contribution is twofold: on one hand, we examine the emergent behavior of DynCP models through the lens of downstream prediction tasks, to reveal what they are learning; on the other, we repurpose and re-propose DynCP as a holistic solution for efficient SE and simultaneous estimation of signal properties. ---