# Research Papers — 2025-10 · bundle page 129 of 217

> Full-text markdown of papers #6401–6450 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/129
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/128.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/130.md)

### Aligning Deep Implicit Preferences by Learning to Reason Defensively

Authors: Peiming Li, Zhiyuan Hu, Yang Tang, Shiyu Li, Xi Chen
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11194v3

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including unstated goals, semantic context and risk tolerances), and they lack the defensive reasoning required to navigate real-world ambiguity. This cognitive gap leads to responses that are superficial, brittle and short-sighted. To address this, we propose Critique-Driven Reasoning Alignment (CDRA), which reframes alignment from a scalar reward-matching task into a structured reasoning process. First, to bridge the preference inference gap, we introduce the DeepPref benchmark. This dataset, comprising 3000 preference-query pairs across 20 topics, is curated by simulating a multi-faceted cognitive council that produces critique-annotated reasoning chains to deconstruct query semantics and reveal latent risks. Second, to instill defensive reasoning, we introduce the Personalized Generative Process Reward Model (Pers-GenPRM), which frames reward modeling as a personalized reasoning task. It generates a critique chain to evaluate a response's alignment with user preferences before outputting a final score based on this rationale. Ultimately, this interpretable, structured reward signal guides policy model through Critique-Driven Policy Alignment, a process-level online reinforcement learning algorithm integrating both numerical and natural language feedback. Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning. Our code and dataset are available at https://github.com/Zephyrian-Hugh/Deep-pref.

---

### Efficient In-Memory Acceleration of Sparse Block Diagonal LLMs

Authors: João Paulo Cardoso de Lima, Marc Dietrich, Jeronimo Castrillon, Asif Ali Khan
Published: 2025-10-13
Categories: cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2510.11192v1

Structured sparsity enables deploying large language models (LLMs) on resource-constrained systems. Approaches like dense-to-sparse fine-tuning are particularly compelling, achieving remarkable structured sparsity by reducing the model size by over 6.7x, while still maintaining acceptable accuracy. Despite this reduction, LLM inference, especially the decode stage being inherently memory-bound, is extremely expensive on conventional Von-Neumann architectures. Compute-in-memory (CIM) architectures mitigate this by performing computations directly in memory, and when paired with sparse LLMs, enable storing and computing the entire model in memory, eliminating the data movement on the off-chip bus and improving efficiency. Nonetheless, naively mapping sparse matrices onto CIM arrays leads to poor array utilization and diminished computational efficiency. In this paper, we present an automated framework with novel mapping and scheduling strategies to accelerate sparse LLM inference on CIM accelerators. By exploiting block-diagonal sparsity, our approach improves CIM array utilization by over 50%, achieving more than 4x reduction in both memory footprint and the number of required floating-point operations.

---

### FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models

Authors: Shengming Yuan, Xinyu Lyu, Shuailong Wang, Beitao Chen, Jingkuan Song, Lianli Gao
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11190v3

Multimodal large language models (MLLMs) face an inherent trade-off between faithfulness and creativity, as different tasks require varying degrees of associative reasoning. However, existing methods lack the flexibility to modulate this reasoning strength, limiting MLLMs' adaptability across factual and creative scenarios. To bridge this gap, we propose equipping MLLMs with mechanisms that enable flexible control over associative reasoning. We begin by investigating the internal mechanisms underlying associative behavior in MLLMs and find that: (1) middle layers play a pivotal role in shaping model's associative tendencies, (2) modifying representations in these layers effectively regulates associative reasoning strength, and (3) hallucinations can be exploited to derive steering vectors that guide this modulation. Building on these findings, we introduce Flexible Association Control (FlexAC), a lightweight and training-free framework for modulating associative behavior in MLLMs. FlexAC first induces hallucination-guided intermediate representations to encode associative directions. Then, it selects high-association instances to construct effective associative steering vectors, whose strengths are adaptively calibrated to balance creative guidance with output stability. Finally, recognizing the multi-dimensional nature of associative reasoning, FlexAC incorporates task-specific associative vectors derived from a forward pass on a few target-domain samples, enabling models to follow diverse associative directions and better adapt to creative tasks. Notably, our method achieves up to a 5.8x improvement in creativity on Creation-MMBench and a 29% reduction in hallucination rate on CHAIR, surpassing existing baselines and demonstrating its effectiveness in enabling flexible control over associative reasoning in MLLMs. Our code is available at https://github.com/ylhz/FlexAC.

---

### Protein as a Second Language for LLMs

Authors: Xinhui Chen, Zuchao Li, Mengqi Gao, Yufeng Zhang, Chak Tou Leong, Haoyang Li, Jiaqi Chen
Published: 2025-10-13
Categories: cs.LG, cs.AI, q-bio.BM
arXiv: https://arxiv.org/abs/2510.11188v1

Deciphering the function of unseen protein sequences is a fundamental challenge with broad scientific impact, yet most existing methods depend on task-specific adapters or large-scale supervised fine-tuning. We introduce the "Protein-as-Second-Language" framework, which reformulates amino-acid sequences as sentences in a novel symbolic language that large language models can interpret through contextual exemplars. Our approach adaptively constructs sequence-question-answer triples that reveal functional cues in a zero-shot setting, without any further training. To support this process, we curate a bilingual corpus of 79,926 protein-QA instances spanning attribute prediction, descriptive understanding, and extended reasoning. Empirically, our method delivers consistent gains across diverse open-source LLMs and GPT-4, achieving up to 17.2% ROUGE-L improvement (average +7%) and even surpassing fine-tuned protein-specific language models. These results highlight that generic LLMs, when guided with protein-as-language cues, can outperform domain-specialized models, offering a scalable pathway for protein understanding in foundation models.

---

### Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization

Authors: Zhengyu Chen, Jinluan Yang, Teng Xiao, Ruochen Zhou, Luan Zhang, Xiangyu Xi, Xiaowei Shi, Wei Wang, Jinggang Wang
Published: 2025-10-13
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.11184v2

Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in reasoning and tool utilization. However, the generalization of tool-augmented reinforcement learning (RL) across diverse domains remains a significant challenge. Standard paradigms often treat tool usage as a linear or isolated event, which becomes brittle when transferring skills from restricted domains (e.g., mathematics) to open-ended tasks. In this work, we investigate the cross-domain generalization of an LLM agent trained exclusively on mathematical problem-solving. To facilitate robust skill transfer, we propose a {\textbf{R}einforcement Learning for \textbf{I}nterleaved \textbf{T}ool \textbf{E}xecution (RITE)}. Unlike traditional methods, RITE enforces a continuous ``Plan-Action-Reflection'' cycle, allowing the model to ground its reasoning in intermediate tool outputs and self-correct during long-horizon tasks. To effectively train this complex interleaved policy, we introduce {Dr. GRPO}, a robust optimization objective that utilizes token-level loss aggregation with importance sampling to mitigate reward sparsity and high-variance credit assignment. Furthermore, we employ a dual-component reward system and dynamic curriculum via online rollout filtering to ensure structural integrity and sample efficiency. Extensive experiments reveal that our approach, despite being trained solely on math tasks, achieves state-of-the-art performance across diverse reasoning domains, demonstrating high token efficiency and strong generalization capabilities.

---

### Saudi Sign Language Translation Using T5

Authors: Ali Alhejab, Tomas Zelezny, Lamya Alkanhal, Ivan Gruber, Yazeed Alharbi, Jakub Straka, Vaclav Javorek, Marek Hruz, Badriah Alkalifah, Ahmed Ali
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11183v1

This paper explores the application of T5 models for Saudi Sign Language (SSL) translation using a novel dataset. The SSL dataset includes three challenging testing protocols, enabling comprehensive evaluation across different scenarios. Additionally, it captures unique SSL characteristics, such as face coverings, which pose challenges for sign recognition and translation. In our experiments, we investigate the impact of pre-training on American Sign Language (ASL) data by comparing T5 models pre-trained on the YouTubeASL dataset with models trained directly on the SSL dataset. Experimental results demonstrate that pre-training on YouTubeASL significantly improves models' performance (roughly $3\times$ in BLEU-4), indicating cross-linguistic transferability in sign language models. Our findings highlight the benefits of leveraging large-scale ASL data to improve SSL translation and provide insights into the development of more effective sign language translation systems. Our code is publicly available at our GitHub repository.

---

### Generalisation of automatic tumour segmentation in histopathological whole-slide images across multiple cancer types

Authors: Ole-Johan Skrede, Manohar Pradhan, Maria Xepapadakis Isaksen, Tarjei Sveinsgjerd Hveem, Ljiljana Vlatkovic, Arild Nesbakken, Kristina Lindemann, Gunnar B Kristensen, Jenneke Kasius, Alain G Zeimet, Odd Terje Brustugun, Lill-Tove Rasmussen Busund et al.
Published: 2025-10-13
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.11182v1

Deep learning is expected to aid pathologists by automating tasks such as tumour segmentation. We aimed to develop one universal tumour segmentation model for histopathological images and examine its performance in different cancer types. The model was developed using over 20 000 whole-slide images from over 4 000 patients with colorectal, endometrial, lung, or prostate carcinoma. Performance was validated in pre-planned analyses on external cohorts with over 3 000 patients across six cancer types. Exploratory analyses included over 1 500 additional patients from The Cancer Genome Atlas. Average Dice coefficient was over 80% in all validation cohorts with en bloc resection specimens and in The Cancer Genome Atlas cohorts. No loss of performance was observed when comparing the universal model with models specialised on single cancer types. In conclusion, extensive and rigorous evaluations demonstrate that generic tumour segmentation by a single model is possible across cancer types, patient populations, sample preparations, and slide scanners.

---

### BLEnD-Vis: Benchmarking Multimodal Cultural Understanding in Vision Language Models

Authors: Bryan Chen Zhengyu Tan, Zheng Weihua, Zhengyuan Liu, Nancy F. Chen, Hwaran Lee, Kenny Tsu Wei Choo, Roy Ka-Wei Lee
Published: 2025-10-13
Categories: cs.CV, cs.CY
arXiv: https://arxiv.org/abs/2510.11178v2

As vision-language models (VLMs) are deployed globally, their ability to understand culturally situated knowledge becomes essential. Yet, existing evaluations largely assess static recall or isolated visual grounding, leaving unanswered whether VLMs possess robust and transferable cultural understanding. We introduce BLEnD-Vis, a multimodal, multicultural benchmark designed to evaluate the robustness of everyday cultural knowledge in VLMs across linguistic rephrasings and visual modalities. Building on the BLEnD dataset, BLEnD-Vis constructs 313 culturally grounded question templates spanning 16 regions and generates three aligned multiple-choice formats: (i) a text-only baseline querying from Region $\rightarrow$ Entity, (ii) an inverted text-only variant (Entity $\rightarrow$ Region), and (iii) a VQA-style version of (ii) with generated images. The resulting benchmark comprises 4,916 images and over 21,000 multiple-choice questions (MCQ) instances, validated through human annotation. BLEnD-Vis reveals significant fragility in current VLM cultural knowledge; models exhibit performance drops under linguistic rephrasing. While visual cues often aid performance, low cross-modal consistency highlights the challenges of robustly integrating textual and visual understanding, particularly in lower-resource regions. BLEnD-Vis thus provides a crucial testbed for systematically analysing cultural robustness and multimodal grounding, exposing limitations and guiding the development of more culturally competent VLMs. Code is available at https://github.com/Social-AI-Studio/BLEnD-Vis.

---

### G2L:From Giga-Scale to Cancer-Specific Large-Scale Pathology Foundation Models via Knowledge Distillation

Authors: Yesung Cho, Sungmin Lee, Geongyu Lee, Minkyung Lee, Jongbae Park, Dongmyung Shin
Published: 2025-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.11176v3

Recent studies in pathology foundation models have shown that scaling training data, diversifying cancer types, and increasing model size consistently improve their performance. However, giga-scale foundation models, which are trained on hundreds of thousands of slides covering tens of cancer types and contain billions of parameters, pose significant challenges for practical use due to their tremendous computational costs in both development and deployment. In this work, we present a novel strategy, named the G2L framework, to increase the performance of large-scale foundation models, which consist of only $15\%$ of the parameters of giga-scale models, to a comparable performance level of giga-scale models in cancer-specific tasks. Our approach applies knowledge distillation, transferring the capabilities of a giga-scale model to a large-scale model, using just 1K pathology slides of a target cancer (e.g., breast, prostate, etc.). The resulting distilled model not only outperformed state-of-the-art models of the same size (i.e., large-scale) across several benchmarks but also, interestingly, surpassed the giga-scale teacher and huge-scale models in some benchmarks. In addition, the distilled model exhibited a higher robustness index, indicating improved resilience to image variations originating from multiple institutions. These findings suggest that the proposed distillation approach for a large-scale model is a data- and parameter-efficient way to achieve giga-scale-level performance for cancer-specific applications without prohibitive computational burden.

---

### Reliable Cross-modal Alignment via Prototype Iterative Construction

Authors: Xiang Ma, Litian Xu, Lexin Fang, Caiming Zhang, Lizhen Cui
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11175v1

Cross-modal alignment is an important multi-modal task, aiming to bridge the semantic gap between different modalities. The most reliable fundamention for achieving this objective lies in the semantic consistency between matched pairs. Conventional methods implicitly assume embeddings contain solely semantic information, ignoring the impact of non-semantic information during alignment, which inevitably leads to information bias or even loss. These non-semantic information primarily manifest as stylistic variations in the data, which we formally define as style information. An intuitive approach is to separate style from semantics, aligning only the semantic information. However, most existing methods distinguish them based on feature columns, which cannot represent the complex coupling relationship between semantic and style information. In this paper, we propose PICO, a novel framework for suppressing style interference during embedding interaction. Specifically, we quantify the probability of each feature column representing semantic information, and regard it as the weight during the embedding interaction. To ensure the reliability of the semantic probability, we propose a prototype iterative construction method. The key operation of this method is a performance feedback-based weighting function, and we have theoretically proven that the function can assign higher weight to prototypes that bring higher performance improvements. Extensive experiments on various benchmarks and model backbones demonstrate the superiority of PICO, outperforming state-of-the-art methods by 5.2\%-14.1\%.

---

### Machine Learning-Integrated Hybrid Fluid-Kinetic Framework for Quantum Electrodynamic Laser Plasma Simulations

Authors: Sadra Saremi, Amirhossein Ahmadkhan Kordbacheh
Published: 2025-10-13
Categories: physics.plasm-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.11174v1

High-intensity laser plasma interactions create complex computational problems because they involve both fluid and kinetic regimes, which need models that maintain physical precision while keeping computational speed. The research introduces a machine learning-based three-dimensional hybrid fluid-particle-in-cell (PIC) system, which links relativistic plasma behavior to automatic regime transitions. The technique employs fluid approximations for stable areas but activates the PIC solver when SwitchNet directs it to unstable sections through its training on physics-based synthetic data. The model uses a smooth transition between Ammosov-Delone-Krainov (ADK) tunneling and multiphoton ionization rates to simulate ionization, while Airy-function approximations simulate quantum electrodynamic (QED) effects for radiation reaction and pair production. The convolutional neural network applies energy conservation through physics-based loss functions, which operate on normalized fields per channel. Monte Carlo dropout provides uncertainty measurement. The hybrid model produces precise predictions with coefficient of determination (R^2) values above 0.95 and mean squared errors below 10^-4 for all field components. This adaptive approach enhances the accuracy and scalability of laser-plasma simulations, providing a unified predictive framework for high-energy-density and particle acceleration applications.

---

### CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation

Authors: Zhenyu Lu, Liupeng Li, Jinpeng Wang, Yan Feng, Bin Chen, Ke Chen, Yaowei Wang
Published: 2025-10-13
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.11173v3

Existing works on reasoning segmentation either connect hidden features from a language model directly to a mask decoder or represent positions in text, which limits interpretability and semantic detail. To solve this, we present CoPRS, a Multi-modal Chain-of-Thought (MCoT)-based positional perception model that bridges language reasoning to segmentation through a differentiable and interpretable positional prior instantiated as a heatmap. By making the reasoning process clear via MCoT and expressing it as a dense, differentiable heatmap, this interface enhances interpretability and diagnostic analysis and yields more concentrated evidence on the target. A learnable concentration token aggregates features of the image and reasoning text to generate this positional prior, which is decoded to precise masks through a lightweight decoder, providing a direct connection between reasoning and segmentation. Across the RefCOCO series and ReasonSeg, CoPRS matches or surpasses the best reported metrics on each standard split under comparable protocols, with performance at or above the prior state of the art across both validation and test partitions. Extensive experiments demonstrate a strong positive correlation among the CoT trajectory, the generated heatmap, and the decoded mask, supporting an interpretable alignment between the reasoning output and downstream mask generation. Collectively, these findings support the utility of this paradigm in bridging reasoning and segmentation and show advantages in concentration driven by reasoning and in more precise mask prediction. Code has been released at https://github.com/ZhenyuLU-Heliodore/CoPRS.

---

### Multiview Manifold Evidential Fusion for PolSAR Image Classification

Authors: Junfei Shi, Haojia Zhang, Haiyan Jin, Junhuai Li, Xiaogang Song, Yuanfan Guo, Haonan Su, Weisi Lin
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11171v1

Polarimetric Synthetic Aperture Radar (PolSAR) covariance matrices and their extracted multi-features - such as scattering angle, entropy, texture, and boundary descriptors - provide complementary and physically interpretable information for image classification. Traditional fusion strategies typically concatenate these features or employ deep learning networks to combine them. However, the covariance matrices and multi-features, as two complementary views, lie on different manifolds with distinct geometric structures. Existing fusion methods also overlook the varying importance of different views and ignore uncertainty, often leading to unreliable predictions. To address these issues, we propose a Multiview Manifold Evidential Fusion (MMEFnet) method to effectively fuse these two views. It gives a new framework to integrate PolSAR manifold learning and evidence fusion into a unified architecture. Specifically, covariance matrices are represented on the Hermitian Positive Definite (HPD) manifold, while multi-features are modeled on the Grassmann manifold. Two different kernel metric learning networks are constructed to learn their manifold representations. Subsequently, a trusted multiview evidence fusion, replacing the conventional softmax classifier, estimates belief mass and quantifies the uncertainty of each view from the learned deep features. Finally, a Dempster-Shafer theory-based fusion strategy combines evidence, enabling a more reliable and interpretable classification. Extensive experiments on three real-world PolSAR datasets demonstrate that the proposed method consistently outperforms existing approaches in accuracy, robustness, and interpretability.

---

### EAGer: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling

Authors: Daniel Scalena, Leonidas Zotos, Elisabetta Fersini, Malvina Nissim, Ahmet Üstün
Published: 2025-10-13
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.11170v2

With the rise of reasoning language models and test-time scaling methods as a paradigm for improving model performance, substantial computation is often required to generate multiple candidate sequences from the same prompt. This enables exploration of different reasoning paths toward the correct solution, however, allocates the same compute budget for each prompt. Grounded on the assumption that different prompts carry different degrees of complexity, and thus different computation needs, we propose EAGer, a training-free generation method that leverages model uncertainty through token-wise entropy distribution to reduce redundant computation and concurrently improve overall performance. EAGer allows branching to multiple reasoning paths only in the presence of high-entropy tokens, and reallocates the saved compute budget to instances where exploration of alternative paths is most needed. We validate EAGer across multiple open-source models on complex reasoning benchmarks, with gains specifically demonstrated on AIME 2025. When target labels are accessible -- as in RLVR training pipelines -- EAGer achieves up to +37% in Pass@k and 59% fewer tokens; in test-time settings it still yields +12% in Pass@k and 64% fewer tokens compared to Full Parallel Sampling.

---

### PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures

Authors: Hind Atbir, Farah Cherfaoui, Guillaume Metzler, Emilie Morvant, Paul Viallard
Published: 2025-10-13
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.11169v2

PAC generalization bounds on the risk, when expressed in terms of the expected loss, are often insufficient to capture imbalances between subgroups in the data. To overcome this limitation, we introduce a new family of risk measures, called constrained f-entropic risk measures, which enable finer control over distributional shifts and subgroup imbalances via f-divergences, and include the Conditional Value at Risk (CVaR), a well-known risk measure. We derive both classical and disintegrated PAC-Bayesian generalization bounds for this family of risks, providing the first disintegratedPAC-Bayesian guarantees beyond standard risks. Building on this theory, we design a self-bounding algorithm that minimizes our bounds directly, yielding models with guarantees at the subgroup level. Finally, we empirically demonstrate the usefulness of our approach.

---

### ELMO: Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces

Authors: Jinbin Zhang, Nasib Ullah, Erik Schultheis, Rohit Babbar
Published: 2025-10-13
Categories: cs.LG, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.11168v1

Large output spaces, also referred to as Extreme multilabel classification (XMC), is a setting that arises, e.g., in large-scale tagging and product-to-product recommendation, and is characterized by the number of labels ranging from hundreds of thousands to millions. This means that the linear classification head, usually only a tiny fraction of the overall model, turns into the main driver for compute and memory demand. Current state-of-the-art XMC methods predominantly rely on FP16-FP32 mixed-precision training, which we show can be unstable, and inefficient in terms of memory usage and computational overhead. Meanwhile, existing low-precision methods typically retain higher precision for the classification layer. In this work, we propose ELMO, a pure low-precision training framework for XMC models using BFloat16 and Float8 data types. By leveraging Kahan summation and stochastic rounding, we demonstrate that XMC models can be effectively trained entirely in Float8, without relying on single-precision master weights or tensor scaling. Low-precision training, combined with our proposed memory optimizations -- gradient fusion and chunking -- enables significant reductions in GPU memory usage. For example, we train a 3-million-label XMC model with only 6.6 GiB of GPU memory, compared to the 39.7 GiB required by the optimized SOTA method, Renee without compromising accuracy.

---

### Bridging Gaps in Hate Speech Detection: Meta-Collections and Benchmarks for Low-Resource Iberian Languages

Authors: Paloma Piot, José Ramom Pichel Campos, Javier Parapar
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11167v1

Hate speech poses a serious threat to social cohesion and individual well-being, particularly on social media, where it spreads rapidly. While research on hate speech detection has progressed, it remains largely focused on English, resulting in limited resources and benchmarks for low-resource languages. Moreover, many of these languages have multiple linguistic varieties, a factor often overlooked in current approaches. At the same time, large language models require substantial amounts of data to perform reliably, a requirement that low-resource languages often cannot meet. In this work, we address these gaps by compiling a meta-collection of hate speech datasets for European Spanish, standardised with unified labels and metadata. This collection is based on a systematic analysis and integration of existing resources, aiming to bridge the data gap and support more consistent and scalable hate speech detection. We extended this collection by translating it into European Portuguese and into a Galician standard that is more convergent with Spanish and another Galician variant that is more convergent with Portuguese, creating aligned multilingual corpora. Using these resources, we establish new benchmarks for hate speech detection in Iberian languages. We evaluate state-of-the-art large language models in zero-shot, few-shot, and fine-tuning settings, providing baseline results for future research. Moreover, we perform a cross-lingual analysis with our target languages. Our findings underscore the importance of multilingual and variety-aware approaches in hate speech detection and offer a foundation for improved benchmarking in underrepresented European languages.

---

### Beyond single-model XAI: aggregating multi-model explanations for enhanced trustworthiness

Authors: Ilaria Vascotto, Alex Rodriguez, Alessandro Bonaita, Luca Bortolussi
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11164v1

The use of Artificial Intelligence (AI) models in real-world and high-risk applications has intensified the discussion about their trustworthiness and ethical usage, from both a technical and a legislative perspective. The field of eXplainable Artificial Intelligence (XAI) addresses this challenge by proposing explanations that bring to light the decision-making processes of complex black-box models. Despite being an essential property, the robustness of explanations is often an overlooked aspect during development: only robust explanation methods can increase the trust in the system as a whole. This paper investigates the role of robustness through the usage of a feature importance aggregation derived from multiple models ($k$-nearest neighbours, random forest and neural networks). Preliminary results showcase the potential in increasing the trustworthiness of the application, while leveraging multiple model's predictive power.

---

### Emergence of hybrid computational dynamics through reinforcement learning

Authors: Roman A. Kononov, Nikita A. Pospelov, Konstantin V. Anokhin, Vladimir V. Nekorkin, Oleg V. Maslennikov
Published: 2025-10-13
Categories: cs.LG, cs.NE, nlin.AO, q-bio.NC
arXiv: https://arxiv.org/abs/2510.11162v1

Understanding how learning algorithms shape the computational strategies that emerge in neural networks remains a fundamental challenge in machine intelligence. While network architectures receive extensive attention, the role of the learning paradigm itself in determining emergent dynamics remains largely unexplored. Here we demonstrate that reinforcement learning (RL) and supervised learning (SL) drive recurrent neural networks (RNNs) toward fundamentally different computational solutions when trained on identical decision-making tasks. Through systematic dynamical systems analysis, we reveal that RL spontaneously discovers hybrid attractor architectures, combining stable fixed-point attractors for decision maintenance with quasi-periodic attractors for flexible evidence integration. This contrasts sharply with SL, which converges almost exclusively to simpler fixed-point-only solutions. We further show that RL sculpts functionally balanced neural populations through a powerful form of implicit regularization -- a structural signature that enhances robustness and is conspicuously absent in the more heterogeneous solutions found by SL-trained networks. The prevalence of these complex dynamics in RL is controllably modulated by weight initialization and correlates strongly with performance gains, particularly as task complexity increases. Our results establish the learning algorithm as a primary determinant of emergent computation, revealing how reward-based optimization autonomously discovers sophisticated dynamical mechanisms that are less accessible to direct gradient-based optimization. These findings provide both mechanistic insights into neural computation and actionable principles for designing adaptive AI systems.

---

### One Size Does Not Fit All: Exploring Variable Thresholds for Distance-Based Multi-Label Text Classification

Authors: Jens Van Nooten, Andriy Kosar, Guy De Pauw, Walter Daelemans
Published: 2025-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.11160v1

Distance-based unsupervised text classification is a method within text classification that leverages the semantic similarity between a label and a text to determine label relevance. This method provides numerous benefits, including fast inference and adaptability to expanding label sets, as opposed to zero-shot, few-shot, and fine-tuned neural networks that require re-training in such cases. In multi-label distance-based classification and information retrieval algorithms, thresholds are required to determine whether a text instance is "similar" to a label or query. Similarity between a text and label is determined in a dense embedding space, usually generated by state-of-the-art sentence encoders. Multi-label classification complicates matters, as a text instance can have multiple true labels, unlike in multi-class or binary classification, where each instance is assigned only one label. We expand upon previous literature on this underexplored topic by thoroughly examining and evaluating the ability of sentence encoders to perform distance-based classification. First, we perform an exploratory study to verify whether the semantic relationships between texts and labels vary across models, datasets, and label sets by conducting experiments on a diverse collection of realistic multi-label text classification (MLTC) datasets. We find that similarity distributions show statistically significant differences across models, datasets and even label sets. We propose a novel method for optimizing label-specific thresholds using a validation set. Our label-specific thresholding method achieves an average improvement of 46% over normalized 0.5 thresholding and outperforms uniform thresholding approaches from previous work by an average of 14%. Additionally, the method demonstrates strong performance even with limited labeled examples.

---

### TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code

Authors: Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic
Published: 2025-10-13
Categories: cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2510.11151v1

Large language Models (LLMs) have shown remarkable proficiency in code generation tasks across various programming languages. However, their outputs often contain subtle but critical vulnerabilities, posing significant risks when deployed in security-sensitive or mission-critical systems. This paper introduces TypePilot, an agentic AI framework designed to enhance the security and robustness of LLM-generated code by leveraging strongly typed and verifiable languages, using Scala as a representative example. We evaluate the effectiveness of our approach in two settings: formal verification with the Stainless framework and general-purpose secure code generation. Our experiments with leading open-source LLMs reveal that while direct code generation often fails to enforce safety constraints, just as naive prompting for more secure code, our type-focused agentic pipeline substantially mitigates input validation and injection vulnerabilities. The results demonstrate the potential of structured, type-guided LLM workflows to improve the SotA of the trustworthiness of automated code generation in high-assurance domains.

---

### Enhanced Sampling for Efficient Learning of Coarse-Grained Machine Learning Potentials

Authors: Weilong Chen, Franz Görlich, Paul Fuchs, Julija Zavadlav
Published: 2025-10-13
Categories: physics.chem-ph, cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.11148v2

Coarse-graining (CG) enables molecular dynamics (MD) simulations of larger systems and longer timescales that are otherwise infeasible with atomistic models. Machine learning potentials (MLPs), with their capacity to capture many-body interactions, can provide accurate approximations of the potential of mean force (PMF) in CG models. Current CG MLPs are typically trained in a bottom-up manner via force matching, which in practice relies on configurations sampled from the unbiased equilibrium Boltzmann distribution to ensure thermodynamic consistency. This convention poses two key limitations: first, sufficiently long atomistic trajectories are needed to reach convergence; and second, even once equilibrated, transition regions remain poorly sampled. To address these issues, we employ enhanced sampling to bias along CG degrees of freedom for data generation, and then recompute the forces with respect to the unbiased potential. This strategy simultaneously shortens the simulation time required to produce equilibrated data and enriches sampling in transition regions, while preserving the correct PMF. We demonstrate its effectiveness on the Müller-Brown potential and capped alanine, achieving notable improvements. Our findings support the use of enhanced sampling for force matching as a promising direction to improve the accuracy and reliability of CG MLPs.

---

### torchsom: The Reference PyTorch Library for Self-Organizing Maps

Authors: Louis Berthier, Ahmed Shokry, Maxime Moreaud, Guillaume Ramelet, Eric Moulines
Published: 2025-10-13
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.11147v2

This paper introduces torchsom, an open-source Python library that provides a reference implementation of the Self-Organizing Map (SOM) in PyTorch. This package offers three main features: (i) dimensionality reduction, (ii) clustering, and (iii) friendly data visualization. It relies on a PyTorch backend, enabling (i) fast and efficient training of SOMs through GPU acceleration, and (ii) easy and scalable integrations with PyTorch ecosystem. Moreover, torchsom follows the scikit-learn API for ease of use and extensibility. The library is released under the Apache 2.0 license with 90% test coverage, and its source code and documentation are available at https://github.com/michelin/TorchSOM.

---

### $How^{2}$: How to learn from procedural How-to questions

Authors: Gautier Dagan, Frank Keller, Alex Lascarides
Published: 2025-10-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.11144v2

An agent facing a planning problem can use answers to how-to questions to reduce uncertainty and fill knowledge gaps, helping it solve both current and future tasks. However, their open ended nature, where valid answers to "How do I X?" range from executable actions to high-level descriptions of X's sub-goals, makes them challenging for AI agents to ask, and for AI experts to answer, in ways that support efficient planning. We introduce $How^{2}$, a memory agent framework that enables agents to ask how-to questions, store the answers, and reuse them for lifelong learning in interactive environments. We evaluate our approach in Plancraft, a Minecraft crafting environment, where agents must complete an assembly task by manipulating inventory items. Using teacher models that answer at varying levels of abstraction, from executable action sequences to high-level subgoal descriptions, we show that lifelong learning agents benefit most from answers that are abstracted and decoupled from the current state. $How^{2}$ offers a way for LLM-based agents to improve their planning capabilities over time by asking questions in interactive environments.

---

### Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis

Authors: Chuke Chen, Biao Luo, Nan Li, Boxiang Wang, Hang Yang, Jing Guo, Ming Xu
Published: 2025-10-13
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.11143v1

The rapid expansion of scientific data has widened the gap between analytical capability and research intent. Existing AI-based analysis tools, ranging from AutoML frameworks to agentic research assistants, either favor automation over transparency or depend on manual scripting that hinders scalability and reproducibility. We present ARIA (Automated Research Intelligence Assistant), a spec-driven, human-in-the-loop framework for automated and interpretable data analysis. ARIA integrates six interoperable layers, namely Command, Context, Code, Data, Orchestration, and AI Module, within a document-centric workflow that unifies human reasoning and machine execution. Through natural-language specifications, researchers define analytical goals while ARIA autonomously generates executable code, validates computations, and produces transparent documentation. Beyond achieving high predictive accuracy, ARIA can rapidly identify optimal feature sets and select suitable models, minimizing redundant tuning and repetitive experimentation. In the Boston Housing case, ARIA discovered 25 key features and determined XGBoost as the best performing model (R square = 0.93) with minimal overfitting. Evaluations across heterogeneous domains demonstrate ARIA's strong performance, interpretability, and efficiency compared with state-of-the-art systems. By combining AI for research and AI for science principles within a spec-driven architecture, ARIA establishes a new paradigm for transparent, collaborative, and reproducible scientific discovery.

---

### Validation of an Artificial Intelligence Tool for the Detection of Sperm DNA Fragmentation Using the TUNEL In Situ Hybridization Assay

Authors: Byron Alexander Jacobs, Aqeel Morris, Ifthakaar Shaik, Frando Lin
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11142v1

Sperm DNA fragmentation (SDF) is a critical parameter in male fertility assessment that conventional semen analysis fails to evaluate. This study presents the validation of a novel artificial intelligence (AI) tool designed to detect SDF through digital analysis of phase contrast microscopy images, using the terminal deoxynucleotidyl transferase dUTP nick end labeling (TUNEL) assay as the gold standard reference. Utilising the established link between sperm morphology and DNA integrity, the present work proposes a morphology assisted ensemble AI model that combines image processing techniques with state-of-the-art transformer based machine learning models (GC-ViT) for the prediction of DNA fragmentation in sperm from phase contrast images. The ensemble model is benchmarked against a pure transformer `vision' model as well as a `morphology-only` model. Promising results show the proposed framework is able to achieve sensitivity of 60\% and specificity of 75\%. This non-destructive methodology represents a significant advancement in reproductive medicine by enabling real-time sperm selection based on DNA integrity for clinical diagnostic and therapeutic applications.

---

### A Comprehensive Forecasting-Based Framework for Time Series Anomaly Detection: Benchmarking on the Numenta Anomaly Benchmark (NAB)

Authors: Mohammad Karami, Mostafa Jalali, Fatemeh Ghassemi
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11141v1

Time series anomaly detection is critical for modern digital infrastructures, yet existing methods lack systematic cross-domain evaluation. We present a comprehensive forecasting-based framework unifying classical methods (Holt-Winters, SARIMA) with deep learning architectures (LSTM, Informer) under a common residual-based detection interface. Our modular pipeline integrates preprocessing (normalization, STL decomposition), four forecasting models, four detection methods, and dual evaluation through forecasting metrics (MAE, RMSE, PCC) and detection metrics (Precision, Recall, F1, AUC). We conduct the first complete evaluation on the Numenta Anomaly Benchmark (58 datasets, 7 categories) with 232 model training runs and 464 detection evaluations achieving 100\% success rate. LSTM achieves best performance (F1: 0.688, ranking first or second on 81\% of datasets) with exceptional correlation on complex patterns (PCC: 0.999). Informer provides competitive accuracy (F1: 0.683) with 30\% faster training. Classical methods achieve perfect predictions on simple synthetic data with 60 lower cost but show 2-3 worse F1-scores on real-world datasets. Forecasting quality dominates detection performance: differences between detection methods (F1: 0.621-0.688) are smaller than between forecasting models (F1: 0.344-0.688). Our findings provide evidence-based guidance: use LSTM for complex patterns, Informer for efficiency-critical deployments, and classical methods for simple periodic data with resource constraints. The complete implementation and results establish baselines for future forecasting-based anomaly detection research.

---

### DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing

Authors: Zhijian Zhou, Xunye Tian, Liuhua Peng, Chao Lei, Antonin Schrab, Danica J. Sutherland, Feng Liu
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11140v1

To adapt kernel two-sample and independence testing to complex structured data, aggregation of multiple kernels is frequently employed to boost testing power compared to single-kernel tests. However, we observe a phenomenon that directly maximizing multiple kernel-based statistics may result in highly similar kernels that capture highly overlapping information, limiting the effectiveness of aggregation. To address this, we propose an aggregated statistic that explicitly incorporates kernel diversity based on the covariance between different kernels. Moreover, we identify a fundamental challenge: a trade-off between the diversity among kernels and the test power of individual kernels, i.e., the selected kernels should be both effective and diverse. This motivates a testing framework with selection inference, which leverages information from the training phase to select kernels with strong individual performance from the learned diverse kernel pool. We provide rigorous theoretical statements and proofs to show the consistency on the test power and control of Type-I error, along with asymptotic analysis of the proposed statistics. Lastly, we conducted extensive empirical experiments demonstrating the superior performance of our proposed approach across various benchmarks for both two-sample and independence testing.

---

### Test-Time Adaptation by Causal Trimming

Authors: Yingnan Liu, Rui Qiao, Mong Li Lee, Wynne Hsu
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11133v1

Test-time adaptation aims to improve model robustness under distribution shifts by adapting models with access to unlabeled target samples. A primary cause of performance degradation under such shifts is the model's reliance on features that lack a direct causal relationship with the prediction target. We introduce Test-time Adaptation by Causal Trimming (TACT), a method that identifies and removes non-causal components from representations for test distributions. TACT applies data augmentations that preserve causal features while varying non-causal ones. By analyzing the changes in the representations using Principal Component Analysis, TACT identifies the highest variance directions associated with non-causal features. It trims the representations by removing their projections on the identified directions, and uses the trimmed representations for the predictions. During adaptation, TACT continuously tracks and refines these directions to get a better estimate of non-causal features. We theoretically analyze the effectiveness of this approach and empirically validate TACT on real-world out-of-distribution benchmarks. TACT consistently outperforms state-of-the-art methods by a significant margin.

---

### video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM

Authors: Guangzhi Sun, Yixuan Li, Xiaodong Wu, Yudong Yang, Wei Li, Zejun Ma, Chao Zhang
Published: 2025-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.11129v2

Long-duration streaming video understanding is fundamental for future AI agents, yet remains limited by ineffective long-term memory. We introduce video-SALMONN S, a memory-enhanced streaming audio-visual large language model that processes over 3-hour videos at 1 FPS and 360p resolution, outperforming strong non-streaming models under the same memory budget. In addition to token merging or downsampling, video-SALMONN S is the first to employ test-time training (TTT) as a streaming memory mechanism for video understanding. TTT continuously transforms short-term multimodal representations into long-term memory embedded in model parameters. To improve long-range dependency modeling and memory capacity, we propose (i) a TTT_MEM layer with an additional long-span prediction objective, (ii) a two-stage training scheme, and (iii) a modality-aware memory reader. We further introduce the Episodic Learning from Video Memory (ELViM) benchmark, simulating agent-like scenarios where models must learn from videos observed hours earlier. video-SALMONN S consistently outperforms both streaming and non-streaming baselines by 3-7% on long video benchmarks. Notably, video-SALMONN S achieves a 15% absolute accuracy improvement over strong non-streaming models on ELViM, demonstrating strong learning abilities from video memory.

---

### Lightweight Facial Landmark Detection in Thermal Images via Multi-Level Cross-Modal Knowledge Transfer

Authors: Qiyi Tong, Olivia Nocentini, Marta Lagomarsino, Kuanqi Cai, Marta Lorenzini, Arash Ajoudani
Published: 2025-10-13
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.11128v2

Facial Landmark Detection (FLD) in thermal imagery is critical for applications in challenging lighting conditions, but it is hampered by the lack of rich visual cues. Conventional cross-modal solutions, like feature fusion or image translation from RGB data, are often computationally expensive or introduce structural artifacts, limiting their practical deployment. To address this, we propose Multi-Level Cross-Modal Knowledge Distillation (MLCM-KD), a novel framework that decouples high-fidelity RGB-to-thermal knowledge transfer from model compression to create both accurate and efficient thermal FLD models. A central challenge during knowledge transfer is the profound modality gap between RGB and thermal data, where traditional unidirectional distillation fails to enforce semantic consistency across disparate feature spaces. To overcome this, we introduce Dual-Injected Knowledge Distillation (DIKD), a bidirectional mechanism designed specifically for this task. DIKD establishes a connection between modalities: it not only guides the thermal student with rich RGB features but also validates the student's learned representations by feeding them back into the frozen teacher's prediction head. This closed-loop supervision forces the student to learn modality-invariant features that are semantically aligned with the teacher, ensuring a robust and profound knowledge transfer. Experiments show that our approach sets a new state-of-the-art on public thermal FLD benchmarks, notably outperforming previous methods while drastically reducing computational overhead.

---

### Refining Hybrid Genetic Search for CVRP via Reinforcement Learning-Finetuned LLM

Authors: Rongjie Zhu, Cong Zhang, Zhiguang Cao
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11121v1

While large language models (LLMs) are increasingly used as automated heuristic designers for vehicle routing problems (VRPs), current state-of-the-art methods predominantly rely on prompting massive, general-purpose models like GPT-4. This work challenges that paradigm by demonstrating that a smaller, specialized LLM, when meticulously fine-tuned, can generate components that surpass expert-crafted heuristics within advanced solvers. We propose RFTHGS, a novel Reinforcement learning (RL) framework for Fine-Tuning a small LLM to generate high-performance crossover operators for the Hybrid Genetic Search (HGS) solver, applied to the Capacitated VRP (CVRP). Our method employs a multi-tiered, curriculum-based reward function that progressively guides the LLM to master generating first compilable, then executable, and finally, superior-performing operators that exceed human expert designs. This is coupled with an operator caching mechanism that discourages plagiarism and promotes diversity during training. Comprehensive experiments show that our fine-tuned LLM produces crossover operators which significantly outperform the expert-designed ones in HGS. The performance advantage remains consistent, generalizing from small-scale instances to large-scale problems with up to 1000 nodes. Furthermore, RFTHGS exceeds the performance of leading neuro-combinatorial baselines, prompt-based methods, and commercial LLMs such as GPT-4o and GPT-4o-mini.

---

### Improving AI Efficiency in Data Centres by Power Dynamic Response

Authors: Andrea Marinoni, Sai Shivareddy, Pietro Lio', Weisi Lin, Erik Cambria, Clare Grey
Published: 2025-10-13
Categories: cs.AI, cs.AR, cs.DC
arXiv: https://arxiv.org/abs/2510.11119v1

The steady growth of artificial intelligence (AI) has accelerated in the recent years, facilitated by the development of sophisticated models such as large language models and foundation models. Ensuring robust and reliable power infrastructures is fundamental to take advantage of the full potential of AI. However, AI data centres are extremely hungry for power, putting the problem of their power management in the spotlight, especially with respect to their impact on environment and sustainable development. In this work, we investigate the capacity and limits of solutions based on an innovative approach for the power management of AI data centres, i.e., making part of the input power as dynamic as the power used for data-computing functions. The performance of passive and active devices are quantified and compared in terms of computational gain, energy efficiency, reduction of capital expenditure, and management costs by analysing power trends from multiple data platforms worldwide. This strategy, which identifies a paradigm shift in the AI data centre power management, has the potential to strongly improve the sustainability of AI hyperscalers, enhancing their footprint on environmental, financial, and societal fields.

---

### Demystifying Numerosity in Diffusion Models -- Limitations and Remedies

Authors: Yaqi Zhao, Xiaochen Wang, Li Dong, Wentao Zhang, Yuhui Yuan
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11117v1

Numerosity remains a challenge for state-of-the-art text-to-image generation models like FLUX and GPT-4o, which often fail to accurately follow counting instructions in text prompts. In this paper, we aim to study a fundamental yet often overlooked question: Can diffusion models inherently generate the correct number of objects specified by a textual prompt simply by scaling up the dataset and model size? To enable rigorous and reproducible evaluation, we construct a clean synthetic numerosity benchmark comprising two complementary datasets: GrayCount250 for controlled scaling studies, and NaturalCount6 featuring complex naturalistic scenes. Second, we empirically show that the scaling hypothesis does not hold: larger models and datasets alone fail to improve counting accuracy on our benchmark. Our analysis identifies a key reason: diffusion models tend to rely heavily on the noise initialization rather than the explicit numerosity specified in the prompt. We observe that noise priors exhibit biases toward specific object counts. In addition, we propose an effective strategy for controlling numerosity by injecting count-aware layout information into the noise prior. Our method achieves significant gains, improving accuracy on GrayCount250 from 20.0\% to 85.3\% and on NaturalCount6 from 74.8\% to 86.3\%, demonstrating effective generalization across settings.

---

### Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning

Authors: Hao Tang, Shengfeng He, Jing Qin
Published: 2025-10-13
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.11115v1

Few-shot learning (FSL) addresses the challenge of classifying novel classes with limited training samples. While some methods leverage semantic knowledge from smaller-scale models to mitigate data scarcity, these approaches often introduce noise and bias due to the data's inherent simplicity. In this paper, we propose a novel framework, Synergistic Knowledge Transfer (SynTrans), which effectively transfers diverse and complementary knowledge from large multimodal models to empower the off-the-shelf few-shot learner. Specifically, SynTrans employs CLIP as a robust teacher and uses a few-shot vision encoder as a weak student, distilling semantic-aligned visual knowledge via an unsupervised proxy task. Subsequently, a training-free synergistic knowledge mining module facilitates collaboration among large multimodal models to extract high-quality semantic knowledge. Building upon this, a visual-semantic bridging module enables bi-directional knowledge transfer between visual and semantic spaces, transforming explicit visual and implicit semantic knowledge into category-specific classifier weights. Finally, SynTrans introduces a visual weight generator and a semantic weight reconstructor to adaptively construct optimal multimodal FSL classifiers. Experimental results on four FSL datasets demonstrate that SynTrans, even when paired with a simple few-shot vision encoder, significantly outperforms current state-of-the-art methods.

---

### Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment

Authors: Chen Liu, Wenfang Yao, Kejing Yin, William K. Cheung, Jing Qin
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11112v1

Longitudinal multimodal data, including electronic health records (EHR) and sequential chest X-rays (CXRs), is critical for modeling disease progression, yet remains underutilized due to two key challenges: (1) redundancy in consecutive CXR sequences, where static anatomical regions dominate over clinically-meaningful dynamics, and (2) temporal misalignment between sparse, irregular imaging and continuous EHR data. We introduce $\texttt{DiPro}$, a novel framework that addresses these challenges through region-aware disentanglement and multi-timescale alignment. First, we disentangle static (anatomy) and dynamic (pathology progression) features in sequential CXRs, prioritizing disease-relevant changes. Second, we hierarchically align these static and dynamic CXR features with asynchronous EHR data via local (pairwise interval-level) and global (full-sequence) synchronization to model coherent progression pathways. Extensive experiments on the MIMIC dataset demonstrate that $\texttt{DiPro}$ could effectively extract temporal clinical dynamics and achieve state-of-the-art performance on both disease progression identification and general ICU prediction tasks.

---

### PhysioME: A Robust Multimodal Self-Supervised Framework for Physiological Signals with Missing Modalities

Authors: Cheol-Hui Lee, Hwa-Yeon Lee, Min-Kyung Jung, Dong-Joo Kim
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11110v1

Missing or corrupted modalities are common in physiological signal-based medical applications owing to hardware constraints or motion artifacts. However, most existing methods assume the availability of all modalities, resulting in substantial performance degradation in the absence of any modality. To overcome this limitation, this study proposes PhysioME, a robust framework designed to ensure reliable performance under missing modality conditions. PhysioME adopts: (1) a multimodal self-supervised learning approach that combines contrastive learning with masked prediction; (2) a Dual-PathNeuroNet backbone tailored to capture the temporal dynamics of each physiological signal modality; and (3) a restoration decoder that reconstructs missing modality tokens, enabling flexible processing of incomplete inputs. The experimental results show that PhysioME achieves high consistency and generalization performance across various missing modality scenarios. These findings highlight the potential of PhysioME as a reliable tool for supporting clinical decision-making in real-world settings with imperfect data availability.

---

### Graph Neural Network-Based Multicast Routing for On-Demand Streaming Services in 6G Networks

Authors: Xiucheng Wang, Zien Wang, Nan Cheng, Wenchao Xu, Wei Quan, Xuemin Shen
Published: 2025-10-13
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2510.11109v1

The increase of bandwidth-intensive applications in sixth-generation (6G) wireless networks, such as real-time volumetric streaming and multi-sensory extended reality, demands intelligent multicast routing solutions capable of delivering differentiated quality-of-service (QoS) at scale. Traditional shortest-path and multicast routing algorithms are either computationally prohibitive or structurally rigid, and they often fail to support heterogeneous user demands, leading to suboptimal resource utilization. Neural network-based approaches, while offering improved inference speed, typically lack topological generalization and scalability. To address these limitations, this paper presents a graph neural network (GNN)-based multicast routing framework that jointly minimizes total transmission cost and supports user-specific video quality requirements. The routing problem is formulated as a constrained minimum-flow optimization task, and a reinforcement learning algorithm is developed to sequentially construct efficient multicast trees by reusing paths and adapting to network dynamics. A graph attention network (GAT) is employed as the encoder to extract context-aware node embeddings, while a long short-term memory (LSTM) module models the sequential dependencies in routing decisions. Extensive simulations demonstrate that the proposed method closely approximates optimal dynamic programming-based solutions while significantly reducing computational complexity. The results also confirm strong generalization to large-scale and dynamic network topologies, highlighting the method's potential for real-time deployment in 6G multimedia delivery scenarios. Code is available at https://github.com/UNIC-Lab/GNN-Routing.

---

### A Vision for Access Control in LLM-based Agent Systems

Authors: Xinfeng Li, Dong Huang, Jie Li, Hongyi Cai, Zhenhong Zhou, Wei Dong, XiaoFeng Wang, Yang Liu
Published: 2025-10-13
Categories: cs.MA, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.11108v2

The autonomy and contextual complexity of LLM-based agents render traditional access control (AC) mechanisms insufficient. Static, rule-based systems designed for predictable environments are fundamentally ill-equipped to manage the dynamic information flows inherent in agentic interactions. This position paper argues for a paradigm shift from binary access control to a more sophisticated model of information governance, positing that the core challenge is not merely about permission, but about governing the flow of information. We introduce Agent Access Control (AAC), a novel framework that reframes AC as a dynamic, context-aware process of information flow governance. AAC operates on two core modules: (1) multi-dimensional contextual evaluation, which assesses not just identity but also relationships, scenarios, and norms; and (2) adaptive response formulation, which moves beyond simple allow/deny decisions to shape information through redaction, summarization, and paraphrasing. This vision, powered by a dedicated AC reasoning engine, aims to bridge the gap between human-like nuanced judgment and scalable Al safety, proposing a new conceptual lens for future research in trustworthy agent design.

---

### MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps

Authors: Jiahui Lei, Kyle Genova, George Kopanas, Noah Snavely, Leonidas Guibas
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11107v1

This paper addresses the challenge of learning semantically and functionally meaningful 3D motion priors from real-world videos, in order to enable prediction of future 3D scene motion from a single input image. We propose a novel pixel-aligned Motion Map (MoMap) representation for 3D scene motion, which can be generated from existing generative image models to facilitate efficient and effective motion prediction. To learn meaningful distributions over motion, we create a large-scale database of MoMaps from over 50,000 real videos and train a diffusion model on these representations. Our motion generation not only synthesizes trajectories in 3D but also suggests a new pipeline for 2D video synthesis: first generate a MoMap, then warp an image accordingly and complete the warped point-based renderings. Experimental results demonstrate that our approach generates plausible and semantically consistent 3D scene motion.

---

### Compositional Zero-Shot Learning: A Survey

Authors: Ans Munir, Faisal Z. Qureshi, Mohsen Ali, Muhammad Haris Khan
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11106v1

Compositional Zero-Shot Learning (CZSL) is a critical task in computer vision that enables models to recognize unseen combinations of known attributes and objects during inference, addressing the combinatorial challenge of requiring training data for every possible composition. This is particularly challenging because the visual appearance of primitives is highly contextual; for example, ``small'' cats appear visually distinct from ``older'' ones, and ``wet'' cars differ significantly from ``wet'' cats. Effectively modeling this contextuality and the inherent compositionality is crucial for robust compositional zero-shot recognition. This paper presents, to our knowledge, the first comprehensive survey specifically focused on Compositional Zero-Shot Learning. We systematically review the state-of-the-art CZSL methods, introducing a taxonomy grounded in disentanglement, with four families of approaches: no explicit disentanglement, textual disentanglement, visual disentanglement, and cross-modal disentanglement. We provide a detailed comparative analysis of these methods, highlighting their core advantages and limitations in different problem settings, such as closed-world and open-world CZSL. Finally, we identify the most significant open challenges and outline promising future research directions. This survey aims to serve as a foundational resource to guide and inspire further advancements in this fascinating and important field. Papers studied in this survey with their official code are available on our github: https://github.com/ans92/Compositional-Zero-Shot-Learning

---

### Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization

Authors: Junjie Lu, Yuliang Liu, Chaofeng Qu, Wei Shen, Zhouhan Lin, Chuheng Zhang, Min Xu
Published: 2025-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.11104v2

Current approaches for strengthening LLM reasoning tend to introduce a training bias toward human-like reasoning trajectories. In step-wise preference optimization, in particular, dependence on human or higher-capacity model annotations for intermediate steps limits exploration of alternative, non-human-like reasoning paths and thus constrains achievable performance. Furthermore, through a small-scale pilot study, we observed that in approximately 75% of cases, the model's first erroneous step occurs after the lowest-confidence point. This suggests that guiding the model at its lowest-confidence point before an error provides more accurate supervision than locating the first explicit error. In this paper, we propose Confidence-Guided Reasoning Path Preference Optimization (CGPO), a method that leverages a confidence signal to identify points of maximal uncertainty in the model's reasoning process and applies self-generated, non-human-like reasoning-path guidance to mitigate trajectory drift. Our experiments span diverse models applied to both code and mathematical reasoning tasks. The results show that, with the same amount of training data, our method using data generated by a small model can achieve better performance in most cases compared with approaches using data generated by a strong model or human-annotated.

---

### A Primer on SO(3) Action Representations in Deep Reinforcement Learning

Authors: Martin Schuck, Sherif Samy, Angela P. Schoellig
Published: 2025-10-13
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.11103v3

Many robotic control tasks require policies to act on orientations, yet the geometry of SO(3) makes this nontrivial. Because SO(3) admits no global, smooth, minimal parameterization, common representations such as Euler angles, quaternions, rotation matrices, and Lie algebra coordinates introduce distinct constraints and failure modes. While these trade-offs are well studied for supervised learning, their implications for actions in reinforcement learning remain unclear. We systematically evaluate SO(3) action representations across three standard continuous control algorithms, PPO, SAC, and TD3, under dense and sparse rewards. We compare how representations shape exploration, interact with entropy regularization, and affect training stability through empirical studies and analyze the implications of different projections for obtaining valid rotations from Euclidean network outputs. Across a suite of robotics benchmarks, we quantify the practical impact of these choices and distill simple, implementation-ready guidelines for selecting and using rotation actions. Our results highlight that representation-induced geometry strongly influences exploration and optimization and show that representing actions as tangent vectors in the local frame yields the most reliable results across algorithms. The project webpage and code are available at amacati.github.io/so3_primer.

---

### HoMer: Addressing Heterogeneities by Modeling Sequential and Set-wise Contexts for CTR Prediction

Authors: Shuwei Chen, Jiajun Cui, Zhengqi Xu, Fan Zhang, Jiangke Fan, Teng Zhang, Xingxing Wang
Published: 2025-10-13
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.11100v2

Click-through rate (CTR) prediction, which models behavior sequence and non-sequential features (e.g., user/item profiles or cross features) to infer user interest, underpins industrial recommender systems. However, most methods face three forms of heterogeneity that degrade predictive performance: (i) Feature Heterogeneity persists when limited sequence side features provide less granular interest representation compared to extensive non-sequential features, thereby impairing sequence modeling performance; (ii) Context Heterogeneity arises because a user's interest in an item will be influenced by other items, yet point-wise prediction neglects cross-item interaction context from the entire item set; (iii) Architecture Heterogeneity stems from the fragmented integration of specialized network modules, which compounds the model's effectiveness, efficiency and scalability in industrial deployments. To tackle the above limitations, we propose HoMer, a Homogeneous-Oriented TransforMer for modeling sequential and set-wise contexts. First, we align sequence side features with non-sequential features for accurate sequence modeling and fine-grained interest representation. Second, we shift the prediction paradigm from point-wise to set-wise, facilitating cross-item interaction in a highly parallel manner. Third, HoMer's unified encoder-decoder architecture achieves dual optimization through structural simplification and shared computation, ensuring computational efficiency while maintaining scalability with model size. Without arduous modification to the prediction pipeline, HoMer successfully scales up and outperforms our industrial baseline by 0.0099 in the AUC metric, and enhances online business metrics like CTR/RPM by 1.99%/2.46%. Additionally, HoMer saves 27% of GPU resources via preliminary engineering optimization, further validating its superiority and practicality.

---

### VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents

Authors: Jiliang Hu, Wenfu Wang, Zuchao Li, Chenxing Li, Yiyang Zhao, Hanzhao Li, Liqiang Zhang, Meng Yu, Dong Yu
Published: 2025-10-13
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2510.11098v5

Recent advances in large audio language models (LALMs) have greatly enhanced multimodal conversational systems. However, existing benchmarks remain limited -- they are mainly English-centric, rely on synthetic speech, and lack comprehensive, discriminative evaluation across multiple dimensions. To address these gaps, we present Voice Chat Bot Bench (VCB Bench) -- a high-quality Chinese benchmark built entirely on real human speech. VCB Bench evaluates LALMs from three complementary perspectives: instruction following (including speech-level control beyond text commands), knowledge understanding (general knowledge, reasoning, and daily dialogue), and robustness (stability under perturbations in content, environment, and speaker traits). Experiments on representative LALMs reveal notable performance gaps and highlight future directions for improvement. VCB Bench provides a reproducible and fine-grained evaluation framework, offering standardized methodology and practical insights for advancing Chinese voice conversational models.

---

### CoDefend: Cross-Modal Collaborative Defense via Diffusion Purification and Prompt Optimization

Authors: Fengling Zhu, Boshi Liu, Jingyu Hua, Sheng Zhong
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11096v1

Multimodal Large Language Models (MLLMs) have achieved remarkable success in tasks such as image captioning, visual question answering, and cross-modal reasoning by integrating visual and textual modalities. However, their multimodal nature also exposes them to adversarial threats, where attackers can perturb either modality or both jointly to induce harmful, misleading, or policy violating outputs. Existing defense strategies, such as adversarial training and input purification, face notable limitations: adversarial training typically improves robustness only against known attacks while incurring high computational costs, whereas conventional purification approaches often suffer from degraded image quality and insufficient generalization to complex multimodal tasks. In this work, we focus on defending the visual modality, which frequently serves as the primary entry point for adversarial manipulation. We propose a supervised diffusion based denoising framework that leverages paired adversarial clean image datasets to fine-tune diffusion models with directional, task specific guidance. Unlike prior unsupervised purification methods such as DiffPure, our approach achieves higher quality reconstructions while significantly improving defense robustness in multimodal tasks. Furthermore, we incorporate prompt optimization as a complementary defense mechanism, enhancing resistance against diverse and unseen attack strategies. Extensive experiments on image captioning and visual question answering demonstrate that our method not only substantially improves robustness but also exhibits strong transferability to unknown adversarial attacks. These results highlight the effectiveness of supervised diffusion based denoising for multimodal defense, paving the way for more reliable and secure deployment of MLLMs in real world applications.

---

### Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution

Authors: Bozhou Zhang, Nan Song, Jingyu Li, Xiatian Zhu, Jiankang Deng, Li Zhang
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11092v1

End-to-end autonomous driving methods aim to directly map raw sensor inputs to future driving actions such as planned trajectories, bypassing traditional modular pipelines. While these approaches have shown promise, they often operate under a one-shot paradigm that relies heavily on the current scene context, potentially underestimating the importance of scene dynamics and their temporal evolution. This limitation restricts the model's ability to make informed and adaptive decisions in complex driving scenarios. We propose a new perspective: the future trajectory of an autonomous vehicle is closely intertwined with the evolving dynamics of its environment, and conversely, the vehicle's own future states can influence how the surrounding scene unfolds. Motivated by this bidirectional relationship, we introduce SeerDrive, a novel end-to-end framework that jointly models future scene evolution and trajectory planning in a closed-loop manner. Our method first predicts future bird's-eye view (BEV) representations to anticipate the dynamics of the surrounding scene, then leverages this foresight to generate future-context-aware trajectories. Two key components enable this: (1) future-aware planning, which injects predicted BEV features into the trajectory planner, and (2) iterative scene modeling and vehicle planning, which refines both future scene prediction and trajectory generation through collaborative optimization. Extensive experiments on the NAVSIM and nuScenes benchmarks show that SeerDrive significantly outperforms existing state-of-the-art methods.

---

### Text-Enhanced Panoptic Symbol Spotting in CAD Drawings

Authors: Xianlin Liu, Yan Gong, Bohao Li, Jiajing Huang, Bowen Du, Junchen Ye, Liyan Xu
Published: 2025-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.11091v1

With the widespread adoption of Computer-Aided Design(CAD) drawings in engineering, architecture, and industrial design, the ability to accurately interpret and analyze these drawings has become increasingly critical. Among various subtasks, panoptic symbol spotting plays a vital role in enabling downstream applications such as CAD automation and design retrieval. Existing methods primarily focus on geometric primitives within the CAD drawings to address this task, but they face following major problems: they usually overlook the rich textual annotations present in CAD drawings and they lack explicit modeling of relationships among primitives, resulting in incomprehensive understanding of the holistic drawings. To fill this gap, we propose a panoptic symbol spotting framework that incorporates textual annotations. The framework constructs unified representations by jointly modeling geometric and textual primitives. Then, using visual features extract by pretrained CNN as the initial representations, a Transformer-based backbone is employed, enhanced with a type-aware attention mechanism to explicitly model the different types of spatial dependencies between various primitives. Extensive experiments on the real-world dataset demonstrate that the proposed method outperforms existing approaches on symbol spotting tasks involving textual annotations, and exhibits superior robustness when applied to complex CAD drawings.

---

### Source-Free Object Detection with Detection Transformer

Authors: Huizai Yao, Sicheng Zhao, Shuo Lu, Hui Chen, Yangyang Li, Guoping Liu, Tengfei Xing, Chenggang Yan, Jianhua Tao, Guiguang Ding
Published: 2025-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.11090v1

Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data. Most existing SFOD approaches are either confined to conventional object detection (OD) models like Faster R-CNN or designed as general solutions without tailored adaptations for novel OD architectures, especially Detection Transformer (DETR). In this paper, we introduce Feature Reweighting ANd Contrastive Learning NetworK (FRANCK), a novel SFOD framework specifically designed to perform query-centric feature enhancement for DETRs. FRANCK comprises four key components: (1) an Objectness Score-based Sample Reweighting (OSSR) module that computes attention-based objectness scores on multi-scale encoder feature maps, reweighting the detection loss to emphasize less-recognized regions; (2) a Contrastive Learning with Matching-based Memory Bank (CMMB) module that integrates multi-level features into memory banks, enhancing class-wise contrastive learning; (3) an Uncertainty-weighted Query-fused Feature Distillation (UQFD) module that improves feature distillation through prediction quality reweighting and query feature fusion; and (4) an improved self-training pipeline with a Dynamic Teacher Updating Interval (DTUI) that optimizes pseudo-label quality. By leveraging these components, FRANCK effectively adapts a source-pre-trained DETR model to a target domain with enhanced robustness and generalization. Extensive experiments on several widely used benchmarks demonstrate that our method achieves state-of-the-art performance, highlighting its effectiveness and compatibility with DETR-based SFOD models.

---

### Modeling AI-Driven Production and Competitiveness A Multi-Agent Economic Simulation of China and the United States

Authors: Yuxinyue Qian, Jun Liu
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11085v1

With the rapid development of artificial intelligence (AI) technology, socio-economic systems are entering a new stage of "human-AI co-creation." Building upon a previously established multi-level intelligent agent economic model, this paper conducts simulation-based comparisons of macroeconomic output evolution in China and the United States under different mechanisms-AI collaboration, network effects, and AI autonomous production. The results show that: (1) when AI functions as an independent productive entity, the overall growth rate of social output far exceeds that of traditional human-labor-based models; (2) China demonstrates clear potential for acceleration in both the expansion of intelligent agent populations and the pace of technological catch-up, offering the possibility of achieving technological convergence or even partial surpassing. This study provides a systematic, model-based analytical framework for understanding AI-driven production system transformation and shifts in international competitiveness, as well as quantitative insights for relevant policy formulation.

---