# Research Papers — 2026-02 · bundle page 2 of 210 > Full-text markdown of papers #51–100 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/2 [← Previous bundle](https://aipod.dev/papers/archive/2026-02.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/3.md) ### NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code Authors: Seemandhar Jain, Keshav Gupta, Kunal Gupta, Manmohan Chandraker Published: 2026-02-28 Categories: cs.CV, cs.MA arXiv: https://arxiv.org/abs/2603.00805v1 The proliferation of neural radiance field (NeRF) research requires significant efforts to reimplement papers before building upon them. We introduce NERFIFY, a multi-agent framework that reliably converts NeRF research papers into trainable Nerfstudio plugins, in contrast to generic paper-to-code methods and frontier models like GPT-5 that usually fail to produce runnable code. NERFIFY achieves domain-specific executability through six key innovations: (1) Context-free grammar (CFG): LLM synthesis is constrained by Nerfstudio formalized as a CFG, ensuring generated code satisfies architectural invariants. (2) Graph-of-Thought code synthesis: Specialized multi-file-agents generate repositories in topological dependency order, validating contracts and errors at each node. (3) Compositional citation recovery: Agents automatically retrieve and integrate components (samplers, encoders, proposal networks) from citation graphs of references. (4) Visual feedback: Artifacts are diagnosed through PSNR-minima ROI analysis, cross-view geometric validation, and VLM-guided patching to iteratively improve quality. (5) Knowledge enhancement: Beyond reproduction, methods can be improved with novel optimizations. (6) Benchmarking: An evaluation framework is designed for NeRF paper-to-code synthesis across 30 diverse papers. On papers without public implementations, NERFIFY achieves visual quality matching expert human code (+/-0.5 dB PSNR, +/-0.2 SSIM) while reducing implementation time from weeks to minutes. NERFIFY demonstrates that a domain-aware design enables code translation for complex vision papers, potentiating accelerated and democratized reproducible research. Code, data and implementations will be publicly released. --- ### Lookahead identification in adversarial bandits: accuracy and memory bounds Authors: Nataly Brukhim, Nicolò Cesa-Bianchi, Carlo Ciliberto Published: 2026-02-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00803v1 We study an identification problem in multi-armed bandits. In each round a learner selects one of $K$ arms and observes its reward, with the goal of eventually identifying an arm that will perform best at a {\it future} time. In adversarial environments, however, past performance may offer little information about the future, raising the question of whether meaningful identification is possible at all. In this work, we introduce \emph{lookahead identification}, a task in which the goal of the learner is to select a future prediction window and commit in advance to an arm whose average reward over that window is within $\varepsilon$ of optimal. Our analysis characterizes both the achievable accuracy of lookahead identification and the memory resources required to obtain it. From an accuracy standpoint, for any horizon $T$ we give an algorithm achieving $\varepsilon = O\bigl(1/\sqrt{\log T}\bigr)$ over $Ω(\sqrt{T})$ prediction windows. This demonstrates that, perhaps surprisingly, identification is possible in adversarial settings, despite significant lack of information. We also prove a near-matching lower bound showing that $\varepsilon = Ω\bigl(1/\log T\bigr)$ is unavoidable. We then turn to investigate the role of memory in our problem, first proving that any algorithm achieving nontrivial accuracy requires $Ω(K)$ bits of memory. Under a natural \emph{local sparsity} condition, we show that the same accuracy guarantees can be achieved using only poly-logarithmic memory. --- ### The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents Authors: Shrey Shah, Levent Ozgur Published: 2026-02-28 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.00801v2 Language agents increasingly act as web-enabled systems that search, browse, and synthesize information from diverse sources. However, these sources can include unreliable or adversarial content, and the robustness of agents to adversarial ranking - where misleading information appears prominently in search results - remains poorly understood. Existing benchmarks evaluate functional navigation or static factuality but cannot causally isolate this vulnerability, and current mitigation strategies for retrieval-augmented generation remain largely untested under such conditions. We introduce Synthetic Web Benchmark, a procedurally generated environment comprising thousands of hyperlinked articles with ground-truth labels for credibility and factuality, process-level interaction traces, and contamination filtering to eliminate training-data leakage. By injecting a single high-plausibility misinformation article into a controllable search rank, we measure the causal effect of adversarial exposure in six frontier models. The results reveal catastrophic failures: accuracy collapses despite unlimited access to truthful sources, with minimal search escalation and severe miscalibration. These findings expose fundamental limitations in how current frontier models handle conflicting information, with immediate implications for deployment in high-stakes domains. Our benchmark enables systematic analysis of these failure modes and provides a controlled testbed for evaluating mitigation strategies under adversarial ranking - a gap in current research. This work establishes a reproducible baseline for developing search-robust and epistemically humble agents capable of resisting manipulation in high-stakes domains. --- ### The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents Authors: Shrey Shah, Levent Ozgur Published: 2026-02-28 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.00801v1 Language agents increasingly act as web-enabled systems that search, browse, and synthesize information from diverse sources. However, these sources can include unreliable or adversarial content, and the robustness of agents to adversarial ranking - where misleading information appears prominently in search results - remains poorly understood. Existing benchmarks evaluate functional navigation or static factuality but cannot causally isolate this vulnerability, and current mitigation strategies for retrieval-augmented generation remain largely untested under such conditions. We introduce Synthetic Web Benchmark, a procedurally generated environment comprising thousands of hyperlinked articles with ground-truth labels for credibility and factuality, process-level interaction traces, and contamination filtering to eliminate training-data leakage. By injecting a single high-plausibility misinformation article into a controllable search rank, we measure the causal effect of adversarial exposure in six frontier models. The results reveal catastrophic failures: accuracy collapses despite unlimited access to truthful sources, with minimal search escalation and severe miscalibration. These findings expose fundamental limitations in how current frontier models handle conflicting information, with immediate implications for deployment in high-stakes domains. Our benchmark enables systematic analysis of these failure modes and provides a controlled testbed for evaluating mitigation strategies under adversarial ranking - a gap in current research. This work establishes a reproducible baseline for developing search-robust and epistemically humble agents capable of resisting manipulation in high-stakes domains. --- ### Efficient Conformal Volumetry for Template-Based Segmentation Authors: Matt Y. Cheung, Ashok Veeraraghavan, Guha Balakrishnan Published: 2026-02-28 Categories: eess.IV, cs.CV, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2603.00798v1 Template-based segmentation, a widely used paradigm in medical imaging, propagates anatomical labels via deformable registration from a labeled atlas to a target image, and is often used to compute volumetric biomarkers for downstream decision-making. While conformal prediction (CP) provides finite-sample valid intervals for scalar metrics, existing segmentation-based uncertainty quantification (UQ) approaches either rely on learned model features, often unavailable in classic template-based pipelines, or treat the registration process as a black box, resulting in overly conservative intervals when applied directly in output space. We introduce ConVOLT, a CP framework that achieves efficient volumetric UQ by conditioning calibration on properties of the estimated deformation field from template-based segmentation. ConVOLT calibrates a learned volumetric scaling factor from deformation space features. We evaluate ConVOLT on template-based segmentation tasks involving global, regional, and label volumetry across multiple datasets and registration methods. ConVOLT achieves target coverage while producing substantially tighter intervals than output-space conformal baselines. Our work paves way to exploit the registration process for efficient UQ in medical imaging pipelines. --- ### Neural Functional Alignment Space: Brain-Referenced Representation of Artificial Neural Networks Authors: Ruiyu Yan, Hanqi Jiang, Yi Pan, Xiaobo Li, Tianming Liu, Xi Jiang, Lin Zhao Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00793v1 We propose the Neural Functional Alignment Space (NFAS), a brain-referenced representational framework for characterizing artificial neural networks on equal functional grounds. NFAS departs from conventional alignment approaches that rely on layer-wise features or task-specific activations by modeling the intrinsic dynamical evolution of stimulus representations across network depth. Specifically, we model layer-wise embeddings as a depth-wise dynamical trajectory and apply Dynamic Mode Decomposition (DMD) to extract the stable mode. This representation is then projected into a biologically anchored coordinate system defined by distributed neural responses. We also introduce the Signal-to-Noise Consistency Index (SNCI) to quantify cross-model consistency at the modality level. Across 45 pretrained models spanning vision, audio, and language, NFAS reveals structured organization within this brain-referenced space, including modality-specific clustering and cross-modal convergence in integrative cortical systems. Our findings suggest that representation dynamics provide a principled basis for --- ### Neural Latent Arbitrary Lagrangian-Eulerian Grids for Fluid-Solid Interaction Authors: Shilong Tao, Zhe Feng, Shaohan Chen, Weichen Zhang, Zhanxing Zhu, Yunhuai Liu Published: 2026-02-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00792v1 Fluid-solid interaction (FSI) problems are fundamental in many scientific and engineering applications, yet effectively capturing the highly nonlinear two-way interactions remains a significant challenge. Most existing deep learning methods are limited to simplified one-way FSI scenarios, often assuming rigid and static solid to reduce complexity. Even in two-way setups, prevailing approaches struggle to capture dynamic, heterogeneous interactions due to the lack of cross-domain awareness. In this paper, we introduce \textbf{Fisale}, a data-driven framework for handling complex two-way \textbf{FSI} problems. It is inspired by classical numerical methods, namely the Arbitrary Lagrangian-Eulerian (\textbf{ALE}) method and the partitioned coupling algorithm. Fisale explicitly models the coupling interface as a distinct component and leverages multiscale latent ALE grids to provide unified, geometry-aware embeddings across domains. A partitioned coupling module (PCM) further decomposes the problem into structured substeps, enabling progressive modeling of nonlinear interdependencies. Compared to existing models, Fisale introduces a more flexible framework that iteratively handles complex dynamics of solid, fluid and their coupling interface on a unified representation, and enables scalable learning of complex two-way FSI behaviors. Experimentally, Fisale excels in three reality-related challenging FSI scenarios, covering 2D, 3D and various tasks. The code is available at \href{https://github.com/therontau0054/Fisale}. --- ### Identifying the Geographic Foci of US Local News Authors: Gangani Ariyarathne, Isuru Ariyarathne, Greatness Emmanuel-King, Kate Lawal, Alexander C. Nwala Published: 2026-02-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00787v1 Local journalism is vital in democratic societies where it informs people about local issues like, school board elections, small businesses, local health services, etc. But mounting economic pressures have made it increasingly difficult for local news stations to report these issues, underscoring the need to identify the salient geographical locations covered in local news (geo-foci). In response, we propose a novel geo-foci model for labeling US local news articles with the geographic locations (i.e., the names of counties, cities, states, countries) central to their subject matter. First, we manually labeled US local news articles from all 50 states with four administrative division labels (local, state, national, and international) corresponding to their geo-foci, and none for articles without a geographic focus. Second, we extracted and disambiguated geographic locations from them using Large Language Models (LLMs), since local news often contains ambiguous geographic entities (e.g., Paris, Texas vs. Paris, France). LLMs outperformed all eight geographic entity disambiguation methods we evaluated. Third, we engineered a rich set of spatial-semantic features capturing the prominence, frequency, and contextual positions of geographic entities. Using these features, we trained a classifier to accurately (F1: 0.86) detect the geographic foci of US local news articles. Our model could be applied to assess shifts from local to national narratives, and more broadly, enable researchers to better study local media. --- ### Interpretable Cross-Network Attention for Resting-State fMRI Representation Learning Authors: Karanpartap Singh, Adam Turnbull, Mohammad Abbasi, Kilian Pohl, Feng Vankee Lin, Ehsan Adeli Published: 2026-02-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00786v1 Understanding how large-scale functional brain networks reorganize during cognitive decline remains a central challenge in neuroimaging. While recent self-supervised models have shown promise for learning representations from resting-state fMRI, their internal mechanisms are difficult to interpret, limiting mechanistic insight. We propose BrainInterNet, a network-aware self-supervised framework based on masked reconstruction with cross-attention that explicitly models inter-network dependencies in rs-fMRI. By selectively masking predefined functional networks and reconstructing them from remaining context, our approach enables direct quantification of network predictability and interpretable analysis of cross-network interactions. We train BrainInterNet on multi-cohort fMRI data (from the ABCD, HCP Development, HCP Young Adults, and HCP Aging datasets) and evaluate on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, in total comprising 5,582 recordings. Our method reveals systematic alterations in the brain's network interactions under AD, including in the default mode, limbic, and attention networks. In parallel, the learned representations support accurate Alzheimer's-spectrum classification and yield a compact summary marker that tracks disease severity longitudinally. Together, these results demonstrate that network-guided masked modeling with cross-attention provides an interpretable and effective framework for characterizing functional reorganization in neurodegeneration. --- ### QANTIS: A Hardware-Validated Quantum Platform for POMDP Planning and Multi-Target Data Association Authors: Bayram Yüksel Eker, Suayb S. Arslan, Özgür Nazlı, Mustafa Serhat Demirgil, Furkan Deligöz Published: 2026-02-28 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2603.00785v1 Autonomous navigation under uncertainty requires solving partially observable Markov decision processes (POMDPs) for planning and assigning sensor measurements to tracked targets--a task known as multi-target data association (MTDA). Both problems become computationally demanding at scale: belief conditioning costs $\mathcal{O}(P(e)^{-1})$ per node under rare evidence, while MTDA is NP-hard. Quantum amplitude amplification can quadratically reduce the belief-update query cost to $\mathcal{O}(P(e)^{-1/2})$, while QUBO reformulations expose MTDA to quantum and quantum-inspired optimisation heuristics. We present QANTIS, a modular platform that integrates quantum belief update (Grover amplitude amplification and BIQAE), QUBO-based data association via FPC-QAOA, and composable error mitigation, and we report a 45-experiment hardware study on three IBM Heron backends. On hardware, a single Grover iterate applied to a Tiger belief oracle amplifies a rare observation probability from $0.179$ to $0.907$ ($5.1\times$; ISA 18) while preserving the Bayesian posterior (Hellinger $0.0015$), increasing usable-shot yield from 1,463 to 7,429. We interpret this as a hardware validation of the quadratic query-complexity mechanism at $k=1$ with posterior preservation, rather than a wall-clock advantage claim. We further demonstrate, to our knowledge, the first closed-loop hybrid quantum-classical Tiger POMDP on superconducting hardware ($T=8$, max Hellinger below $0.015$), and empirically characterise NISQ feasibility boundaries: ZNE-based error mitigation is beneficial below ISA $\approx 100$ and harmful above ISA $\gtrsim 1{,}000$; FPC-QAOA is meaningful at $\leq 15$ QUBO variables (ISA $\lesssim 450$). These results characterise practical operating regimes on current superconducting hardware rather than wall-clock quantum advantage at today's problem scales. --- ### DUCX: Decomposing Unfairness in Tool-Using Chest X-ray Agents Authors: Zikang Xu, Ruinan Jin, Xiaoxiao Li Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00777v2 Fairness in medical agents is becoming critical as tool-using clinical AI systems orchestrate specialized vision and language modules for tasks such as chest X-ray question answering. While these medical AI agents can improve flexibility, their added pipeline complexity also creates new pathways for demographic bias beyond standalone models. We present DUCK, Decomposing Unfairness in Chest X-ray agents, a systematic audit of fairness in tool-using chest X-ray agents instantiated with MedRAX. To localize where disparities arise, we introduce a stage-wise fairness decomposition that separates end-to-end bias from three agent-specific sources: tool exposure bias, or utility gaps conditioned on tool presence; tool transition bias, or subgroup differences in tool-routing patterns; and model reasoning bias, or subgroup differences in synthesis behaviors. Extensive experiments on tool-using agentic frameworks across five driver backbones reveal that demographic gaps persist in end-to-end performance, with equalized odds up to 20.79% and the lowest fairness-utility tradeoff down to 28.65%. Intermediate behaviors, including tool usage, transition patterns, and reasoning traces, exhibit distinct subgroup disparities that are not predictable from end-to-end evaluation alone. For example, conditioned on segmentation-tool availability, the subgroup utility gap reaches as high as 50%. Our findings underscore the need for process-level fairness auditing and debiasing to ensure the equitable deployment of clinical agentic systems. Code: https://github.com/Nanboy-Ronan/DUCK. --- ### Generalizing Score-based generative models for Heavy-tailed Distributions Authors: Tiziano Fassina, Gabriel Cardoso, Sylvan Le Corff, Thomas Romary Published: 2026-02-28 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.00772v2 Score-based generative models (SGMs) have achieved remarkable empirical success, motivating their application to a broad range of data distributions. However, extending them to heavy-tailed targets remains a largely open problem. Although dedicated models for heavy-tailed distributions have been proposed, their generative fidelity remains unclear and they lack solid theoretical foundations, leaving important questions open in this regime. In this paper, we address this gap through two theoretical contributions. First, we show that combining early stopping with a suitable initialization is sufficient to extend the diffusion framework to any target distribution; in particular, we establish the well-posedness of the backward process and prove convergence of the approximated diffusion in KL divergence. Second, we derive novel theoretical guarantees for generation with normalizing flows, obtaining convergence results that hold under mild conditions on the flow family and without any assumption on the tail behavior of the target distribution. Building on these results, we propose a unified generative framework for heavy-tailed distributions: a normalizing flow is first trained to capture the tail behavior and is then used as an initialization prior for an SGM, which refines the samples by recovering fine-grained structural details. This design leverages the complementary strengths of the two model classes within a theoretically principled pipeline, overcoming the limitations of existing approaches. --- ### Analyzing and Improving Fast Sampling of Text-to-Image Diffusion Models Authors: Zhenyu Zhou, Defang Chen, Siwei Lyu, Chun Chen, Can Wang Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00763v2 Text-to-image diffusion models have achieved unprecedented success but still struggle to produce high-quality results under limited sampling budgets. Existing training-free sampling acceleration methods are typically developed independently, leaving the overall performance and compatibility among these methods unexplored. In this paper, we bridge this gap by systematically elucidating the design space, and our comprehensive experiments identify the sampling time schedule as the most pivotal factor. Inspired by the geometric properties of diffusion models revealed through the Frenet-Serret formulas, we propose constant total rotation schedule (TORS), a scheduling strategy that ensures uniform geometric variation along the sampling trajectory. TORS outperforms previous training-free acceleration methods and produces high-quality images with 10 sampling steps on Flux.1-Dev and Stable Diffusion 3.5. Extensive experiments underscore the adaptability of our method to unseen models, hyperparameters, and downstream applications. Code is available at https://github.com/zju-pi/TORS. --- ### Analyzing and Improving Fast Sampling of Text-to-Image Diffusion Models Authors: Zhenyu Zhou, Defang Chen, Siwei Lyu, Chun Chen, Can Wang Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00763v1 Text-to-image diffusion models have achieved unprecedented success but still struggle to produce high-quality results under limited sampling budgets. Existing training-free sampling acceleration methods are typically developed independently, leaving the overall performance and compatibility among these methods unexplored. In this paper, we bridge this gap by systematically elucidating the design space, and our comprehensive experiments identify the sampling time schedule as the most pivotal factor. Inspired by the geometric properties of diffusion models revealed through the Frenet-Serret formulas, we propose constant total rotation schedule (TORS), a scheduling strategy that ensures uniform geometric variation along the sampling trajectory. TORS outperforms previous training-free acceleration methods and produces high-quality images with 10 sampling steps on Flux.1-Dev and Stable Diffusion 3.5. Extensive experiments underscore the adaptability of our method to unseen models, hyperparameters, and downstream applications. --- ### Identifying and Characterising Response in Clinical Trials: Development and Validation of a Machine Learning Approach in Colorectal Cancer Authors: Adam Marcus, Paul Agapow Published: 2026-02-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00757v1 Precision medicine promises to transform health care by offering individualised treatments that dramatically improve clinical outcomes. A necessary prerequisite is to identify subgroups of patients who respond differently to different therapies. Current approaches are limited to static measures of treatment success, neglecting the repeated measures found in most clinical trials. Our approach combines the concept of partly conditional modelling with treatment effect estimation based on the Virtual Twins method. The resulting time-specific responses to treatment are characterised using survLIME, an extension of Local Interpretable Model-agnostic Explanations (LIME) to survival data. Performance was evaluated using synthetic data and applied to clinical trials examining the effectiveness of panitumumab to treat metastatic colorectal cancer. An area under the receiver operating characteristic curve (AUC) of 0.77 for identifying fixed responders was achieved in a 1000 patient simulation. When considering dynamic responders, partly conditional modelling increased the AUC from 0.597 to 0.685. Applying the approach to colorectal cancer trials found genetic mutations, sites of metastasis, and ethnicity as important factors for response to treatment. Our approach can accommodate a dynamic response to treatment while potentially providing better performance than existing methods in instances of a fixed response to treatment. When applied to clinical data we attain results consistent with the literature. --- ### Stroke outcome and evolution prediction from CT brain using a spatiotemporal diffusion autoencoder Authors: Adam Marcus, Paul Bentley, Daniel Rueckert Published: 2026-02-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00756v1 Stroke is a major cause of death and disability worldwide. Accurate outcome and evolution prediction has the potential to revolutionize stroke care by individualizing clinical decision-making leading to better outcomes. However, despite a plethora of attempts and the rich data provided by neuroimaging, modelling the ultimate fate of brain tissue remains a challenging task. In this work, we apply recent ideas in the field of diffusion probabilistic models to generate a self-supervised semantically meaningful stroke representation from Computed Tomography (CT) images. We then improve this representation by extending the method to accommodate longitudinal images and the time from stroke onset. The effectiveness of our approach is evaluated on a dataset consisting of 5,824 CT images from 3,573 patients across two medical centers with minimal labels. Comparative experiments show that our method achieves the best performance for predicting next-day severity and functional outcome at discharge. --- ### BornoViT: A Novel Efficient Vision Transformer for Bengali Handwritten Basic Characters Classification Authors: Rafi Hassan Chowdhury, Naimul Haque, Kaniz Fatiha Published: 2026-02-28 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.00755v1 Handwritten character classification in the Bengali script is a significant challenge due to the complexity and variability of the characters. The models commonly used for classification are often computationally expensive and data-hungry, making them unsuitable for resource-limited languages such as Bengali. In this experiment, we propose a novel, efficient, and lightweight Vision Transformer model that effectively classifies Bengali handwritten basic characters and digits, addressing several shortcomings of traditional methods. The proposed solution utilizes a deep convolutional neural network (DCNN) in a more simplified manner compared to traditional DCNN architectures, with the aim of reducing computational burden. With only 0.65 million parameters, a model size of 0.62 MB, and 0.16 GFLOPs, our model, BornoViT, is significantly lighter than current state-of-the-art models, making it more suitable for resource-limited environments, which is essential for Bengali handwritten character classification. BornoViT was evaluated on the BanglaLekha Isolated dataset, achieving an accuracy of 95.77%, and demonstrating superior efficiency compared to existing state-of-the-art approaches. Furthermore, the model was evaluated on our self-collected dataset, Bornomala, consisting of approximately 222 samples from different age groups, where it achieved an accuracy of 91.51%. --- ### General Proximal Flow Networks Authors: Alexander Strunk, Roland Assam Published: 2026-02-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00751v1 This paper introduces General Proximal Flow Networks (GPFNs), a generalization of Bayesian Flow Networks that broadens the class of admissible belief-update operators. In Bayesian Flow Networks, each update step is a Bayesian posterior update, which is equivalent to a proximal step with respect to the Kullback-Leibler divergence. GPFNs replace this fixed choice with an arbitrary divergence or distance function, such as the Wasserstein distance, yielding a unified proximal-operator framework for iterative generative modeling. The corresponding training and sampling procedures are derived, establishing a formal link to proximal optimization and recovering the standard BFN update as a special case. Empirical evaluations confirm that adapting the divergence to the underlying data geometry yields measurable improvements in generation quality, highlighting the practical benefits of this broader framework. --- ### SpectroFusion-ViT: A Lightweight Transformer for Speech Emotion Recognition Using Harmonic Mel-Chroma Fusion Authors: Faria Ahmed, Rafi Hassan Chowdhury, Fatema Tuz Zohora Moon, Sabbir Ahmed Published: 2026-02-28 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2603.00746v1 Speech is a natural means of conveying emotions, making it an effective method for understanding and representing human feelings. Reliable speech emotion recognition (SER) is central to applications in human-computer interaction, healthcare, education, and customer service. However, most SER methods depend on heavy backbone models or hand-crafted features that fail to balance accuracy and efficiency, particularly for low-resource languages like Bangla. In this work, we present SpectroFusion-ViT, a lightweight SER framework built utilizing EfficientViT-b0, a compact Vision Transformer architecture equipped with self-attention to capture long-range temporal and spectral patterns. The model contains only 2.04M parameters and requires 0.1 GFLOPs, enabling deployment in resource-constrained settings without compromising accuracy. Our pipeline first performs preprocessing and augmentation on raw audio, then extracts Chroma and Mel-frequency cepstral coefficient (MFCC) features. These representations are fused into a complementary time-frequency descriptor that preserves both fine-grained spectral detail and broader harmonic structure. Using transfer learning, EfficientViT-b0 is fine-tuned for multi-class emotion classification. We evaluate the system on two benchmark Bangla emotional speech datasets, SUBESCO and BanglaSER, which vary in speaker diversity, recording conditions, and acoustic characteristics. The proposed approach achieves 92.56% accuracy on SUBESCO and 82.19% on BanglaSER, surpassing existing state-of-the-art methods. These findings demonstrate that lightweight transformer architectures can deliver robust SER performance while remaining computationally efficient for real-world deployment. --- ### Bi-cLSTM: Residual-Corrected Bidirectional LSTM for Aero-Engine RUL Estimation Authors: Rafi Hassan Chowdhury, Nabil Daiyan, Faria Ahmed, Md Redwan Iqbal, Morsalin Sheikh Published: 2026-02-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00745v1 Accurate Remaining Useful Life (RUL) prediction is a key requirement for effective Prognostics and Health Management (PHM) in safety-critical systems such as aero-engines. Existing deep learning approaches, particularly LSTM-based models, often struggle to generalize across varying operating conditions and are sensitive to noise in multivariate sensor data. To address these challenges, we propose a novel Bidirectional Residual Corrected LSTM (Bi-cLSTM) model for robust RUL estimation. The proposed architecture combines bidirectional temporal modeling with an adaptive residual correction mechanism to iteratively refine sequence representations. In addition, we introduce a condition-aware preprocessing pipeline incorporating regime-based normalization, feature selection, and exponential smoothing to improve robustness under complex operating environments. Extensive experiments on all four subsets of the NASA C-MAPSS dataset demonstrate that the proposed Bi-cLSTM consistently outperforms LSTM-based baselines and achieves competitive state-of-the-art performance, particularly in challenging multi-condition scenarios. These results highlight the effectiveness of combining bidirectional temporal learning with residual correction for reliable RUL prediction. --- ### ResGene-T: A Tensor-Based Residual Network Approach for Genomic Prediction Authors: Kuldeep Pathak, Kapil Ahuja, Eric de Sturler Published: 2026-02-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00744v1 In this work, we propose a new deep learning model for Genomic Prediction (GP), which involves correlating genotypic data with phenotypic. The genotypes are typically fed as a sequence of characters to the 1D-Convolution Neural Network layer of the underlying deep learning model. Inspired by earlier work that represented genotype as a 2D-image for genotype-phenotype classification, we extend this idea to GP, which is a regression task. We use a ResNet-18 as the underlying architecture, and term this model as ResGene-2D. Although the 2D-image representation captures biological interactions well, it requires all the layers of the model to do so. This limits training efficiency. Thus, as seen in the earlier work that proposed a 2D-image representation, our ResGene-2D performs almost the same as other models (3% improvement). To overcome this, we propose a novel idea of converting the 2D-image into a 3D/ tensor and feed this to the ResNet-18 architecture, and term this model as ResGene-T. We evaluate our proposed models on three crop species having ten phenotypic traits and compare it with seven most popular models (two statistical, two machine learning, and three deep learning). ResGene-T performs the best among all these seven methods (gains from 14.51% to 41.51%). --- ### To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters Authors: Sara Dragutinović, Yedi Zhang, Rajesh Ranganath Published: 2026-02-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00742v2 While Adam has long been the ubiquitous default optimizer for deep neural networks, Muon has recently seen rapid adoption due to its superior training speed. Although much of the literature focuses on validating the benefits of Muon, our work investigates the potential downsides of the mechanism driving this speedup. On the theoretical front, we analyze the learning dynamics of simplified Muon on deep linear networks and linear attention. Our analysis reveals that Muon gains speed by avoiding saddle points, but does so at the expense of the simplicity bias characteristic of Gradient Descent (GD), where the complexity of the functional solution learned grows sequentially. Experiments demonstrate the consequences of losing the simplicity bias, showing that Muon struggles to uncover common underlying structure across tasks and may be prone to fitting spurious features. More broadly, this paper serves as a reminder that faster optimization is rarely a free lunch; improvements in optimization can come at the cost of changes in the inductive biases that shape generalization. --- ### Data-driven Synthesis of Magnetic Resonance Spectroscopy Data using a Variational Autoencoder Authors: Dennis M. J. van de Sande, Julian P. Merkofer, Sina Amirrajab, Mitko Veta, Gerhard S. Drenthen, Jacobus F. A. Jansen, Marcel Breeuwer Published: 2026-02-28 Categories: physics.med-ph, cs.LG arXiv: https://arxiv.org/abs/2603.00736v1 The development of deep learning methods for magnetic resonance spectroscopy (MRS) is often hindered by limited availability of large, high-quality training datasets. While physics-based simulations are commonly used to mitigate this limitation, accurately modeling all in-vivo signal components remains challenging. In this work, we propose a data-driven framework for synthesizing in-vivo MRS data using a variational autoencoder (VAE) trained exclusively on measured single-voxel spectroscopy data. The model learns a low-dimensional latent representation of complex-valued spectra and enables generation of new samples through latent-space sampling and interpolation. The generative performance of the proposed approach is evaluated using a comprehensive set of complementary analyses, including reconstruction quality, feature-level similarity using low-dimensional embeddings, application-based signal quality metrics, and metabolite quantification agreement. The results demonstrate that the VAE accurately reconstructs dominant spectral patterns and generates synthetic spectra that occupy the same feature space as in-vivo data. In an example application targeting GABA-edited spectroscopy, augmenting limited subsets of transients with synthetic spectra improves signal quality metrics such as signal-to-noise ratio, linewidth, and shape scores. However, the results also reveal limitations of the generative approach, including under-representation of stochastic noise and reduced accuracy in absolute metabolite quantification, particularly for applications sensitive to concentration estimates. These findings highlight both potential and limitations of data-driven MRS synthesis. Beyond the proposed model, this study introduces a structured evaluation framework for generative MRS methods, emphasizing the importance of application-aware validation when synthetic data are used for downstream analysis. --- ### UniHM: Unified Dexterous Hand Manipulation with Vision Language Model Authors: Zhenhao Zhang, Jiaxin Liu, Ye Shi, Jingya Wang Published: 2026-02-28 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.00732v1 Planning physically feasible dexterous hand manipulation is a central challenge in robotic manipulation and Embodied AI. Prior work typically relies on object-centric cues or precise hand-object interaction sequences, foregoing the rich, compositional guidance of open-vocabulary instruction. We introduce UniHM, the first framework for unified dexterous hand manipulation guided by free-form language commands. We propose a Unified Hand-Dexterous Tokenizer that maps heterogeneous dexterous-hand morphologies into a single shared codebook, improving cross-dexterous hand generalization and scalability to new morphologies. Our vision language action model is trained solely on human-object interaction data, eliminating the need for massive real-world teleoperation datasets, and demonstrates strong generalizability in producing human-like manipulation sequences from open-ended language instructions. To ensure physical realism, we introduce a physics-guided dynamic refinement module that performs segment-wise joint optimization under generative and temporal priors, yielding smooth and physically feasible manipulation sequences. Across multiple datasets and real-world evaluations, UniHM attains state-of-the-art results on both seen and unseen objects and trajectories, demonstrating strong generalization and high physical feasibility. Our project page at \href{https://unihm.github.io/}{https://unihm.github.io/}. --- ### MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning Authors: Tianmeng Hu, Biao Luo, Chunhua Yang, Tingwen Huang Published: 2026-02-28 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2603.00730v1 Deep reinforcement learning (RL) has been applied extensively to solve complex decision-making problems. In many real-world scenarios, tasks often have several conflicting objectives and may require multiple agents to cooperate, which are the multi-objective multi-agent decision-making problems. However, only few works have been conducted on this intersection. Existing approaches are limited to separate fields and can only handle multi-agent decision-making with a single objective, or multi-objective decision-making with a single agent. In this paper, we propose MO-MIX to solve the multi-objective multi-agent reinforcement learning (MOMARL) problem. Our approach is based on the centralized training with decentralized execution (CTDE) framework. A weight vector representing preference over the objectives is fed into the decentralized agent network as a condition for local action-value function estimation, while a mixing network with parallel architecture is used to estimate the joint action-value function. In addition, an exploration guide approach is applied to improve the uniformity of the final non-dominated solutions. Experiments demonstrate that the proposed method can effectively solve the multi-objective multi-agent cooperative decision-making problem and generate an approximation of the Pareto set. Our approach not only significantly outperforms the baseline method in all four kinds of evaluation metrics, but also requires less computational cost. --- ### Qwen3-Coder-Next Technical Report Authors: Ruisheng Cao, Mouxiang Chen, Jiawei Chen, Zeyu Cui, Yunlong Feng, Binyuan Hui, Yuheng Jing, Kaixin Li, Mingze Li, Junyang Lin, Zeyao Ma, Kashun Shum et al. Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00729v1 We present Qwen3-Coder-Next, an open-weight language model specialized for coding agents. Qwen3-Coder-Next is an 80-billion-parameter model that activates only 3 billion parameters during inference, enabling strong coding capability with efficient inference. In this work, we explore how far strong training recipes can push the capability limits of models with small parameter footprints. To achieve this, we perform agentic training through large-scale synthesis of verifiable coding tasks paired with executable environments, allowing learning directly from environment feedback via mid-training and reinforcement learning. Across agent-centric benchmarks including SWE-Bench and Terminal-Bench, Qwen3-Coder-Next achieves competitive performance relative to its active parameter count. We release both base and instruction-tuned open-weight versions to support research and real-world coding agent development. --- ### LaSTR: Language-Driven Time-Series Segment Retrieval Authors: Kota Dohi, Harsh Purohit, Tomoya Nishida, Takashi Endo, Yusuke Ohtsubo, Koichiro Yawata, Koki Takeshita, Tatsuya Sasaki, Yohei Kawaguchi Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00725v1 Effectively searching time-series data is essential for system analysis, but existing methods often require expert-designed similarity criteria or rely on global, series-level descriptions. We study language-driven segment retrieval: given a natural language query, the goal is to retrieve relevant local segments from large time-series repositories. We build large-scale segment--caption training data by applying TV2-based segmentation to LOTSA windows and generating segment descriptions with GPT-5.2, and then train a Conformer-based contrastive retriever in a shared text--time-series embedding space. On a held-out test split, we evaluate single-positive retrieval together with caption-side consistency (SBERT and VLM-as-a-judge) under multiple candidate pool sizes. Across all settings, LaSTR outperforms random and CLIP baselines, yielding improved ranking quality and stronger semantic agreement between retrieved segments and query intent. --- ### RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models Authors: Andrew Zhuoer Feng, Cunxiang Wang, Bosi Wen, Yidong Wang, Yu Luo, Hongning Wang, Minlie Huang Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00724v1 Large language model alignment via reinforcement learning depends critically on reward function quality. However, static, domain-specific reward models are often costly to train and exhibit poor generalization in out-of-distribution scenarios encountered during RL iterations. We present RLAR (Reinforcement Learning from Agent Rewards), an agent-driven framework that dynamically assigns tailored reward functions to individual queries. Specifically, RLAR transforms reward acquisition into a dynamic tool synthesis and invocation task. It leverages LLM agents to autonomously retrieve optimal reward models from the Internet and synthesize programmatic verifiers through code generation. This allows the reward system to self-evolve with the shifting data distributions during training. Experimental results demonstrate that RLAR yields consistent performance gains ranging from 10 to 60 across mathematics, coding, translation, and dialogue tasks. On RewardBench-V2, RLAR significantly outperforms static baselines and approaches the performance upper bound, demonstrating superior generalization through dynamic reward orchestration. The data and code are available on this link: https://github.com/ZhuoerFeng/RLAR. --- ### MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search Authors: Minkyoung Cho, Insu Jang, Shuowei Jin, Zesen Zhao, Adityan Jothi, Ethem F. Can, Min-Hung Chen, Z. Morley Mao Published: 2026-02-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00720v1 Fine-tuning Multimodal Large Language Models (MLLMs) with parameter-efficient methods like Low-Rank Adaptation (LoRA) is crucial for task adaptation. However, imbalanced training dynamics across modalities often lead to suboptimal accuracy due to negative interference, a challenge typically addressed with inefficient heuristic methods such as manually tuning separate learning rates. To overcome this, we introduce MARS (Multimodal Adaptive Rank Search), an approach to discover optimal rank pairs that balance training dynamics while maximizing performance. Our key innovation, a proposed framework of dual scaling laws, enables this search: one law models module-specific convergence time to prune the search space to candidates with aligned dynamics, while the other predicts final task performance to select the optimal pair from the pruned set. By re-purposing the LoRA rank as a controller for modality-specific convergence speed, MARS outperforms baseline methods and provides a robust, automated strategy for optimizing MLLM fine-tuning. --- ### SkillCraft: Can LLM Agents Learn to Use Tools Skillfully? Authors: Shiqi Chen, Jingze Gai, Ruochen Zhou, Jinghan Zhang, Tongyao Zhu, Junlong Li, Kangrui Wang, Zihan Wang, Zhengyu Chen, Klara Kaleb, Ning Miao, Siyang Gao et al. Published: 2026-02-28 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2603.00718v2 Real-world tool-using agents operate over long-horizon workflows with recurring structure and diverse demands, where effective behavior requires not only invoking atomic tools but also abstracting, and reusing higher-level tool compositions. However, existing benchmarks mainly measure instance-level success under static tool sets, offering limited insight into agents' ability to acquire such reusable skills. We address this gap by introducing SkillCraft, a benchmark explicitly stress-test agent ability to form and reuse higher-level tool compositions, where we call Skills. SkillCraft features realistic, highly compositional tool-use scenarios with difficulty scaled along both quantitative and structural dimensions, designed to elicit skill abstraction and cross-task reuse. We further propose a lightweight evaluation protocol that enables agents to auto-compose atomic tools into executable Skills, cache and reuse them inside and across tasks, thereby improving efficiency while accumulating a persistent library of reusable skills. Evaluating state-of-the-art agents on SkillCraft, we observe substantial efficiency gains, with token usage reduced by up to 80% by skill saving and reuse. Moreover, success rate strongly correlates with tool composition ability at test time, underscoring compositional skill acquisition as a core capability. --- ### Smoothing the Semantic Landscape: Generalizable AI-Generated Image Detection via Text-Induced Flatness Authors: Qinghui He, Haifeng Zhang, Yanan Luo, Bo Liu, Xiuli Bi, Bin Xiao Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00717v3 Recent advances in generative models have exposed a fundamental weakness of image fake detectors: they often fail to generalize to unseen synthesis methods. We attribute this failure to an optimization pathology in which detectors overfit to source-coupled artifacts and converge to sharp solutions, resulting in unstable decision boundaries under generator shifts. To address this issue, we propose a geometric optimization framework that treats diverse textual prompts as structured semantic perturbations in the joint image--text space. To ensure that these perturbations provide reliable supervision, we introduce an entropy-based anchor selection mechanism that discards ambiguous prompt conditions and retains semantically compatible anchors for each input. Based on these anchors, we further impose two complementary regularizations: (i) perturbation consistency regularization, which enforces stable predictions across nearby semantic conditions and encourages local smoothness of the decision function; and (ii) manifold expansion regularization, which preserves feature diversity in the residual space and alleviates representation collapse. Together, these components steer optimization toward flatter and more transferable solutions. Extensive experiments on multiple benchmarks show that our method substantially improves cross-generator generalization, outperforming previous state-of-the-art methods by 5.65\% in average accuracy. --- ### Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalization Authors: Qinghui He, Haifeng Zhang, Xiuli Bi, Bo Liu, Chi-Man Pun, Bin Xiao Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00717v2 The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely to make classifiers data-dependent, resulting in narrow decision margins and, consequently, limited generalization ability to unseen generative models. We observe that both real and generated images intend to form clustered low-dimensional manifolds within high-level feature spaces extracted by pre-trained visual encoders. Building on this observation, we propose a single-class attribution modeling framework that first amplifies the intrinsic differences between real and generated images by constructing a compact attribution space from any single-class training set, either composed of real images or generated ones, and then establishes a more stable decision boundary upon the enlarged separation. This process enhances class distinction and mitigates the reliance on generator-specific artifacts, thereby improving cross-model generalization. Extensive experiments show that our method generalizes well across various unseen generative models, outperforming existing detectors by as much as 7.21% in accuracy and 7.20% in cross-model generalization. --- ### Frozen Policy Iteration: Computationally Efficient RL under Linear $Q^π$ Realizability for Deterministic Dynamics Authors: Yijing Ke, Zihan Zhang, Ruosong Wang Published: 2026-02-28 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.00716v1 We study computationally and statistically efficient reinforcement learning under the linear $Q^π$ realizability assumption, where any policy's $Q$-function is linear in a given state-action feature representation. Prior methods in this setting are either computationally intractable, or require (local) access to a simulator. In this paper, we propose a computationally efficient online RL algorithm, named Frozen Policy Iteration, under the linear $Q^π$ realizability setting that works for Markov Decision Processes (MDPs) with stochastic initial states, stochastic rewards and deterministic transitions. Our algorithm achieves a regret bound of $\widetilde{O}(\sqrt{d^2H^6T})$, where $d$ is the dimensionality of the feature space, $H$ is the horizon length, and $T$ is the total number of episodes. Our regret bound is optimal for linear (contextual) bandits which is a special case of our setting with $H = 1$. Existing policy iteration algorithms under the same setting heavily rely on repeatedly sampling the same state by access to the simulator, which is not implementable in the online setting with stochastic initial states studied in this paper. In contrast, our new algorithm circumvents this limitation by strategically using only high-confidence part of the trajectory data and freezing the policy for well-explored states, which ensures that all data used by our algorithm remains effectively on-policy during the whole course of learning. We further demonstrate the versatility of our approach by extending it to the Uniform-PAC setting and to function classes with bounded eluder dimension. --- ### A Reconstruction System for Industrial Pipeline Inner Walls Using Panoramic Image Stitching with Endoscopic Imaging Authors: Rui Ma, Yifeng Wang, Ziteng Yang, Jing Guo, Naomi Imali Okanda, Xinghui Li Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00714v2 Visual analysis and reconstruction of pipeline inner walls remain challenging in industrial inspection scenarios. This paper presents a dedicated reconstruction system for pipeline inner walls via industrial endoscopes, which is built on panoramic image stitching technology. Equipped with a custom graphical user interface (GUI), the system extracts key frames from endoscope video footage, and integrates polar coordinate transformation with image stitching techniques to unwrap annular video frames of pipeline inner walls into planar panoramic images. Experimental results demonstrate that the proposed method enables efficient processing of industrial endoscope videos, and the generated panoramic stitched images preserve all detailed features of pipeline inner walls in their entirety. This provides intuitive and accurate visual support for defect detection and condition assessment of pipeline inner walls. In comparison with the traditional frame-by-frame video review method, the proposed approach significantly elevates the efficiency of pipeline inner wall reconstruction and exhibits considerable engineering application value. --- ### IU: Imperceptible Universal Backdoor Attack Authors: Hsin Lin, Yan-Lun Chen, Ren-Hung Hwang, Chia-Mu Yu Published: 2026-02-28 Categories: cs.CR, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.00711v1 Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually salient patterns, making them easier to detect and less practical at scale. In this work, we introduce a novel imperceptible universal backdoor attack that simultaneously controls all target classes with minimal poisoning while preserving stealth. Our key idea is to leverage graph convolutional networks (GCNs) to model inter-class relationships and generate class-specific perturbations that are both effective and visually invisible. The proposed framework optimizes a dual-objective loss that balances stealthiness (measured by perceptual similarity metrics such as PSNR) and attack success rate (ASR), enabling scalable, multi-target backdoor injection. Extensive experiments on ImageNet-1K with ResNet architectures demonstrate that our method achieves high ASR (up to 91.3%) under poisoning rates as low as 0.16%, while maintaining benign accuracy and evading state-of-the-art defenses. These results highlight the emerging risks of invisible universal backdoors and call for more robust detection and mitigation strategies. --- ### Reward-Modulated Local Learning in Spiking Encoders: Controlled Benchmarks with STDP and Hybrid Rate Readouts Authors: Debjyoti Chakraborty Published: 2026-02-28 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2603.00710v1 This paper presents a controlled empirical study of biologically motivated local learning for handwritten digit recognition. We evaluate an STDP-inspired competitive proxy and a practical hybrid benchmark built on the same spiking population encoder. The proxy is motivated by leaky integrate-and-fire E/I circuit models with three-factor delayed reward modulation. The hybrid update is local in pre x post rates but uses supervised labels and no timing-based credit assignment. On sklearn digits, fixed-seed evaluation shows classical pixel baselines from 98.06 to 98.22% accuracy, while local spike-based models reach 86.39 +/- 4.75% (hybrid default) and 87.17 +/- 3.74% (STDP-style competitive proxy). Ablations identify normalization and reward-shaping settings as the strongest observed levers, with a best hybrid ablation of 95.52 +/- 1.11%. A network-free synthetic temporal benchmark supports the same timing-versus-rate interpretation under matched local-update training. A descriptive 2x2 analysis further shows reward-shaping effects can reverse sign across stabilization regimes, so reward-shaping conclusions should be reported jointly with normalization settings. --- ### Towards Khmer Scene Document Layout Detection Authors: Marry Kong, Rina Buoy, Sovisal Chenda, Nguonly Taing, Masakazu Iwamura, Koichi Kise Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00707v1 While document layout analysis for Latin scripts has advanced significantly, driven by the advent of large multimodal models (LMMs), progress for the Khmer language remains constrained because of the scarcity of annotated training data. This gap is particularly acute for scene documents, where perspective distortions and complex backgrounds challenge traditional methods. Given the structural complexities of Khmer script, such as diacritics and multi-layer character stacking, existing Latin-based layout analysis models fail to accurately delineate semantic layout units, particularly for dense text regions (e.g., list items). In this paper, we present the first comprehensive study on Khmer scene document layout detection. We contribute a novel framework comprising three key elements: (1) a robust training and benchmarking dataset specifically for Khmer scene layouts; (2) an open-source document augmentation tool capable of synthesizing realistic scene documents to scale training data; and (3) layout detection baselines utilizing YOLO-based architectures with oriented bounding boxes (OBB) to handle geometric distortions. To foster further research in the Khmer document analysis and recognition (DAR) community, we release our models, code, and datasets in this gated repository (in review). --- ### Towards Universal Khmer Text Recognition Authors: Marry Kong, Rina Buoy, Sovisal Chenda, Nguonly Taing, Masakazu Iwamura, Koichi Kise Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00702v1 Khmer is a low-resource language characterized by a complex script, presenting significant challenges for optical character recognition (OCR). While document printed text recognition has advanced because of available datasets, performance on other modalities, such as handwritten and scene text, remains limited by data scarcity. Training modality-specific models for each modality does not allow cross-modality transfer learning, from which modalities with limited data could otherwise benefit. Moreover, deploying many modality-specific models results in significant memory overhead and requires error-prone routing each input image to the appropriate model. On the other hand, simply training on a combined dataset with a non-uniform data distribution across different modalities often leads to degraded performance on underrepresented modalities. To address these, we propose a universal Khmer text recognition (UKTR) framework capable of handling diverse text modalities. Central to our method is a novel modality-aware adaptive feature selection (MAFS) technique designed to adapt visual features according to a particular input image modality and enhance recognition robustness across modalities. Extensive experiments demonstrate that our model achieves state-of-the-art (SoTA) performance. Furthermore, we introduce the first comprehensive benchmark for universal Khmer text recognition, which we release to the community to facilitate future research. Our datasets and models can be accessible via this gated repository\footnote{in review}. --- ### TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction Authors: Yihui Li, Chengxin Lv, Zichen Tang, Hongyu Yang, Di Huang Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00697v1 We present TokenSplat, a feed-forward framework for joint 3D Gaussian reconstruction and camera pose estimation from unposed multi-view images. At its core, TokenSplat introduces a Token-aligned Gaussian Prediction module that aligns semantically corresponding information across views directly in the feature space. Guided by coarse token positions and fusion confidence, it aggregates multi-scale contextual features to enable long-range cross-view reasoning and reduce redundancy from overlapping Gaussians. To further enhance pose robustness and disentangle viewpoint cues from scene semantics, TokenSplat employs learnable camera tokens and an Asymmetric Dual-Flow Decoder (ADF-Decoder) that enforces directionally constrained communication between camera and image tokens. This maintains clean factorization within a feed-forward architecture, enabling coherent reconstruction and stable pose estimation without iterative refinement. Extensive experiments demonstrate that TokenSplat achieves higher reconstruction fidelity and novel-view synthesis quality in pose-free settings, and significantly improves pose estimation accuracy compared to prior pose-free methods. Project page: https://kidleyh.github.io/tokensplat/. --- ### DRIV-EX: Counterfactual Explanations for Driving LLMs Authors: Amaia Cardiel, Eloi Zablocki, Elias Ramzi, Eric Gaussier Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00696v2 Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque. We propose to study their decision process through counterfactual explanations, which identify the minimal semantic changes to a scene description required to alter a driving plan. We introduce DRIV-EX, a method that leverages gradient-based optimization on continuous embeddings to identify the input shifts required to flip the model's decision. Crucially, to avoid the incoherent text typical of unconstrained continuous optimization, DRIV-EX uses these optimized embeddings solely as a semantic guide: they are used to bias a controlled decoding process that re-generates the original scene description. This approach effectively steers the generation toward the counterfactual target while guaranteeing the linguistic fluency, domain validity, and proximity to the original input, essential for interpretability. Evaluated using the LC-LLM planner on a textual transcription of the highD dataset, DRIV-EX generates valid, fluent counterfactuals more reliably than existing baselines. It successfully exposes latent biases and provides concrete insights to improve the robustness of LLM-based driving agents. The code is available at "https://github.com/Amaia-CARDIEL/DRIV_EX" . --- ### STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification Authors: Xingguo Xu, Zhanyu Liu, Weixiang Zhou, Yuansheng Gao, Junjie Cao, Yuhao Wang, Jixiang Luo, Dell Zhang Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00695v1 Multi-modal object Re-Identification (ReID) aims to exploit complementary information from different modalities to retrieve specific objects. However, existing methods often rely on hard token filtering or simple fusion strategies, which can lead to the loss of discriminative cues and increased background interference. To address these challenges, we propose STMI, a novel multi-modal learning framework consisting of three key components: (1) Segmentation-Guided Feature Modulation (SFM) module leverages SAM-generated masks to enhance foreground representations and suppress background noise through learnable attention modulation; (2) Semantic Token Reallocation (STR) module employs learnable query tokens and an adaptive reallocation mechanism to extract compact and informative representations without discarding any tokens; (3) Cross-Modal Hypergraph Interaction (CHI) module constructs a unified hypergraph across modalities to capture high-order semantic relationships. Extensive experiments on public benchmarks (i.e., RGBNT201, RGBNT100, and MSVR310) demonstrate the effectiveness and robustness of our proposed STMI framework in multi-modal ReID scenarios. --- ### Wild-Drive: Off-Road Scene Captioning and Path Planning via Robust Multi-modal Routing and Efficient Large Language Model Authors: Zihang Wang, Xu Li, Benwu Wang, Wenkai Zhu, Xieyuanli Chen, Dong Kong, Kailin Lyu, Yinan Du, Yiming Peng, Haoyang Che Published: 2026-02-28 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.00694v1 Explainability and transparent decision-making are essential for the safe deployment of autonomous driving systems. Scene captioning summarizes environmental conditions and risk factors in natural language, improving transparency, safety, and human--robot interaction. However, most existing approaches target structured urban scenarios; in off-road environments, they are vulnerable to single-modality degradations caused by rain, fog, snow, and darkness, and they lack a unified framework that jointly models structured scene captioning and path planning. To bridge this gap, we propose Wild-Drive, an efficient framework for off-road scene captioning and path planning. Wild-Drive adopts modern multimodal encoders and introduces a task-conditioned modality-routing bridge, MoRo-Former, to adaptively aggregate reliable information under degraded sensing. It then integrates an efficient large language model (LLM), together with a planning token and a gate recurrent unit (GRU) decoder, to generate structured captions and predict future trajectories. We also build the OR-C2P Benchmark, which covers structured off-road scene captioning and path planning under diverse sensor corruption conditions. Experiments on OR-C2P dataset and a self-collected dataset show that Wild-Drive outperforms prior LLM-based methods and remains more stable under degraded sensing. The code and benchmark will be publicly available at https://github.com/wangzihanggg/Wild-Drive. --- ### AIoT-based Continuous, Contextualized, and Explainable Driving Assessment for Older Adults Authors: Yimeng Liu, Fangwei Zhang, Maolin Gan, Jialuo Du, Jingkai Lin, Yawen Wang, Fei Sun, Honglei Chen, Linda Hill, Ruofeng Liu, Tianxing Li, Zhichao Cao Published: 2026-02-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.00691v1 The world is undergoing a major demographic shift as older adults become a rapidly growing share of the population, creating new challenges for driving safety. In car-dependent regions such as the United States, driving remains essential for independence, access to services, and social participation. At the same time, aging can introduce gradual changes in vision, attention, reaction time, and driving control that quietly reduce safety. Today's assessment methods rely largely on infrequent clinic visits or simple screening tools, offering only a brief snapshot and failing to reflect how an older adult actually drives on the road. Our work starts from the observation that everyday driving provides a continuous record of functional ability and captures how a driver responds to traffic, navigates complex roads, and manages routine behavior. Leveraging this insight, we propose AURA, an Artificial Intelligence of Things (AIoT) framework for continuous, real-world assessment of driving safety among older adults. AURA integrates richer in-vehicle sensing, multi-scale behavioral modeling, and context-aware analysis to extract detailed indicators of driving performance from routine trips. It organizes fine-grained actions into longer behavioral trajectories and separates age-related performance changes from situational factors such as traffic, road design, or weather. By integrating sensing, modeling, and interpretation within a privacy-preserving edge architecture, AURA provides a foundation for proactive, individualized support that helps older adults drive safely. This paper outlines the design principles, challenges, and research opportunities needed to build reliable, real-world monitoring systems that promote safer aging behind the wheel. --- ### SCOUT: Fast Spectral CT Imaging in Ultra LOw-data Regimes via PseUdo-label GeneraTion Authors: Guoquan Wei, Liu Shi, Shaoyu Wang, Mohan Li, Cunfeng Wei, Qiegen Liu Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00687v1 Noise and artifacts during computed tomography (CT) scans are a fundamental challenge affecting disease diagnosis. However, current methods either involve excessively long reconstruction times or rely on data-driven models for optimization, failing to adequately consider the valuable information inherent in the data itself, especially medical 3D data. This work proposes a reconstruction method under ultra-low raw data conditions, requiring no external data and avoiding lengthy pre-training processes. By leveraging spatial nonlocal similarity and the conjugate properties of the projection domain to generate pseudo-3D data for self-supervised training, high-fidelity results can be achieved in a very short time. Extensive experiments demonstrate that this method not only mitigates detector-induced ring artifacts but also exhibits unprecedented capabilities in detail recovery. This method provides a new paradigm for research using unlabeled raw projection data. Code is available at https://github.com/yqx7150/SCOUT. --- ### RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis Authors: Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo, Bosi Wen, Yidong Wang, Lin Fan, Yilin Zhou, Zikang Wang, Wenbo Yu, Lindong Wu, Hongning Wang, Minlie Huang Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00686v1 Large Language Models have evolved from single-round generators into long-horizon agents, capable of complex text synthesis scenarios. However, current evaluation frameworks lack the ability to assess the actual synthesis operations, such as outlining, drafting, and editing. Consequently, they fail to evaluate the actual and detailed capabilities of LLMs. To bridge this gap, we introduce RAVEL, an agentic framework that enables the LLM testers to autonomously plan and execute typical synthesis operations, including outlining, drafting, reviewing, and refining. Complementing this framework, we present C3EBench, a comprehensive benchmark comprising 1,258 samples derived from professional human writings. We utilize a "reverse-engineering" pipeline to isolate specific capabilities across four tasks: Cloze, Edit, Expand, and End-to-End. Through our analysis of 14 LLMs, we uncover that most LLMs struggle with tasks that demand contextual understanding under limited or under-specified instructions. By augmenting RAVEL with SOTA LLMs as operators, we find that such agentic text synthesis is dominated by the LLM's reasoning capability rather than raw generative capacity. Furthermore, we find that a strong reasoner can guide a weaker generator to yield higher-quality results, whereas the inverse does not hold. Our code and data are available at this link: https://github.com/ZhuoerFeng/RAVEL-Reasoning-Agents-Text-Eval. --- ### Polynomial Mixing for Efficient Self-supervised Speech Encoders Authors: Eva Feillet, Ryan Whetten, David Picard, Alexandre Allauzen Published: 2026-02-28 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.00683v1 State-of-the-art speech-to-text models typically employ Transformer-based encoders that model token dependencies via self-attention mechanisms. However, the quadratic complexity of self-attention in both memory and computation imposes significant constraints on scalability. In this work, we propose a novel token-mixing mechanism, the Polynomial Mixer (PoM), as a drop-in replacement for multi-head self-attention. PoM computes a polynomial representation of the input with linear complexity with respect to the input sequence length. We integrate PoM into a self-supervised speech representation learning framework based on BEST-RQ and evaluate its performance on downstream speech recognition tasks. Experimental results demonstrate that PoM achieves a competitive word error rate compared to full self-attention and other linear-complexity alternatives, offering an improved trade-off between performance and efficiency in time and memory. --- ### CoLC: Communication-Efficient Collaborative Perception with LiDAR Completion Authors: Yushan Han, Hui Zhang, Qiming Xia, Yi Jin, Yidong Li Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00682v1 Collaborative perception empowers autonomous agents to share complementary information and overcome perception limitations. While early fusion offers more perceptual complementarity and is inherently robust to model heterogeneity, its high communication cost has limited its practical deployment, prompting most existing works to favor intermediate or late fusion. To address this, we propose a communication-efficient early Collaborative perception framework that incorporates LiDAR Completion to restore scene completeness under sparse transmission, dubbed as CoLC. Specifically, the CoLC integrates three complementary designs. First, each neighbor agent applies Foreground-Aware Point Sampling (FAPS) to selectively transmit informative points that retain essential structural and contextual cues under bandwidth constraints. The ego agent then employs Completion-Enhanced Early Fusion (CEEF) to reconstruct dense pillars from the received sparse inputs and adaptively fuse them with its own observations, thereby restoring spatial completeness. Finally, the Dense-Guided Dual Alignment (DGDA) strategy enforces semantic and geometric consistency between the enhanced and dense pillars during training, ensuring consistent and robust feature learning. Experiments on both simulated and real-world datasets demonstrate that CoLC achieves superior perception-communication trade-offs and remains robust under heterogeneous model settings. The code is available at https://github.com/CatOneTwo/CoLC. --- ### MemPO: Self-Memory Policy Optimization for Long-Horizon Agents Authors: Ruoran Li, Xinghua Zhang, Haiyang Yu, Shitong Duan, Xiang Li, Wenxin Xiang, Chonghua Liao, Xudong Guo, Yongbin Li, Jinli Suo Published: 2026-02-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.00680v4 Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introduce the external memory module and look up the relevant information from the stored memory, which prevents the model itself from proactively managing its memory content and aligning with the agent's overarching task objectives. To address these limitations, we propose the self-memory policy optimization algorithm (MemPO), which enables the agent (policy model) to autonomously summarize and manage their memory during interaction with environment. By improving the credit assignment mechanism based on memory effectiveness, the policy model can selectively retain crucial information, significantly reducing token consumption while preserving task performance. Extensive experiments and analyses confirm that MemPO achieves absolute F1 score gains of 25.98 over the base model and 7.1 over the previous SOTA baseline, while reducing token usage by 67.58% and 73.12%. The code is released at https://github.com/TheNewBeeKing/MemPO. --- ### K^2-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control Authors: Zhe Wu, Donglin Mo, Hongjin Lu, Junliang Xing, Jianheng Liu, Yuheng Jing, Kai Li, Kun Shao, Jianye Hao, Yuanchun Shi Published: 2026-02-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.00676v1 Existing mobile device control agents often perform poorly when solving complex tasks requiring long-horizon planning and precise operations, typically due to a lack of relevant task experience or unfamiliarity with skill execution. We propose K2-Agent, a hierarchical framework that models human-like cognition by separating and co-evolving declarative (knowing what) and procedural (knowing how) knowledge for planning and execution. K2-Agent's high level reasoner is bootstrapped from a single demonstration per task and runs a Summarize-Reflect-Locate-Revise (SRLR) loop to distill and iteratively refine task-level declarative knowledge through self-evolution. The low-level executor is trained with our curriculum-guided Group Relative Policy Optimization (C-GRPO), which (i) constructs a balanced sample pool using decoupled reward signals and (ii) employs dynamic demonstration injection to guide the model in autonomously generating successful trajectories for training. On the challenging AndroidWorld benchmark, K2-Agent achieves a 76.1% success rate using only raw screenshots and open-source backbones. Furthermore, K2-Agent shows powerful dual generalization: its high-level declarative knowledge transfers across diverse base models, while its low-level procedural skills achieve competitive performance on unseen tasks in ScreenSpot-v2 and Android-in-the-Wild (AitW). --- ### Specializing Foundation Models via Mixture of Low-Rank Experts for Comprehensive Head CT Analysis Authors: Youngjin Yoo, Han Liu, Bogdan Georgescu, Yanbo Zhang, Sasa Grbic, Michael Baumgartner, Thomas J. Re, Jyotipriya Das, Poikavila Ullaskrishnan, Eva Eibenberger, Andrei Chekkoury, Uttam K. Bodanapally et al. Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00675v1 Foundation models pre-trained on large-scale datasets demonstrate strong transfer learning capabilities; however, their adaptation to complex multi-label diagnostic tasks-such as comprehensive head CT finding detection-remains understudied. Standard parameter-efficient fine-tuning methods such as LoRA apply uniform adaptations across pathology types, which may limit performance for diverse medical findings. We propose a Mixture of Low-Rank Experts (MoLRE) framework that extends LoRA with multiple specialized low-rank adapters and unsupervised soft routing. This approach enables conditional feature adaptation with less than 0.5% additional parameters and without explicit pathology supervision. We present a comprehensive benchmark of MoLRE across six state-of-the-art medical imaging foundation models spanning 2D and 3D architectures, general-domain, medical-domain, and head CT-specific pretraining, and model sizes ranging from 7M to 431M parameters. Using over 70,000 non-contrast head CT scans with 75 annotated findings-including hemorrhage, infarction, trauma, mass lesions, structural abnormalities, and chronic changes-our experiments demonstrate consistent performance improvements across all models. Gains vary substantially: general-purpose and medical-domain models show the largest improvements (DINOv3-Base: +4.6%; MedGemma: +4.3%), whereas 3D CT-specialized or very large models show more modest gains (+0.2-1.3%). The combination of MoLRE and MedGemma achieves the highest average detection AUC of 0.917. These findings highlight the importance of systematic benchmarking on target clinical tasks, as pretraining domain, architecture, and model scale interact in non-obvious ways. ---