# Research Papers — 2025-10 · bundle page 20 of 217 > Full-text markdown of papers #951–1000 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-10/page/20 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/19.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/21.md) ### RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models Authors: Zijun Liao, Yian Zhao, Xin Shan, Yu Yan, Chang Liu, Lei Lu, Xiangyang Ji, Jie Chen Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25257v2 Real-time object detection has achieved substantial progress through meticulously designed architectures and optimization strategies. However, the pursuit of high-speed inference via lightweight network designs often leads to degraded feature representation, which hinders further performance improvements and practical on-device deployment. In this paper, we propose a cost-effective and highly adaptable distillation framework that harnesses the rapidly evolving capabilities of Vision Foundation Models (VFMs) to enhance lightweight object detectors. Given the significant architectural and learning objective disparities between VFMs and resource-constrained detectors, achieving stable and task-aligned semantic transfer is challenging. To address this, on one hand, we introduce a \textbf{Deep Semantic Injector (DSI)} module that facilitates the integration of high-level representations from VFMs into the deep layers of the detector. On the other hand, we devise a \textbf{Gradient-guided Adaptive Modulation (GAM)} strategy, which dynamically adjusts the intensity of semantic transfer based on gradient norm ratios. Without increasing deployment and inference overhead, our approach painlessly delivers striking and consistent performance gains across diverse DETR-based models, underscoring its practical utility for real-time detection. Our new model family, RT-DETRv4, achieves state-of-the-art results on COCO, attaining AP scores of $49.8/53.7/55.4/57.0$ at corresponding speeds of $273/169/124/78$ FPS. Code is publicly available at https://github.com/RT-DETRs/RT-DETRv4. --- ### Scaling Up Bayesian DAG Sampling Authors: Daniele Nikzad, Alexander Zhilkin, Juha Harviainen, Jack Kuipers, Giusi Moffa, Mikko Koivisto Published: 2025-10-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.25254v1 Bayesian inference of Bayesian network structures is often performed by sampling directed acyclic graphs along an appropriately constructed Markov chain. We present two techniques to improve sampling. First, we give an efficient implementation of basic moves, which add, delete, or reverse a single arc. Second, we expedite summing over parent sets, an expensive task required for more sophisticated moves: we devise a preprocessing method to prune possible parent sets so as to approximately preserve the sums. Our empirical study shows that our techniques can yield substantial efficiency gains compared to previous methods. --- ### BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training Authors: Wenjie Zhou, Bohan Wang, Wei Chen, Xueqi Cheng Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25244v2 Recent studies \citep{gur2018gradient,song2024does, wen2024understanding} highlight a fundamental dichotomy in deep learning optimization: Although parameter updates along the top eigendirections of the loss Hessian (Dom-space) capture most of the update magnitude, they often contribute minimally to loss reduction. In contrast, updates in the orthogonal component (Bulk-space) have smaller magnitudes but drive most learning progress. In this work, we further advance the understanding of this phenomenon and introduce the \textbf{Bulk-Space-Filtration-Accelerator (BSFA)}, a novel plug-and-play framework. BSFA accelerates training by differentially scaling update components projected onto these distinct subspaces, simultaneously enhancing stability by moderating updates in the dominant subspace and boosting convergence speed by amplifying those in the bulk-space. To ensure BSFA is both practical and scalable for contemporary large models, we introduce two key innovations: an efficient estimator using Principal Component Analysis (PCA) on historical updates for fast subspace estimation, and a block-wise strategy that applies this estimation on a per-parameter-block basis. These designs make BSFA computationally tractable and highly effective. We demonstrate BSFA's acceleration across various tasks, notably achieving approximately 2$\times$ speedup when pre-training LLaMA-72M on WikiText-103 and LLaMA-134M on OpenWebText compared to vanilla AdamW. --- ### One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors Authors: Hao Huang, Geeta Chandra Raju Bethala, Shuaihang Yuan, Congcong Wen, Mengyu Wang, Anthony Tzes, Yi Fang Published: 2025-10-29 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2510.25241v2 Whole-body humanoid motion represents a fundamental challenge in robotics, requiring balance, coordination, and adaptability to enable human-like behaviors. However, existing methods typically require multiple training samples per motion, rendering the collection of high-quality human motion datasets both labor-intensive and costly. To address this, we propose a data-efficient adaptation approach that learns a new humanoid motion from a single non-walking target sample together with auxiliary walking motions and a walking-trained base model. The core idea lies in leveraging order-preserving optimal transport to compute distances between walking and non-walking sequences, followed by interpolation along geodesics to generate new intermediate pose skeletons, which are then optimized for collision-free configurations and retargeted to the humanoid before integration into a simulated environment for policy adaptation via reinforcement learning. Experimental evaluations on the CMU MoCap dataset demonstrate that our method consistently outperforms baselines, achieving superior performance across metrics. Our code is available at: https://github.com/hhuang-code/One-shot-WBM. --- ### Generative Bayesian Optimization: Generative Models as Acquisition Functions Authors: Rafael Oliveira, Daniel M. Steinberg, Edwin V. Bonilla Published: 2025-10-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.25240v3 We present a general strategy for turning generative models into candidate solution samplers for batch Bayesian optimization (BO). The use of generative models for BO enables large batch scaling as generative sampling, optimization of non-continuous design spaces, and high-dimensional and combinatorial design. Inspired by the success of direct preference optimization (DPO), we show that one can train a generative model with noisy, simple utility values directly computed from observations to then form proposal distributions whose densities are proportional to the expected utility, i.e., BO's acquisition function values. Furthermore, this approach is generalizable beyond preference-based feedback to general types of reward signals and loss functions. This perspective avoids the construction of surrogate (regression or classification) models, common in previous methods that have used generative models for black-box optimization. Theoretically, we show that the generative models within the BO process follow a sequence of distributions which asymptotically approximate an optimal target under certain conditions. We also evaluate the performance through experiments on challenging optimization problems involving large batches in high dimensions. --- ### Mapping and Classification of Trees Outside Forests using Deep Learning Authors: Moritz Lucas, Hamid Ebrahimy, Viacheslav Barkov, Ralf Pecenka, Kai-Uwe Kühnberger, Björn Waske Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25239v2 Trees Outside Forests (TOF) play an important role in agricultural landscapes by supporting biodiversity, sequestering carbon, and regulating microclimates. Yet, most studies have treated TOF as a single class or relied on rigid rule-based thresholds, limiting ecological interpretation and adaptability across regions. To address this, we evaluate deep learning for TOF classification using a newly generated dataset and high-resolution aerial imagery from four agricultural landscapes in Germany. Specifically, we compare convolutional neural networks (CNNs), vision transformers, and hybrid CNN-transformer models across six semantic segmentation architectures (ABCNet, LSKNet, FT-UNetFormer, DC-Swin, BANet, and U-Net) to map four categories of woody vegetation: Forest, Patch, Linear, and Tree, derived from previous studies and governmental products. Overall, the models achieved good classification accuracy across the four landscapes, with the FT-UNetFormer performing best (mean Intersection-over-Union 0.74; mean F1 score 0.84), underscoring the importance of spatial context understanding in TOF mapping and classification. Our results show good results for Forest and Linear class and reveal challenges particularly in classifying complex structures with high edge density, notably the Patch and Tree class. Our generalization experiments highlight the need for regionally diverse training data to ensure reliable large-scale mapping. The dataset and code are openly available at https://github.com/Moerizzy/TOFMapper --- ### VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations Authors: Qianqian Qiao, DanDan Zheng, Yihang Bo, Bao Peng, Heng Huang, Longteng Jiang, Huaye Wang, Jingdong Chen, Jun Zhou, Xin Jin Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25238v2 Video aesthetic assessment, a vital area in multimedia computing, integrates computer vision with human cognition. Its progress is limited by the lack of standardized datasets and robust models, as the temporal dynamics of video and multimodal fusion challenges hinder direct application of image-based methods. This study introduces VADB, the largest video aesthetic database with 10,490 diverse videos annotated by 37 professionals across multiple aesthetic dimensions, including overall and attribute-specific aesthetic scores, rich language comments and objective tags. We propose VADB-Net, a dual-modal pre-training framework with a two-stage training strategy, which outperforms existing video quality assessment models in scoring tasks and supports downstream video aesthetic assessment tasks. The dataset and source code are available at https://github.com/BestiVictory/VADB. --- ### DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysis Authors: Yinqi Cai, Jichang Li, Zhaolun Li, Weikai Chen, Rushi Lan, Xi Xie, Xiaonan Luo, Guanbin Li Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25237v2 Recent advances in deep generative models have made it easier to manipulate face videos, raising significant concerns about their potential misuse for fraud and misinformation. Existing detectors often perform well in in-domain scenarios but fail to generalize across diverse manipulation techniques due to their reliance on forgery-specific artifacts. In this work, we introduce DeepShield, a novel deepfake detection framework that balances local sensitivity and global generalization to improve robustness across unseen forgeries. DeepShield enhances the CLIP-ViT encoder through two key components: Local Patch Guidance (LPG) and Global Forgery Diversification (GFD). LPG applies spatiotemporal artifact modeling and patch-wise supervision to capture fine-grained inconsistencies often overlooked by global models. GFD introduces domain feature augmentation, leveraging domain-bridging and boundary-expanding feature generation to synthesize diverse forgeries, mitigating overfitting and enhancing cross-domain adaptability. Through the integration of novel local and global analysis for deepfake detection, DeepShield outperforms state-of-the-art methods in cross-dataset and cross-manipulation evaluations, achieving superior robustness against unseen deepfake attacks. Code is available at https://github.com/lijichang/DeepShield. --- ### Learning Disentangled Speech- and Expression-Driven Blendshapes for 3D Talking Face Animation Authors: Yuxiang Mao, Zhijie Zhang, Zhiheng Zhang, Jiawei Liu, Chen Zeng, Shihong Xia Published: 2025-10-29 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2510.25234v1 Expressions are fundamental to conveying human emotions. With the rapid advancement of AI-generated content (AIGC), realistic and expressive 3D facial animation has become increasingly crucial. Despite recent progress in speech-driven lip-sync for talking-face animation, generating emotionally expressive talking faces remains underexplored. A major obstacle is the scarcity of real emotional 3D talking-face datasets due to the high cost of data capture. To address this, we model facial animation driven by both speech and emotion as a linear additive problem. Leveraging a 3D talking-face dataset with neutral expressions (VOCAset) and a dataset of 3D expression sequences (Florence4D), we jointly learn a set of blendshapes driven by speech and emotion. We introduce a sparsity constraint loss to encourage disentanglement between the two types of blendshapes while allowing the model to capture inherent secondary cross-domain deformations present in the training data. The learned blendshapes can be further mapped to the expression and jaw pose parameters of the FLAME model, enabling the animation of 3D Gaussian avatars. Qualitative and quantitative experiments demonstrate that our method naturally generates talking faces with specified expressions while maintaining accurate lip synchronization. Perceptual studies further show that our approach achieves superior emotional expressivity compared to existing methods, without compromising lip-sync quality. --- ### From Medical Records to Diagnostic Dialogues: A Clinical-Grounded Approach and Dataset for Psychiatric Comorbidity Authors: Tianxi Wan, Jiaming Luo, Siyuan Chen, Kunyao Lan, Jianhua Chen, Haiyang Geng, Mengyue Wu Published: 2025-10-29 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.25232v2 Psychiatric comorbidity is clinically significant yet challenging due to the complexity of multiple co-occurring disorders. To address this, we develop a novel approach integrating synthetic patient electronic medical record (EMR) construction and multi-agent diagnostic dialogue generation. We create 502 synthetic EMRs for common comorbid conditions using a pipeline that ensures clinical relevance and diversity. Our multi-agent framework transfers the clinical interview protocol into a hierarchical state machine and context tree, supporting over 130 diagnostic states while maintaining clinical standards. Through this rigorous process, we construct PsyCoTalk, the first large-scale dialogue dataset supporting comorbidity, containing 3,000 multi-turn diagnostic dialogues validated by psychiatrists. This dataset enhances diagnostic accuracy and treatment planning, offering a valuable resource for psychiatric comorbidity research. Compared to real-world clinical transcripts, PsyCoTalk exhibits high structural and linguistic fidelity in terms of dialogue length, token distribution, and diagnostic reasoning strategies. Licensed psychiatrists confirm the realism and diagnostic validity of the dialogues. This dataset enables the development and evaluation of models capable of multi-disorder psychiatric screening in a single conversational pass. --- ### Balanced conic rectified flow Authors: Shin Seong Kim, Mingi Kwon, Jaeseok Jeong, Youngjung Uh Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25229v1 Rectified flow is a generative model that learns smooth transport mappings between two distributions through an ordinary differential equation (ODE). Unlike diffusion-based generative models, which require costly numerical integration of a generative ODE to sample images with state-of-the-art quality, rectified flow uses an iterative process called reflow to learn smooth and straight ODE paths. This allows for relatively simple and efficient generation of high-quality images. However, rectified flow still faces several challenges. 1) The reflow process requires a large number of generative pairs to preserve the target distribution, leading to significant computational costs. 2) Since the model is typically trained using only generated image pairs, its performance heavily depends on the 1-rectified flow model, causing it to become biased towards the generated data. In this work, we experimentally expose the limitations of the original rectified flow and propose a novel approach that incorporates real images into the training process. By preserving the ODE paths for real images, our method effectively reduces reliance on large amounts of generated data. Instead, we demonstrate that the reflow process can be conducted efficiently using a much smaller set of generated and real images. In CIFAR-10, we achieved significantly better FID scores, not only in one-step generation but also in full-step simulations, while using only of the generative pairs compared to the original method. Furthermore, our approach induces straighter paths and avoids saturation on generated images during reflow, leading to more robust ODE learning while preserving the distribution of real images. --- ### 'Studies for': A Human-AI Co-Creative Sound Artwork Using a Real-time Multi-channel Sound Generation Model Authors: Chihiro Nagashima, Akira Takahashi, Zhi Zhong, Shusuke Takahashi, Yuki Mitsufuji Published: 2025-10-29 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2510.25228v2 This paper explores the integration of AI technologies into the artistic workflow through the creation of Studies for, a generative sound installation developed in collaboration with sound artist Evala (https://www.ntticc.or.jp/en/archive/works/studies-for/). The installation employs SpecMaskGIT, a lightweight yet high-quality sound generation AI model, to generate and playback eight-channel sound in real-time, creating an immersive auditory experience over the course of a three-month exhibition. The work is grounded in the concept of a "new form of archive," which aims to preserve the artistic style of an artist while expanding beyond artists' past artworks by continued generation of new sound elements. This speculative approach to archival preservation is facilitated by training the AI model on a dataset consisting of over 200 hours of Evala's past sound artworks. By addressing key requirements in the co-creation of art using AI, this study highlights the value of the following aspects: (1) the necessity of integrating artist feedback, (2) datasets derived from an artist's past works, and (3) ensuring the inclusion of unexpected, novel outputs. In Studies for, the model was designed to reflect the artist's artistic identity while generating new, previously unheard sounds, making it a fitting realization of the concept of "a new form of archive." We propose a Human-AI co-creation framework for effectively incorporating sound generation AI models into the sound art creation process and suggest new possibilities for creating and archiving sound art that extend an artist's work beyond their physical existence. Demo page: https://sony.github.io/studies-for/ --- ### Aligning What You Separate: Denoised Patch Mixing for Source-Free Domain Adaptation in Medical Image Segmentation Authors: Quang-Khai Bui-Tran, Thanh-Huy Nguyen, Hoang-Thien Nguyen, Ba-Thinh Lam, Nguyen Lan Vi Vu, Phat K. Huynh, Ulas Bagci, Min Xu Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25227v1 Source-Free Domain Adaptation (SFDA) is emerging as a compelling solution for medical image segmentation under privacy constraints, yet current approaches often ignore sample difficulty and struggle with noisy supervision under domain shift. We present a new SFDA framework that leverages Hard Sample Selection and Denoised Patch Mixing to progressively align target distributions. First, unlabeled images are partitioned into reliable and unreliable subsets through entropy-similarity analysis, allowing adaptation to start from easy samples and gradually incorporate harder ones. Next, pseudo-labels are refined via Monte Carlo-based denoising masks, which suppress unreliable pixels and stabilize training. Finally, intra- and inter-domain objectives mix patches between subsets, transferring reliable semantics while mitigating noise. Experiments on benchmark datasets show consistent gains over prior SFDA and UDA methods, delivering more accurate boundary delineation and achieving state-of-the-art Dice and ASSD scores. Our study highlights the importance of progressive adaptation and denoised supervision for robust segmentation under domain shift. --- ### Cost-Sensitive Unbiased Risk Estimation for Multi-Class Positive-Unlabeled Learning Authors: Miao Zhang, Junpeng Li, Changchun Hua, Yana Yang Published: 2025-10-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.25226v1 Positive--Unlabeled (PU) learning considers settings in which only positive and unlabeled data are available, while negatives are missing or left unlabeled. This situation is common in real applications where annotating reliable negatives is difficult or costly. Despite substantial progress in PU learning, the multi-class case (MPU) remains challenging: many existing approaches do not ensure \emph{unbiased risk estimation}, which limits performance and stability. We propose a cost-sensitive multi-class PU method based on \emph{adaptive loss weighting}. Within the empirical risk minimization framework, we assign distinct, data-dependent weights to the positive and \emph{inferred-negative} (from the unlabeled mixture) loss components so that the resulting empirical objective is an unbiased estimator of the target risk. We formalize the MPU data-generating process and establish a generalization error bound for the proposed estimator. Extensive experiments on \textbf{eight} public datasets, spanning varying class priors and numbers of classes, show consistent gains over strong baselines in both accuracy and stability. --- ### ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation Authors: Ziyi Liu, Bahar Sarrafzadeh, Pei Zhou, Longqi Yang, Jieyu Zhao, Ashish Sharma Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25224v3 While Large Language Models (LLMs) are increasingly used in agentic frameworks to assist individual users, there is a growing need for agents that can proactively manage complex, multi-party collaboration. Systematic evaluation methods for such proactive agents remain scarce, limiting progress in developing AI that can effectively support multiple people together. Negotiation offers a demanding testbed for this challenge, requiring socio-cognitive intelligence to navigate conflicting interests between multiple participants and multiple topics and build consensus. Here, we present ProMediate, the first framework for evaluating proactive AI mediator agents in complex, multi-topic, multi-party negotiations. ProMediate consists of two core components: (i) a simulation testbed based on realistic negotiation cases and theory-driven difficulty levels (ProMediate-Easy, ProMediate-Medium, and ProMediate-Hard), with a plug-and-play proactive AI mediator grounded in socio-cognitive mediation theories, capable of flexibly deciding when and how to intervene; and (ii) a socio-cognitive evaluation framework with a new suite of metrics to measure consensus changes, intervention latency, mediator effectiveness, and intelligence. Together, these components establish a systematic framework for assessing the socio-cognitive intelligence of proactive AI agents in multi-party settings. Our results show that a socially intelligent mediator agent outperforms a generic baseline, via faster, better-targeted interventions. In the ProMediate-Hard setting, our social mediator increases consensus change by 3.6 percentage points compared to the generic baseline (10.65\% vs 7.01\%) while being 77\% faster in response (15.98s vs. 3.71s). In conclusion, ProMediate provides a rigorous, theory-grounded testbed to advance the development of proactive, socially intelligent agents. --- ### FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Data Authors: Kun Ouyang, Haoyu Wang, Dong Fang Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25223v3 Event log data, recording fine-grained user actions and system events, represent one of the most valuable assets for modern digital services. However, the complexity and heterogeneity of industrial event logs--characterized by large scale, high dimensionality, diverse data types, and intricate temporal or relational structures--make feature engineering extremely challenging. Existing automatic feature engineering approaches, such as AutoML or genetic methods, often suffer from limited explainability, rigid predefined operations, and poor adaptability to complicated heterogeneous data. In this paper, we propose FELA (Feature Engineering LLM Agents), a multi-agent evolutionary system that autonomously extracts meaningful and high-performing features from complex industrial event log data. FELA integrates the reasoning and coding capabilities of large language models (LLMs) with an insight-guided self-evolution paradigm. Specifically, FELA employs specialized agents--Idea Agents, Code Agents, and Critic Agents--to collaboratively generate, validate, and implement novel feature ideas. An Evaluation Agent summarizes feedback and updates a hierarchical knowledge base and dual-memory system to enable continual improvement. Moreover, FELA introduces an agentic evolution algorithm, combining reinforcement learning and genetic algorithm principles to balance exploration and exploitation across the idea space. Extensive experiments on real industrial datasets demonstrate that FELA can generate explainable, domain-relevant features that significantly improve model performance while reducing manual effort. Our results highlight the potential of LLM-based multi-agent systems as a general framework for automated, interpretable, and adaptive feature engineering in complex real-world environments. --- ### MSF-Net: Multi-Stage Feature Extraction and Fusion for Robust Photometric Stereo Authors: Shiyu Qin, Zhihao Cai, Kaixuan Wang, Lin Qi, Junyu Dong Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25221v1 Photometric stereo is a technique aimed at determining surface normals through the utilization of shading cues derived from images taken under different lighting conditions. However, existing learning-based approaches often fail to accurately capture features at multiple stages and do not adequately promote interaction between these features. Consequently, these models tend to extract redundant features, especially in areas with intricate details such as wrinkles and edges. To tackle these issues, we propose MSF-Net, a novel framework for extracting information at multiple stages, paired with selective update strategy, aiming to extract high-quality feature information, which is critical for accurate normal construction. Additionally, we have developed a feature fusion module to improve the interplay among different features. Experimental results on the DiLiGenT benchmark show that our proposed MSF-Net significantly surpasses previous state-of-the-art methods in the accuracy of surface normal estimation. --- ### GReF: A Unified Generative Framework for Efficient Reranking via Ordered Multi-token Prediction Authors: Zhijie Lin, Zhuofeng Li, Chenglei Dai, Wentian Bao, Shuai Lin, Enyun Yu, Haoxiang Zhang, Liang Zhao Published: 2025-10-29 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.25220v1 In a multi-stage recommendation system, reranking plays a crucial role in modeling intra-list correlations among items. A key challenge lies in exploring optimal sequences within the combinatorial space of permutations. Recent research follows a two-stage (generator-evaluator) paradigm, where a generator produces multiple feasible sequences, and an evaluator selects the best one. In practice, the generator is typically implemented as an autoregressive model. However, these two-stage methods face two main challenges. First, the separation of the generator and evaluator hinders end-to-end training. Second, autoregressive generators suffer from inference efficiency. In this work, we propose a Unified Generative Efficient Reranking Framework (GReF) to address the two primary challenges. Specifically, we introduce Gen-Reranker, an autoregressive generator featuring a bidirectional encoder and a dynamic autoregressive decoder to generate causal reranking sequences. Subsequently, we pre-train Gen-Reranker on the item exposure order for high-quality parameter initialization. To eliminate the need for the evaluator while integrating sequence-level evaluation during training for end-to-end optimization, we propose post-training the model through Rerank-DPO. Moreover, for efficient autoregressive inference, we introduce ordered multi-token prediction (OMTP), which trains Gen-Reranker to simultaneously generate multiple future items while preserving their order, ensuring practical deployment in real-time recommender systems. Extensive offline experiments demonstrate that GReF outperforms state-of-the-art reranking methods while achieving latency that is nearly comparable to non-autoregressive models. Additionally, GReF has also been deployed in a real-world video app Kuaishou with over 300 million daily active users, significantly improving online recommendation quality. --- ### A Benchmark Suite for Multi-Objective Optimization in Battery Thermal Management System Design Authors: Kaichen Ouyang, Yezhi Xia Published: 2025-10-29 Categories: cs.NE arXiv: https://arxiv.org/abs/2510.25219v1 Synthetic Benchmark Problems (SBPs) are commonly used to evaluate the performance of metaheuristic algorithms. However, these SBPs often contain various unrealistic properties, potentially leading to underestimation or overestimation of algorithmic performance. While several benchmark suites comprising real-world problems have been proposed for various types of metaheuristics, a notable gap exists for Constrained Multi-objective Optimization Problems (CMOPs) derived from practical engineering applications, particularly in the domain of Battery Thermal Management System (BTMS) design. To address this gap, this study develops and presents a specialized benchmark suite for multi-objective optimization in BTMS. This suite comprises a diverse collection of real-world constrained problems, each defined via accurate surrogate models based on recent research to efficiently represent complex thermal-fluid interactions. The primary goal of this benchmark suite is to provide a practical and relevant testing ground for evolutionary algorithms and optimization methods focused on energy storage thermal management. Future work will involve establishing comprehensive baseline results using state-of-the-art algorithms, conducting comparative analyses, and developing a standardized ranking scheme to facilitate robust performance assessment. --- ### Human Resilience in the AI Era -- What Machines Can't Replace Authors: Shaoshan Liu, Anina Schwarzenbach, Yiyu Shi Published: 2025-10-29 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2510.25218v2 AI is changing work and decision making faster than many institutions can adapt their operating practices. We argue that this adaptation gap makes human resilience a core capability for the AI era. We define resilience as the capacity to absorb disruption while preserving effective action and human agency around core purposes. The framework operates at three interacting levels. Psychological resilience keeps a person goal-directed under stress. Social resilience makes trusted support and correction available across a group. Organizational resilience turns detected problems into learning and recovery. We connect established resilience and technostress research with direct AI-in-the-loop experiments. General resilience is trainable, while AI-specific causal evidence is still emerging. Direct AI studies show that assistance can raise productivity and spread expertise. Other experiments show improved expressed empathy and more calibrated reliance. We translate these findings into a practical agenda for AI education, workplace design, governance, and evaluation. The central proposal is socio-technical: structural safeguards define the operating boundary, while resilient people and institutions provide adaptive capacity when conditions change. --- ### U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching Authors: Junsheng Zhou, Xingyu Shi, Haichuan Song, Yi Fang, Yu-Shen Liu, Zhizhong Han Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25210v1 Point clouds captured by scanning sensors are often perturbed by noise, which have a highly negative impact on downstream tasks (e.g. surface reconstruction and shape understanding). Previous works mostly focus on training neural networks with noisy-clean point cloud pairs for learning denoising priors, which requires extensively manual efforts. In this work, we introduce U-CAN, an Unsupervised framework for point cloud denoising with Consistency-Aware Noise2Noise matching. Specifically, we leverage a neural network to infer a multi-step denoising path for each point of a shape or scene with a noise to noise matching scheme. We achieve this by a novel loss which enables statistical reasoning on multiple noisy point cloud observations. We further introduce a novel constraint on the denoised geometry consistency for learning consistency-aware denoising patterns. We justify that the proposed constraint is a general term which is not limited to 3D domain and can also contribute to the area of 2D image denoising. Our evaluations under the widely used benchmarks in point cloud denoising, upsampling and image denoising show significant improvement over the state-of-the-art unsupervised methods, where U-CAN also produces comparable results with the supervised methods. --- ### Selective Learning for Deep Time Series Forecasting Authors: Yisong Fu, Zezhi Shao, Chengqing Yu, Yujie Li, Zhulin An, Qi Wang, Yongjun Xu, Fei Wang Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25207v1 Benefiting from high capacity for capturing complex temporal patterns, deep learning (DL) has significantly advanced time series forecasting (TSF). However, deep models tend to suffer from severe overfitting due to the inherent vulnerability of time series to noise and anomalies. The prevailing DL paradigm uniformly optimizes all timesteps through the MSE loss and learns those uncertain and anomalous timesteps without difference, ultimately resulting in overfitting. To address this, we propose a novel selective learning strategy for deep TSF. Specifically, selective learning screens a subset of the whole timesteps to calculate the MSE loss in optimization, guiding the model to focus on generalizable timesteps while disregarding non-generalizable ones. Our framework introduces a dual-mask mechanism to target timesteps: (1) an uncertainty mask leveraging residual entropy to filter uncertain timesteps, and (2) an anomaly mask employing residual lower bound estimation to exclude anomalous timesteps. Extensive experiments across eight real-world datasets demonstrate that selective learning can significantly improve the predictive performance for typical state-of-the-art deep models, including 37.4% MSE reduction for Informer, 8.4% for TimesNet, and 6.5% for iTransformer. --- ### RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models Authors: Tianqianjin Lin, Xi Zhao, Xingyao Zhang, Rujiao Long, Yi Xu, Zhuoren Jiang, Wenbo Su, Bo Zheng Published: 2025-10-29 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.25206v1 Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For tasks beyond the LLM's current competence, such reasoning path can be hard to sample, and learning risks reinforcing familiar but suboptimal reasoning. We are motivated by the insight from cognitive science that Why is this the answer is often an easier question than What is the answer, as it avoids the heavy cognitive load of open-ended exploration, opting instead for explanatory reconstruction-systematically retracing the reasoning that links a question to its answer. We show that LLMs can similarly leverage answers to derive high-quality reasoning paths. We formalize this phenomenon and prove that conditioning on answer provably increases the expected utility of sampled reasoning paths, thereby transforming intractable problems into learnable ones. Building on this insight, we introduce RAVR (Reference-Answer-guided Variational Reasoning), an end-to-end framework that uses answer-conditioned reasoning as a variational surrogate for question-only reasoning. Experiments in both general and math domains demonstrate consistent improvements over strong baselines. We further analyze the reasoning behavior and find that RAVR reduces hesitation, strengthens conclusion consolidation, and promotes problem-specific strategies in reasoning. --- ### Energy-Efficient Autonomous Driving with Adaptive Perception and Robust Decision Authors: Yuyang Xia, Zibo Liang, Liwei Deng, Yan Zhao, Han Su, Kai Zheng Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25205v1 Autonomous driving is an emerging technology that is expected to bring significant social, economic, and environmental benefits. However, these benefits come with rising energy consumption by computation engines, limiting the driving range of vehicles, especially electric ones. Perception computing is typically the most power-intensive component, as it relies on largescale deep learning models to extract environmental features. Recently, numerous studies have employed model compression techniques, such as sparsification, quantization, and distillation, to reduce computational consumption. However, these methods often result in either a substantial model size or a significant drop in perception accuracy compared to high-computation models. To address these challenges, we propose an energy-efficient autonomous driving framework, called EneAD. In the adaptive perception module, a perception optimization strategy is designed from the perspective of data management and tuning. Firstly, we manage multiple perception models with different computational consumption and adjust the execution framerate dynamically. Then, we define them as knobs and design a transferable tuning method based on Bayesian optimization to identify promising knob values that achieve low computation while maintaining desired accuracy. To adaptively switch the knob values in various traffic scenarios, a lightweight classification model is proposed to distinguish the perception difficulty in different scenarios. In the robust decision module, we propose a decision model based on reinforcement learning and design a regularization term to enhance driving stability in the face of perturbed perception results. Extensive experiments evidence the superiority of our framework in both energy consumption and driving performance. EneAD can reduce perception consumption by 1.9x to 3.5x and thus improve driving range by 3.9% to 8.5% --- ### AI-Powered Early Detection of Critical Diseases using Image Processing and Audio Analysis Authors: Manisha More, Kavya Bhand, Kaustubh Mukdam, Kavya Sharma, Manas Kawtikwar, Hridayansh Kaware, Prajwal Kavhar Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25199v1 Early diagnosis of critical diseases can significantly improve patient survival and reduce treatment costs. However, existing diagnostic techniques are often costly, invasive, and inaccessible in low-resource regions. This paper presents a multimodal artificial intelligence (AI) diagnostic framework integrating image analysis, thermal imaging, and audio signal processing for early detection of three major health conditions: skin cancer, vascular blood clots, and cardiopulmonary abnormalities. A fine-tuned MobileNetV2 convolutional neural network was trained on the ISIC 2019 dataset for skin lesion classification, achieving 89.3% accuracy, 91.6% sensitivity, and 88.2% specificity. A support vector machine (SVM) with handcrafted features was employed for thermal clot detection, achieving 86.4% accuracy (AUC = 0.89) on synthetic and clinical data. For cardiopulmonary analysis, lung and heart sound datasets from PhysioNet and Pascal were processed using Mel-Frequency Cepstral Coefficients (MFCC) and classified via Random Forest, reaching 87.2% accuracy and 85.7% sensitivity. Comparative evaluation against state-of-the-art models demonstrates that the proposed system achieves competitive results while remaining lightweight and deployable on low-cost devices. The framework provides a promising step toward scalable, real-time, and accessible AI-based pre-diagnostic healthcare solutions. --- ### Testing Cross-Lingual Text Comprehension In LLMs Using Next Sentence Prediction Authors: Ritesh Sunil Chavan, Jack Mostow Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25187v1 While large language models are trained on massive datasets, this data is heavily skewed towards English. Does their impressive performance reflect genuine ability or just this data advantage? To find out, we tested them in a setting where they could not rely on data abundance: low-resource languages. Building on prior work Agarwal et al. (2025) that used Next Sentence Prediction (NSP) as a test, we created a large-scale benchmark with 10,000 questions each for English (a high-resource language), Swahili (medium-resource), and Hausa (low-resource). We then tested several top models, including GPT-4 Turbo, Gemini 1.5 Flash, and LLaMA 3 70B, to see how their performance holds up. The results painted a clear picture of how levels of language resources impact outcomes. While all models excelled in English, their accuracy dropped in Swahili and fell sharply in Hausa, with LLaMA 3 struggling the most. The story became even more interesting when we introduced Chain-of-Thought (CoT) prompting. For the struggling LLaMA 3, CoT acted as a helpful guide, significantly boosting its accuracy. However, for the more capable GPT-4 and Gemini, the same technique often backfired, leading to a kind of "overthinking" that hurt their results in the cross-lingual context. This reveals that Chain-of-Thought is not a universal solution; its effectiveness depends heavily on the model's baseline capability and the specific context of the task. Our framework pinpoints LLM weaknesses, highlights when CoT helps or hinders cross-lingual NSP performance, and factors influencing their decisions. --- ### Mask-Robust Face Verification for Online Learning via YOLOv5 and Residual Networks Authors: Zhifeng Wang, Minghui Wang, Chunyan Zeng, Jialong Yao, Yang Yang, Hongmin Xu Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25184v1 In the contemporary landscape, the fusion of information technology and the rapid advancement of artificial intelligence have ushered school education into a transformative phase characterized by digitization and heightened intelligence. Concurrently, the global paradigm shift caused by the Covid-19 pandemic has catalyzed the evolution of e-learning, accentuating its significance. Amidst these developments, one pivotal facet of the online education paradigm that warrants attention is the authentication of identities within the digital learning sphere. Within this context, our study delves into a solution for online learning authentication, utilizing an enhanced convolutional neural network architecture, specifically the residual network model. By harnessing the power of deep learning, this technological approach aims to galvanize the ongoing progress of online education, while concurrently bolstering its security and stability. Such fortification is imperative in enabling online education to seamlessly align with the swift evolution of the educational landscape. This paper's focal proposition involves the deployment of the YOLOv5 network, meticulously trained on our proprietary dataset. This network is tasked with identifying individuals' faces culled from images captured by students' open online cameras. The resultant facial information is then channeled into the residual network to extract intricate features at a deeper level. Subsequently, a comparative analysis of Euclidean distances against students' face databases is performed, effectively ascertaining the identity of each student. --- ### Fed-PELAD: Communication-Efficient Federated Learning for Massive MIMO CSI Feedback with Personalized Encoders and a LoRA-Adapted Shared Decoder Authors: Yixiang Zhou, Tong Wu, Meixia Tao, Jianhua Mo Published: 2025-10-29 Categories: cs.IT, cs.AI arXiv: https://arxiv.org/abs/2510.25181v1 This paper addresses the critical challenges of communication overhead, data heterogeneity, and privacy in deep learning for channel state information (CSI) feedback in massive MIMO systems. To this end, we propose Fed-PELAD, a novel federated learning framework that incorporates personalized encoders and a LoRA-adapted shared decoder. Specifically, personalized encoders are trained locally on each user equipment (UE) to capture device-specific channel characteristics, while a shared decoder is updated globally via the coordination of the base station (BS) by using Low-Rank Adaptation (LoRA). This design ensures that only compact LoRA adapter parameters instead of full model updates are transmitted for aggregation. To further enhance convergence stability, we introduce an alternating freezing strategy with calibrated learning-rate ratio during LoRA aggregation. Extensive simulations on 3GPP-standard channel models demonstrate that Fed-PELAD requires only 42.97\% of the uplink communication cost compared to conventional methods while achieving a performance gain of 1.2 dB in CSI feedback accuracy under heterogeneous conditions. --- ### Agentic Moderation: Multi-Agent Design for Safer Vision-Language Models Authors: Juan Ren, Mark Dras, Usman Naseem Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25179v1 Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety alignment by introducing Agentic Moderation, a model-agnostic framework that leverages specialised agents to defend multimodal systems against jailbreak attacks. Unlike prior approaches that apply as a static layer over inputs or outputs and provide only binary classifications (safe or unsafe), our method integrates dynamic, cooperative agents, including Shield, Responder, Evaluator, and Reflector, to achieve context-aware and interpretable moderation. Extensive experiments across five datasets and four representative Large Vision-Language Models (LVLMs) demonstrate that our approach reduces the Attack Success Rate (ASR) by 7-19%, maintains a stable Non-Following Rate (NF), and improves the Refusal Rate (RR) by 4-20%, achieving robust, interpretable, and well-balanced safety performance. By harnessing the flexibility and reasoning capacity of agentic architectures, Agentic Moderation provides modular, scalable, and fine-grained safety enforcement, highlighting the broader potential of agentic systems as a foundation for automated safety governance. --- ### Machine Learning and CPU (Central Processing Unit) Scheduling Co-Optimization over a Network of Computing Centers Authors: Mohammadreza Doostmohammadian, Zulfiya R. Gabidullina, Hamid R. Rabiee Published: 2025-10-29 Categories: cs.LG, cs.DC, cs.MA, eess.SY, math.OC arXiv: https://arxiv.org/abs/2510.25176v1 In the rapidly evolving research on artificial intelligence (AI) the demand for fast, computationally efficient, and scalable solutions has increased in recent years. The problem of optimizing the computing resources for distributed machine learning (ML) and optimization is considered in this paper. Given a set of data distributed over a network of computing-nodes/servers, the idea is to optimally assign the CPU (central processing unit) usage while simultaneously training each computing node locally via its own share of data. This formulates the problem as a co-optimization setup to (i) optimize the data processing and (ii) optimally allocate the computing resources. The information-sharing network among the nodes might be time-varying, but with balanced weights to ensure consensus-type convergence of the algorithm. The algorithm is all-time feasible, which implies that the computing resource-demand balance constraint holds at all iterations of the proposed solution. Moreover, the solution allows addressing possible log-scale quantization over the information-sharing channels to exchange log-quantized data. For some example applications, distributed support-vector-machine (SVM) and regression are considered as the ML training models. Results from perturbation theory, along with Lyapunov stability and eigen-spectrum analysis, are used to prove the convergence towards the optimal case. As compared to existing CPU scheduling solutions, the proposed algorithm improves the cost optimality gap by more than $50\%$. --- ### Test-Time Adaptive Object Detection with Foundation Model Authors: Yingjie Gao, Yanan Zhang, Zhi Cai, Di Huang Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25175v1 In recent years, test-time adaptive object detection has attracted increasing attention due to its unique advantages in online domain adaptation, which aligns more closely with real-world application scenarios. However, existing approaches heavily rely on source-derived statistical characteristics while making the strong assumption that the source and target domains share an identical category space. In this paper, we propose the first foundation model-powered test-time adaptive object detection method that eliminates the need for source data entirely and overcomes traditional closed-set limitations. Specifically, we design a Multi-modal Prompt-based Mean-Teacher framework for vision-language detector-driven test-time adaptation, which incorporates text and visual prompt tuning to adapt both language and vision representation spaces on the test data in a parameter-efficient manner. Correspondingly, we propose a Test-time Warm-start strategy tailored for the visual prompts to effectively preserve the representation capability of the vision branch. Furthermore, to guarantee high-quality pseudo-labels in every test batch, we maintain an Instance Dynamic Memory (IDM) module that stores high-quality pseudo-labels from previous test samples, and propose two novel strategies-Memory Enhancement and Memory Hallucination-to leverage IDM's high-quality instances for enhancing original predictions and hallucinating images without available pseudo-labels, respectively. Extensive experiments on cross-corruption and cross-dataset benchmarks demonstrate that our method consistently outperforms previous state-of-the-art methods, and can adapt to arbitrary cross-domain and cross-category target data. Code is available at https://github.com/gaoyingjay/ttaod_foundation. --- ### Classifier Enhancement Using Extended Context and Domain Experts for Semantic Segmentation Authors: Huadong Tang, Youpeng Zhao, Min Xu, Jun Wang, Qiang Wu Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25174v1 Prevalent semantic segmentation methods generally adopt a vanilla classifier to categorize each pixel into specific classes. Although such a classifier learns global information from the training data, this information is represented by a set of fixed parameters (weights and biases). However, each image has a different class distribution, which prevents the classifier from addressing the unique characteristics of individual images. At the dataset level, class imbalance leads to segmentation results being biased towards majority classes, limiting the model's effectiveness in identifying and segmenting minority class regions. In this paper, we propose an Extended Context-Aware Classifier (ECAC) that dynamically adjusts the classifier using global (dataset-level) and local (image-level) contextual information. Specifically, we leverage a memory bank to learn dataset-level contextual information of each class, incorporating the class-specific contextual information from the current image to improve the classifier for precise pixel labeling. Additionally, a teacher-student network paradigm is adopted, where the domain expert (teacher network) dynamically adjusts contextual information with ground truth and transfers knowledge to the student network. Comprehensive experiments illustrate that the proposed ECAC can achieve state-of-the-art performance across several datasets, including ADE20K, COCO-Stuff10K, and Pascal-Context. --- ### D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction Authors: Kejing Xia, Jidong Jia, Ke Jin, Yucai Bai, Li Sun, Dacheng Tao, Youjian Zhang Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25173v2 Recently, Gaussian Splatting (GS) has shown great potential for urban scene reconstruction in the field of autonomous driving. However, current urban scene reconstruction methods often depend on multimodal sensors as inputs, \textit{i.e.} LiDAR and images. Though the geometry prior provided by LiDAR point clouds can largely mitigate ill-posedness in reconstruction, acquiring such accurate LiDAR data is still challenging in practice: i) precise spatiotemporal calibration between LiDAR and other sensors is required, as they may not capture data simultaneously; ii) reprojection errors arise from spatial misalignment when LiDAR and cameras are mounted at different locations. To avoid the difficulty of acquiring accurate LiDAR depth, we propose D$^2$GS, a LiDAR-free urban scene reconstruction framework. In this work, we obtain geometry priors that are as effective as LiDAR while being denser and more accurate. $\textbf{First}$, we initialize a dense point cloud by back-projecting multi-view metric depth predictions. This point cloud is then optimized by a Progressive Pruning strategy to improve the global consistency. $\textbf{Second}$, we jointly refine Gaussian geometry and predicted dense metric depth via a Depth Enhancer. Specifically, we leverage diffusion priors from a depth foundation model to enhance the depth maps rendered by Gaussians. In turn, the enhanced depths provide stronger geometric constraints during Gaussian training. $\textbf{Finally}$, we improve the accuracy of ground geometry by constraining the shape and normal attributes of Gaussians within road regions. Extensive experiments on the Waymo dataset demonstrate that our method consistently outperforms state-of-the-art methods, producing more accurate geometry even when compared with those using ground-truth LiDAR data. --- ### A Study on Inference Latency for Vision Transformers on Mobile Devices Authors: Zhuojin Li, Marco Paolieri, Leana Golubchik Published: 2025-10-29 Categories: cs.CV, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2510.25166v2 Given the significant advances in machine learning techniques on mobile devices, particularly in the domain of computer vision, in this work we quantitatively study the performance characteristics of 190 real-world vision transformers (ViTs) on mobile devices. Through a comparison with 102 real-world convolutional neural networks (CNNs), we provide insights into the factors that influence the latency of ViT architectures on mobile devices. Based on these insights, we develop a dataset including measured latencies of 1000 synthetic ViTs with representative building blocks and state-of-the-art architectures from two machine learning frameworks and six mobile platforms. Using this dataset, we show that inference latency of new ViTs can be predicted with sufficient accuracy for real-world applications. --- ### Transformers in Medicine: Improving Vision-Language Alignment for Medical Image Captioning Authors: Yogesh Thakku Suresh, Vishwajeet Shivaji Hogale, Luca-Alexandru Zamfira, Anandavardhana Hegde Published: 2025-10-29 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.25164v2 We present a transformer-based multimodal framework for generating clinically relevant captions for MRI scans. Our system combines a DEiT-Small vision transformer as an image encoder, MediCareBERT for caption embedding, and a custom LSTM-based decoder. The architecture is designed to semantically align image and textual embeddings, using hybrid cosine-MSE loss and contrastive inference via vector similarity. We benchmark our method on the MultiCaRe dataset, comparing performance on filtered brain-only MRIs versus general MRI images against state-of-the-art medical image captioning methods including BLIP, R2GenGPT, and recent transformer-based approaches. Results show that focusing on domain-specific data improves caption accuracy and semantic alignment. Our work proposes a scalable, interpretable solution for automated medical image reporting. --- ### Target-Guided Bayesian Flow Networks for Quantitatively Constrained CAD Generation Authors: Wenhao Zheng, Chenwei Sun, Wenbo Zhang, Jiancheng Lv, Xianggen Liu Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25163v1 Deep generative models, such as diffusion models, have shown promising progress in image generation and audio generation via simplified continuity assumptions. However, the development of generative modeling techniques for generating multi-modal data, such as parametric CAD sequences, still lags behind due to the challenges in addressing long-range constraints and parameter sensitivity. In this work, we propose a novel framework for quantitatively constrained CAD generation, termed Target-Guided Bayesian Flow Network (TGBFN). For the first time, TGBFN handles the multi-modality of CAD sequences (i.e., discrete commands and continuous parameters) in a unified continuous and differentiable parameter space rather than in the discrete data space. In addition, TGBFN penetrates the parameter update kernel and introduces a guided Bayesian flow to control the CAD properties. To evaluate TGBFN, we construct a new dataset for quantitatively constrained CAD generation. Extensive comparisons across single-condition and multi-condition constrained generation tasks demonstrate that TGBFN achieves state-of-the-art performance in generating high-fidelity, condition-aware CAD sequences. The code is available at https://github.com/scu-zwh/TGBFN. --- ### Model-Document Protocol for AI Search Authors: Hongjin Qian, Zheng Liu Published: 2025-10-29 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2510.25160v2 AI search depends on linking large language models (LLMs) with vast external knowledge sources. Yet web pages, PDF files, and other raw documents are not inherently LLM-ready: they are long, noisy, and unstructured. Conventional retrieval methods treat these documents as verbatim text and return raw passages, leaving the burden of fragment assembly and contextual reasoning to the LLM. This gap underscores the need for a new retrieval paradigm that redefines how models interact with documents. We introduce the Model-Document Protocol (MDP), a general framework that formalizes how raw text is bridged to LLMs through consumable knowledge representations. Rather than treating retrieval as passage fetching, MDP defines multiple pathways that transform unstructured documents into task-specific, LLM-ready inputs. These include agentic reasoning, which curates raw evidence into coherent context; memory grounding, which accumulates reusable notes to enrich reasoning; and structured leveraging, which encodes documents into formal representations such as graphs or key-value caches. All three pathways share the same goal: ensuring that what reaches the LLM is not raw fragments but compact, structured knowledge directly consumable for reasoning. As an instantiation, we present MDP-Agent, which realizes the protocol through an agentic process: constructing document-level gist memories for global coverage, performing diffusion-based exploration with vertical exploitation to uncover layered dependencies, and applying map-reduce style synthesis to integrate large-scale evidence into compact yet sufficient context. Experiments on information-seeking benchmarks demonstrate that MDP-Agent outperforms baselines, validating both the soundness of the MDP framework and the effectiveness of its agentic instantiation. --- ### Towards Real-Time Inference of Thin Liquid Film Thickness Profiles from Interference Patterns Using Vision Transformers Authors: Gautam A. Viruthagiri, Arnuv Tandon, Gerald G. Fuller, Vinny Chandran Suja Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25157v1 Thin film interferometry is a powerful technique for non-invasively measuring liquid film thickness with applications in ophthalmology, but its clinical translation is hindered by the challenges in reconstructing thickness profiles from interference patterns - an ill-posed inverse problem complicated by phase periodicity, imaging noise and ambient artifacts. Traditional reconstruction methods are either computationally intensive, sensitive to noise, or require manual expert analysis, which is impractical for real-time diagnostics. To address this challenge, here we present a vision transformer-based approach for real-time inference of thin liquid film thickness profiles directly from isolated interferograms. Trained on a hybrid dataset combining physiologically-relevant synthetic and experimental tear film data, our model leverages long-range spatial correlations to resolve phase ambiguities and reconstruct temporally coherent thickness profiles in a single forward pass from dynamic interferograms acquired in vivo and ex vivo. The network demonstrates state-of-the-art performance on noisy, rapidly-evolving films with motion artifacts, overcoming limitations of conventional phase-unwrapping and iterative fitting methods. Our data-driven approach enables automated, consistent thickness reconstruction at real-time speeds on consumer hardware, opening new possibilities for continuous monitoring of pre-lens ocular tear films and non-invasive diagnosis of conditions such as the dry eye disease. --- ### TabMGP: Martingale Posterior with TabPFN Authors: Kenyon Ng, Edwin Fong, David T. Frazier, Jeremias Knoblauch, Susan Wei Published: 2025-10-29 Categories: stat.ME, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2510.25154v3 Bayesian inference provides principled uncertainty quantification but is often limited by the challenges of prior and likelihood elicitation. The martingale posterior (MGP) (Fong et al., 2023) offers an alternative by replacing these requirements with a predictive rule. In addition, the MGP focuses inference on parameters defined through a loss function. This framework is especially resonant in the era of foundation transformers; practitioners increasingly leverage models like TabPFN for their state-of-the-art capabilities, yet often require epistemic uncertainty for a scientific estimand $θ$ that need not parameterise the implicit latent model. The MGP provides a mechanism to recover these posterior distributions. We introduce TabMGP, an MGP built on TabPFN for tabular data. TabMGP produces credible sets with near-nominal coverage and often outperforms both handcrafted MGP constructions and standard Bayesian baselines. --- ### Explainable Disentanglement on Discrete Speech Representations for Noise-Robust ASR Authors: Shreyas Gopal, Ashutosh Anshul, Haoyang Li, Yue Heng Yeo, Hexin Liu, Eng Siong Chng Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25150v1 Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works that quantize Whisper embeddings for speech-to-unit modeling, we propose disentangling semantic speech content from background noise in the latent space. Our end-to-end model separates clean speech in the form of codebook tokens, while extracting interpretable noise vectors as quantization residue which are supervised via a lightweight classifier. We show that our approach improves alignment between clean/noisy speech and text, producing speech tokens that display a high degree of noiseinvariance, and improves ASR performance. Keeping Whisper frozen, we show an 82% reduction in error rate compared to Whisper, and 35% improvement over baseline methods on the VBDemand test set. Further analyses show that the learned token space generalizes well to both seen and unseen acoustic conditions. --- ### Machine Learning Guided Optimal Transmission Switching to Mitigate Wildfire Ignition Risk Authors: Weimin Huang, Ryan Piansky, Bistra Dilkina, Daniel K. Molzahn Published: 2025-10-29 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2510.25147v3 To mitigate acute wildfire ignition risks, utilities de-energize power lines in high-risk areas. The Optimal Power Shutoff (OPS) problem optimizes line energization statuses to manage wildfire ignition risks through de-energizations while reducing load shedding. OPS problems are computationally challenging Mixed-Integer Linear Programs (MILPs) that must be solved rapidly and frequently in operational settings. For a particular power system, OPS instances share a common structure with varying parameters related to wildfire risks, loads, and renewable generation. This motivates the use of Machine Learning (ML) for solving OPS problems by exploiting shared patterns across instances. In this paper, we develop an ML-guided framework that quickly produces high-quality de-energization decisions by extending existing ML-guided MILP solution methods while integrating domain knowledge on the number of energized and de-energized lines. Results on a large-scale realistic California-based synthetic test system show that the proposed ML-guided method produces high-quality solutions faster than traditional optimization methods. --- ### EA3D: Online Open-World 3D Object Extraction from Streaming Videos Authors: Xiaoyu Zhou, Jingqi Wang, Yuang Jia, Yongtao Wang, Deqing Sun, Ming-Hsuan Yang Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25146v1 Current 3D scene understanding methods are limited by offline-collected multi-view data or pre-constructed 3D geometry. In this paper, we present ExtractAnything3D (EA3D), a unified online framework for open-world 3D object extraction that enables simultaneous geometric reconstruction and holistic scene understanding. Given a streaming video, EA3D dynamically interprets each frame using vision-language and 2D vision foundation encoders to extract object-level knowledge. This knowledge is integrated and embedded into a Gaussian feature map via a feed-forward online update strategy. We then iteratively estimate visual odometry from historical frames and incrementally update online Gaussian features with new observations. A recurrent joint optimization module directs the model's attention to regions of interest, simultaneously enhancing both geometric reconstruction and semantic understanding. Extensive experiments across diverse benchmarks and tasks, including photo-realistic rendering, semantic and instance segmentation, 3D bounding box and semantic occupancy estimation, and 3D mesh generation, demonstrate the effectiveness of EA3D. Our method establishes a unified and efficient framework for joint online 3D reconstruction and holistic scene understanding, enabling a broad range of downstream tasks. --- ### EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shift Authors: Wan Jiang, Jing Yan, Xiaojing Chen, Lin Shen, Chenhao Lin, Yunfeng Diao, Richang Hong Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25141v2 Diffusion models have recently achieved remarkable photorealism, making it increasingly difficult to distinguish real images from generated ones, raising significant privacy and security concerns. In response, we present a key finding: structural edits enhance the reconstruction of real images while degrading that of generated images, creating a distinctive edit-induced reconstruction error shift. This asymmetric shift enhances the separability between real and generated images. Building on this insight, we propose EIRES, a training-free method that leverages structural edits to reveal inherent differences between real and generated images. To explain the discriminative power of this shift, we derive the reconstruction error lower bound under edit perturbations. Since EIRES requires no training, thresholding depends solely on the natural separability of the signal, where a larger margin yields more reliable detection. Extensive experiments show that EIRES is effective across diverse generative models and remains robust on the unbiased subset, even under post-processing operations. --- ### DINO-YOLO: Self-Supervised Pre-training for Data-Efficient Object Detection in Civil Engineering Applications Authors: Malaisree P, Youwai S, Kitkobsin T, Janrungautai S, Amorndechaphon D, Rojanavasu P Published: 2025-10-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.25140v2 Object detection in civil engineering applications is constrained by limited annotated data in specialized domains. We introduce DINO-YOLO, a hybrid architecture combining YOLOv12 with DINOv3 self-supervised vision transformers for data-efficient detection. DINOv3 features are strategically integrated at two locations: input preprocessing (P0) and mid-backbone enhancement (P3). Experimental validation demonstrates substantial improvements: Tunnel Segment Crack detection (648 images) achieves 12.4% improvement, Construction PPE (1K images) gains 13.7%, and KITTI (7K images) shows 88.6% improvement, while maintaining real-time inference (30-47 FPS). Systematic ablation across five YOLO scales and nine DINOv3 variants reveals that Medium-scale architectures achieve optimal performance with DualP0P3 integration (55.77% mAP@0.5), while Small-scale requires Triple Integration (53.63%). The 2-4x inference overhead (21-33ms versus 8-16ms baseline) remains acceptable for field deployment on NVIDIA RTX 5090. DINO-YOLO establishes state-of-the-art performance for civil engineering datasets (<10K images) while preserving computational efficiency, providing practical solutions for construction safety monitoring and infrastructure inspection in data-constrained environments. --- ### Conditional neural field for spatial dimension reduction of turbulence data: a comparison study Authors: Junyi Guo, Pan Du, Xiantao Fan, Yahui Li, Jian-Xun Wang Published: 2025-10-29 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2510.25135v1 We investigate conditional neural fields (CNFs), mesh-agnostic, coordinate-based decoders conditioned on a low-dimensional latent, for spatial dimensionality reduction of turbulent flows. CNFs are benchmarked against Proper Orthogonal Decomposition and a convolutional autoencoder within a unified encoding-decoding framework and a common evaluation protocol that explicitly separates in-range (interpolative) from out-of-range (strict extrapolative) testing beyond the training horizon, with identical preprocessing, metrics, and fixed splits across all baselines. We examine three conditioning mechanisms: (i) activation-only modulation (often termed FiLM), (ii) low-rank weight and bias modulation (termed FP), and (iii) last-layer inner-product coupling, and introduce a novel domain-decomposed CNF that localizes complexities. Across representative turbulence datasets (WMLES channel inflow, DNS channel inflow, and wall pressure fluctuations over turbulent boundary layers), CNF-FP achieves the lowest training and in-range testing errors, while CNF-FiLM generalizes best for out-of-range scenarios once moderate latent capacity is available. Domain decomposition significantly improves out-of-range accuracy, especially for the more demanding datasets. The study provides a rigorous, physics-aware basis for selecting conditioning, capacity, and domain decomposition when using CNFs for turbulence compression and reconstruction. --- ### Region-CAM: Towards Accurate Object Regions in Class Activation Maps for Weakly Supervised Learning Tasks Authors: Qingdong Cai, Charith Abhayaratne Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25134v1 Class Activation Mapping (CAM) methods are widely applied in weakly supervised learning tasks due to their ability to highlight object regions. However, conventional CAM methods highlight only the most discriminative regions of the target. These highlighted regions often fail to cover the entire object and are frequently misaligned with object boundaries, thereby limiting the performance of downstream weakly supervised learning tasks, particularly Weakly Supervised Semantic Segmentation (WSSS), which demands pixel-wise accurate activation maps to get the best results. To alleviate the above problems, we propose a novel activation method, Region-CAM. Distinct from network feature weighting approaches, Region-CAM generates activation maps by extracting semantic information maps (SIMs) and performing semantic information propagation (SIP) by considering both gradients and features in each of the stages of the baseline classification model. Our approach highlights a greater proportion of object regions while ensuring activation maps to have precise boundaries that align closely with object edges. Region-CAM achieves 60.12% and 58.43% mean intersection over union (mIoU) using the baseline model on the PASCAL VOC training and validation datasets, respectively, which are improvements of 13.61% and 13.13% over the original CAM (46.51% and 45.30%). On the MS COCO validation set, Region-CAM achieves 36.38%, a 16.23% improvement over the original CAM (20.15%). We also demonstrate the superiority of Region-CAM in object localization tasks, using the ILSVRC2012 validation set. Region-CAM achieves 51.7% in Top-1 Localization accuracy Loc1. Compared with LayerCAM, an activation method designed for weakly supervised object localization, Region-CAM achieves 4.5% better performance in Loc1. --- ### EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation Authors: Chao Song, Zhiyuan Liu, Han Huang, Liang Wang, Qiong Wang, Jianyu Shi, Hui Yu, Yihang Zhou, Yang Zhang Published: 2025-10-29 Categories: q-bio.BM, cs.LG arXiv: https://arxiv.org/abs/2510.25132v1 Designing enzyme backbones with substrate-specific functionality is a critical challenge in computational protein engineering. Current generative models excel in protein design but face limitations in binding data, substrate-specific control, and flexibility for de novo enzyme backbone generation. To address this, we introduce EnzyBind, a dataset with 11,100 experimentally validated enzyme-substrate pairs specifically curated from PDBbind. Building on this, we propose EnzyControl, a method that enables functional and substrate-specific control in enzyme backbone generation. Our approach generates enzyme backbones conditioned on MSA-annotated catalytic sites and their corresponding substrates, which are automatically extracted from curated enzyme-substrate data. At the core of EnzyControl is EnzyAdapter, a lightweight, modular component integrated into a pretrained motif-scaffolding model, allowing it to become substrate-aware. A two-stage training paradigm further refines the model's ability to generate accurate and functional enzyme structures. Experiments show that our EnzyControl achieves the best performance across structural and functional metrics on EnzyBind and EnzyBench benchmarks, with particularly notable improvements of 13\% in designability and 13\% in catalytic efficiency compared to the baseline models. The code is released at https://github.com/Vecteur-libre/EnzyControl. --- ### Lipschitz-aware Linearity Grafting for Certified Robustness Authors: Yongjin Han, Suhyun Kim Published: 2025-10-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.25130v2 Lipschitz constant is a fundamental property in certified robustness, as smaller values imply robustness to adversarial examples when a model is confident in its prediction. However, identifying the worst-case adversarial examples is known to be an NP-complete problem. Although over-approximation methods have shown success in neural network verification to address this challenge, reducing approximation errors remains a significant obstacle. Furthermore, these approximation errors hinder the ability to obtain tight local Lipschitz constants, which are crucial for certified robustness. Originally, grafting linearity into non-linear activation functions was proposed to reduce the number of unstable neurons, enabling scalable and complete verification. However, no prior theoretical analysis has explained how linearity grafting improves certified robustness. We instead consider linearity grafting primarily as a means of eliminating approximation errors rather than reducing the number of unstable neurons, since linear functions do not require relaxation. In this paper, we provide two theoretical contributions: 1) why linearity grafting improves certified robustness through the lens of the $l_\infty$ local Lipschitz constant, and 2) grafting linearity into non-linear activation functions, the dominant source of approximation errors, yields a tighter local Lipschitz constant. Based on these theoretical contributions, we propose a Lipschitz-aware linearity grafting method that removes dominant approximation errors, which are crucial for tightening the local Lipschitz constant, thereby improving certified robustness, even without certified training. Our extensive experiments demonstrate that grafting linearity into these influential activations tightens the $l_\infty$ local Lipschitz constant and enhances certified robustness. --- ### AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians Authors: Xiyu Zhang, Chong Bao, Yipeng Chen, Hongjia Zhai, Yitong Dong, Hujun Bao, Zhaopeng Cui, Guofeng Zhang Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25129v1 3D reconstruction of indoor and urban environments is a prominent research topic with various downstream applications. However, existing geometric priors for addressing low-texture regions in indoor and urban settings often lack global consistency. Moreover, Gaussian Splatting and implicit SDF fields often suffer from discontinuities or exhibit computational inefficiencies, resulting in a loss of detail. To address these issues, we propose an Atlanta-world guided implicit-structured Gaussian Splatting that achieves smooth indoor and urban scene reconstruction while preserving high-frequency details and rendering efficiency. By leveraging the Atlanta-world model, we ensure the accurate surface reconstruction for low-texture regions, while the proposed novel implicit-structured GS representations provide smoothness without sacrificing efficiency and high-frequency details. Specifically, we propose a semantic GS representation to predict the probability of all semantic regions and deploy a structure plane regularization with learnable plane indicators for global accurate surface reconstruction. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in both indoor and urban scenes, delivering superior surface reconstruction quality. --- ### An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation Authors: Uzair Akbar, Niki Kilbertus, Hao Shen, Krikamol Muandet, Bo Dai Published: 2025-10-29 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.25128v2 The technique of data augmentation (DA) is often used in machine learning for regularization purposes to better generalize under i.i.d. settings. In this work, we present a unifying framework with topics in causal inference to make a case for the use of DA beyond just the i.i.d. setting, but for generalization across interventions as well. Specifically, we argue that when the outcome generating mechanism is invariant to our choice of DA, then such augmentations can effectively be thought of as interventions on the treatment generating mechanism itself. This can potentially help to reduce bias in causal effect estimation arising from hidden confounders. In the presence of such unobserved confounding we typically make use of instrumental variables (IVs) -- sources of treatment randomization that are conditionally independent of the outcome. However, IVs may not be as readily available as DA for many applications, which is the main motivation behind this work. By appropriately regularizing IV based estimators, we introduce the concept of IV-like (IVL) regression for mitigating confounding bias and improving predictive performance across interventions even when certain IV properties are relaxed. Finally, we cast parameterized DA as an IVL regression problem and show that when used in composition can simulate a worst-case application of such DA, further improving performance on causal estimation and generalization tasks beyond what simple DA may offer. This is shown both theoretically for the population case and via simulation experiments for the finite sample case using a simple linear example. We also present real data experiments to support our case. ---