# Research Papers — 2025-11 · bundle page 27 of 197 > Full-text markdown of papers #1301–1350 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/27 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/26.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/28.md) ### Pessimistic Verification for Open Ended Math Questions Authors: Yanxing Huang, Zihan Tang, Zejin Lin, Peng Li, Yang Liu Published: 2025-11-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.21522v1 The key limitation of the verification performance lies in the ability of error detection. With this intuition we designed several variants of pessimistic verification, which are simple workflows that could significantly improve the verification of open-ended math questions. In pessimistic verification we construct multiple parallel verifications for the same proof, and the proof is deemed incorrect if any one of them reports an error. This simple technique significantly improves the performance across many math verification benchmarks without incurring substantial computational resources. Its token efficiency even surpassed extended long-CoT in test-time scaling. Our case studies further indicate that the majority of false negatives in stronger models are actually caused by annotation errors in the original dataset, so our method's performance is in fact underestimated. Self-verification for mathematical problems can effectively improve the reliability and performance of language model outputs, and it also plays a critical role in enabling long-horizon mathematical tasks. We believe that research on pessimistic verification will help enhance the mathematical capabilities of language models across a wide range of tasks. --- ### Self-Paced Learning for Images of Antinuclear Antibodies Authors: Yiyang Jiang, Guangwu Qian, Jiaxin Wu, Qi Huang, Qing Li, Yongkang Wu, Xiao-Yong Wei Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21519v2 Antinuclear antibody (ANA) testing is a crucial method for diagnosing autoimmune disorders, including lupus, Sjögren's syndrome, and scleroderma. Despite its importance, manual ANA detection is slow, labor-intensive, and demands years of training. ANA detection is complicated by over 100 coexisting antibody types, resulting in vast fluorescent pattern combinations. Although machine learning and deep learning have enabled automation, ANA detection in real-world clinical settings presents unique challenges as it involves multi-instance, multi-label (MIML) learning. In this paper, a novel framework for ANA detection is proposed that handles the complexities of MIML tasks using unaltered microscope images without manual preprocessing. Inspired by human labeling logic, it identifies consistent ANA sub-regions and assigns aggregated labels accordingly. These steps are implemented using three task-specific components: an instance sampler, a probabilistic pseudo-label dispatcher, and self-paced weight learning rate coefficients. The instance sampler suppresses low-confidence instances by modeling pattern confidence, while the dispatcher adaptively assigns labels based on instance distinguishability. Self-paced learning adjusts training according to empirical label observations. Our framework overcomes limitations of traditional MIML methods and supports end-to-end optimization. Extensive experiments on one ANA dataset and three public medical MIML benchmarks demonstrate the superiority of our framework. On the ANA dataset, our model achieves up to +7.0% F1-Macro and +12.6% mAP gains over the best prior method, setting new state-of-the-art results. It also ranks top-2 across all key metrics on public datasets, reducing Hamming loss and one-error by up to 18.2% and 26.9%, respectively. The source code can be accessed at https://github.com/fletcherjiang/ANA-SelfPacedLearning. --- ### Self-Paced Learning for Images of Antinuclear Antibodies Authors: Yiyang Jiang, Guangwu Qian, Jiaxin Wu, Qi Huang, Qing Li, Yongkang Wu, Xiao-Yong Wei Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21519v1 Antinuclear antibody (ANA) testing is a crucial method for diagnosing autoimmune disorders, including lupus, Sjögren's syndrome, and scleroderma. Despite its importance, manual ANA detection is slow, labor-intensive, and demands years of training. ANA detection is complicated by over 100 coexisting antibody types, resulting in vast fluorescent pattern combinations. Although machine learning and deep learning have enabled automation, ANA detection in real-world clinical settings presents unique challenges as it involves multi-instance, multi-label (MIML) learning. In this paper, a novel framework for ANA detection is proposed that handles the complexities of MIML tasks using unaltered microscope images without manual preprocessing. Inspired by human labeling logic, it identifies consistent ANA sub-regions and assigns aggregated labels accordingly. These steps are implemented using three task-specific components: an instance sampler, a probabilistic pseudo-label dispatcher, and self-paced weight learning rate coefficients. The instance sampler suppresses low-confidence instances by modeling pattern confidence, while the dispatcher adaptively assigns labels based on instance distinguishability. Self-paced learning adjusts training according to empirical label observations. Our framework overcomes limitations of traditional MIML methods and supports end-to-end optimization. Extensive experiments on one ANA dataset and three public medical MIML benchmarks demonstrate the superiority of our framework. On the ANA dataset, our model achieves up to +7.0% F1-Macro and +12.6% mAP gains over the best prior method, setting new state-of-the-art results. It also ranks top-2 across all key metrics on public datasets, reducing Hamming loss and one-error by up to 18.2% and 26.9%, respectively. The source code can be accessed at https://github.com/fletcherjiang/ANA-SelfPacedLearning. --- ### Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation Authors: Lina Conti, Dennis Fucci, Marco Gaido, Matteo Negri, Guillaume Wisniewski, Luisa Bentivogli Published: 2025-11-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21517v2 Unlike text, speech conveys information about the speaker, such as gender, through acoustic cues like pitch. This gives rise to modality-specific bias concerns. For example, in speech translation (ST), when translating from languages with notional gender, such as English, into languages where gender-ambiguous terms referring to the speaker are assigned grammatical gender, the speaker's vocal characteristics may play a role in gender assignment. This risks misgendering speakers, whether through masculine defaults or vocal-based assumptions. Yet, how ST models make these decisions remains poorly understood. We investigate the mechanisms ST models use to assign gender to speaker-referring terms across three language pairs (en-es/fr/it). To do so, we examine how training data patterns, internal language model (ILM) biases, and acoustic information interact. We find that models do not simply replicate term-specific gender associations from training data, but learn broader patterns of masculine prevalence. While the ILM exhibits strong masculine bias, models can override these preferences based on acoustic input. Using contrastive feature attribution on spectrograms, we reveal that the model with higher gender accuracy relies on a previously unknown mechanism: using first-person pronouns to link gendered terms back to the speaker, accessing gender information distributed across the frequency spectrum rather than concentrated in pitch. --- ### Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation Authors: Lina Conti, Dennis Fucci, Marco Gaido, Matteo Negri, Guillaume Wisniewski, Luisa Bentivogli Published: 2025-11-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21517v1 Unlike text, speech conveys information about the speaker, such as gender, through acoustic cues like pitch. This gives rise to modality-specific bias concerns. For example, in speech translation (ST), when translating from languages with notional gender, such as English, into languages where gender-ambiguous terms referring to the speaker are assigned grammatical gender, the speaker's vocal characteristics may play a role in gender assignment. This risks misgendering speakers, whether through masculine defaults or vocal-based assumptions. Yet, how ST models make these decisions remains poorly understood. We investigate the mechanisms ST models use to assign gender to speaker-referring terms across three language pairs (en-es/fr/it), examining how training data patterns, internal language model (ILM) biases, and acoustic information interact. We find that models do not simply replicate term-specific gender associations from training data, but learn broader patterns of masculine prevalence. While the ILM exhibits strong masculine bias, models can override these preferences based on acoustic input. Using contrastive feature attribution on spectrograms, we reveal that the model with higher gender accuracy relies on a previously unknown mechanism: using first-person pronouns to link gendered terms back to the speaker, accessing gender information distributed across the frequency spectrum rather than concentrated in pitch. --- ### Mechanistic Interpretability for Transformer-based Time Series Classification Authors: Matīss Kalnāre, Sofoklis Kitharidis, Thomas Bäck, Niki van Stein Published: 2025-11-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.21514v1 Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their internal decision-making challenging. Existing explainability methods often focus on input-output attributions, leaving the internal mechanisms largely opaque. This paper addresses this gap by adapting various Mechanistic Interpretability techniques; activation patching, attention saliency, and sparse autoencoders, from NLP to transformer architectures designed explicitly for time series classification. We systematically probe the internal causal roles of individual attention heads and timesteps, revealing causal structures within these models. Through experimentation on a benchmark time series dataset, we construct causal graphs illustrating how information propagates internally, highlighting key attention heads and temporal positions driving correct classifications. Additionally, we demonstrate the potential of sparse autoencoders for uncovering interpretable latent features. Our findings provide both methodological contributions to transformer interpretability and novel insights into the functional mechanics underlying transformer performance in time series classification tasks. --- ### IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference Authors: Wanli Zhong, Haibo Feng, Zirui Zhou, Hanyang Peng, Shiqi Yu Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21513v2 Deploying Transformer models on edge devices is limited by latency and energy budgets. While INT8 quantization effectively accelerates the primary matrix multiplications, it exposes the softmax-related path as the dominant bottleneck. This stage incurs a costly dequantize -> softmax -> requantize detour, which can account for up to 65% of total attention latency and disrupts the end-to-end integer dataflow critical for edge hardware efficiency. To address this limitation, we present IntAttention, the first fully integer attention pipeline that serves as a training-free drop-in replacement. At the core of our approach lies IndexSoftmax, a hardware-friendly operator that replaces floating-point exponentials entirely within the integer domain. IntAttention integrates sparsity-aware clipping, a 32-entry lookup table approximation, and direct integer normalization, thereby eliminating datatype conversion overhead along the attention path. Experiments on Armv8 CPUs show that our method achieves up to 3.7x speedup and 61% energy reduction over FP16 baselines, and up to 2.0x speedup over conventional INT8 attention pipelines. Across diverse language and vision models, as well as additional reasoning and long-context evaluations, IntAttention maintains strong overall fidelity and demonstrates a more favorable trade-off than existing LUT-based softmax approximations. Code is available at https://github.com/WanliZhong/IntAttention --- ### IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference Authors: Wanli Zhong, Haibo Feng, Zirui Zhou, Hanyang Peng, Shiqi Yu Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21513v1 Deploying Transformer models on edge devices is limited by latency and energy budgets. While INT8 quantization effectively accelerates the primary matrix multiplications, it exposes the softmax as the dominant bottleneck. This stage incurs a costly dequantize-softmax-requantize detour, which can account for up to 65% of total attention latency and disrupts the end-to-end integer dataflow critical for edge hardware efficiency. To address this limitation, we present IntAttention, the first fully integer, plug-and-play attention pipeline without retraining. At the core of our approach lies IndexSoftmax, a hardware-friendly operator that replaces floating-point exponentials entirely within the integer domain. IntAttention integrates sparsity-aware clipping, a 32-entry lookup-table approximation, and direct integer normalization, thereby eliminating all datatype conversion overhead. We evaluate IntAttention and demonstrate consistent and substantial gains. Our method achieves up to 3.7x speedup and 61% energy reduction over FP16 baselines and 2.0x faster than conventional INT8 attention pipelines on Armv8 CPUs. These gains are achieved with high-fidelity accuracy comparable to baselines across diverse language and vision models, enabling practical and efficient Transformer inference on commodity edge devices. Code will be released in later version of this work. --- ### Tool-RoCo: An Agent-as-Tool Self-organization Large Language Model Benchmark in Multi-robot Cooperation Authors: Ke Zhang, Xiaoning Zhao, Ce Zheng, Jiahong Ning, Dandan Zhu, Wenqi Zhang, Chen Sun, Toshiharu Sugawara Published: 2025-11-26 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2511.21510v2 This study proposes Tool-RoCo, a novel benchmark for evaluating large language models (LLMs) in long-term multi-agent cooperation based on RoCo, a multi-robot cooperative benchmark. Recent research on LLM-based multi-agent systems has relied on predefined orchestration, while ignoring agent autonomy. Tool-RoCo treats other agents as tools and introduces cooperative tools, leveraging tool usage to evaluate multi-agent cooperation and self-organization. Tool usage means that each agent (LLM) selects a tool from a candidate set based on the current state, receives feedback, and adjusts its selection in subsequent rounds. To evaluate different autonomy levels, we propose four LLM paradigms: (1) centralized cooperation, where a single LLM allocates tools to all agents; (2) centralized self-organization, where a central LLM autonomously activates agents while keeping others inactive; (3) decentralized cooperation, where each agent has its own LLM and calls tools based on local information; and (4) self-organization, where a randomly chosen initial agent can request collaboration, activating additional agents via tool calls. Tool-RoCo includes three multi-robot tasks, SORT, PACK, and CABINET, to measure format and parameter accuracy and agent coordination through tool usage. The results using several LLMs showed that cooperative tools accounted for only 7.09% of all tools, indicating that LLM-based agents rarely invoked others as assistants. Moreover, activation tools accounted for 96.42%, suggesting that current LLMs tend to maintain active agents while seldom deactivating them for adaptive coordination. Tool-RoCo provides a systematic benchmark to evaluate LLM autonomy and cooperation in multi-agent tasks. Code and Demo: https://github.com/ColaZhang22/Tool-Roco --- ### Tool-RoCo: An Agent-as-Tool Self-organization Large Language Model Benchmark in Multi-robot Cooperation Authors: Ke Zhang, Xiaoning Zhao, Ce Zheng, Jiahong Ning, Dandan Zhu, Wenqi Zhang, Chen Sun, Toshiharu Sugawara Published: 2025-11-26 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2511.21510v1 This study proposes Tool-RoCo, a novel benchmark for evaluating large language models (LLMs) in long-term multi-agent cooperation based on RoCo, a multi-robot cooperative benchmark. Recent research on LLM-based multi-agent systems has relied on predefined orchestration, while ignoring agent autonomy. Tool-RoCo treats other agents as tools and introduces cooperative tools, leveraging tool usage to evaluate multi-agent cooperation and self-organization. Tool usage means that each agent (LLM) selects a tool from a candidate set based on the current state, receives feedback, and adjusts its selection in subsequent rounds. To evaluate different autonomy levels, we propose four LLM paradigms: (1) centralized cooperation, where a single LLM allocates tools to all agents; (2) centralized self-organization, where a central LLM autonomously activates agents while keeping others inactive; (3) decentralized cooperation, where each agent has its own LLM and calls tools based on local information; and (4) self-organization, where a randomly chosen initial agent can request collaboration, activating additional agents via tool calls. Tool-RoCo includes three multi-robot tasks, SORT, PACK, and CABINET, to measure format and parameter accuracy and agent coordination through tool usage. The results using several LLMs showed that cooperative tools accounted for only 7.09% of all tools, indicating that LLM-based agents rarely invoked others as assistants. Moreover, activation tools accounted for 96.42%, suggesting that current LLMs tend to maintain active agents while seldom deactivating them for adaptive coordination. Tool-RoCo provides a systematic benchmark to evaluate LLM autonomy and cooperation in multi-agent tasks. Code and Demo: https://github.com/ColaZhang22/Tool-Roco --- ### Generalized Design Choices for Deepfake Detectors Authors: Lorenzo Pellegrini, Serafino Pandolfini, Davide Maltoni, Matteo Ferrara, Marco Prati, Marco Ramilli Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21507v2 The effectiveness of deepfake detection methods often depends less on their core design and more on implementation details such as data preprocessing, augmentation strategies, and optimization techniques. These factors make it difficult to fairly compare detectors and to understand which factors truly contribute to their performance. To address this, we systematically investigate how different design choices influence the accuracy and generalization capabilities of deepfake detection models, focusing on aspects related to training, inference, and incremental updates. By isolating the impact of individual factors, we aim to establish robust, architecture-agnostic best practices for the design and development of future deepfake detection systems. Our experiments identify a set of design choices that consistently improve deepfake detection and enable state-of-the-art performance on the AI-GenBench benchmark. --- ### Generalized Design Choices for Deepfake Detectors Authors: Lorenzo Pellegrini, Serafino Pandolfini, Davide Maltoni, Matteo Ferrara, Marco Prati, Marco Ramilli Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21507v1 The effectiveness of deepfake detection methods often depends less on their core design and more on implementation details such as data preprocessing, augmentation strategies, and optimization techniques. These factors make it difficult to fairly compare detectors and to understand which factors truly contribute to their performance. To address this, we systematically investigate how different design choices influence the accuracy and generalization capabilities of deepfake detection models, focusing on aspects related to training, inference, and incremental updates. By isolating the impact of individual factors, we aim to establish robust, architecture-agnostic best practices for the design and development of future deepfake detection systems. Our experiments identify a set of design choices that consistently improve deepfake detection and enable state-of-the-art performance on the AI-GenBench benchmark. --- ### CanKD: Cross-Attention-based Non-local operation for Feature-based Knowledge Distillation Authors: Shizhe Sun, Wataru Ohyama Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21503v1 We propose Cross-Attention-based Non-local Knowledge Distillation (CanKD), a novel feature-based knowledge distillation framework that leverages cross-attention mechanisms to enhance the knowledge transfer process. Unlike traditional self-attention-based distillation methods that align teacher and student feature maps independently, CanKD enables each pixel in the student feature map to dynamically consider all pixels in the teacher feature map. This non-local knowledge transfer more thoroughly captures pixel-wise relationships, improving feature representation learning. Our method introduces only an additional loss function to achieve superior performance compared with existing attention-guided distillation methods. Extensive experiments on object detection and image segmentation tasks demonstrate that CanKD outperforms state-of-the-art feature and hybrid distillation methods. These experimental results highlight CanKD's potential as a new paradigm for attention-guided distillation in computer vision tasks. Code is available at https://github.com/tori-hotaru/CanKD --- ### Lost in Time? A Meta-Learning Framework for Time-Shift-Tolerant Physiological Signal Transformation Authors: Qian Hong, Cheng Bian, Xiao Zhou, Xiaoyu Li, Yelei Li, Zijing Zeng Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21500v1 Translating non-invasive signals such as photoplethysmography (PPG) and ballistocardiography (BCG) into clinically meaningful signals like arterial blood pressure (ABP) is vital for continuous, low-cost healthcare monitoring. However, temporal misalignment in multimodal signal transformation impairs transformation accuracy, especially in capturing critical features like ABP peaks. Conventional synchronization methods often rely on strong similarity assumptions or manual tuning, while existing Learning with Noisy Labels (LNL) approaches are ineffective under time-shifted supervision, either discarding excessive data or failing to correct label shifts. To address this challenge, we propose ShiftSyncNet, a meta-learning-based bi-level optimization framework that automatically mitigates performance degradation due to time misalignment. It comprises a transformation network (TransNet) and a time-shift correction network (SyncNet), where SyncNet learns time offsets between training pairs and applies Fourier phase shifts to align supervision signals. Experiments on one real-world industrial dataset and two public datasets show that ShiftSyncNet outperforms strong baselines by 9.4%, 6.0%, and 12.8%, respectively. The results highlight its effectiveness in correcting time shifts, improving label quality, and enhancing transformation accuracy across diverse misalignment scenarios, pointing toward a unified direction for addressing temporal inconsistencies in multimodal physiological transformation. --- ### Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning Authors: Taehoon Kim, Donghwan Jang, Bohyung Han Published: 2025-11-26 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.21490v1 We present a novel training approach, named Merge-and-Bound (M&B) for Class Incremental Learning (CIL), which directly manipulates model weights in the parameter space for optimization. Our algorithm involves two types of weight merging: inter-task weight merging and intra-task weight merging. Inter-task weight merging unifies previous models by averaging the weights of models from all previous stages. On the other hand, intra-task weight merging facilitates the learning of current task by combining the model parameters within current stage. For reliable weight merging, we also propose a bounded update technique that aims to optimize the target model with minimal cumulative updates and preserve knowledge from previous tasks; this strategy reveals that it is possible to effectively obtain new models near old ones, reducing catastrophic forgetting. M&B is seamlessly integrated into existing CIL methods without modifying architecture components or revising learning objectives. We extensively evaluate our algorithm on standard CIL benchmarks and demonstrate superior performance compared to state-of-the-art methods. --- ### Frequency-Aware Token Reduction for Efficient Vision Transformer Authors: Dong-Jae Lee, Jiwan Hur, Jaehyun Choi, Jaemyung Yu, Junmo Kim Published: 2025-11-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.21477v1 Vision Transformers have demonstrated exceptional performance across various computer vision tasks, yet their quadratic computational complexity concerning token length remains a significant challenge. To address this, token reduction methods have been widely explored. However, existing approaches often overlook the frequency characteristics of self-attention, such as rank collapsing and over-smoothing phenomenon. In this paper, we propose a frequency-aware token reduction strategy that improves computational efficiency while preserving performance by mitigating rank collapsing. Our method partitions tokens into high-frequency tokens and low-frequency tokens. high-frequency tokens are selectively preserved, while low-frequency tokens are aggregated into a compact direct current token to retain essential low-frequency components. Through extensive experiments and analysis, we demonstrate that our approach significantly improves accuracy while reducing computational overhead and mitigating rank collapsing and over smoothing. Furthermore, we analyze the previous methods, shedding light on their implicit frequency characteristics and limitations. --- ### MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices Authors: Shuai Zhang, Bao Tang, Siyuan Yu, Yueting Zhu, Jingfeng Yao, Ya Zou, Shanglin Yuan, Li Yu, Wenyu Liu, Xinggang Wang Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21475v1 Recently, video generation has witnessed rapid advancements, drawing increasing attention to image-to-video (I2V) synthesis on mobile devices. However, the substantial computational complexity and slow generation speed of diffusion models pose significant challenges for real-time, high-resolution video generation on resource-constrained mobile devices. In this work, we propose MobileI2V, a 270M lightweight diffusion model for real-time image-to-video generation on mobile devices. The core lies in: (1) We analyzed the performance of linear attention modules and softmax attention modules on mobile devices, and proposed a linear hybrid architecture denoiser that balances generation efficiency and quality. (2) We design a time-step distillation strategy that compresses the I2V sampling steps from more than 20 to only two without significant quality loss, resulting in a 10-fold increase in generation speed. (3) We apply mobile-specific attention optimizations that yield a 2-fold speed-up for attention operations during on-device inference. MobileI2V enables, for the first time, fast 720p image-to-video generation on mobile devices, with quality comparable to existing models. Under one-step conditions, the generation speed of each frame of 720p video is less than 100 ms. Our code is available at: https://github.com/hustvl/MobileI2V. --- ### Going with the Speed of Sound: Pushing Neural Surrogates into Highly-turbulent Transonic Regimes Authors: Fabian Paischer, Leo Cotteleer, Yann Dreze, Richard Kurle, Dylan Rubini, Maurits Bleeker, Tobias Kronlachner, Johannes Brandstetter Published: 2025-11-26 Categories: cs.CE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.21474v2 The widespread use of neural surrogates in automotive aerodynamics, enabled by datasets such as DrivAerML and DrivAerNet++, has primarily focused on bluff-body flows with large wakes. Extending these methods to aerospace, particularly in the transonic regime, remains challenging due to the high level of non-linearity of compressible flows and 3D effects such as wingtip vortices. Existing aerospace datasets predominantly focus on 2D airfoils, neglecting these critical 3D phenomena. To address this gap, we present a new dataset of CFD simulations for 3D wings in the transonic regime. The dataset comprises volumetric and surface-level fields for around $30,000$ samples with unique geometry and inflow conditions. This allows computation of lift and drag coefficients, providing a foundation for data-driven aerodynamic optimization of the drag-lift Pareto front. We evaluate several state-of-the-art neural surrogates on our dataset, including Transolver and AB-UPT, focusing on their out-of-distribution (OOD) generalization over geometry and inflow variations. AB-UPT demonstrates strong performance for transonic flowfields and reproduces physically consistent drag-lift Pareto fronts even for unseen wing configurations. Our results demonstrate that AB-UPT can approximate drag-lift Pareto fronts for unseen geometries, highlighting its potential as an efficient and effective tool for rapid aerodynamic design exploration. To facilitate future research, we open-source our dataset at https://huggingface.co/datasets/EmmiAI/Emmi-Wing. --- ### Going with the Speed of Sound: Pushing Neural Surrogates into Highly-turbulent Transonic Regimes Authors: Fabian Paischer, Leo Cotteleer, Yann Dreze, Richard Kurle, Dylan Rubini, Maurits Bleeker, Tobias Kronlachner, Johannes Brandstetter Published: 2025-11-26 Categories: cs.CE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.21474v1 The widespread use of neural surrogates in automotive aerodynamics, enabled by datasets such as DrivAerML and DrivAerNet++, has primarily focused on bluff-body flows with large wakes. Extending these methods to aerospace, particularly in the transonic regime, remains challenging due to the high level of non-linearity of compressible flows and 3D effects such as wingtip vortices. Existing aerospace datasets predominantly focus on 2D airfoils, neglecting these critical 3D phenomena. To address this gap, we present a new dataset of CFD simulations for 3D wings in the transonic regime. The dataset comprises volumetric and surface-level fields for around $30,000$ samples with unique geometry and inflow conditions. This allows computation of lift and drag coefficients, providing a foundation for data-driven aerodynamic optimization of the drag-lift Pareto front. We evaluate several state-of-the-art neural surrogates on our dataset, including Transolver and AB-UPT, focusing on their out-of-distribution (OOD) generalization over geometry and inflow variations. AB-UPT demonstrates strong performance for transonic flowfields and reproduces physically consistent drag-lift Pareto fronts even for unseen wing configurations. Our results demonstrate that AB-UPT can approximate drag-lift Pareto fronts for unseen geometries, highlighting its potential as an efficient and effective tool for rapid aerodynamic design exploration. To facilitate future research, we open-source our dataset at https://huggingface.co/datasets/EmmiAI/Emmi-Wing. --- ### Hierarchical Ranking Neural Network for Long Document Readability Assessment Authors: Yurui Zheng, Yijun Chen, Shaohong Zhang Published: 2025-11-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21473v1 Readability assessment aims to evaluate the reading difficulty of a text. In recent years, while deep learning technology has been gradually applied to readability assessment, most approaches fail to consider either the length of the text or the ordinal relationship of readability labels. This paper proposes a bidirectional readability assessment mechanism that captures contextual information to identify regions with rich semantic information in the text, thereby predicting the readability level of individual sentences. These sentence-level labels are then used to assist in predicting the overall readability level of the document. Additionally, a pairwise sorting algorithm is introduced to model the ordinal relationship between readability levels through label subtraction. Experimental results on Chinese and English datasets demonstrate that the proposed model achieves competitive performance and outperforms other baseline models. --- ### SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition Authors: Peiran Xu, Sudong Wang, Yao Zhu, Jianing Li, Gege Qi, Yunjian Zhang Published: 2025-11-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.21471v4 Spatial cognition is fundamental to real-world multimodal intelligence, allowing models to effectively interact with the physical environment. While multimodal large language models (MLLMs) have made significant strides, existing benchmarks often oversimplify spatial cognition, reducing it to a single-dimensional metric, which fails to capture the hierarchical structure and interdependence of spatial abilities. To address this gap, we propose a hierarchical spatial cognition framework that decomposes spatial intelligence into five progressively complex levels from basic observation to high-level planning. Building upon this taxonomy, we construct SpatialBench, a large-scale, fine-grained benchmark covering 15 tasks aligned with these cognitive levels. To provide a unified evaluation across heterogeneous tasks, we further introduce a high-level capability-oriented metric that reliably assesses a model's overall spatial reasoning ability. Extensive experiments over massive MLLMs reveal distinct performance stratification across cognitive levels: models exhibit strong perceptual grounding yet remain limited in symbolic reasoning, causal inference, and planning. Additional human tests demonstrate that humans perform selective, goal-directed abstraction, while MLLMs tend to over-attend to surface details without coherent spatial intent. Our work establishes the first systematic framework for measuring hierarchical spatial cognition in MLLMs, laying the foundation for future spatially intelligent systems. --- ### SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition Authors: Peiran Xu, Sudong Wang, Yao Zhu, Jianing Li, Yunjian Zhang Published: 2025-11-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.21471v1 Spatial cognition is fundamental to real-world multimodal intelligence, allowing models to effectively interact with the physical environment. While multimodal large language models (MLLMs) have made significant strides, existing benchmarks often oversimplify spatial cognition, reducing it to a single-dimensional metric, which fails to capture the hierarchical structure and interdependence of spatial abilities. To address this gap, we propose a hierarchical spatial cognition framework that decomposes spatial intelligence into five progressively complex levels from basic observation to high-level planning. Building upon this taxonomy, we construct SpatialBench, a large-scale, fine-grained benchmark covering 15 tasks aligned with these cognitive levels. To provide a unified evaluation across heterogeneous tasks, we further introduce a high-level capability-oriented metric that reliably assesses a model's overall spatial reasoning ability. Extensive experiments over massive MLLMs reveal distinct performance stratification across cognitive levels: models exhibit strong perceptual grounding yet remain limited in symbolic reasoning, causal inference, and planning. Additional human tests demonstrate that humans perform selective, goal-directed abstraction, while MLLMs tend to over-attend to surface details without coherent spatial intent. Our work establishes the first systematic framework for measuring hierarchical spatial cognition in MLLMs, laying the foundation for future spatially intelligent systems. --- ### Mean-Field Model for Two-Layer Neural Networks Trained with Consensus-Based Optimization Authors: William De Deyn, Michael Herty, Giovanni Samaey Published: 2025-11-26 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2511.21466v3 We study Consensus-Based Optimization (CBO) for two-layer neural network training. We compare the performance of CBO against Adam on two test cases and demonstrate how a hybrid approach, combining CBO with Adam, provides faster convergence than CBO. Additionally, in the context of multi-task learning, we recast CBO into a formulation that offers less memory overhead. The CBO method allows for a mean-field model formulation, which we couple with the mean-field model of the neural network. To this end, we first reformulate CBO within the optimal transport framework. As the number of particles tends to infinity, we lift the corresponding dynamics to the Wasserstein-over-Wasserstein space and show that the variance decreases monotonically. We confirm numerically that both mean-field models converge. --- ### Mean-Field Limits for Two-Layer Neural Networks Trained with Consensus-Based Optimization Authors: William De Deyn, Michael Herty, Giovanni Samaey Published: 2025-11-26 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2511.21466v1 We study two-layer neural networks and train these with a particle-based method called consensus-based optimization (CBO). We compare the performance of CBO against Adam on two test cases and demonstrate how a hybrid approach, combining CBO with Adam, provides faster convergence than CBO. In the context of multi-task learning, we recast CBO into a formulation that offers less memory overhead. The CBO method allows for a mean-field limit formulation, which we couple with the mean-field limit of the neural network. To this end, we first reformulate CBO within the optimal transport framework. Finally, in the limit of infinitely many particles, we define the corresponding dynamics on the Wasserstein-over-Wasserstein space and show that the variance decreases monotonically. --- ### Ensemble Performance Through the Lens of Linear Independence of Classifier Votes in Data Streams Authors: Enes Bektas, Fazli Can Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21465v1 Ensemble learning improves classification performance by combining multiple base classifiers. While increasing the number of classifiers generally enhances accuracy, excessively large ensembles can lead to computational inefficiency and diminishing returns. This paper investigates the relationship between ensemble size and performance through the lens of linear independence among classifier votes in data streams. We propose that ensembles composed of linearly independent classifiers maximize representational capacity, particularly under a geometric model. We then generalize the importance of linear independence to the weighted majority voting problem. By modeling the probability of achieving linear independence among classifier outputs, we derive a theoretical framework that explains the trade-off between ensemble size and accuracy. Our analysis leads to a theoretical estimate of the ensemble size required to achieve a user-specified probability of linear independence. We validate our theory through experiments on both real-world and synthetic datasets using two ensemble methods, OzaBagging and GOOWE. Our results confirm that this theoretical estimate effectively identifies the point of performance saturation for robust ensembles like OzaBagging. Conversely, for complex weighting schemes like GOOWE, our framework reveals that high theoretical diversity can trigger algorithmic instability. Our implementation is publicly available to support reproducibility and future research. --- ### MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning Authors: Junjian Wang, Lidan Zhao, Xi Sheryl Zhang Published: 2025-11-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.21460v1 Ensuring the safety of embodied AI agents during task planning is critical for real-world deployment, especially in household environments where dangerous instructions pose significant risks. Existing methods often suffer from either high computational costs due to preference alignment training or over-rejection when using single-agent safety prompts. To address these limitations, we propose MADRA, a training-free Multi-Agent Debate Risk Assessment framework that leverages collective reasoning to enhance safety awareness without sacrificing task performance. MADRA employs multiple LLM-based agents to debate the safety of a given instruction, guided by a critical evaluator that scores responses based on logical soundness, risk identification, evidence quality, and clarity. Through iterative deliberation and consensus voting, MADRA significantly reduces false rejections while maintaining high sensitivity to dangerous tasks. Additionally, we introduce a hierarchical cognitive collaborative planning framework that integrates safety, memory, planning, and self-evolution mechanisms to improve task success rates through continuous learning. We also contribute SafeAware-VH, a benchmark dataset for safety-aware task planning in VirtualHome, containing 800 annotated instructions. Extensive experiments on AI2-THOR and VirtualHome demonstrate that our approach achieves over 90% rejection of unsafe tasks while ensuring that safe-task rejection is low, outperforming existing methods in both safety and execution efficiency. Our work provides a scalable, model-agnostic solution for building trustworthy embodied agents. --- ### The Phish, The Spam, and The Valid: Generating Feature-Rich Emails for Benchmarking LLMs Authors: Rebeka Toth, Tamas Bisztray, Nils Gruschka Published: 2025-11-26 Categories: cs.CR, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2511.21448v5 In this paper, we introduce a metadata-enriched generation framework (PhishFuzzer) that seeds real emails into Large Language Models (LLMs) to produce 23,100 diverse, structurally consistent email variants across controlled entity and length dimensions. Unlike prior corpora, our dataset features strict three-class labels (Phishing, Spam, Valid), provides full URL and attachment metadata, and annotates each email with attacker intent. Using this dataset, we benchmark two state-of-the-art LLMs (Qwen-2.5-72B and Gemini-3.1-Pro) under both Basic (body, subject) and Full (+URL, sender, attachment) settings. By applying formal confidence metrics (Task Success Rate and Confidence Index), we analyze model reliability, robustness against linguistic fuzzing, and the impact of structural metadata on detection accuracy. Our fully open-source framework and dataset provide a rigorous foundation for evaluating next-generation email security systems. To support open science, we make the PhishFuzzer Dataset, the generation scripts and prompts available on GitHub: https://github.com/DataPhish/PhishFuzzer --- ### Constructing and Benchmarking: a Labeled Email Dataset for Text-Based Phishing and Spam Detection Framework Authors: Rebeka Toth, Tamas Bisztray, Richard Dubniczky Published: 2025-11-26 Categories: cs.CR, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2511.21448v1 Phishing and spam emails remain a major cybersecurity threat, with attackers increasingly leveraging Large Language Models (LLMs) to craft highly deceptive content. This study presents a comprehensive email dataset containing phishing, spam, and legitimate messages, explicitly distinguishing between human- and LLM-generated content. Each email is annotated with its category, emotional appeal (e.g., urgency, fear, authority), and underlying motivation (e.g., link-following, credential theft, financial fraud). We benchmark multiple LLMs on their ability to identify these emotional and motivational cues and select the most reliable model to annotate the full dataset. To evaluate classification robustness, emails were also rephrased using several LLMs while preserving meaning and intent. A state-of-the-art LLM was then assessed on its performance across both original and rephrased emails using expert-labeled ground truth. The results highlight strong phishing detection capabilities but reveal persistent challenges in distinguishing spam from legitimate emails. Our dataset and evaluation framework contribute to improving AI-assisted email security systems. To support open science, all code, templates, and resources are available on our project site. --- ### EWE: An Agentic Framework for Extreme Weather Analysis Authors: Zhe Jiang, Jiong Wang, Xiaoyu Yue, Zijie Guo, Wenlong Zhang, Fenghua Ling, Wanli Ouyang, Lei Bai Published: 2025-11-26 Categories: cs.AI, physics.ao-ph arXiv: https://arxiv.org/abs/2511.21444v1 Extreme weather events pose escalating risks to global society, underscoring the urgent need to unravel their underlying physical mechanisms. Yet the prevailing expert-driven, labor-intensive diagnostic paradigm has created a critical analytical bottleneck, stalling scientific progress. While AI for Earth Science has achieved notable advances in prediction, the equally essential challenge of automated diagnostic reasoning remains largely unexplored. We present the Extreme Weather Expert (EWE), the first intelligent agent framework dedicated to this task. EWE emulates expert workflows through knowledge-guided planning, closed-loop reasoning, and a domain-tailored meteorological toolkit. It autonomously produces and interprets multimodal visualizations from raw meteorological data, enabling comprehensive diagnostic analyses. To catalyze progress, we introduce the first benchmark for this emerging field, comprising a curated dataset of 103 high-impact events and a novel step-wise evaluation metric. EWE marks a step toward automated scientific discovery and offers the potential to democratize expertise and intellectual resources, particularly for developing nations vulnerable to extreme weather. --- ### EvRainDrop: HyperGraph-guided Completion for Effective Frame and Event Stream Aggregation Authors: Futian Wang, Fan Zhang, Xiao Wang, Mengqi Wang, Dexing Huang, Jin Tang Published: 2025-11-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.21439v1 Event cameras produce asynchronous event streams that are spatially sparse yet temporally dense. Mainstream event representation learning algorithms typically use event frames, voxels, or tensors as input. Although these approaches have achieved notable progress, they struggle to address the undersampling problem caused by spatial sparsity. In this paper, we propose a novel hypergraph-guided spatio-temporal event stream completion mechanism, which connects event tokens across different times and spatial locations via hypergraphs and leverages contextual information message passing to complete these sparse events. The proposed method can flexibly incorporate RGB tokens as nodes in the hypergraph within this completion framework, enabling multi-modal hypergraph-based information completion. Subsequently, we aggregate hypergraph node information across different time steps through self-attention, enabling effective learning and fusion of multi-modal features. Extensive experiments on both single- and multi-label event classification tasks fully validated the effectiveness of our proposed framework. The source code of this paper will be released on https://github.com/Event-AHU/EvRainDrop. --- ### Conversational No-code, Multi-agentic Disease Module Identification and Drug Repurposing Prediction with ChatDRex Authors: Simon Süwer, Kester Bagemihl, Sylvie Baier, Lucia Dicunta, Markus List, Jan Baumbach, Andreas Maier, Fernando M. Delgado-Chaves Published: 2025-11-26 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.21438v2 Repurposing approved drugs offers a time-efficient and cost-effective alternative to traditional drug development. However, in silico prediction of repurposing candidates is challenging and requires the effective collaboration of specialists in various fields, including pharmacology, medicine, biology, and bioinformatics. Fragmented, specialized algorithms and tools often address only narrow aspects of the overall problem. Heterogeneous, unstructured data landscapes require the expertise of specialized users. Hence, these data services do not integrate smoothly across workflows. With ChatDRex, we present a conversation-based, multi-agent system that facilitates the execution of complex bioinformatic analyses aiming for network-based drug repurposing prediction. It builds on the integrated systems medicine knowledge graph (NeDRex KG). ChatDRex provides natural language access to its extensive biomedical knowledge base. It integrates bioinformatics agents for network analysis, literature mining, and drug repurposing. These are complemented by agents that evaluate functional coherence for in silico validation. Its flexible multi-agent design assigns specific tasks to specialized agents, including query routing, data retrieval, algorithm execution, and result visualization. A dedicated reasoning module keeps the user in the loop and allows for hallucination detection. By enabling physicians and researchers without computer science expertise to control complex analyses with natural language, ChatDRex democratizes access to bioinformatics as an important resource for drug repurposing. It enables clinical experts to generate hypotheses and explore drug repurposing opportunities, ultimately accelerating the discovery of novel therapies and advancing personalized medicine and translational research. ChatDRex is publicly available at apps.cosy.bio/chatdrex. --- ### Conversational no-code and multi-agentic disease module identification and drug repurposing prediction with ChatDRex Authors: Simon Süwer, Kester Bagemihl, Sylvie Baier, Lucia Dicunta, Markus List, Jan Baumbach, Andreas Maier, Fernando M. Delgado-Chaves Published: 2025-11-26 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.21438v1 Repurposing approved drugs offers a time-efficient and cost-effective alternative to traditional drug development. However, in silico prediction of repurposing candidates is challenging and requires the effective collaboration of specialists in various fields, including pharmacology, medicine, biology, and bioinformatics. Fragmented, specialized algorithms and tools often address only narrow aspects of the overall problem, and heterogeneous, unstructured data landscapes require specialized users to be involved. Hence, these data services do not integrate smoothly across workflows. With ChatDRex, we present a conversation-based, multi-agent system that facilitates the execution of complex bioinformatic analyses aiming for network-based drug repurposing prediction. It builds on the integrated systems medicine knowledge graph NeDRex. ChatDRex provides natural language access to its extensive biomedical KG and integrates bioinformatics agents for network analysis and drug repurposing, complemented by agents for functional coherence evaluation for in silico validation, as well as agents for literature mining and for discussing the obtained results in a scientific context. Its flexible multi-agent design assigns specific tasks to specialized agents, including query routing, data retrieval, algorithm execution, and result visualization. A dedicated reasoning module keeps the user in the loop and allows for hallucination detection. By enabling physicians and researchers without computer science expertise to control complex analyses in natural language, ChatDRex democratizes access to bioinformatics as an important resource for drug repurposing. It enables clinical experts to generate hypotheses and explore drug repurposing opportunities, ultimately accelerating the discovery of novel therapies and advancing personalized medicine and translational research. --- ### A Systematic Study of In-the-Wild Model Merging for Large Language Models Authors: Oğuz Kağan Hitit, Leander Girrbach, Zeynep Akata Published: 2025-11-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.21437v2 Model merging combines multiple fine-tuned checkpoints into a single model without additional training, offering an attractive approach to reusing models and efficiently improving performance. However, it remains unclear whether the advantages reported for settings where all merged experts have distinct roles and are tuned on clearly separated tasks also hold in settings where the merged experts do not have clearly distinct roles, but are trained on overlapping or even conflicting objectives. To evaluate this setting, we present a large-scale, systematic evaluation of "in-the-wild" model merging of heterogeneous experts, that may have been trained on overlapping or conflicting objectives. Concretely, we evaluate six state-of-the-art merging methods, including recent subspace methods, across four open-weight LLMs, twelve fine-tuned checkpoints per base model, and sixteen standard LLM benchmarks. Evaluating through standardized benchmarks, we measure both the probability that a model merged from a heterogeneous set of experts outperforms the base model and we measure relative gains over the best individual checkpoint. Our results show that the oldest and simplest method, Task Arithmetic, is the only approach that reliably yields performance gains on LLMs in this "in-the-wild" setting. Other interference-aware and subspace merging methods typically do not result in notable improvements over the base model. Our findings indicate that current merging techniques mostly do not enable extracting useful weight updates from heterogeneous and potentially conflicting versions. This motivates the design of LLM-specific merging algorithms and merging-aware fine-tuning methods. --- ### A Systematic Study of Model Merging Techniques in Large Language Models Authors: Oğuz Kağan Hitit, Leander Girrbach, Zeynep Akata Published: 2025-11-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.21437v1 Model merging combines multiple fine-tuned checkpoints into a single model without additional training, offering an attractive approach to reusing models and efficiently improving performance. However, it remains unclear whether the advantages reported for smaller models and classifiers generalize to LLMs. We present a large-scale, systematic evaluation of six state-of-the-art merging methods, including recent subspace methods, across four open-weight LLMs, twelve fine-tuned checkpoints per base model, and sixteen standard LLM benchmarks. Evaluating through standardized benchmarks, we measure both the probability that a merged model outperforms the base model and relative gains over the best individual checkpoint. Our results show that the oldest and simplest method, Task Arithmetic, is the only approach that reliably yields performance gains on LLMs. Other interference-aware and subspace merging methods typically result in significant performance drops. Our findings indicate that current merging techniques do not directly transfer to modern LLMs. This motivates the design of LLM-specific merging algorithms and merging-aware fine-tuning methods. Code will be released upon acceptance of this paper. --- ### From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings Authors: Jiajie Zhang, Sören Schwertfeger, Alexander Kleiner Published: 2025-11-26 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2511.21428v2 We present a novel unsupervised framework to unlock vast unlabeled human demonstration data from continuous industrial video streams for Vision-Language-Action (VLA) model pre-training. Our method first trains a lightweight motion tokenizer to encode motion dynamics, then employs an unsupervised action segmenter leveraging a novel "Latent Action Energy" metric to discover and segment semantically coherent action primitives. The pipeline outputs both segmented video clips and their corresponding latent action sequences, providing structured data directly suitable for VLA pre-training. Evaluations on public benchmarks and a proprietary electric motor assembly dataset demonstrate effective segmentation of key tasks performed by humans at workstations. Further clustering and quantitative assessment via a Vision-Language Model confirm the semantic coherence of the discovered action primitives. To our knowledge, this is the first fully automated end-to-end system for extracting and organizing VLA pre-training data from unstructured industrial videos, offering a scalable solution for embodied AI integration in manufacturing. --- ### From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings Authors: Jiajie Zhang, Sören Schwertfeger, Alexander Kleiner Published: 2025-11-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.21428v1 We present a novel unsupervised framework to unlock vast unlabeled human demonstration data from continuous industrial video streams for Vision-Language-Action (VLA) model pre-training. Our method first trains a lightweight motion tokenizer to encode motion dynamics, then employs an unsupervised action segmenter leveraging a novel "Latent Action Energy" metric to discover and segment semantically coherent action primitives. The pipeline outputs both segmented video clips and their corresponding latent action sequences, providing structured data directly suitable for VLA pre-training. Evaluations on public benchmarks and a proprietary electric motor assembly dataset demonstrate effective segmentation of key tasks performed by humans at workstations. Further clustering and quantitative assessment via a Vision-Language Model confirm the semantic coherence of the discovered action primitives. To our knowledge, this is the first fully automated end-to-end system for extracting and organizing VLA pre-training data from unstructured industrial videos, offering a scalable solution for embodied AI integration in manufacturing. --- ### E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework Authors: Adeela Islam, Stefano Fiorini, Manuel Lecha, Theodore Tsesmelis, Stuart James, Pietro Morerio, Alessio Del Bue Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21422v1 3D reassembly is a fundamental geometric problem, and in recent years it has increasingly been challenged by deep learning methods rather than classical optimization. While learning approaches have shown promising results, most still rely primarily on geometric features to assemble a whole from its parts. As a result, methods struggle when geometry alone is insufficient or ambiguous, for example, for small, eroded, or symmetric fragments. Additionally, solutions do not impose physical constraints that explicitly prevent overlapping assemblies. To address these limitations, we introduce E-M3RF, an equivariant multimodal 3D reassembly framework that takes as input the point clouds, containing both point positions and colors of fractured fragments, and predicts the transformations required to reassemble them using SE(3) flow matching. Each fragment is represented by both geometric and color features: i) 3D point positions are encoded as rotationconsistent geometric features using a rotation-equivariant encoder, ii) the colors at each 3D point are encoded with a transformer. The two feature sets are then combined to form a multimodal representation. We experimented on four datasets: two synthetic datasets, Breaking Bad and Fantastic Breaks, and two real-world cultural heritage datasets, RePAIR and Presious, demonstrating that E-M3RF on the RePAIR dataset reduces rotation error by 23.1% and translation error by 13.2%, while Chamfer Distance decreases by 18.4% compared to competing methods. --- ### SAM Guided Semantic and Motion Changed Region Mining for Remote Sensing Change Captioning Authors: Futian Wang, Mengqi Wang, Xiao Wang, Haowen Wang, Jin Tang Published: 2025-11-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.21420v1 Remote sensing change captioning is an emerging and popular research task that aims to describe, in natural language, the content of interest that has changed between two remote sensing images captured at different times. Existing methods typically employ CNNs/Transformers to extract visual representations from the given images or incorporate auxiliary tasks to enhance the final results, with weak region awareness and limited temporal alignment. To address these issues, this paper explores the use of the SAM (Segment Anything Model) foundation model to extract region-level representations and inject region-of-interest knowledge into the captioning framework. Specifically, we employ a CNN/Transformer model to extract global-level vision features, leverage the SAM foundation model to delineate semantic- and motion-level change regions, and utilize a specially constructed knowledge graph to provide information about objects of interest. These heterogeneous sources of information are then fused via cross-attention, and a Transformer decoder is used to generate the final natural language description of the observed changes. Extensive experimental results demonstrate that our method achieves state-of-the-art performance across multiple widely used benchmark datasets. The source code of this paper will be released on https://github.com/Event-AHU/SAM_ChangeCaptioning --- ### New Hybrid Heuristics for Pseudo-Boolean Propagation Authors: Mia Müßig, Jan Johannsen Published: 2025-11-26 Categories: cs.AI, math.OC arXiv: https://arxiv.org/abs/2511.21417v2 In pseudo-boolean solving the currently most successful unit propagation strategy is a hybrid mode combining the watched literal scheme with the counting method. This short paper introduces new heuristics for this hybrid decision, which are able to drastically outperform the current method in the RoundingSAT solver. --- ### New Hybrid Heuristics for Pseudo-Boolean Propagation Authors: Mia Müßig, Jan Johannsen Published: 2025-11-26 Categories: cs.AI, math.OC arXiv: https://arxiv.org/abs/2511.21417v1 In pseudo-boolean solving the currently most successful unit propagation strategy is a hybrid mode combining the watched literal scheme with the counting method. This short paper introduces new heuristics for this hybrid decision, which are able to drastically outperform the current method in the RoundingSAT solver. --- ### Odin: Oriented Dual-module Integration for Text-rich Network Representation Learning Authors: Kaifeng Hong, Yinglong Zhang, Xiaoying Hong, Xuewen Xia, Xing Xu Published: 2025-11-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.21416v2 Text-attributed graphs require models to effectively combine strong textual understanding with structurally informed reasoning. Existing approaches either rely on GNNs--limited by over-smoothing and hop-dependent diffusion--or employ Transformers that overlook graph topology and treat nodes as isolated sequences. We propose Odin (Oriented Dual-module INtegration), a new architecture that injects graph structure into Transformers at selected depths through an oriented dual-module mechanism. Unlike message-passing GNNs, Odin does not rely on multi-hop diffusion; instead, multi-hop structures are integrated at specific Transformer layers, yielding low-, mid-, and high-level structural abstraction aligned with the model's semantic hierarchy. Because aggregation operates on the global (CLS) representation, Odin fundamentally avoids over-smoothing and decouples structural abstraction from neighborhood size or graph topology. We further establish that Odin's expressive power strictly contains that of both pure Transformers and GNNs. To make the design efficient in large-scale or low-resource settings, we introduce Light Odin, a lightweight variant that preserves the same layer-aligned structural abstraction for faster training and inference. Experiments on multiple text-rich graph benchmarks show that Odin achieves state-of-the-art accuracy, while Light Odin delivers competitive performance with significantly reduced computational cost. Together, Odin and Light Odin form a unified, hop-free framework for principled structure-text integration. The source code of this model has been released at https://github.com/hongkaifeng/Odin. --- ### Odin: Oriented Dual-module Integration for Text-rich Network Representation Learning Authors: Kaifeng Hong, Yinglong Zhang, Xiaoying Hong, Xuewen Xia, Xing Xu Published: 2025-11-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.21416v1 Text-attributed graphs require models to effectively combine strong textual understanding with structurally informed reasoning. Existing approaches either rely on GNNs--limited by over-smoothing and hop-dependent diffusion--or employ Transformers that overlook graph topology and treat nodes as isolated sequences. We propose Odin (Oriented Dual-module INtegration), a new architecture that injects graph structure into Transformers at selected depths through an oriented dual-module mechanism.Unlike message-passing GNNs, Odin does not rely on multi-hop diffusion; instead, multi-hop structures are integrated at specific Transformer layers, yielding low-, mid-, and high-level structural abstraction aligned with the model's semantic hierarchy. Because aggregation operates on the global (CLS) representation, Odin fundamentally avoids over-smoothing and decouples structural abstraction from neighborhood size or graph topology. We further establish that Odin's expressive power strictly contains that of both pure Transformers and GNNs.To make the design efficient in large-scale or low-resource settings, we introduce Light Odin, a lightweight variant that preserves the same layer-aligned structural abstraction for faster training and inference. Experiments on multiple text-rich graph benchmarks show that Odin achieves state-of-the-art accuracy, while Light Odin delivers competitive performance with significantly reduced computational cost. Together, Odin and Light Odin form a unified, hop-free framework for principled structure-text integration. The source code of this model has been released at https://github.com/hongkaifeng/Odin. --- ### DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models Authors: Mingue Park, Prin Phunyaphibarn, Phillip Y. Lee, Minhyuk Sung Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21415v2 We introduce DiverseVAR, a framework that enhances the diversity of text-conditioned visual autoregressive models (VAR) at test time without requiring retraining, fine-tuning, or substantial computational overhead. While VAR models have recently emerged as strong competitors to diffusion and flow models for image generation, they suffer from a critical limitation in diversity, often producing nearly identical images even for simple prompts. This issue has largely gone unnoticed amid the predominant focus on image quality. We address this limitation at test time in two stages. First, inspired by diversity enhancement techniques in diffusion models, we propose injecting noise into the text embedding. This introduces a trade-off between diversity and image quality: as diversity increases, the image quality sharply declines. To preserve quality, we propose scale-travel: a novel latent refinement technique inspired by time-travel strategies in diffusion models. Specifically, we use a multi-scale autoencoder to extract coarse-scale tokens that enable us to resume generation at intermediate stages. Extensive experiments show that combining text-embedding noise injection with our scale-travel refinement significantly enhances diversity while minimizing image-quality degradation, achieving a new Pareto frontier in the diversity-quality trade-off. Project page: https://diverse-var.github.io --- ### DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models Authors: Mingue Park, Prin Phunyaphibarn, Phillip Y. Lee, Minhyuk Sung Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21415v1 We introduce DiverseVAR, a framework that enhances the diversity of text-conditioned visual autoregressive models (VAR) at test time without requiring retraining, fine-tuning, or substantial computational overhead. While VAR models have recently emerged as strong competitors to diffusion and flow models for image generation, they suffer from a critical limitation in diversity, often producing nearly identical images even for simple prompts. This issue has largely gone unnoticed amid the predominant focus on image quality. We address this limitation at test time in two stages. First, inspired by diversity enhancement techniques in diffusion models, we propose injecting noise into the text embedding. This introduces a trade-off between diversity and image quality: as diversity increases, the image quality sharply declines. To preserve quality, we propose scale-travel: a novel latent refinement technique inspired by time-travel strategies in diffusion models. Specifically, we use a multi-scale autoencoder to extract coarse-scale tokens that enable us to resume generation at intermediate stages. Extensive experiments show that combining text-embedding noise injection with our scale-travel refinement significantly enhances diversity while minimizing image-quality degradation, achieving a new Pareto frontier in the diversity-quality trade-off. --- ### SUPN: Shallow Universal Polynomial Networks for Efficient Function Approximation Authors: Zachary Morrow, Michael Penwarden, Brian Chen, Aurya Javeed, Akil Narayan, John D. Jakeman Published: 2025-11-26 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2511.21414v2 Deep neural networks (DNNs) and Kolmogorov-Arnold networks (KANs) are flexible function approximators, but their accuracy can require substantial network depth, width, and trainable parameter counts. Beyond making the resulting networks less transparent, large parameter spaces can increase training cost and produce solutions that are sensitive to optimization and parameter initialization, leading to variability in generalization error. For these reasons, we propose Shallow Universal Polynomial Networks (SUPNs), which retain a single hidden layer while increasing the expressivity of each unit through a learnable multivariate polynomial inside each activation, which we refer to as a polynomial pre-activation. This construction trades architectural depth and width for greater expressivity within each hidden unit, reducing parameter counts and training cost while preserving a shallow computational graph. We establish two complementary universal approximation results: SUPNs are universal by increasing network width at fixed polynomial complexity, as in classical shallow-network approximation, and by increasing polynomial complexity at fixed finite width. We further prove that finite SUPNs can approach the best approximation attainable in a prescribed polynomial space to arbitrary relative tolerance, derive explicit quasi-optimal parameters, and establish corresponding convergence rates. We empirically evaluate SUPNs against DNNs, KANs, and polynomial projection on smooth, nonsmooth, and discontinuous function-approximation problems in one, two, and ten dimensions using more than 16,000 trained models. Across the target functions studied, SUPNs frequently achieve lower approximation error and variability than DNNs and KANs at comparable parameter counts while retaining lower training cost, supporting their use as efficient function approximators when the target structure is not known a priori. --- ### SUPN: Shallow Universal Polynomial Networks Authors: Zachary Morrow, Michael Penwarden, Brian Chen, Aurya Javeed, Akil Narayan, John D. Jakeman Published: 2025-11-26 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2511.21414v1 Deep neural networks (DNNs) and Kolmogorov-Arnold networks (KANs) are popular methods for function approximation due to their flexibility and expressivity. However, they typically require a large number of trainable parameters to produce a suitable approximation. Beyond making the resulting network less transparent, overparameterization creates a large optimization space, likely producing local minima in training that have quite different generalization errors. In this case, network initialization can have an outsize impact on the model's out-of-sample accuracy. For these reasons, we propose shallow universal polynomial networks (SUPNs). These networks replace all but the last hidden layer with a single layer of polynomials with learnable coefficients, leveraging the strengths of DNNs and polynomials to achieve sufficient expressivity with far fewer parameters. We prove that SUPNs converge at the same rate as the best polynomial approximation of the same degree, and we derive explicit formulas for quasi-optimal SUPN parameters. We complement theory with an extensive suite of numerical experiments involving SUPNs, DNNs, KANs, and polynomial projection in one, two, and ten dimensions, consisting of over 13,000 trained models. On the target functions we numerically studied, for a given number of trainable parameters, the approximation error and variability are often lower for SUPNs than for DNNs and KANs by an order of magnitude. In our examples, SUPNs even outperform polynomial projection on non-smooth functions. --- ### Automated Dynamic AI Inference Scaling on HPC-Infrastructure: Integrating Kubernetes, Slurm and vLLM Authors: Tim Trappen, Robert Keßler, Roland Pabel, Viktor Achter, Stefan Wesner Published: 2025-11-26 Categories: cs.DC, cs.AI, cs.DB, cs.PF arXiv: https://arxiv.org/abs/2511.21413v1 Due to rising demands for Artificial Inteligence (AI) inference, especially in higher education, novel solutions utilising existing infrastructure are emerging. The utilisation of High-Performance Computing (HPC) has become a prevalent approach for the implementation of such solutions. However, the classical operating model of HPC does not adapt well to the requirements of synchronous, user-facing dynamic AI application workloads. In this paper, we propose our solution that serves LLMs by integrating vLLM, Slurm and Kubernetes on the supercomputer \textit{RAMSES}. The initial benchmark indicates that the proposed architecture scales efficiently for 100, 500 and 1000 concurrent requests, incurring only an overhead of approximately 500 ms in terms of end-to-end latency. --- ### Subjective Depth and Timescale Transformers: Learning Where and When to Compute Authors: Frederico Wieser, Martin Benfeghoul, Haitham Bou Ammar, Jun Wang, Zafeirios Fountas Published: 2025-11-26 Categories: cs.LG, cs.AI, cs.CL, cs.IT arXiv: https://arxiv.org/abs/2511.21408v1 The rigid, uniform allocation of computation in standard Transformer (TF) architectures can limit their efficiency and scalability, particularly for large-scale models and long sequences. Addressing this, we introduce Subjective Depth Transformers (SDT) and Subjective Timescale Transformers (STT), two distinct architectures that leverage Bayesian surprise signals to dynamically route computation, learning where and when to compute within decoder-only TFs. SDT augments a decoder-only stack with alternating Decision and Dynamic layers: a Decision layer computes a full block 'posterior' and a lightweight 'prior,' while a Dynamic layer employs fixed-capacity Top-K routing based on Bayesian surprise (Expected and Unexpected Change), maintaining a static compute graph. STT extends this conditional computation to the temporal domain: a transition network predicts residual updates, forming a temporal 'change hypothesis' that informs a router to dynamically execute or bypass TF blocks for each token, managing KV-cache contributions. Both architectures exhibit the predicted shift from novelty to prediction driven gating over training, suggesting alignment with surprise based principles. While operating at reduced capacity, they offer preliminary insights into the compute-accuracy trade-offs of conditional computation. The proposed architectures establish a flexible framework for efficiency, reducing self-attention computation by 75% and KV-cache requirements by 50% within each compute skipping layer, setting a pathway for more efficient models. --- ### Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation Authors: Zhifeng Hao, Qibin Song, Ruichu Cai, Boyan Xu Published: 2025-11-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.21402v1 Recent divide-and-conquer reasoning approaches, particularly those based on Chain-of-Thought (CoT), have substantially improved the Text-to-SQL capabilities of Large Language Models (LLMs). However, when applied to complex enterprise databases, such methods struggle to maintain coherent reasoning due to limited context capacity, unreliable schema linking, and weak grounding in database semantics. To overcome these issues, we introduce DSR-SQL, a \textbf{D}ual-\textbf{S}tate \textbf{R}easoning framework that models Text-to-SQL as an interaction between an adaptive context state and a progressive generation state. The first constructs a compact, semantically faithful environment by refining large schemas and selecting relevant structures, while the second formalizes SQL synthesis as feedback-guided state transitions, enabling the model to self-correct and align with user intent. Without any post-training or in-context examples, DSR-SQL achieves competitive performance, reaching 35.28\% execution accuracy on Spider 2.0-Snow and 68.32\% on BIRD development set. Our implementation will be open-sourced at: https://github.com/DMIRLAB-Group/DSR-SQL. --- ### Can LLMs extract human-like fine-grained evidence for evidence-based fact-checking? Authors: Antonín Jarolím, Martin Fajčík, Lucia Makaiová Published: 2025-11-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.21401v1 Misinformation frequently spreads in user comments under online news articles, highlighting the need for effective methods to detect factually incorrect information. To strongly support or refute claims extracted from such comments, it is necessary to identify relevant documents and pinpoint the exact text spans that justify or contradict each claim. This paper focuses on the latter task -- fine-grained evidence extraction for Czech and Slovak claims. We create new dataset, containing two-way annotated fine-grained evidence created by paid annotators. We evaluate large language models (LLMs) on this dataset to assess their alignment with human annotations. The results reveal that LLMs often fail to copy evidence verbatim from the source text, leading to invalid outputs. Error-rate analysis shows that the {llama3.1:8b model achieves a high proportion of correct outputs despite its relatively small size, while the gpt-oss-120b model underperforms despite having many more parameters. Furthermore, the models qwen3:14b, deepseek-r1:32b, and gpt-oss:20b demonstrate an effective balance between model size and alignment with human annotations. ---