# Research Papers — 2025-11 · bundle page 12 of 197 > Full-text markdown of papers #551–600 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/12 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/11.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/13.md) ### Optimizing Multimodal Language Models through Attention-based Interpretability Authors: Alexander Sergeev, Evgeny Kotelnikov Published: 2025-11-28 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2511.23375v1 Modern large language models become multimodal, analyzing various data formats like text and images. While fine-tuning is effective for adapting these multimodal language models (MLMs) to downstream tasks, full fine-tuning is computationally expensive. Parameter-Efficient Fine-Tuning (PEFT) methods address this by training only a small portion of model weights. However, MLMs are difficult to interpret, making it challenging to identify which components are most effective for training to balance efficiency and performance. We propose an attention-based interpretability method for MLMs by analyzing attention scores relative to image tokens. The core idea is to identify attention heads that focus on image key objects. We utilize this information to select optimal model components for PEFT in multimodal models. Our contributions include a method for identifying attention heads associated with image key objects, its application to PEFT for image captioning, and the creation of a new dataset containing images, key object masks, and their textual descriptions. We conducted experiments on MLMs with 2-3 billion parameters to validate the method's effectiveness. By calculating Head Impact (HI) scores we quantify an attention head's focus on key objects, indicating its significance in image understanding. Our fine-tuning experiments demonstrate that adapting layers with the highest HI scores leads to the most significant shifts in metrics compared to pre-trained, randomly selected, or lowest-HI-score layers. This indicates that fine-tuning a small percentage (around 0.01%) of parameters in these crucial layers can substantially influence image understanding capabilities. --- ### Scaling HuBERT for African Languages: From Base to Large and XL Authors: Antoine Caubrière, Elodie Gauthier Published: 2025-11-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.23370v1 Despite recent progress in multilingual speech processing, African languages remain under-represented in both research and deployed systems, particularly when it comes to strong, open-weight encoders that transfer well under low-resource supervision. Self-supervised learning has proven especially promising in such settings, yet most publicly released models targeting African speech remain at BASE scale, leaving unanswered whether larger encoders, trained exclusively on Africa-centric audio, offer tangible benefits and how model capacity interacts with data composition. This work addresses that gap by introducing SSA-HuBERT-Large (317M parameters) and SSA-HuBERT-XL (964M parameters), the first large models trained solely on African speech, alongside a BASE size counterpart. We release these models as open weights: see https://huggingface.co/collections/Orange/african-speech-foundation-models. By conducting a carefully controlled experimental study focused exclusively on Sub-Saharan languages, covering automatic speech recognition (ASR) and language identification (LID) tasks, we demonstrate that larger architectures significantly improve performance by effectively leveraging large audio datasets. --- ### SimScale: Learning to Drive via Real-World Simulation at Scale Authors: Haochen Tian, Tianyu Li, Haochen Liu, Jiazhi Yang, Yihang Qiu, Guang Li, Junli Wang, Yinfeng Gao, Zhang Zhang, Liang Wang, Hangjun Ye, Tieniu Tan et al. Published: 2025-11-28 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.23369v3 Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such cases are underrepresented in real-world corpus collected by human experts. To complement for the lack of data diversity, we introduce a novel and scalable simulation framework capable of synthesizing massive unseen states upon existing driving logs. Our pipeline utilizes advanced neural rendering with a reactive environment to generate high-fidelity multi-view observations controlled by the perturbed ego trajectory. Furthermore, we develop a pseudo-expert trajectory generation mechanism for these newly simulated states to provide action supervision. Upon the synthesized data, we find that a simple co-training strategy on both real-world and simulated samples can lead to significant improvements in both robustness and generalization for various planning methods on challenging real-world benchmarks, up to +8.6 EPDMS on navhard and +2.9 on navtest. More importantly, such policy improvement scales smoothly by increasing simulation data only, even without extra real-world data streaming in. We further reveal several crucial findings of such a sim-real learning system, which we term SimScale, including the design of pseudo-experts and the scaling properties for different policy architectures. Simulation data and code have been released at https://github.com/OpenDriveLab/SimScale. --- ### Agentic AI Framework for Smart Inventory Replenishment Authors: Toqeer Ali Syed, Salman Jan, Gohar Ali, Ali Akarma, Ahmad Ali, Qurat-ul-Ain Mastoi Published: 2025-11-28 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.23366v1 In contemporary retail, the variety of products available (e.g. clothing, groceries, cosmetics, frozen goods) make it difficult to predict the demand, prevent stockouts, and find high-potential products. We suggest an agentic AI model that will be used to monitor the inventory, initiate purchase attempts to the appropriate suppliers, and scan for trending or high-margin products to incorporate. The system applies demand forecasting, supplier selection optimization, multi-agent negotiation and continuous learning. We apply a prototype to a setting in the store of a middle scale mart, test its performance on three conventional and artificial data tables, and compare the results to the base heuristics. Our findings indicate that there is a decrease in stockouts, a reduction of inventory holding costs, and an improvement in product mix turnover. We address constraints, scalability as well as improvement prospect. --- ### A Hierarchical Computer Vision Pipeline for Physiological Data Extraction from Bedside Monitors Authors: Vinh Chau, Khoa Le Dinh Van, Hon Huynh Ngoc, Binh Nguyen Thien, Hao Nguyen Thien, Vy Nguyen Quang, Phuc Vo Hong, Yen Lam Minh, Kieu Pham Tieu, Trinh Nguyen Thi Diem, Louise Thwaites, Hai Ho Bich Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23355v1 In many low-resource healthcare settings, bedside monitors remain standalone legacy devices without network connectivity, creating a persistent interoperability gap that prevents seamless integration of physiological data into electronic health record (EHR) systems. To address this challenge without requiring costly hardware replacement, we present a computer vision-based pipeline for the automated capture and digitisation of vital sign data directly from bedside monitor screens. Our method employs a hierarchical detection framework combining YOLOv11 for accurate monitor and region of interest (ROI) localisation with PaddleOCR for robust text extraction. To enhance reliability across variable camera angles and lighting conditions, a geometric rectification module standardizes the screen perspective before character recognition. We evaluated the system on a dataset of 6,498 images collected from open-source corpora and real-world intensive care units in Vietnam. The model achieved a mean Average Precision (mAP@50-95) of 99.5% for monitor detection and 91.5% for vital sign ROI localisation. The end-to-end extraction accuracy exceeded 98.9% for core physiological parameters, including heart rate, oxygen saturation SpO2, and arterial blood pressure. These results demonstrate that a lightweight, camera-based approach can reliably transform unstructured information from screen captures into structured digital data, providing a practical and scalable pathway to improve information accessibility and clinical documentation in low-resource settings. --- ### Functional Program Synthesis with Higher-Order Functions and Recursion Schemes Authors: Matheus Campos Fernandes Published: 2025-11-28 Categories: cs.NE arXiv: https://arxiv.org/abs/2511.23354v1 Program synthesis is the process of generating a computer program following a set of specifications, such as a set of input-output examples. It can be modeled as a search problem in which the search space is the set of all valid programs. As the search space is vast, brute force is usually not feasible, and search heuristics, such as genetic programming, also have difficulty navigating it without guidance. This text presents 2 novel GP algorithms that synthesize pure, typed, and functional programs: HOTGP and Origami. HOTGP uses strong types and a functional grammar, synthesizing Haskell code, with support for higher-order functions, $λ$-functions, and parametric polymorphism. Experimental results show that HOTGP is competitive with the state of the art. Additionally, Origami is an algorithm that tackles the challenge of effectively handling loops and recursion by exploring Recursion Schemes, in which the programs are composed of well-defined templates with only a few parts that need to be synthesized. The first implementation of Origami can synthesize solutions in several Recursion Schemes and data structures, being competitive with other GP methods in the literature, as well as LLMs. The latest version of Origami employs a novel procedure, called AC/DC, designed to improve the search-space exploration. It achieves considerable improvement over its previous version by raising success rates on every problem. Compared to similar methods in the literature, it has the highest count of problems solved with success rates of $100\%$, $\geq 75\%$, and $\geq 25\%$ across all benchmarks. In $18\%$ of all benchmark problems, it stands as the only method to reach $100\%$ success rate, being the first known approach to achieve it on any problem in PSB2. It also demonstrates competitive performance to LLMs, achieving the highest overall win-rate against Copilot among all GP methods. --- ### Distributed Dynamic Associative Memory via Online Convex Optimization Authors: Bowen Wang, Matteo Zecchin, Osvaldo Simeone Published: 2025-11-28 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2511.23347v2 An associative memory (AM) enables cue-response recall, and it has recently been recognized as a key mechanism underlying modern neural architectures such as Transformers. In this work, we introduce the concept of distributed dynamic associative memory (DDAM), which extends classical AM to settings with multiple agents and time-varying data streams. In DDAM, each agent maintains a local AM that must not only store its own associations but also selectively memorize information from other agents based on a specified interest matrix. To address this problem, we propose a novel tree-based distributed online gradient descent algorithm, termed DDAM-TOGD, which enables each agent to update its memory on the fly via inter-agent communication over designated routing trees. We derive rigorous performance guarantees for DDAM-TOGD, proving sublinear static regret in stationary environments and a path-length dependent dynamic regret bound in non-stationary environments. These theoretical results provide insights into how communication delays and network structure impact performance. Building on the regret analysis, we further introduce a combinatorial tree design strategy that optimizes the routing trees to minimize communication delays, thereby improving regret bounds. Numerical experiments demonstrate that the proposed DDAM-TOGD framework achieves superior accuracy and robustness compared to representative online learning baselines such as consensus-based distributed optimization, confirming the benefits of the proposed approach in dynamic, distributed environments. --- ### Overcoming the Curvature Bottleneck in MeanFlow Authors: Xinxi Zhang, Shiwei Tan, Quang Nguyen, Quan Dao, Ligong Han, Xiaoxiao He, Tunyu Zhang, Chengzhi Mao, Dimitris Metaxas, Vladimir Pavlovic Published: 2025-11-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.23342v3 MeanFlow offers a promising framework for one-step generative modeling by directly learning a mean-velocity field, bypassing expensive numerical integration. However, we find that the highly curved generative trajectories of existing models induce a noisy loss landscape, severely bottlenecking convergence and model quality. We leverage a fundamental geometric principle to overcome this: mean-velocity estimation is drastically simpler along straight paths. Building on this insight, we propose Rectified MeanFlow, a self-distillation approach that learns the mean-velocity field over a straightened velocity field, induced by rectified couplings from a pretrained model. To further promote linearity, we introduce a distance-based truncation heuristic that prunes residual high-curvature pairs. By smoothing the optimization landscape, our method achieves strong one-step generation performance. We improve the FID of baseline MeanFlow models from 30.9 to 8.6 under same training budget, and outperform the recent 2-rectified flow++ by 33.4% in FID while running 26x faster. Our work suggests that the difficulty of one-step flow generation stems partially from the rugged optimization landscapes induced by curved trajectories. Code is available at https://github.com/Xinxi-Zhang/Re-MeanFlow. --- ### ParaGate: Parasitic-Driven Domain Adaptation Transfer Learning for Netlist Performance Prediction Authors: Bin Sun, Jingyi Zhou, Jianan Mu, Zhiteng Chao, Tianmeng Yang, Ziyue Xu, Jing Ye, Huawei Li Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.23340v1 In traditional EDA flows, layout-level performance metrics are only obtainable after placement and routing, hindering global optimization at earlier stages. Although some neural-network-based solutions predict layout-level performance directly from netlists, they often face generalization challenges due to the black-box heuristics of commercial placement-and-routing tools, which create disparate data across designs. To this end, we propose ParaGate, a three-step cross-stage prediction framework that infers layout-level timing and power from netlists. First, we propose a two-phase transfer-learning approach to predict parasitic parameters, pre-training on mid-scale circuits and fine-tuning on larger ones to capture extreme conditions. Next, we rely on EDA tools for timing analysis, offloading the long-path numerical reasoning. Finally, ParaGate performs global calibration using subgraph features. Experiments show that ParaGate achieves strong generalization with minimal fine-tuning data: on openE906, its arrival-time R2 from 0.119 to 0.897. These results demonstrate that ParaGate could provide guidance for global optimization in the synthesis and placement stages. --- ### Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach Authors: Shuqi Liu, Han Wu, Guanzhi Deng, Jianshu Chen, Xiaoyang Wang, Linqi Song Published: 2025-11-28 Categories: cs.CL, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2511.23335v1 Knowledge-enhanced text generation aims to enhance the quality of generated text by utilizing internal or external knowledge sources. While language models have demonstrated impressive capabilities in generating coherent and fluent text, the lack of interpretability presents a substantial obstacle. The limited interpretability of generated text significantly impacts its practical usability, particularly in knowledge-enhanced text generation tasks that necessitate reliability and explainability. Existing methods often employ domain-specific knowledge retrievers that are tailored to specific data characteristics, limiting their generalizability to diverse data types and tasks. To overcome this limitation, we directly leverage the two-tier architecture of structured knowledge, consisting of high-level entities and low-level knowledge triples, to design our task-agnostic structured knowledge hunter. Specifically, we employ a local-global interaction scheme for structured knowledge representation learning and a hierarchical transformer-based pointer network as the backbone for selecting relevant knowledge triples and entities. By combining the strong generative ability of language models with the high faithfulness of the knowledge hunter, our model achieves high interpretability, enabling users to comprehend the model output generation process. Furthermore, we empirically demonstrate the effectiveness of our model in both internal knowledge-enhanced table-to-text generation on the RotoWireFG dataset and external knowledge-enhanced dialogue response generation on the KdConv dataset. Our task-agnostic model outperforms state-of-the-art methods and corresponding language models, setting new standards on the benchmark. --- ### Markovian Scale Prediction: A New Era of Visual Autoregressive Generation Authors: Yu Zhang, Jingyi Liu, Yiwei Shi, Qi Zhang, Duoqian Miao, Changwei Wang, Longbing Cao Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23334v3 Visual AutoRegressive modeling (VAR) based on next-scale prediction has revitalized autoregressive visual generation. Although its full-context dependency, i.e., modeling all previous scales for next-scale prediction, facilitates more stable and comprehensive representation learning by leveraging complete information flow, the resulting computational inefficiency and substantial overhead severely hinder VAR's practicality and scalability. This motivates us to develop a new VAR model with better performance and efficiency without full-context dependency. To address this, we reformulate VAR as a non-full-context Markov process, proposing Markov-VAR. It is achieved via Markovian Scale Prediction: we treat each scale as a Markov state and introduce a sliding window that compresses certain previous scales into a compact history vector to compensate for historical information loss owing to non-full-context dependency. Integrating the history vector with the Markov state yields a representative dynamic state that evolves under a Markov process. Extensive experiments demonstrate that Markov-VAR is extremely simple yet highly effective: Compared to VAR on ImageNet, Markov-VAR reduces FID by 10.5% (256 $\times$ 256) and decreases peak memory consumption by 83.8% (1024 $\times$ 1024). We believe that Markov-VAR can serve as a foundation for future research on visual autoregressive generation and other downstream tasks. --- ### UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes Authors: Shuo Ni, Di Wang, He Chen, Haonan Guo, Ning Zhang, Jing Zhang Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23332v3 Instruction-driven segmentation in remote sensing generates masks from guidance, offering great potential for accessible and generalizable applications. However, existing methods suffer from fragmented task formulations and limited instruction data, hindering effective understanding and generalization. To address these issues, we introduce GeoSeg-1M, the first million-scale dataset for remote sensing instruction-driven segmentation, constructed via an automatic mask filtering and instruction generation pipeline that synthesizes referring, interactive, and reasoning segmentation instructions from multiple public datasets. GeoSeg-1M contains 590K images, 117 categories, and 1.1M image-mask-instruction triplets. Building upon this foundation, we further curate GeoSeg-Bench, a challenging benchmark designed to evaluate contextual understanding and reasoning capabilities across diverse instruction-driven tasks and complex geospatial scenes. Furthermore, we present UniGeoSeg, a unified framework that serves as a strong baseline, incorporating task-aware text enhancement, latent knowledge memory, and a progressive training strategy to facilitate multi-task learning. Extensive experiments demonstrate the state-of-the-art performance of UniGeoSeg across GeoSeg-Bench and diverse public benchmarks, while exhibiting strong zero-shot generalization. Datasets and source code were released at https://github.com/MiliLab/UniGeoSeg. --- ### A Perceptually Inspired Variational Framework for Color Enhancement Authors: Rodrigo Palma-Amestoy, Edoardo Provenzi, Marcelo Bertalmío, Vicent Caselles Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23329v1 Basic phenomenology of human color vision has been widely taken as an inspiration to devise explicit color correction algorithms. The behavior of these models in terms of significative image features (such as contrast and dispersion) can be difficult to characterize. To cope with this, we propose to use a variational formulation of color contrast enhancement that is inspired by the basic phenomenology of color perception. In particular, we devise a set of basic requirements to be fulfilled by an energy to be considered as `perceptually inspired', showing that there is an explicit class of functionals satisfying all of them. We single out three explicit functionals that we consider of basic interest, showing similarities and differences with existing models. The minima of such functionals is computed using a gradient descent approach. We also present a general methodology to reduce the computational cost of the algorithms under analysis from ${\cal O}(N^2)$ to ${\cal O}(N\log N)$, being $N$ the number of input pixels. --- ### Tackling a Challenging Corpus for Early Detection of Gambling Disorder: UNSL at MentalRiskES 2025 Authors: Horacio Thompson, Marcelo Errecalde Published: 2025-11-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.23325v1 Gambling disorder is a complex behavioral addiction that is challenging to understand and address, with severe physical, psychological, and social consequences. Early Risk Detection (ERD) on the Web has become a key task in the scientific community for identifying early signs of mental health behaviors based on social media activity. This work presents our participation in the MentalRiskES 2025 challenge, specifically in Task 1, aimed at classifying users at high or low risk of developing a gambling-related disorder. We proposed three methods based on a CPI+DMC approach, addressing predictive effectiveness and decision-making speed as independent objectives. The components were implemented using the SS3, BERT with extended vocabulary, and SBERT models, followed by decision policies based on historical user analysis. Although it was a challenging corpus, two of our proposals achieved the top two positions in the official results, performing notably in decision metrics. Further analysis revealed some difficulty in distinguishing between users at high and low risk, reinforcing the need to explore strategies to improve data interpretation and quality, and to promote more transparent and reliable ERD systems for mental disorders. --- ### Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models Authors: Xiang Hu, Zhanchao Zhou, Ruiqi Liang, Zehuan Li, Wei Wu, Jianguo Li Published: 2025-11-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.23319v1 This work explores the challenge of building ``Machines that Can Remember'', framing long-term memory as the problem of efficient ultra-long context modeling. We argue that this requires three key properties: \textbf{sparsity}, \textbf{random-access flexibility}, and \textbf{length generalization}. To address ultra-long-context modeling, we leverage Hierarchical Sparse Attention (HSA), a novel attention mechanism that satisfies all three properties. We integrate HSA into Transformers to build HSA-UltraLong, which is an 8B-parameter MoE model trained on over 8 trillion tokens and is rigorously evaluated on different tasks with in-domain and out-of-domain context lengths to demonstrate its capability in handling ultra-long contexts. Results show that our model performs comparably to full-attention baselines on in-domain lengths while achieving over 90\% accuracy on most in-context retrieval tasks with contexts up to 16M. This report outlines our experimental insights and open problems, contributing a foundation for future research in ultra-long context modeling. --- ### Emergent Coordination and Phase Structure in Independent Multi-Agent Reinforcement Learning Authors: Azusa Yamaguchi Published: 2025-11-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.23315v1 A clearer understanding of when coordination emerges, fluctuates, or collapses in decentralized multi-agent reinforcement learning (MARL) is increasingly sought in order to characterize the dynamics of multi-agent learning systems. We revisit fully independent Q-learning (IQL) as a minimal decentralized testbed and run large-scale experiments across environment size L and agent density rho. We construct a phase map using two axes - the cooperative success rate (CSR) and a stability index derived from TD-error variance - revealing three distinct regimes: a coordinated and stable phase, a fragile transition region, and a jammed or disordered phase. A sharp double Instability Ridge separates these regimes and corresponds to persistent kernel drift, the time-varying shift of each agent's effective transition kernel induced by others' policy updates. Synchronization analysis further shows that temporal alignment is required for sustained cooperation, and that competition between drift and synchronization generates the fragile regime. Removing agent identifiers eliminates drift entirely and collapses the three-phase structure, demonstrating that small inter-agent asymmetries are a necessary driver of drift. Overall, the results show that decentralized MARL exhibits a coherent phase structure governed by the interaction between scale, density, and kernel drift, suggesting that emergent coordination behaves as a distribution-interaction-driven phase phenomenon. --- ### Toward Automatic Safe Driving Instruction: A Large-Scale Vision Language Model Approach Authors: Haruki Sakajo, Hiroshi Takato, Hiroshi Tsutsui, Komei Soda, Hidetaka Kamigaito, Taro Watanabe Published: 2025-11-28 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.23311v1 Large-scale Vision Language Models (LVLMs) exhibit advanced capabilities in tasks that require visual information, including object detection. These capabilities have promising applications in various industrial domains, such as autonomous driving. For example, LVLMs can generate safety-oriented descriptions of videos captured by road-facing cameras. However, ensuring comprehensive safety requires monitoring driver-facing views as well to detect risky events, such as the use of mobiles while driving. Thus, the ability to process synchronized inputs is necessary from both driver-facing and road-facing cameras. In this study, we develop models and investigate the capabilities of LVLMs by constructing a dataset and evaluating their performance on this dataset. Our experimental results demonstrate that while pre-trained LVLMs have limited effectiveness, fine-tuned LVLMs can generate accurate and safety-aware driving instructions. Nonetheless, several challenges remain, particularly in detecting subtle or complex events in the video. Our findings and error analysis provide valuable insights that can contribute to the improvement of LVLM-based systems in this domain. --- ### Variance-Aware Baselines and Adaptive Learning Rates for Reinforcement Learning with Verifiable Rewards Authors: Zixun Huang, Jiayi Sheng, Zeyu Zheng Published: 2025-11-28 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.23310v4 Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective paradigm for post-training large language models, yet the design of its baselines and learning-rate schedules remains largely heuristic. This limits our understanding of the statistical properties of policy-gradient estimators and their interaction with optimization dynamics. In this work, we develop a theoretical framework for variance-aware baseline design and adaptive learning-rate selection in RLVR. Under a KL-regularized policy-optimization setting, we establish the unbiasedness of the resulting gradient estimator, derive exact variance expressions including the KL cross-covariance, and obtain an optimization-loss upper bound that enables principled reasoning about learning dynamics. Building on these results, we prove convergence guarantees and derive an adaptive learning-rate schedule governed by the signal-to-noise ratio (SNR) of the policy gradient. We further show that the variance-optimal baseline is a gradient-weighted estimator of the KL-regularized reward, providing a principled alternative to commonly used reward-based baselines. These results lead to two complementary improvements: a variance-optimal baseline and an SNR-adaptive learning-rate rule. Experiments on Qwen3-4B-Base show that each component independently improves policy-optimization performance. The learning-rate rule can also be naturally integrated with existing policy optimization methods to yield further gains, while combining it with the variance-optimal baseline gives the full Optimal Baseline and Learning-Rate Policy Optimization (OBLR-PO) method and achieves the strongest overall performance. --- ### Hard-Constrained Neural Networks with Physics-Embedded Architecture for Residual Dynamics Learning and Invariant Enforcement in Cyber-Physical Systems Authors: Enzo Nicolás Spotorno, Josafat Leal Filho, Antônio Augusto Fröhlich Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.23307v1 This paper presents a framework for physics-informed learning in complex cyber-physical systems governed by differential equations with both unknown dynamics and algebraic invariants. First, we formalize the Hybrid Recurrent Physics-Informed Neural Network (HRPINN), a general-purpose architecture that embeds known physics as a hard structural constraint within a recurrent integrator to learn only residual dynamics. Second, we introduce the Projected HRPINN (PHRPINN), a novel extension that integrates a predict-project mechanism to strictly enforce algebraic invariants by design. The framework is supported by a theoretical analysis of its representational capacity. We validate HRPINN on a real-world battery prognostics DAE and evaluate PHRPINN on a suite of standard constrained benchmarks. The results demonstrate the framework's potential for achieving high accuracy and data efficiency, while also highlighting critical trade-offs between physical consistency, computational cost, and numerical stability, providing practical guidance for its deployment. --- ### Multi-Modal Scene Graph with Kolmogorov-Arnold Experts for Audio-Visual Question Answering Authors: Zijian Fu, Changsheng Lv, Xianlin Zhang, Mengshi Qi, Huadong Ma Published: 2025-11-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.23304v3 In this paper, we propose a novel Multi-Modal Scene Graph with Kolmogorov-Arnold Expert Network for Audio-Visual Question Answering (SHRIKE). The task aims to mimic human reasoning by extracting and fusing information from audio-visual scenes, with the main challenge being the identification of question-relevant cues from complex audio-visual content. Existing methods fail to capture the structural information within videos and suffer from insufficient fine-grained modeling of multi-modal features. To address these issues, we are the first to introduce a new multi-modal scene graph that explicitly models objects and their relationships as a visually grounded, structured representation of the audio-visual scene, yielding 461,292 relation triplets over 9,288 musical performance videos. Furthermore, we design a Kolmogorov-Arnold Network (KAN)-based Mixture of Experts (MoE) to enhance the expressive power of the temporal integration stage. This enables more fine-grained modeling of cross-modal interactions within the question-aware fused audio-visual representation, capturing richer and more nuanced patterns and improving temporal reasoning performance. We evaluate the model on the established MUSIC-AVQA and MUSIC-AVQA v2 benchmarks, where it achieves state-of-the-art performance, reaching 78.14% average accuracy on MUSIC-AVQA, surpassing the previous best method QA-TIGER and ranking first under all four configurations of MUSIC-AVQA v2.0. Code and model checkpoints will be publicly released at https://github.com/feel12348/SHRIKE. --- ### FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting Authors: Tianhao Xie, Linlian Jiang, Xinxin Zuo, Yang Wang, Tiberiu Popa Published: 2025-11-28 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2511.23292v3 Realistic scene appearance modeling has advanced rapidly with Gaussian Splatting, which enables real-time, high-quality rendering. Recent advances introduced per-primitive textures that incorporate spatial color variations within each Gaussian, improving their expressiveness. However, texture-based Gaussians parameterize appearance with a uniform per-Gaussian sampling grid, allocating equal sampling density regardless of local visual complexity, which leads to inefficient texture space utilization. We introduce FACT-GS, a Frequency-Aligned Complexity-aware Texture Gaussian Splatting framework that allocates texture sampling density according to local visual frequency. Grounded in adaptive sampling theory, FACT-GS reformulates texture parameterization as a differentiable sampling-density allocation problem, replacing the uniform textures with a learnable frequency-aware allocation strategy implemented via a deformation field whose Jacobian modulates local sampling density. Built on 2D Gaussian Splatting, FACT-GS performs non-uniform sampling on fixed-resolution texture grids, preserving real-time performance while recovering sharper high-frequency details under the same parameter budget. --- ### Machine Learning for Scientific Visualization: Ensemble Data Analysis Authors: Hamid Gadirov Published: 2025-11-28 Categories: cs.LG, cs.AI, cs.CV, cs.GR arXiv: https://arxiv.org/abs/2511.23290v1 Scientific simulations and experimental measurements produce vast amounts of spatio-temporal data, yet extracting meaningful insights remains challenging due to high dimensionality, complex structures, and missing information. Traditional analysis methods often struggle with these issues, motivating the need for more robust, data-driven approaches. This dissertation explores deep learning methodologies to improve the analysis and visualization of spatio-temporal scientific ensembles, focusing on dimensionality reduction, flow estimation, and temporal interpolation. First, we address high-dimensional data representation through autoencoder-based dimensionality reduction for scientific ensembles. We evaluate the stability of projection metrics under partial labeling and introduce a Pareto-efficient selection strategy to identify optimal autoencoder variants, ensuring expressive and reliable low-dimensional embeddings. Next, we present FLINT, a deep learning model for high-quality flow estimation and temporal interpolation in both flow-supervised and flow-unsupervised settings. FLINT reconstructs missing velocity fields and generates high-fidelity temporal interpolants for scalar fields across 2D+time and 3D+time ensembles without domain-specific assumptions or extensive finetuning. To further improve adaptability and generalization, we introduce HyperFLINT, a hypernetwork-based approach that conditions on simulation parameters to estimate flow fields and interpolate scalar data. This parameter-aware adaptation yields more accurate reconstructions across diverse scientific domains, even with sparse or incomplete data. Overall, this dissertation advances deep learning techniques for scientific visualization, providing scalable, adaptable, and high-quality solutions for interpreting complex spatio-temporal ensembles. --- ### Transformer-Driven Triple Fusion Framework for Enhanced Multimodal Author Intent Classification in Low-Resource Bangla Authors: Ariful Islam, Tanvir Mahmud, Md Rifat Hossen Published: 2025-11-28 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2511.23287v1 The expansion of the Internet and social networks has led to an explosion of user-generated content. Author intent understanding plays a crucial role in interpreting social media content. This paper addresses author intent classification in Bangla social media posts by leveraging both textual and visual data. Recognizing limitations in previous unimodal approaches, we systematically benchmark transformer-based language models (mBERT, DistilBERT, XLM-RoBERTa) and vision architectures (ViT, Swin, SwiftFormer, ResNet, DenseNet, MobileNet), utilizing the Uddessho dataset of 3,048 posts spanning six practical intent categories. We introduce a novel intermediate fusion strategy that significantly outperforms early and late fusion on this task. Experimental results show that intermediate fusion, particularly with mBERT and Swin Transformer, achieves 84.11% macro-F1 score, establishing a new state-of-the-art with an 8.4 percentage-point improvement over prior Bangla multimodal approaches. Our analysis demonstrates that integrating visual context substantially enhances intent classification. Cross-modal feature integration at intermediate levels provides optimal balance between modality-specific representation and cross-modal learning. This research establishes new benchmarks and methodological standards for Bangla and other low-resource languages. We call our proposed framework BangACMM (Bangla Author Content MultiModal). --- ### Closing the Generalization Gap in Parameter-efficient Federated Edge Learning Authors: Xinnong Du, Zhonghao Lyu, Xiaowen Cao, Chunyang Wen, Shuguang Cui, Jie Xu Published: 2025-11-28 Categories: cs.LG, cs.DC, cs.IT arXiv: https://arxiv.org/abs/2511.23282v1 Federated edge learning (FEEL) provides a promising foundation for edge artificial intelligence (AI) by enabling collaborative model training while preserving data privacy. However, limited and heterogeneous local datasets, as well as resource-constrained deployment, severely degrade both model generalization and resource utilization, leading to a compromised learning performance. Therefore, we propose a parameter-efficient FEEL framework that jointly leverages model pruning and client selection to tackle such challenges. First, we derive an information-theoretic generalization statement that characterizes the discrepancy between training and testing function losses and embed it into the convergence analysis. It reveals that a larger local generalization statement can undermine the global convergence. Then, we formulate a generalization-aware average squared gradient norm bound minimization problem, by jointly optimizing the pruning ratios, client selection, and communication-computation resources under energy and delay constraints. Despite its non-convexity, the resulting mixed-integer problem is efficiently solved via an alternating optimization algorithm. Extensive experiments demonstrate that the proposed design achieves superior learning performance than state-of-the-art baselines, validating the effectiveness of coupling generalization-aware analysis with system-level optimization for efficient FEEL. --- ### MCP vs RAG vs NLWeb vs HTML: A Comparison of the Effectiveness and Efficiency of Different Agent Interfaces to the Web (Technical Report) Authors: Aaron Steiner, Ralph Peeters, Christian Bizer Published: 2025-11-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.23281v1 Large language model agents are increasingly used to automate web tasks such as product search, offer comparison, and checkout. Current research explores different interfaces through which these agents interact with websites, including traditional HTML browsing, retrieval-augmented generation (RAG) over pre-crawled content, communication via Web APIs using the Model Context Protocol (MCP), and natural-language querying through the NLWeb interface. However, no prior work has compared these four architectures within a single controlled environment using identical tasks. To address this gap, we introduce a testbed consisting of four simulated e-shops, each offering its products via HTML, MCP, and NLWeb interfaces. For each interface (HTML, RAG, MCP, and NLWeb) we develop specialized agents that perform the same sets of tasks, ranging from simple product searches and price comparisons to complex queries for complementary or substitute products and checkout processes. We evaluate the agents using GPT 4.1, GPT 5, GPT 5 mini, and Claude Sonnet 4 as underlying LLM. Our evaluation shows that the RAG, MCP and NLWeb agents outperform HTML on both effectiveness and efficiency. Averaged over all tasks, F1 rises from 0.67 for HTML to between 0.75 and 0.77 for the other agents. Token usage falls from about 241k for HTML to between 47k and 140k per task. The runtime per task drops from 291 seconds to between 50 and 62 seconds. The best overall configuration is RAG with GPT 5 achieving an F1 score of 0.87 and a completion rate of 0.79. Also taking cost into consideration, RAG with GPT 5 mini offers a good compromise between API usage fees and performance. Our experiments show the choice of the interaction interface has a substantial impact on both the effectiveness and efficiency of LLM-based web agents. --- ### Auditable Context-Aware HFMD Forecasting with Structured LLM Agents Authors: Joongwon Chae, Runming Wang, Chen Xiong, Gong Yunhan, Lian Zhang, Ji Jiansong, Dongmei Yu, Peiwu Qin Published: 2025-11-28 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2511.23276v2 Effective HFMD surveillance requires forecasts capturing both time-series patterns and contextual drivers such as school calendars, weather, and policy or surveillance reports. In clinical settings, forecasts must be trusted and actionable; thus, beyond point accuracy, decision-makers require concise, auditable explanations of why risk is expected to rise or fall. Classical models (e.g., ARIMA and Prophet) and foundation models (e.g., Chronos, Moirai, and TimesFM) treat external covariates as numerical inputs, lacking semantic reasoning to reflect epidemiological mechanisms or resolve conflicting signals. We propose a two-agent neuro-symbolic framework that decouples contextual interpretation from probabilistic forecasting. An LLM-based Event Interpreter ingests heterogeneous signals -- school schedules, weather summaries, government reports, and clinical guidelines -- and outputs a scalar transmission-impact signal. A Forecast Generator combines this signal with historical case counts to produce point forecasts that are mapped to probabilistic predictions through Poisson/negative-binomial moment matching. We focus on one-week-ahead rolling forecasts, aligning with weekly hospital-capacity planning and the rapid, context-driven inflections typical of HFMD. We evaluate on two datasets: Hong Kong surveillance (90 target weeks in 2023--2024) and Lishui hospital visits (33 target weeks in 2024). Against traditional and foundation-model baselines, our approach achieves competitive point accuracy while providing robust 90\% intervals (coverage approximately 0.85--1.00) and concise rationales. This demonstrates that integrating domain knowledge through LLM-based agents can match strong numerical forecasters while yielding interpretable, context-aware forecasts aligned with public-health decision-making. --- ### Simultaneous Image Quality Improvement and Artefacts Correction in Accelerated MRI Authors: Georgia Kanli, Daniele Perlo, Selma Boudissa, Radovan Jirik, Olivier Keunen Published: 2025-11-28 Categories: cs.CV, cs.AI, physics.med-ph arXiv: https://arxiv.org/abs/2511.23274v1 MR data are acquired in the frequency domain, known as k-space. Acquiring high-quality and high-resolution MR images can be time-consuming, posing a significant challenge when multiple sequences providing complementary contrast information are needed or when the patient is unable to remain in the scanner for an extended period of time. Reducing k-space measurements is a strategy to speed up acquisition, but often leads to reduced quality in reconstructed images. Additionally, in real-world MRI, both under-sampled and full-sampled images are prone to artefacts, and correcting these artefacts is crucial for maintaining diagnostic accuracy. Deep learning methods have been proposed to restore image quality from under-sampled data, while others focused on the correction of artefacts that result from the noise or motion. No approach has however been proposed so far that addresses both acceleration and artefacts correction, limiting the performance of these models when these degradation factors occur simultaneously. To address this gap, we present a method for recovering high-quality images from under-sampled data with simultaneously correction for noise and motion artefact called USArt (Under-Sampling and Artifact correction model). Customized for 2D brain anatomical images acquired with Cartesian sampling, USArt employs a dual sub-model approach. The results demonstrate remarkable increase of signal-to-noise ratio (SNR) and contrast in the images restored. Various under-sampling strategies and degradation levels were explored, with the gradient under-sampling strategy yielding the best outcomes. We achieved up to 5x acceleration and simultaneously artefacts correction without significant degradation, showcasing the model's robustness in real-world settings. --- ### Learning a Single Token to Replace Long System Prompts in LLMs Authors: Jiancheng Dong, Pengyue Jia, Jingyu Peng, Maolin Wang, Yuhao Wang, Lixin Su, Xin Sun, Shuaiqiang Wang, Dawei Yin, Xiangyu Zhao Published: 2025-11-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.23271v2 Long system prompts are widely used to steer Large Language Models (LLMs), but repeatedly processing them at inference time is inefficient and consumes valuable context budget. This motivates a central question: can the behavioral effect of a long system prompt be retained using only a minimal learned representation? To enable this, we propose a lightweight training framework that learns a single Behavior-Equivalent Token ((BE)). The framework first trains (BE) to encode the semantic content of the original system prompt via reconstruction, and then distills the prompt's downstream behavior into this single token. Importantly, our method requires no update to the pretrained LLM weights, no auxiliary compression models, and no labeled responses. Empirical evaluations on three datasets show that replacing long prompts with a single (BE) token yields up to a $3000\times$ prompt compression ratio, while retaining about 98% of the downstream performance of the original system prompts. This substantially reduces inference cost and frees nearly the entire context window for user inputs and model outputs. --- ### OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning Authors: Timothy Ossowski, Sheng Zhang, Qianchu Liu, Guanghui Qin, Reuben Tan, Tristan Naumann, Junjie Hu, Hoifung Poon Published: 2025-11-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.23269v1 High-quality and carefully curated data is a cornerstone of training medical large language models, as it directly impacts both generalization and robustness to unseen clinical tasks. We investigate strategies for training and data curation to develop a robust multimodal reasoning model in the medical domain. Our work focuses on supervised fine-tuning (SFT) and explores data recipes that leverage structured reasoning traces. Using our proposed data recipe, we scale experiments to a dataset of over 8 million examples and 6.8 billion response tokens, achieving state-of-the-art performance among open-source models across diverse out-of-distribution medical benchmark tasks. Our results further indicate that curating a high-quality, diverse training dataset with varying structured reasoning trace lengths enables the fine-tuned model to self-calibrate its reasoning trajectory lengths based on the downstream task, without explicit supervision. We present key insights, describe the data curation strategy, and outline next steps toward developing robust medical vision-language reasoning system. --- ### BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learning Authors: Ariful Islam, Md Rifat Hossen, Tanvir Mahmud Published: 2025-11-28 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2511.23264v1 Multi-aspect sentiment analysis of Bangla e-commerce reviews remains challenging due to limited annotated datasets, morphological complexity, code-mixing phenomena, and domain shift issues, affecting 300 million Bangla-speaking users. Existing approaches lack explainability and cross-domain generalization capabilities crucial for practical deployment. We present BanglaSentNet, an explainable hybrid deep learning framework integrating LSTM, BiLSTM, GRU, and BanglaBERT through dynamic weighted ensemble learning for multi-aspect sentiment classification. We introduce a dataset of 8,755 manually annotated Bangla product reviews across four aspects (Quality, Service, Price, Decoration) from major Bangladeshi e-commerce platforms. Our framework incorporates SHAP-based feature attribution and attention visualization for transparent insights. BanglaSentNet achieves 85% accuracy and 0.88 F1-score, outperforming standalone deep learning models by 3-7% and traditional approaches substantially. The explainability suite achieves 9.4/10 interpretability score with 87.6% human agreement. Cross-domain transfer learning experiments reveal robust generalization: zero-shot performance retains 67-76% effectiveness across diverse domains (BanglaBook reviews, social media, general e-commerce, news headlines); few-shot learning with 500-1000 samples achieves 90-95% of full fine-tuning performance, significantly reducing annotation costs. Real-world deployment demonstrates practical utility for Bangladeshi e-commerce platforms, enabling data-driven decision-making for pricing optimization, service improvement, and customer experience enhancement. This research establishes a new state-of-the-art benchmark for Bangla sentiment analysis, advances ensemble learning methodologies for low-resource languages, and provides actionable solutions for commercial applications. --- ### Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning Authors: Yang Li, Zhiyuan He, Yuxuan Huang, Zhuhanling Xiao, Chao Yu, Meng Fang, Kun Shao, Jun Wang Published: 2025-11-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.23262v1 Recent Vision-Language Models (VLMs) exhibit strong perceptual reasoning abilities, yet they often struggle to adapt efficiently when encountering novel tasks at test time. In contrast, humans leverage the metacognitive model with memory, enabling continuous strategy refinement through metacognitive control when faced with new challenges. To bridge this gap, we propose metacognitive test-time reasoning (MCTR), a framework that equips models with the ability to learn, adapt, and improve during test time through metacognitive self-updating. Inspired by the dual structure of human metacognition, MCTR comprises meta-level and object-level VLM reasoning modules, each equipped with dedicated memory systems for hierarchical adaptive reasoning. Specifically, MCTR consists of (1) a meta-reasoning module which incrementally builds a structured memory by discovering and storing task-relevant rules, environmental patterns, and action-outcome relationships from test-time observations as natural language descriptions; and (2) an action-reasoning module that determines optimal actions through context-aware perception and strategic reasoning by dynamically retrieving and integrating knowledge from memory. The action-reasoning module continuously updates its policy through proposed metacognitive test-time reinforcement learning, adapting as knowledge memory evolves. We evaluate MCTR on 45 Atari games (33 seen, 12 unseen). MCTR demonstrates robust test-time adaptation, achieving 9/12 top-1 results on unseen games compared with baselines. Analyses through ablations, learning dynamics, and case studies reveal the complementary contributions of both components and show meta-reasoning evolving toward human-like adaptation strategies. --- ### An Improved and Generalised Analysis for Spectral Clustering Authors: George Tyler, Luca Zanetti Published: 2025-11-28 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2511.23261v1 We revisit the theoretical performances of Spectral Clustering, a classical algorithm for graph partitioning that relies on the eigenvectors of a matrix representation of the graph. Informally, we show that Spectral Clustering works well as long as the smallest eigenvalues appear in groups well separated from the rest of the matrix representation's spectrum. This arises, for example, whenever there exists a hierarchy of clusters at different scales, a regime not captured by previous analyses. Our results are very general and can be applied beyond the traditional graph Laplacian. In particular, we study Hermitian representations of digraphs and show Spectral Clustering can recover partitions where edges between clusters are oriented mostly in the same direction. This has applications in, for example, the analysis of trophic levels in ecological networks. We demonstrate that our results accurately predict the performances of Spectral Clustering on synthetic and real-world data sets. --- ### Time Series Forecasting via Direct Per-Step Probability Distribution Modeling Authors: Linghao Kong, Xiaopeng Hong Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.23260v1 Deep neural network-based time series prediction models have recently demonstrated superior capabilities in capturing complex temporal dependencies. However, it is challenging for these models to account for uncertainty associated with their predictions, because they directly output scalar values at each time step. To address such a challenge, we propose a novel model named interleaved dual-branch Probability Distribution Network (interPDN), which directly constructs discrete probability distributions per step instead of a scalar. The regression output at each time step is derived by computing the expectation of the predictive distribution on a predefined support set. To mitigate prediction anomalies, a dual-branch architecture is introduced with interleaved support sets, augmented by coarse temporal-scale branches for long-term trend forecasting. Outputs from another branch are treated as auxiliary signals to impose self-supervised consistency constraints on the current branch's prediction. Extensive experiments on multiple real-world datasets demonstrate the superior performance of interPDN. --- ### Robust HRRP Recognition under Interrupted Sampling Repeater Jamming using a Prior Jamming Information-Guided Network Authors: Guozheng Sun, Lei Wang, Yanhao Wang, Jie Wang, Yimin Liu Published: 2025-11-28 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2511.23256v2 Radar automatic target recognition (RATR) based on high-resolution range profile (HRRP) has attracted increasing attention due to its ability to capture fine-grained structural features. However, recognizing targets under electronic countermeasures (ECM), especially the mainstream interrupted-sampling repeater jamming (ISRJ), remains a significant challenge, as HRRPs often suffer from serious feature distortion. To address this, we propose a robust HRRP recognition method guided by prior jamming information. Specifically, we introduce a point spread function (PSF) as prior information to model the HRRP distortion induced by ISRJ. Based on this, we design a recognition network that leverages this prior through a prior-guided feature interaction module and a hybrid loss function to enhance the model's discriminative capability. With the aid of prior information, the model can learn invariant features within distorted HRRP under different jamming parameters. Both the simulated and measured-data experiments demonstrate that our method consistently outperforms state-of-the-art approaches and exhibits stronger generalization capabilities when facing unseen jamming parameters. --- ### AgroCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for Agriculture Authors: Yibin Wen, Qingmei Li, Zi Ye, Jiarui Zhang, Xiaoya Fan, Zurong Mai, Jing Wu, Shuohong Lou, Yuhang Chen, Henglian Huang, Yang Zhang, Defeng Gu et al. Published: 2025-11-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.23253v3 Recent advancements in Vision-Language Models (VLMs) have significantly impacted various industries. In agriculture, these multimodal capabilities hold great promise for applications such as precision farming, crop monitoring, pest detection, and environmental sustainability. However, while several Visual Question Answering (VQA) datasets and benchmarks have been developed to assess VLM performance, they often fail to effectively evaluate the critical reasoning and problem-solving skills needed in complex agricultural contexts. To address this gap, we introduce AgroCoT, a VQA dataset that integrates Chain-of-Thought (CoT) reasoning, specifically designed to evaluate the reasoning capabilities of VLMs. With 4,759 carefully curated samples, AgroCoT provides a comprehensive and robust evaluation of reasoning abilities, particularly in zero-shot scenarios, focusing on the models' ability to engage in logical reasoning and effective problem-solving. Our evaluation of 30 representative VLMs, including both proprietary and open-source models, reveals a gap in their reasoning capabilities, which underscores the importance of incorporating CoT for assessments. Our dataset is available at https://huggingface.co/datasets/AgroCoT/AgroCoT. --- ### One-Shot Secure Aggregation: A Hybrid Cryptographic Protocol for Private Federated Learning in IoT Authors: Imraul Emmaka, Tran Viet Xuan Phuong Published: 2025-11-28 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.23252v1 Federated Learning (FL) offers a promising approach to collaboratively train machine learning models without centralizing raw data, yet its scalability is often throttled by excessive communication overhead. This challenge is magnified in Internet of Things (IoT) environments, where devices face stringent bandwidth, latency, and energy constraints. Conventional secure aggregation protocols, while essential for protecting model updates, frequently require multiple interaction rounds, large payload sizes, and per-client costs rendering them impractical for many edge deployments. In this work, we present Hyb-Agg, a lightweight and communication-efficient secure aggregation protocol that integrates Multi-Key CKKS (MK-CKKS) homomorphic encryption with Elliptic Curve Diffie-Hellman (ECDH)-based additive masking. Hyb-Agg reduces the secure aggregation process to a single, non-interactive client-to-server transmission per round, ensuring that per-client communication remains constant regardless of the number of participants. This design eliminates partial decryption exchanges, preserves strong privacy under the RLWE, CDH, and random oracle assumptions, and maintains robustness against collusion by the server and up to $N-2$ clients. We implement and evaluate Hyb-Agg on both high-performance and resource-constrained devices, including a Raspberry Pi 4, demonstrating that it delivers sub-second execution times while achieving a constant communication expansion factor of approximately 12x over plaintext size. By directly addressing the communication bottleneck, Hyb-Agg enables scalable, privacy-preserving federated learning that is practical for real-world IoT deployments. --- ### Learning to Predict Aboveground Biomass from RGB Images with 3D Synthetic Scenes Authors: Silvia Zuffi Published: 2025-11-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.23249v1 Forests play a critical role in global ecosystems by supporting biodiversity and mitigating climate change via carbon sequestration. Accurate aboveground biomass (AGB) estimation is essential for assessing carbon storage and wildfire fuel loads, yet traditional methods rely on labor-intensive field measurements or remote sensing approaches with significant limitations in dense vegetation. In this work, we propose a novel learning-based method for estimating AGB from a single ground-based RGB image. We frame this as a dense prediction task, introducing AGB density maps, where each pixel represents tree biomass normalized by the plot area and each tree's image area. We leverage the recently introduced synthetic 3D SPREAD dataset, which provides realistic forest scenes with per-image tree attributes (height, trunk and canopy diameter) and instance segmentation masks. Using these assets, we compute AGB via allometric equations and train a model to predict AGB density maps, integrating them to recover the AGB estimate for the captured scene. Our approach achieves a median AGB estimation error of 1.22 kg/m^2 on held-out SPREAD data and 1.94 kg/m^2 on a real-image dataset. To our knowledge, this is the first method to estimate aboveground biomass directly from a single RGB image, opening up the possibility for a scalable, interpretable, and cost-effective solution for forest monitoring, while also enabling broader participation through citizen science initiatives. --- ### Heteroscedastic Neural Networks for Path Loss Prediction with Link-Specific Uncertainty Authors: Jonathan Ethier Published: 2025-11-28 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2511.23243v1 Traditional and modern machine learning-based path loss models typically assume a constant prediction variance. We propose a neural network that jointly predicts the mean and link-specific variance by minimizing a Gaussian negative log-likelihood, enabling heteroscedastic uncertainty estimates. We compare shared, partially shared, and independent-parameter architectures using accuracy, calibration, and sharpness metrics on blind test sets from large public RF drive-test datasets. The shared-parameter architecture performs best, achieving an RMSE of 7.4 dB, 95.1 percent coverage for 95 percent prediction intervals, and a mean interval width of 29.6 dB. These uncertainty estimates further support link-specific coverage margins, improve RF planning and interference analyses, and provide effective self-diagnostics of model weaknesses. --- ### Synthetic Industrial Object Detection: GenAI vs. Feature-Based Methods Authors: Jose Moises Araya-Martinez, Adrián Sanchis Reig, Gautham Mohan, Sarvenaz Sardari, Jens Lambrecht, Jörg Krüger Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23241v1 Reducing the burden of data generation and annotation remains a major challenge for the cost-effective deployment of machine learning in industrial and robotics settings. While synthetic rendering is a promising solution, bridging the sim-to-real gap often requires expert intervention. In this work, we benchmark a range of domain randomization (DR) and domain adaptation (DA) techniques, including feature-based methods, generative AI (GenAI), and classical rendering approaches, for creating contextualized synthetic data without manual annotation. Our evaluation focuses on the effectiveness and efficiency of low-level and high-level feature alignment, as well as a controlled diffusion-based DA method guided by prompts generated from real-world contexts. We validate our methods on two datasets: a proprietary industrial dataset (automotive and logistics) and a public robotics dataset. Results show that if render-based data with enough variability is available as seed, simpler feature-based methods, such as brightness-based and perceptual hashing filtering, outperform more complex GenAI-based approaches in both accuracy and resource efficiency. Perceptual hashing consistently achieves the highest performance, with mAP50 scores of 98% and 67% on the industrial and robotics datasets, respectively. Additionally, GenAI methods present significant time overhead for data generation at no apparent improvement of sim-to-real mAP values compared to simpler methods. Our findings offer actionable insights for efficiently bridging the sim-to-real gap, enabling high real-world performance from models trained exclusively on synthetic data. --- ### Towards Understanding Transformers in Learning Random Walks Authors: Wei Shi, Yuan Cao Published: 2025-11-28 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.23239v1 Transformers have proven highly effective across various applications, especially in handling sequential data such as natural languages and time series. However, transformer models often lack clear interpretability, and the success of transformers has not been well understood in theory. In this paper, we study the capability and interpretability of transformers in learning a family of classic statistical models, namely random walks on circles. We theoretically demonstrate that, after training with gradient descent, a one-layer transformer model can achieve optimal accuracy in predicting random walks. Importantly, our analysis reveals that the trained model is interpretable: the trained softmax attention serves as a token selector, focusing on the direct parent state; subsequently, the value matrix executes a one-step probability transition to predict the location of the next state based on this parent state. We also show that certain edge cases not covered by our theory are indeed failure cases, demonstrating that our theoretical conditions are tight. By investigating these success and failure cases, it is revealed that gradient descent with small initialization may fail or struggle to converge to a good solution in certain simple tasks even beyond random walks. Experiments are conducted to support our theoretical findings. --- ### SDE-Attention: Latent Attention in SDE-RNNs for Irregularly Sampled Time Series with Missing Data Authors: Yuting Fang, Qouc Le Gia, Flora Salim Published: 2025-11-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.23238v1 Irregularly sampled time series with substantial missing observations are common in healthcare and sensor networks. We introduce SDE-Attention, a family of SDE-RNNs equipped with channel-level attention on the latent pre-RNN state, including channel recalibration, time-varying feature attention, and pyramidal multi-scale self-attention. We therefore conduct a comparison on a synthetic periodic dataset and real-world benchmarks, under varying missing rate. Latent-space attention consistently improves over a vanilla SDE-RNN. On the univariate UCR datasets, the LSTM-based time-varying feature model SDE-TVF-L achieves the highest average accuracy, raising mean performance by approximately 4, 6, and 10 percentage points over the baseline at 30%, 60% and 90% missingness, respectively (averaged across datasets). On multivariate UEA benchmarks, attention-augmented models again outperform the backbone, with SDE-TVF-L yielding up to a 7% gain in mean accuracy under high missingness. Among the proposed mechanisms, time-varying feature attention is the most robust on univariate datasets. On multivariate datasets, different attention types excel on different tasks, showing that SDE-Attention can be flexibly adapted to the structure of each problem. --- ### Tourism Question Answer System in Indian Language using Domain-Adapted Foundation Models Authors: Praveen Gatla, Anushka, Nikita Kanwar, Gouri Sahoo, Rajesh Kumar Mundotiya Published: 2025-11-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.23235v1 This article presents the first comprehensive study on designing a baseline extractive question-answering (QA) system for the Hindi tourism domain, with a specialized focus on the Varanasi-a cultural and spiritual hub renowned for its Bhakti-Bhaav (devotional ethos). Targeting ten tourism-centric subdomains-Ganga Aarti, Cruise, Food Court, Public Toilet, Kund, Museum, General, Ashram, Temple and Travel, the work addresses the absence of language-specific QA resources in Hindi for culturally nuanced applications. In this paper, a dataset comprising 7,715 Hindi QA pairs pertaining to Varanasi tourism was constructed and subsequently augmented with 27,455 pairs generated via Llama zero-shot prompting. We propose a framework leveraging foundation models-BERT and RoBERTa, fine-tuned using Supervised Fine-Tuning (SFT) and Low-Rank Adaptation (LoRA), to optimize parameter efficiency and task performance. Multiple variants of BERT, including pre-trained languages (e.g., Hindi-BERT), are evaluated to assess their suitability for low-resource domain-specific QA. Evaluation metrics - F1, BLEU, and ROUGE-L - highlight trade-offs between answer precision and linguistic fluency. Experiments demonstrate that LoRA-based fine-tuning achieves competitive performance (85.3\% F1) while reducing trainable parameters by 98\% compared to SFT, striking a balance between efficiency and accuracy. Comparative analysis across models reveals that RoBERTa with SFT outperforms BERT variants in capturing contextual nuances, particularly for culturally embedded terms (e.g., Aarti, Kund). This work establishes a foundational baseline for Hindi tourism QA systems, emphasizing the role of LORA in low-resource settings and underscoring the need for culturally contextualized NLP frameworks in the tourism domain. --- ### Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering Authors: Qiming Li, Xiaocheng Feng, Yixuan Ma, Zekai Ye, Ruihan Chen, Xiachong Feng, Bing Qin Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23231v2 Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) demonstrate strong reasoning capabilities, yet their performance in English significantly outperforms that in low-resource languages, raising fairness concerns in multilingual applications. Existing approaches either rely on costly multilingual training or employ prompting with external translation tools, both of which are resource-intensive and sensitive to translation quality. To address these limitations, we propose a training-free inference-time method to enhance Multilingual Reasoning capabilities via Representation Engineering (MRRE) without using any additional training data or tools. MRRE sequentially injects two precomputed vectors at specific layers during inference processing: cross-lingual reasoning enhancement vectors, which steer non-English reasoning representations toward English space to unlock multilingual reasoning, and target-language output anchoring vectors, which restore the distribution of the target language to preserve input-output language consistency. Comprehensive experiments across six advanced LLMs and LVLMs on four reasoning benchmarks demonstrate that MRRE consistently enhances non-English reasoning by an average gain of 5.48% and up to 7.54% in low-resource languages (Thai and Swahili), while improving input-output language consistency by 3.78%. --- ### Action-guided generation of 3D functionality segmentation data Authors: Jaime Corsetti, Francesco Giuliari, Davide Boscaini, Pedro Hermosilla, Andrea Pilzer, Guofeng Mei, Alexandros Delitzas, Francis Engelmann, Fabio Poiesi Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23230v2 3D functionality segmentation aims to identify the interactive element in a 3D scene required to perform an action described in free-form language (e.g., the handle to ``Open the second drawer of the cabinet near the bed''). Progress has been constrained by the scarcity of annotated real-world data, as collecting and labeling fine-grained 3D masks is prohibitively expensive. To address this limitation, we introduce SynthFun3D, the first method for generating 3D functionality segmentation data directly from action descriptions. Given an action description, SynthFun3D constructs a plausible 3D scene by retrieving objects with part-level annotations from a large-scale asset repository and arranging them under spatial and semantic constraints. SynthFun3D renders multi-view images and automatically identifies the target functional element, producing precise ground-truth masks without manual annotation. We demonstrate the effectiveness of the generated data by training a VLM-based 3D functionality segmentation model. Augmenting real-world data with our synthetic data consistently improves performance, with gains of +2.2 mAP, +6.3 mAR, and +5.7 mIoU over real-only training. This shows that action-guided synthetic data generation provides a scalable and effective complement to manual annotation for 3D functionality understanding. Project page: tev-fbk.github.io/synthfun3d. --- ### PointCNN++: Performant Convolution on Native Points Authors: Lihan Li, Haofeng Zhong, Rui Bu, Mingchao Sun, Wenzheng Chen, Baoquan Chen, Yangyan Li Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23227v3 Existing convolutional learning methods for 3D point cloud data are divided into two paradigms: point-based methods that preserve geometric precision but often face performance challenges, and voxel-based methods that achieve high efficiency through quantization at the cost of geometric fidelity. This loss of precision is a critical bottleneck for tasks such as point cloud registration. We propose PointCNN++, a novel architectural design that fundamentally mitigates this precision-performance trade-off. It $\textbf{generalizes sparse convolution from voxels to points}$, treating voxel-based convolution as a specialized, degraded case of our more general point-based convolution. First, we introduce a point-centric convolution where the receptive field is centered on the original, high-precision point coordinates. Second, to make this high-fidelity operation performant, we design a computational strategy that operates $\textbf{natively}$ on points. We formulate the convolution on native points as a Matrix-Vector Multiplication and Reduction (MVMR) problem, for which we develop a dedicated, highly-optimized GPU kernel. Experiments demonstrate that PointCNN++ $\textbf{uses an order of magnitude less memory and is several times faster}$ than representative point-based methods. Furthermore, when used as a simple replacement for the voxel-based backbones it generalizes, it $\textbf{significantly improves point cloud registration accuracies while proving both more memory-efficient and faster}$. PointCNN++ shows that preserving geometric detail and achieving high performance are not mutually exclusive, paving the way for a new class of 3D learning with high fidelity and efficiency. Our code will be open sourced. --- ### TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies Authors: Guang Liang, Jie Shao, Ningyuan Tang, Xinyao Liu, Jianxin Wu Published: 2025-11-28 Categories: cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.23225v1 Native FP8 support in modern hardware is essential for training large Transformers, but is severely hindered by extreme activation outliers. Existing solutions either rely on complex mixed-precision engineering or invasive architectural modifications. This paper fundamentally challenges the conventional wisdom that outliers are data-driven. We demonstrate that extreme outliers are a data-independent, mechanically-produced artifact of training, originating from specific structural properties of the weight matrices (i.e., colinearity). Based on this insight, we propose TWEO (Transformers Without Extreme Outliers), a novel, non-invasive loss function. TWEO effectively prevents extreme outliers via a very simple loss term, which reduces outliers from 10000+ to less than 20. TWEO then enables full-model FP8 pre-training with neither engineering tricks nor architectural changes for both LLM and ViT. When standard FP8 training catastrophically collapses, TWEO achieves performance comparable to the BF16 baseline while delivering a 36% increase in training throughput. Also, TWEO enables a new quantization paradigm. Hardware-friendly W8A8 per-tensor static quantization of LLMs, previously considered completely unusable due to outliers, achieves SOTA performance for the first time on TWEO-trained models. --- ### Nonstabilizerness Estimation using Graph Neural Networks Authors: Vincenzo Lipardi, Domenica Dibenedetto, Georgios Stamoulis, Evert van Nieuwenburg, Mark H. M. Winands Published: 2025-11-28 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2511.23224v2 This article proposes a Graph Neural Network (GNN) approach to estimate nonstabilizerness in quantum circuits, measured by the stabilizer Rényi entropy (SRE). Nonstabilizerness is a fundamental resource for quantum advantage, and efficient SRE estimations are highly beneficial in practical applications. We address the nonstabilizerness estimation problem through three supervised learning formulations starting from easier classification tasks to the more challenging regression task. Experimental results show that the proposed GNN manages to capture meaningful features from the graph-based circuit representation, resulting in robust generalization performances achieved across diverse scenarios. In classification tasks, the GNN is trained on product states and generalizes on circuits evolved under Clifford operations, entangled states, and circuits with higher number of qubits. In the regression task, the GNN significantly improves the SRE estimation on out-of-distribution circuits with higher number of qubits and gate counts compared to previous work, for both unstructured random quantum circuits and structured circuits derived from the transverse-field Ising model. Moreover, the graph representation of quantum circuits naturally integrates hardware-specific information. Simulations on noisy quantum hardware highlight the potential of the proposed GNN to predict the SRE measured on quantum devices. --- ### DAONet-YOLOv8: An Occlusion-Aware Dual-Attention Network for Tea Leaf Pest and Disease Detection Authors: Yefeng Wu, Shan Wan, Ling Wu, Yecheng Zhao Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23222v1 Accurate detection of tea leaf pests and diseases in real plantations remains challenging due to complex backgrounds, variable illumination, and frequent occlusions among dense branches and leaves. Existing detectors often suffer from missed detections and false positives in such scenarios. To address these issues, we propose DAONet-YOLOv8, an enhanced YOLOv8 variant with three key improvements: (1) a Dual-Attention Fusion Module (DAFM) that combines convolutional local feature extraction with self-attention based global context modeling to focus on subtle lesion regions while suppressing background noise; (2) an occlusion-aware detection head (Detect-OAHead) that learns the relationship between visible and occluded parts to compensate for missing lesion features; and (3) a C2f-DSConv module employing dynamic synthesis convolutions with multiple kernel shapes to better capture irregular lesion boundaries. Experiments on our real-world tea plantation dataset containing six pest and disease categories demonstrate that DAONet-YOLOv8 achieves 92.97% precision, 92.80% recall, 97.10% mAP@50 and 76.90% mAP@50:95, outperforming the YOLOv8n baseline by 2.34, 4.68, 1.40 and 1.80 percentage points respectively, while reducing parameters by 16.7%. Comparative experiments further confirm that DAONet-YOLOv8 achieves superior performance over mainstream detection models. --- ### Robust 3DGS-based SLAM via Adaptive Kernel Smoothing Authors: Shouhe Zhang, Dayong Ren, Wen Jie Li, Piaopiao Yu, Sensen Song, Kaikai Shao, Yurong Qian Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23221v3 In this paper, we challenge the conventional notion in 3DGS-SLAM that rendering quality is the primary determinant of tracking accuracy. We argue that, compared to solely pursuing a perfect scene representation, it is more critical to enhance the robustness of the rasterization process against parameter errors to ensure stable camera pose tracking. To address this challenge, we propose a novel approach that leverages a smooth kernel strategy to enhance the robustness of 3DGS-based SLAM. Unlike conventional methods that focus solely on minimizing rendering error, our core insight is to make the rasterization process more resilient to imperfections in the 3DGS parameters. We hypothesize that by allowing each Gaussian to influence a smoother, wider distribution of pixels during rendering, we can mitigate the detrimental effects of parameter noise from outlier Gaussians. This approach intentionally introduces a controlled blur to the rendered image, which acts as a regularization term, stabilizing the subsequent pose optimization. While a complete redesign of the rasterization pipeline is an ideal solution, we propose a practical and effective alternative that is readily integrated into existing 3DGS frameworks. Our method, termed Corrective Blurry KNN (CB-KNN), adaptively modifies the RGB values and locations of the K-nearest neighboring Gaussians within a local region. This dynamic adjustment generates a smoother local rendering, reducing the impact of erroneous GS parameters on the overall image. Experimental results demonstrate that our approach, while maintaining the overall quality of the scene reconstruction (mapping), significantly improves the robustness and accuracy of camera pose tracking. --- ### Instruction Tuning of Large Language Models for Tabular Data Generation-in One Day Authors: Milad Abdollahzadeh, Abdul Raheem, Zilong Zhao, Uzair Javaid, Kevin Yee, Nalam Venkata Abhishek, Tram Truong-Huu, Biplab Sikdar Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23220v1 Tabular instruction tuning has emerged as a promising research direction for improving LLMs understanding of tabular data. However, the majority of existing works only consider question-answering and reasoning tasks over tabular data, leaving tabular data generation largely unnoticed. In this work, for the first time, we explore the efficacy of instruction tuning in improving LLMs tabular data generation capabilities. More specifically, given the high data and computation requirements of tabular instruction tuning, we aim to address the possibility of instruction tuning for tabular data generation with limited data and computational resources. To achieve this, we first create a high-quality instruction dataset for tabular data, enabling efficient LLM comprehension. We then instruction-tune an open-source LLM (Llama3.1-8B-Instruct) on the training set of this dataset to improve its tabular data generation performance. Our experimental results show that by using our high-quality dataset and instruction-tuning on only 7K instructions with an A100 GPU, for less than 6 hours, we achieve tabular data generation performance on par with the most capable commercial LLM, GPT-4o. ---