# Research Papers — 2025-10 · bundle page 165 of 217

> Full-text markdown of papers #8201–8250 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/165
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/164.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/166.md)

### COMPASS: Benchmarking Constrained Optimization in LLM Agents

Authors: Tian Qin, Felix Bai, Ting-Yao Hu, Raviteja Vemulapalli, Hema Swetha Koppula, Zhiyang Xu, Bowen Jin, Mert Cemri, Jiarui Lu, Zirui Wang, Meng Cao
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07043v2

Human decision-making often involves constrained optimization. As LLM agents are deployed to assist with real-world tasks like travel planning, shopping, and scheduling, they must mirror this capability. We introduce COMPASS, a benchmark that evaluates whether LLM agents can perform constrained optimization in realistic travel planning settings. To success in these tasks, agents must engage in multi-turn conversations with user to gather task information as well as use tools to gather information from the database. Then agents must propose a solution that not only satisfies hard constraints but also optimizes user's utility objective. Evaluating state-of-the-art models, we reveal a significant feasible-optimal gap: while models achieve 70-90% feasibility (constraint satisfaction), they reach only 20-60% optimality (utility optimization). Our analysis shows that tool use is not the bottleneck. Instead, the core limitation is insufficient exploration of the search space, with success strongly correlating with information gathered. Coding agents show a promising approach to mitigate this gap. Together, COMPASS provides a testbed for developing LLM agents that can truly mirror human decision-making by both satisfying constraints and optimizing objectives.

---

### U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking

Authors: Fenghe Tang, Chengqi Dong, Wenxin Ma, Zikang Xu, Heqin Zhu, Zihang Jiang, Rongsheng Wang, Yuhao Wang, Chenxu Wu, Shaohua Kevin Zhou
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07041v1

Over the past decade, U-Net has been the dominant architecture in medical image segmentation, leading to the development of thousands of U-shaped variants. Despite its widespread adoption, there is still no comprehensive benchmark to systematically evaluate their performance and utility, largely because of insufficient statistical validation and limited consideration of efficiency and generalization across diverse datasets. To bridge this gap, we present U-Bench, the first large-scale, statistically rigorous benchmark that evaluates 100 U-Net variants across 28 datasets and 10 imaging modalities. Our contributions are threefold: (1) Comprehensive Evaluation: U-Bench evaluates models along three key dimensions: statistical robustness, zero-shot generalization, and computational efficiency. We introduce a novel metric, U-Score, which jointly captures the performance-efficiency trade-off, offering a deployment-oriented perspective on model progress. (2) Systematic Analysis and Model Selection Guidance: We summarize key findings from the large-scale evaluation and systematically analyze the impact of dataset characteristics and architectural paradigms on model performance. Based on these insights, we propose a model advisor agent to guide researchers in selecting the most suitable models for specific datasets and tasks. (3) Public Availability: We provide all code, models, protocols, and weights, enabling the community to reproduce our results and extend the benchmark with future methods. In summary, U-Bench not only exposes gaps in previous evaluations but also establishes a foundation for fair, reproducible, and practically relevant benchmarking in the next decade of U-Net-based segmentation models. The project can be accessed at: https://fenghetan9.github.io/ubench. Code is available at: https://github.com/FengheTan9/U-Bench.

---

### Tool-Augmented Policy Optimization: Synergizing Reasoning and Adaptive Tool Use with Reinforcement Learning

Authors: Wenxun Wu, Yuanyang Li, Guhan Chen, Linyue Wang, Hongyang Chen
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07038v2

Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on benchmarks involving mathematical reasoning. However, language models relying solely on direct inference still struggle with tasks demanding up-to-date knowledge or computational tools such as calculators and code interpreters for complex arithmetic operations. To overcome these limitations, we propose Tool-Augmented Policy Optimization (TAPO), a novel reinforcement learning framework that systematically integrates multi-hop reasoning with adaptive tool-calling capabilities. Our approach employs a modified version of Dynamic Sampling Policy Optimization (DAPO), a recently developed RL paradigm, which we adapt specifically for tool invocation scenarios, enabling models to dynamically interleave complex reasoning with on-demand tool usage (including search APIs and Python interpreters). To support this research, we introduce two new datasets: TAPO-easy-60K and TAPO-hard-18K, specifically designed to train and evaluate both fact-based reasoning and mathematical calculation capabilities. Our experiments on Qwen2.5-3B and Qwen2.5-7B models demonstrate the effectiveness of our approach, with both models achieving state-of-the-art performance on tasks requiring external knowledge and mathematical computation among methods with comparable parameters. Notably, TAPO achieves more efficient tool utilization than baseline methods while preventing excessive calls caused by reward hacking. These results highlight the significant potential of combining advanced reasoning with tool usage to enhance model performance in knowledge-intensive and computationally demanding tasks.

---

### Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities

Authors: Rajvee Sheth, Samridhi Raj Sinha, Mahavir Patil, Himanshu Beniwal, Mayank Singh
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07037v6

Amidst the rapid advances of large language models (LLMs), most LLMs still struggle with mixed-language inputs, limited Codeswitching (CSW) datasets, and evaluation biases, which hinder their deployment in multilingual societies. This survey provides the first comprehensive analysis of CSW-aware LLM research, reviewing 327 studies spanning five research areas, 15+ NLP tasks, 30+ datasets, and 80+ languages. We categorize recent advances by architecture, training strategy, and evaluation methodology, outlining how LLMs have reshaped CSW modeling and identifying the challenges that persist. The paper concludes with a roadmap that emphasizes the need for inclusive datasets, fair evaluation, and linguistically grounded models to achieve truly multilingual capabilities https://github.com/lingo-iitgn/awesome-code-mixing/.

---

### Unified Molecule Pre-training with Flexible 2D and 3D Modalities: Single and Paired Modality Integration

Authors: Tengwei Song, Min Wu, Yuan Fang
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.07035v1

Molecular representation learning plays a crucial role in advancing applications such as drug discovery and material design. Existing work leverages 2D and 3D modalities of molecular information for pre-training, aiming to capture comprehensive structural and geometric insights. However, these methods require paired 2D and 3D molecular data to train the model effectively and prevent it from collapsing into a single modality, posing limitations in scenarios where a certain modality is unavailable or computationally expensive to generate. To overcome this limitation, we propose FlexMol, a flexible molecule pre-training framework that learns unified molecular representations while supporting single-modality input. Specifically, inspired by the unified structure in vision-language models, our approach employs separate models for 2D and 3D molecular data, leverages parameter sharing to improve computational efficiency, and utilizes a decoder to generate features for the missing modality. This enables a multistage continuous learning process where both modalities contribute collaboratively during training, while ensuring robustness when only one modality is available during inference. Extensive experiments demonstrate that FlexMol achieves superior performance across a wide range of molecular property prediction tasks, and we also empirically demonstrate its effectiveness with incomplete data. Our code and data are available at https://github.com/tewiSong/FlexMol.

---

### Auditing a KB Elicitation of Frontier LLM Knowledge: A Multi-dimensional Analysis of GPTKB v1.5

Authors: Shrestha Ghosh, Luca Giordano, Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.07024v4

LLMs are remarkable artifacts that have revolutionized a range of knowledge-intensive tasks. A significant contributor is their factual knowledge, which, to date, remains poorly understood, and is usually analyzed from biased samples. In this paper, we provide a framework and the results of a multi-dimensional analysis of GPTKB v1.5 (Hu et al., 2025a), a recursively elicited Knowledge Base (KB) of 100 million facts (or beliefs) of a frontier LLM, namely, GPT-4.1. Given the scale of the elicited facts, we provide a multi-dimensional approach to qualitatively and quantitatively analyze these facts as opposed to the mainstream fact completion benchmarks, which are prone to availability bias. We find that the models' factual knowledge differs quite significantly from established knowledge bases, and that its accuracy is significantly lower than indicated by previous benchmarks. We also find that inconsistency, ambiguity and hallucinations are major issues, shedding light on future research opportunities in neuro-symbolic AI concerning extraction, consolidation and verification of factual LLM knowledge.

---

### Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy

Authors: ZiHeng Huang, Di Wu, Jun Bai, Jiale Zhang, Sicong Cao, Ji Zhang, Yingjie Hu
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.07022v1

Machine unlearning is critical for enforcing data deletion rights like the "right to be forgotten." As a decentralized paradigm, Federated Learning (FL) also requires unlearning, but realistic implementations face two major challenges. First, fairness in Federated Unlearning (FU) is often overlooked. Exact unlearning methods typically force all clients into costly retraining, even those uninvolved. Approximate approaches, using gradient ascent or distillation, make coarse interventions that can unfairly degrade performance for clients with only retained data. Second, most FU evaluations rely on synthetic data assumptions (IID/non-IID) that ignore real-world heterogeneity. These unrealistic benchmarks obscure the true impact of unlearning and limit the applicability of current methods. We first conduct a comprehensive benchmark of existing FU methods under realistic data heterogeneity and fairness conditions. We then propose a novel, fairness-aware FU approach, Federated Cross-Client-Constrains Unlearning (FedCCCU), to explicitly address both challenges. FedCCCU offers a practical and scalable solution for real-world FU. Experimental results show that existing methods perform poorly in realistic settings, while our approach consistently outperforms them.

---

### Native Hybrid Attention for Efficient Sequence Modeling

Authors: Jusen Du, Jiaxi Hu, Tao Zhang, Weigao Sun, Yu Cheng
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.07019v3

Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a novel hybrid architecture of linear and full attention that integrates both intra & inter-layer hybridization into a unified layer design. NHA maintains long-term context in key-value slots updated by a linear RNN, and augments them with short-term tokens from a sliding window. A single softmax attention operation is then applied over all keys and values, enabling per-token and per-head context-dependent weighting without requiring additional fusion parameters. The inter-layer behavior is controlled through a single hyperparameter, the sliding window size, which allows smooth adjustment between purely linear and full attention while keeping all layers structurally uniform. Experimental results show that NHA surpasses Transformers and other hybrid baselines on recall-intensive and commonsense reasoning tasks. Furthermore, pretrained LLMs can be structurally hybridized with NHA, achieving competitive accuracy while delivering significant efficiency gains. Code is available at https://github.com/JusenD/NHA.

---

### Sharpness-Aware Data Generation for Zero-shot Quantization

Authors: Dung Hoang-Anh, Cuong Pham Trung Le, Jianfei Cai, Thanh-Toan Do
Published: 2025-10-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.07018v1

Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic data for quantizing the full-precision model. While it is well-known that deep neural networks with low sharpness have better generalization ability, none of the previous zero-shot quantization works considers the sharpness of the quantized model as a criterion for generating training data. This paper introduces a novel methodology that takes into account quantized model sharpness in synthetic data generation to enhance generalization. Specifically, we first demonstrate that sharpness minimization can be attained by maximizing gradient matching between the reconstruction loss gradients computed on synthetic and real validation data, under certain assumptions. We then circumvent the problem of the gradient matching without real validation set by approximating it with the gradient matching between each generated sample and its neighbors. Experimental evaluations on CIFAR-100 and ImageNet datasets demonstrate the superiority of the proposed method over the state-of-the-art techniques in low-bit quantization settings.

---

### Bayesian Modelling of Multi-Year Crop Type Classification Using Deep Neural Networks and Hidden Markov Models

Authors: Gianmarco Perantoni, Giulio Weikmann, Lorenzo Bruzzone
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07008v1

The temporal consistency of yearly land-cover maps is of great importance to model the evolution and change of the land cover over the years. In this paper, we focus the attention on a novel approach to classification of yearly satellite image time series (SITS) that combines deep learning with Bayesian modelling, using Hidden Markov Models (HMMs) integrated with Transformer Encoder (TE) based DNNs. The proposed approach aims to capture both i) intricate temporal correlations in yearly SITS and ii) specific patterns in multiyear crop type sequences. It leverages the cascade classification of an HMM layer built on top of the TE, discerning consistent yearly crop-type sequences. Validation on a multiyear crop type classification dataset spanning 47 crop types and six years of Sentinel-2 acquisitions demonstrates the importance of modelling temporal consistency in the predicted labels. HMMs enhance the overall performance and F1 scores, emphasising the effectiveness of the proposed approach.

---

### Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languages

Authors: Neel Prabhanjan Rachamalla, Aravind Konakalla, Gautam Rajeev, Ashish Kulkarni, Chandra Khatri, Shubham Agarwal
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.07000v1

The effectiveness of Large Language Models (LLMs) depends heavily on the availability of high-quality post-training data, particularly instruction-tuning and preference-based examples. Existing open-source datasets, however, often lack multilingual coverage, cultural grounding, and suffer from task diversity gaps that are especially pronounced for Indian languages. We introduce a human-in-the-loop pipeline that combines translations with synthetic expansion to produce reliable and diverse Indic post-training data. Using this pipeline, we curate two datasets: Pragyaan-IT (22.5K) and Pragyaan-Align (100K) across 10 Indian languages covering 13 broad and 56 sub-categories, leveraging 57 diverse datasets. Our dataset protocol incorporates several often-overlooked dimensions and emphasize task diversity, multi-turn dialogue, instruction fidelity, safety alignment, and preservation of cultural nuance, providing a foundation for more inclusive and effective multilingual LLMs.

---

### Towards Reliable Retrieval in RAG Systems for Large Legal Datasets

Authors: Markus Reuter, Tobias Lingenberg, Rūta Liepiņa, Francesca Lagioia, Marco Lippi, Giovanni Sartor, Andrea Passerini, Burcu Sayin
Published: 2025-10-08
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.06999v1

Retrieval-Augmented Generation (RAG) is a promising approach to mitigate hallucinations in Large Language Models (LLMs) for legal applications, but its reliability is critically dependent on the accuracy of the retrieval step. This is particularly challenging in the legal domain, where large databases of structurally similar documents often cause retrieval systems to fail. In this paper, we address this challenge by first identifying and quantifying a critical failure mode we term Document-Level Retrieval Mismatch (DRM), where the retriever selects information from entirely incorrect source documents. To mitigate DRM, we investigate a simple and computationally efficient technique which we refer to as Summary-Augmented Chunking (SAC). This method enhances each text chunk with a document-level synthetic summary, thereby injecting crucial global context that would otherwise be lost during a standard chunking process. Our experiments on a diverse set of legal information retrieval tasks show that SAC greatly reduces DRM and, consequently, also improves text-level retrieval precision and recall. Interestingly, we find that a generic summarization strategy outperforms an approach that incorporates legal expert domain knowledge to target specific legal elements. Our work provides evidence that this practical, scalable, and easily integrable technique enhances the reliability of RAG systems when applied to large-scale legal document datasets.

---

### The Limits of Goal-Setting Theory in LLM-Driven Assessment

Authors: Mrityunjay Kumar
Published: 2025-10-08
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.06997v1

Many users interact with AI tools like ChatGPT using a mental model that treats the system as human-like, which we call Model H. According to goal-setting theory, increased specificity in goals should reduce performance variance. If Model H holds, then prompting a chatbot with more detailed instructions should lead to more consistent evaluation behavior. This paper tests that assumption through a controlled experiment in which ChatGPT evaluated 29 student submissions using four prompts with increasing specificity. We measured consistency using intra-rater reliability (Cohen's Kappa) across repeated runs. Contrary to expectations, performance did not improve consistently with increased prompt specificity, and performance variance remained largely unchanged. These findings challenge the assumption that LLMs behave like human evaluators and highlight the need for greater robustness and improved input integration in future model development.

---

### Root Cause Analysis of Outliers in Unknown Cyclic Graphs

Authors: Daniela Schkoda, Dominik Janzing
Published: 2025-10-08
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2510.06995v2

We study the propagation of outliers in cyclic causal graphs with linear structural equations, tracing them back to one or several "root cause" nodes. We show that it is possible to identify a short list of potential root causes provided that the perturbation is sufficiently strong and propagates according to the same structural equations as in the normal mode. This shortlist consists of the true root causes together with those of its parents lying on a cycle with the root cause. Notably, our method does not require prior knowledge of the causal graph and yields encouraging results on simulated data and real data from biology and cloud computing.

---

### RedTWIZ: Diverse LLM Red Teaming via Adaptive Attack Planning

Authors: Artur Horal, Daniel Pina, Henrique Paz, Iago Paulo, João Soares, Rafael Ferreira, Diogo Tavares, Diogo Glória-Silva, João Magalhães, David Semedo
Published: 2025-10-08
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2510.06994v1

This paper presents the vision, scientific contributions, and technical details of RedTWIZ: an adaptive and diverse multi-turn red teaming framework, to audit the robustness of Large Language Models (LLMs) in AI-assisted software development. Our work is driven by three major research streams: (1) robust and systematic assessment of LLM conversational jailbreaks; (2) a diverse generative multi-turn attack suite, supporting compositional, realistic and goal-oriented jailbreak conversational strategies; and (3) a hierarchical attack planner, which adaptively plans, serializes, and triggers attacks tailored to specific LLM's vulnerabilities. Together, these contributions form a unified framework -- combining assessment, attack generation, and strategic planning -- to comprehensively evaluate and expose weaknesses in LLMs' robustness. Extensive evaluation is conducted to systematically assess and analyze the performance of the overall system and each component. Experimental results demonstrate that our multi-turn adversarial attack strategies can successfully lead state-of-the-art LLMs to produce unsafe generations, highlighting the pressing need for more research into enhancing LLM's robustness.

---

### No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts

Authors: Girolamo Macaluso, Lorenzo Mandelli, Mirko Bicchierai, Stefano Berretti, Andrew D. Bagdanov
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06988v1

Diffusion models have recently advanced human motion generation, producing realistic and diverse animations from textual prompts. However, adapting these models to unseen actions or styles typically requires additional motion capture data and full retraining, which is costly and difficult to scale. We propose a post-training framework based on Reinforcement Learning that fine-tunes pretrained motion diffusion models using only textual prompts, without requiring any motion ground truth. Our approach employs a pretrained text-motion retrieval network as a reward signal and optimizes the diffusion policy with Denoising Diffusion Policy Optimization, effectively shifting the model's generative distribution toward the target domain without relying on paired motion data. We evaluate our method on cross-dataset adaptation and leave-one-out motion experiments using the HumanML3D and KIT-ML datasets across both latent- and joint-space diffusion architectures. Results from quantitative metrics and user studies show that our approach consistently improves the quality and diversity of generated motions, while preserving performance on the original distribution. Our approach is a flexible, data-efficient, and privacy-preserving solution for motion adaptation.

---

### Spiral Model Technique For Data Science & Machine Learning Lifecycle

Authors: Rohith Mahadevan
Published: 2025-10-08
Categories: cs.LG, cs.IR, cs.SE
arXiv: https://arxiv.org/abs/2510.06987v1

Analytics play an important role in modern business. Companies adapt data science lifecycles to their culture to seek productivity and improve their competitiveness among others. Data science lifecycles are fairly an important contributing factor to start and end a project that are data dependent. Data science and Machine learning life cycles comprises of series of steps that are involved in a project. A typical life cycle states that it is a linear or cyclical model that revolves around. It is mostly depicted that it is possible in a traditional data science life cycle to start the process again after reaching the end of cycle. This paper suggests a new technique to incorporate data science life cycle to business problems that have a clear end goal. A new technique called spiral technique is introduced to emphasize versatility, agility and iterative approach to business processes.

---

### Revisiting Mixout: An Overlooked Path to Robust Finetuning

Authors: Masih Aminbeidokhti, Heitor Rapela Medeiros, Eric Granger, Marco Pedersoli
Published: 2025-10-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.06982v1

Finetuning vision foundation models often improves in-domain accuracy but comes at the cost of robustness under distribution shift. We revisit Mixout, a stochastic regularizer that intermittently replaces finetuned weights with their pretrained reference, through the lens of a single-run, weight-sharing implicit ensemble. This perspective reveals three key levers that govern robustness: the \emph{masking anchor}, \emph{resampling frequency}, and \emph{mask sparsity}. Guided by this analysis, we introduce GMixout, which (i) replaces the fixed anchor with an exponential moving-average snapshot that adapts during training, and (ii) regulates masking period via an explicit resampling-frequency hyperparameter. Our sparse-kernel implementation updates only a small fraction of parameters with no inference-time overhead, enabling training on consumer-grade GPUs. Experiments on benchmarks covering covariate shift, corruption, and class imbalance, ImageNet / ImageNet-LT, DomainNet, iWildCam, and CIFAR100-C, GMixout consistently improves in-domain accuracy beyond zero-shot performance while surpassing both Model Soups and strong parameter-efficient finetuning baselines under distribution shift.

---

### Relational Database Distillation: From Structured Tables to Condensed Graph Data

Authors: Xinyi Gao, Jingxi Zhang, Lijian Chen, Tong Chen, Lizhen Cui, Hongzhi Yin
Published: 2025-10-08
Categories: cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2510.06980v2

Relational databases (RDBs) underpin the majority of global data management systems, where information is structured into multiple interdependent tables. To effectively use the knowledge within RDBs for predictive tasks, recent advances leverage graph representation learning to capture complex inter-table relations as multi-hop dependencies. Despite achieving state-of-the-art performance, these methods remain hindered by the prohibitive storage overhead and excessive training time, due to the massive scale of the database and the computational burden of intensive message passing across interconnected tables. To alleviate these concerns, we propose and study the problem of Relational Database Distillation (RDD). Specifically, we aim to distill large-scale RDBs into compact heterogeneous graphs while retaining the predictive power (i.e., utility) required for training graph-based models. Multi-modal column information is preserved through node features, and primary-foreign key relations are encoded via heterogeneous edges, thereby maintaining both data fidelity and relational structure. To ensure adaptability across diverse downstream tasks without engaging the traditional, inefficient bi-level distillation framework, we further design a kernel ridge regression-guided objective with pseudo-labels, which produces quality features for the distilled graph. Extensive experiments on multiple real-world RDBs demonstrate that our solution substantially reduces the data size while maintaining competitive performance on classification and regression tasks, creating an effective pathway for scalable learning with RDBs.

---

### VelLMes: A high-interaction AI-based deception framework

Authors: Muris Sladić, Veronica Valeros, Carlos Catania, Sebastian Garcia
Published: 2025-10-08
Categories: cs.CR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.06975v1

There are very few SotA deception systems based on Large Language Models. The existing ones are limited only to simulating one type of service, mainly SSH shells. These systems - but also the deception technologies not based on LLMs - lack an extensive evaluation that includes human attackers. Generative AI has recently become a valuable asset for cybersecurity researchers and practitioners, and the field of cyber-deception is no exception. Researchers have demonstrated how LLMs can be leveraged to create realistic-looking honeytokens, fake users, and even simulated systems that can be used as honeypots. This paper presents an AI-based deception framework called VelLMes, which can simulate multiple protocols and services such as SSH Linux shell, MySQL, POP3, and HTTP. All of these can be deployed and used as honeypots, thus VelLMes offers a variety of choices for deception design based on the users' needs. VelLMes is designed to be attacked by humans, so interactivity and realism are key for its performance. We evaluate the generative capabilities and the deception capabilities. Generative capabilities were evaluated using unit tests for LLMs. The results of the unit tests show that, with careful prompting, LLMs can produce realistic-looking responses, with some LLMs having a 100% passing rate. In the case of the SSH Linux shell, we evaluated deception capabilities with 89 human attackers. The results showed that about 30% of the attackers thought that they were interacting with a real system when they were assigned an LLM-based honeypot. Lastly, we deployed 10 instances of the SSH Linux shell honeypot on the Internet to capture real-life attacks. Analysis of these attacks showed us that LLM honeypots simulating Linux shells can perform well against unstructured and unexpected attacks on the Internet, responding correctly to most of the issued commands.

---

### Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups

Authors: Geng Liu, Feng Li, Junjie Mu, Mengxiao Zhu, Francesco Pierri
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06974v2

Large language models (LLMs) are increasingly deployed in user-facing applications, raising concerns that they may reflect and amplify social biases. We investigate social identity biases in Chinese LLMs using Mandarin-specific prompts across ten representative models. Our evaluation compares ingroup ("We") and outgroup ("They") framings across 240 social groups salient in the Chinese context, using a two-tiered measurement framework that assesses both sentiment and toxicity. The prompt design explicitly accounts for linguistic properties of Mandarin, including the distinction between the default gender-neutral plural pronoun and its explicitly feminine counterpart, enabling a controlled comparison of social identity framing effects. Across models, we observe systematic ingroup-outgroup asymmetries, although their expression differs across measurement dimensions. In particular, instruction tuning often reduces sentiment asymmetries, while toxicity gaps remain more persistent. Moreover, the feminine-marked plural pronoun is associated with higher toxicity than the default gender-neutral plural in several models. Our study introduces a language-aware evaluation framework for Chinese LLMs and shows that (i) social identity biases previously documented in English also manifest in Chinese and that (ii) Mandarin-specific linguistic structure can reveal bias patterns that are not directly observable in English-only settings.

---

### Addressing the ID-Matching Challenge in Long Video Captioning

Authors: Zhantao Yang, Huangji Wang, Ruili Feng, Han Zhang, Yuting Hu, Shangwen Zhu, Junyan Li, Yu Liu, Fan Cheng
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06973v1

Generating captions for long and complex videos is both critical and challenging, with significant implications for the growing fields of text-to-video generation and multi-modal understanding. One key challenge in long video captioning is accurately recognizing the same individuals who appear in different frames, which we refer to as the ID-Matching problem. Few prior works have focused on this important issue. Those that have, usually suffer from limited generalization and depend on point-wise matching, which limits their overall effectiveness. In this paper, unlike previous approaches, we build upon LVLMs to leverage their powerful priors. We aim to unlock the inherent ID-Matching capabilities within LVLMs themselves to enhance the ID-Matching performance of captions. Specifically, we first introduce a new benchmark for assessing the ID-Matching capabilities of video captions. Using this benchmark, we investigate LVLMs containing GPT-4o, revealing key insights that the performance of ID-Matching can be improved through two methods: 1) enhancing the usage of image information and 2) increasing the quantity of information of individual descriptions. Based on these insights, we propose a novel video captioning method called Recognizing Identities for Captioning Effectively (RICE). Extensive experiments including assessments of caption quality and ID-Matching performance, demonstrate the superiority of our approach. Notably, when implemented on GPT-4o, our RICE improves the precision of ID-Matching from 50% to 90% and improves the recall of ID-Matching from 15% to 80% compared to baseline. RICE makes it possible to continuously track different individuals in the captions of long videos.

---

### Falsification-driven reinforcement learning for maritime motion planning

Authors: Marlon Müller, Florian Finkeldei, Hanna Krasowski, Murat Arcak, Matthias Althoff
Published: 2025-10-08
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2510.06970v2

Compliance with maritime traffic rules is essential for the safe operation of autonomous vessels, yet training reinforcement learning (RL) agents to adhere to them is challenging. The behavior of RL agents is shaped by the training scenarios they encounter, but creating scenarios that capture the complexity of maritime navigation is non-trivial, and real-world data alone is insufficient. To address this, we propose a falsification-driven RL approach that generates adversarial training scenarios in which the vessel under test violates maritime traffic rules, which are expressed as signal temporal logic specifications. Our experiments on open-sea navigation with two vessels demonstrate that the proposed approach provides more relevant training scenarios and achieves more consistent rule compliance.

---

### Learning Global Representation from Queries for Vectorized HD Map Construction

Authors: Shoumeng Qiu, Xinrun Li, Yang Long, Xiangyang Xue, Varun Ojha, Jian Pu
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.06969v1

The online construction of vectorized high-definition (HD) maps is a cornerstone of modern autonomous driving systems. State-of-the-art approaches, particularly those based on the DETR framework, formulate this as an instance detection problem. However, their reliance on independent, learnable object queries results in a predominantly local query perspective, neglecting the inherent global representation within HD maps. In this work, we propose \textbf{MapGR} (\textbf{G}lobal \textbf{R}epresentation learning for HD \textbf{Map} construction), an architecture designed to learn and utilize a global representations from queries. Our method introduces two synergistic modules: a Global Representation Learning (GRL) module, which encourages the distribution of all queries to better align with the global map through a carefully designed holistic segmentation task, and a Global Representation Guidance (GRG) module, which endows each individual query with explicit, global-level contextual information to facilitate its optimization. Evaluations on the nuScenes and Argoverse2 datasets validate the efficacy of our approach, demonstrating substantial improvements in mean Average Precision (mAP) compared to leading baselines.

---

### Generating Surface for Text-to-3D using 2D Gaussian Splatting

Authors: Huanning Dong, Fan Li, Ping Kuang, Jianwen Min
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.06967v1

Recent advancements in Text-to-3D modeling have shown significant potential for the creation of 3D content. However, due to the complex geometric shapes of objects in the natural world, generating 3D content remains a challenging task. Current methods either leverage 2D diffusion priors to recover 3D geometry, or train the model directly based on specific 3D representations. In this paper, we propose a novel method named DirectGaussian, which focuses on generating the surfaces of 3D objects represented by surfels. In DirectGaussian, we utilize conditional text generation models and the surface of a 3D object is rendered by 2D Gaussian splatting with multi-view normal and texture priors. For multi-view geometric consistency problems, DirectGaussian incorporates curvature constraints on the generated surface during optimization process. Through extensive experiments, we demonstrate that our framework is capable of achieving diverse and high-fidelity 3D content creation.

---

### EDUMATH: Generating Standards-aligned Educational Math Word Problems

Authors: Bryan R. Christ, Penelope Molitz, Beau LeBlond, Zachary Gottesman, Jonathan Kropko, Thomas Hartvigsen
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.06965v2

Math word problems (MWPs) are critical K-12 educational tools, and customizing them to students' interests and ability levels can enhance learning. However, teachers struggle to find time to customize MWPs for students given large class sizes and increasing burnout. We propose that LLMs can support math education by generating MWPs customized to student interests and math education standards. We use a joint human expert-LLM judge approach to evaluate over 11,000 MWPs generated by open and closed LLMs and develop the first teacher-annotated dataset for standards-aligned educational MWP generation. We show the value of our data by using it to train a 12B open model that matches the performance of larger and more capable open models. We also use our teacher-annotated data to train a text classifier that enables a 30B open LLM to outperform existing closed baselines without any training. Next, we show our models' MWPs are more similar to human-written MWPs than those from existing models. We conclude by conducting the first study of customized LLM-generated MWPs with grade school students, finding they perform similarly on our models' MWPs relative to human-written MWPs but consistently prefer our customized MWPs.

---

### Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation

Authors: Vaibhav Srivastav, Steven Zheng, Eric Bezzam, Eustache Le Bihan, Nithin Rao Koluguri, Piotr Żelasko, Somshubra Majumdar, Adel Moumen, Sanchit Gandhi
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2510.06961v4

We present the Open ASR Leaderboard, a reproducible benchmarking platform with community contributions from academia and industry. It compares 86 open-source and proprietary systems across 12 datasets, with English short- and long-form and multilingual short-form tracks. We standardize word error rate (WER) and inverse real-time factor (RTFx) evaluation for consistent accuracy-efficiency comparisons across model architectures and toolkits (e.g., ESPNet, NeMo, SpeechBrain, Transformers). We observe that Conformer-based encoders paired with transformer-based decoders achieve the best average WER, while connectionist temporal classification (CTC) and token-and-duration transducer (TDT) decoders offer superior RTFx, making them better suited for long-form and batched processing. All code and dataset loaders are open-sourced to support transparent, extensible evaluation. We present our evaluation methodology to facilitate community-driven benchmarking in ASR and other tasks.

---

### Accelerating Sparse Ternary GEMM for Quantized ML on Apple Silicon

Authors: Baraq Lipshitz, Alessio Melone, Charalampos Maraziaris, Muhammed Bilal
Published: 2025-10-08
Categories: cs.PF, cs.LG
arXiv: https://arxiv.org/abs/2510.06957v2

Sparse Ternary General Matrix-Matrix Multiplication (GEMM) remains under-optimized in existing libraries for Apple Silicon CPUs. We present a Sparse Ternary GEMM kernel optimized specifically for Apple's M-series processors. We propose a set of architecture-aware optimizations, including a novel blocked and interleaved sparse data format to improve memory locality, strategies to increase Instruction-Level Parallelism (ILP), and NEON-based Single Instruction Multiple Data (SIMD) vectorization to exploit data-level parallelism. Our scalar implementation achieves up to a 5.98x performance increase over a traditional Ternary Compressed Sparse Column (TCSC) baseline for large matrices with 50% ternary nonzero values (sparsity), reaching up to a 50.2% of the processor's theoretical peak performance, and remains stable across varying sparsity levels. Our vectorized implementation delivers up to a 5.59x performance increase for large matrices with 25% sparsity, and remains stable across varying sparsity levels.

---

### High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization

Authors: Masih Aminbeidokhti, Heitor Rapela Medeiros, Srikanth Muralidharan, Eric Granger, Marco Pedersoli
Published: 2025-10-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.06955v2

Ensembling fine-tuned models initialized from powerful pre-trained weights is a common strategy to improve robustness under distribution shifts, but it comes with substantial computational costs due to the need to train and store multiple models. Dropout offers a lightweight alternative by simulating ensembles through random neuron deactivation; however, when applied to pre-trained models, it tends to over-regularize and disrupt critical representations necessary for generalization. In this work, we investigate Mixout, a stochastic regularization technique that provides an alternative to Dropout for domain generalization. Rather than deactivating neurons, Mixout mitigates overfitting by probabilistically swapping a subset of fine-tuned weights with their pre-trained counterparts during training, thereby maintaining a balance between adaptation and retention of prior knowledge. Our study reveals that achieving strong performance with Mixout on domain generalization benchmarks requires a notably high masking probability of 0.9 for ViTs and 0.8 for ResNets. While this may seem like a simple adjustment, it yields two key advantages for domain generalization: (1) higher masking rates more strongly penalize deviations from the pre-trained parameters, promoting better generalization to unseen domains; and (2) high-rate masking substantially reduces computational overhead, cutting gradient computation by up to 45% and gradient memory usage by up to 90%. Experiments across five domain generalization benchmarks, PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet, using ResNet and ViT architectures, show that our approach, High-rate Mixout, achieves out-of-domain accuracy comparable to ensemble-based methods while significantly reducing training costs.

---

### From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics

Authors: Zheng-An Chen, Tao Luo
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06954v1

Although transformer-based models have shown exceptional empirical performance, the fundamental principles governing their training dynamics are inadequately characterized beyond configuration-specific studies. Inspired by empirical evidence showing improved reasoning capabilities under small initialization scales in language models, we employ the gradient flow analytical framework established in (Zhou et al. NeurIPS 2022) to systematically investigate linearized Transformer training dynamics. Our theoretical analysis dissects the dynamics of attention modules into two distinct stages. In the first stage, asymmetric weight perturbations from random initialization sustain non-degenerate gradient dynamics in parameter matrices, facilitating systematic escape from small initialization regimes. Subsequently, these matrices undergo condensation, progressively aligning toward the target orientation. In the second stage, the previously static key-query matrices actively participate in training, driving the normalized matrices toward asymptotic rank collapse. This two-stage framework generalizes classical directional convergence results.

---

### Revisiting the Uniform Information Density Hypothesis in LLM Reasoning

Authors: Minju Gwak, Guijin Son, Jaehyung Kim
Published: 2025-10-08
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.06953v3

The Uniform Information Density (UID) hypothesis proposes that effective communication is achieved by maintaining a stable flow of information. In this work, we revisit this principle in the context of Large Language Model (LLM) reasoning, asking whether step-level uniformity reflects reasoning quality. To this end, we introduce a novel framework to quantify uniformity of information flow at both local and global levels, using an entropy-based stepwise density metric. Across experiments on seven reasoning benchmarks, we see a counter-intuitive pattern: while high-quality reasoning exhibit smooth step-by-step transitions local uniformity and structured, non-uniform information flow at the trajectory level global non-uniformity. The results demonstrate that these uniformities outperform alternative internal signals as predictors of reasoning quality, and such divergence with human communication is not a model deficiency, but a byproduct of distinct objectives between human communication and LLM reasoning.

---

### OBJVanish: Physically Realizable Text-to-3D Adv. Generation of LiDAR-Invisible Objects

Authors: Bing Li, Wuqi Wang, Yanan Zhang, Jingzheng Li, Haigen Min, Wei Feng, Xingyu Zhao, Jie Zhang, Qing Guo
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06952v1

LiDAR-based 3D object detectors are fundamental to autonomous driving, where failing to detect objects poses severe safety risks. Developing effective 3D adversarial attacks is essential for thoroughly testing these detection systems and exposing their vulnerabilities before real-world deployment. However, existing adversarial attacks that add optimized perturbations to 3D points have two critical limitations: they rarely cause complete object disappearance and prove difficult to implement in physical environments. We introduce the text-to-3D adversarial generation method, a novel approach enabling physically realizable attacks that can generate 3D models of objects truly invisible to LiDAR detectors and be easily realized in the real world. Specifically, we present the first empirical study that systematically investigates the factors influencing detection vulnerability by manipulating the topology, connectivity, and intensity of individual pedestrian 3D models and combining pedestrians with multiple objects within the CARLA simulation environment. Building on the insights, we propose the physically-informed text-to-3D adversarial generation (Phy3DAdvGen) that systematically optimizes text prompts by iteratively refining verbs, objects, and poses to produce LiDAR-invisible pedestrians. To ensure physical realizability, we construct a comprehensive object pool containing 13 3D models of real objects and constrain Phy3DAdvGen to generate 3D objects based on combinations of objects in this set. Extensive experiments demonstrate that our approach can generate 3D pedestrians that evade six state-of-the-art (SOTA) LiDAR 3D detectors in both CARLA simulation and physical environments, thereby highlighting vulnerabilities in safety-critical applications.

---

### Grouped Differential Attention

Authors: Junghwan Lim, Sungmin Lee, Dongseok Kim, Wai Ting Cheung, Beomgyu Kim, Taehwan Kim, Haesol Lee, Junhyeok Lee, Dongpin Oh, Eunhwan Park
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06949v1

The self-attention mechanism, while foundational to modern Transformer architectures, suffers from a critical inefficiency: it frequently allocates substantial attention to redundant or noisy context. Differential Attention addressed this by using subtractive attention maps for signal and noise, but its required balanced head allocation imposes rigid constraints on representational flexibility and scalability. To overcome this, we propose Grouped Differential Attention (GDA), a novel approach that introduces unbalanced head allocation between signal-preserving and noise-control groups. GDA significantly enhances signal focus by strategically assigning more heads to signal extraction and fewer to noise-control, stabilizing the latter through controlled repetition (akin to GQA). This design achieves stronger signal fidelity with minimal computational overhead. We further extend this principle to group-differentiated growth, a scalable strategy that selectively replicates only the signal-focused heads, thereby ensuring efficient capacity expansion. Through large-scale pretraining and continual training experiments, we demonstrate that moderate imbalance ratios in GDA yield substantial improvements in generalization and stability compared to symmetric baselines. Our results collectively establish that ratio-aware head allocation and selective expansion offer an effective and practical path toward designing scalable, computation-efficient Transformer architectures.

---

### Fisher Information, Training and Bias in Fourier Regression Models

Authors: Lorenzo Pastori, Veronika Eyring, Mierk Schwabe
Published: 2025-10-08
Categories: cs.LG, cond-mat.dis-nn, physics.data-an, quant-ph
arXiv: https://arxiv.org/abs/2510.06945v2

Motivated by the growing interest in quantum machine learning, in particular quantum neural networks (QNNs), we study how recently introduced evaluation metrics based on the Fisher information matrix (FIM) are effective for predicting their training and prediction performance. We exploit the equivalence between a broad class of QNNs and Fourier models, and study the interplay between the \emph{effective dimension} and the \emph{bias} of a model towards a given task, investigating how these affect the model's training and performance. We show that for a model that is completely agnostic, or unbiased, towards the function to be learned, a higher effective dimension likely results in a better trainability and performance. On the other hand, for models that are biased towards the function to be learned a lower effective dimension is likely beneficial during training. To obtain these results, we derive an analytical expression of the FIM for Fourier models and identify the features controlling a model's effective dimension. This allows us to construct models with tunable effective dimension and bias, and to compare their training. We furthermore introduce a tensor network representation of the considered Fourier models, which could be a tool of independent interest for the analysis of QNN models. Overall, these findings provide an explicit example of the interplay between geometrical properties, model-task alignment and training, which are relevant for the broader machine learning community.

---

### Revisiting Node Affinity Prediction in Temporal Graphs

Authors: Or Feldman, Krishna Sri Ipsit Mantri, Moshe Eliasof, Chaim Baskin
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06940v3

Node affinity prediction is a common task that is widely used in temporal graph learning with applications in social and financial networks, recommender systems, and more. Recent works have addressed this task by adapting state-of-the-art dynamic link property prediction models to node affinity prediction. However, simple heuristics, such as Persistent Forecast or Moving Average, outperform these models. In this work, we analyze the challenges in training current Temporal Graph Neural Networks for node affinity prediction and suggest appropriate solutions. Combining the solutions, we develop NAViS - Node Affinity prediction model using Virtual State, by exploiting the equivalence between heuristics and state space models. While promising, training NAViS is non-trivial. Therefore, we further introduce a novel loss function for node affinity prediction. We evaluate NAViS on TGB and show that it outperforms the state-of-the-art, including heuristics. Our source code is available at https://github.com/orfeld415/NAVIS

---

### Expressive and Scalable Quantum Fusion for Multimodal Learning

Authors: Tuyen Nguyen, Trong Nghia Hoang, Phi Le Nguyen, Hai L. Vu, Truong Cong Thang
Published: 2025-10-08
Categories: quant-ph, cs.AI
arXiv: https://arxiv.org/abs/2510.06938v1

The aim of this paper is to introduce a quantum fusion mechanism for multimodal learning and to establish its theoretical and empirical potential. The proposed method, called the Quantum Fusion Layer (QFL), replaces classical fusion schemes with a hybrid quantum-classical procedure that uses parameterized quantum circuits to learn entangled feature interactions without requiring exponential parameter growth. Supported by quantum signal processing principles, the quantum component efficiently represents high-order polynomial interactions across modalities with linear parameter scaling, and we provide a separation example between QFL and low-rank tensor-based methods that highlights potential quantum query advantages. In simulation, QFL consistently outperforms strong classical baselines on small but diverse multimodal tasks, with particularly marked improvements in high-modality regimes. These results suggest that QFL offers a fundamentally new and scalable approach to multimodal fusion that merits deeper exploration on larger systems.

---

### PyCFRL: A Python library for counterfactually fair offline reinforcement learning via sequential data preprocessing

Authors: Jianhan Zhang, Jitao Wang, Chengchun Shi, John D. Piette, Donglin Zeng, Zhenke Wu
Published: 2025-10-08
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.06935v1

Reinforcement learning (RL) aims to learn and evaluate a sequential decision rule, often referred to as a "policy", that maximizes the population-level benefit in an environment across possibly infinitely many time steps. However, the sequential decisions made by an RL algorithm, while optimized to maximize overall population benefits, may disadvantage certain individuals who are in minority or socioeconomically disadvantaged groups. To address this problem, we introduce PyCFRL, a Python library for ensuring counterfactual fairness in offline RL. PyCFRL implements a novel data preprocessing algorithm for learning counterfactually fair RL policies from offline datasets and provides tools to evaluate the values and counterfactual unfairness levels of RL policies. We describe the high-level functionalities of PyCFRL and demonstrate one of its major use cases through a data example. The library is publicly available on PyPI and Github (https://github.com/JianhanZhang/PyCFRL), and detailed tutorials can be found in the PyCFRL documentation (https://pycfrl-documentation.netlify.app).

---

### Textual interpretation of transient image classifications from large language models

Authors: Fiorenzo Stoppa, Turan Bulmus, Steven Bloemen, Stephen J. Smartt, Paul J. Groot, Paul Vreeswijk, Ken W. Smith
Published: 2025-10-08
Categories: astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2510.06931v1

Modern astronomical surveys deliver immense volumes of transient detections, yet distinguishing real astrophysical signals (for example, explosive events) from bogus imaging artefacts remains a challenge. Convolutional neural networks are effectively used for real versus bogus classification; however, their reliance on opaque latent representations hinders interpretability. Here we show that large language models (LLMs) can approach the performance level of a convolutional neural network on three optical transient survey datasets (Pan-STARRS, MeerLICHT and ATLAS) while simultaneously producing direct, human-readable descriptions for every candidate. Using only 15 examples and concise instructions, Google's LLM, Gemini, achieves a 93% average accuracy across datasets that span a range of resolution and pixel scales. We also show that a second LLM can assess the coherence of the output of the first model, enabling iterative refinement by identifying problematic cases. This framework allows users to define the desired classification behaviour through natural language and examples, bypassing traditional training pipelines. Furthermore, by generating textual descriptions of observed features, LLMs enable users to query classifications as if navigating an annotated catalogue, rather than deciphering abstract latent spaces. As next-generation telescopes and surveys further increase the amount of data available, LLM-based classification could help bridge the gap between automated detection and transparent, human-level understanding.

---

### IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction

Authors: Ran Yi, Teng Hu, Zihan Su, Jiangning Zhang, Lizhuang Ma
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06928v2

Autoregressive models have emerged as a powerful paradigm for visual content creation, but often overlook the intrinsic structural properties of visual data. Our prior work, IAR, initiated a direction to address this by reorganizing the visual codebook based on embedding similarity, thereby improving generation robustness. However, it is constrained by the rigidity of pre-trained codebooks and the inaccuracies of hard, uniform clustering. To overcome these limitations, we propose IAR2, an advanced autoregressive framework that enables a hierarchical semantic-detail synthesis process. At the core of IAR2 is a novel Semantic-Detail Associated Dual Codebook, which decouples image representations into a semantic codebook for global semantic information and a detail codebook for fine-grained refinements. It expands the quantization capacity from a linear to a polynomial scale, significantly enhancing expressiveness. To accommodate this dual representation, we propose a Semantic-Detail Autoregressive Prediction scheme coupled with a Local-Context Enhanced Autoregressive Head, which performs hierarchical prediction-first the semantic token, then the detail token-while leveraging a local context window to enhance spatial coherence. Furthermore, for conditional generation, we introduce a Progressive Attention-Guided Adaptive CFG mechanism that dynamically modulates the guidance scale for each token based on its relevance to the condition and its temporal position in the generation sequence, improving conditional alignment without sacrificing realism. Extensive experiments demonstrate that IAR2 sets a new state-of-the-art for autoregressive image generation, achieving a FID of 1.50 on ImageNet. Our model not only surpasses previous methods in performance but also demonstrates superior computational efficiency, highlighting the effectiveness of our structured, coarse-to-fine generation strategy.

---

### Label-frugal satellite image change detection with generative virtual exemplar learning

Authors: Hichem Sahbi
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06926v1

Change detection is a major task in remote sensing which consists in finding all the occurrences of changes in multi-temporal satellite or aerial images. The success of existing methods, and particularly deep learning ones, is tributary to the availability of hand-labeled training data that capture the acquisition conditions and the subjectivity of the user (oracle). In this paper, we devise a novel change detection algorithm, based on active learning. The main contribution of our work resides in a new model that measures how important is each unlabeled sample, and provides an oracle with only the most critical samples (also referred to as virtual exemplars) for further labeling. These exemplars are generated, using an invertible graph convnet, as the optimum of an adversarial loss that (i) measures representativity, diversity and ambiguity of the data, and thereby (ii) challenges (the most) the current change detection criteria, leading to a better re-estimate of these criteria in the subsequent iterations of active learning. Extensive experiments show the positive impact of our label-efficient learning model against comparative methods.

---

### Quantum Sparse Recovery and Quantum Orthogonal Matching Pursuit

Authors: Armando Bellante, Stefano Vanerio, Stefano Zanero
Published: 2025-10-08
Categories: quant-ph, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2510.06925v1

We study quantum sparse recovery in non-orthogonal, overcomplete dictionaries: given coherent quantum access to a state and a dictionary of vectors, the goal is to reconstruct the state up to $\ell_2$ error using as few vectors as possible. We first show that the general recovery problem is NP-hard, ruling out efficient exact algorithms in full generality. To overcome this, we introduce Quantum Orthogonal Matching Pursuit (QOMP), the first quantum analogue of the classical OMP greedy algorithm. QOMP combines quantum subroutines for inner product estimation, maximum finding, and block-encoded projections with an error-resetting design that avoids iteration-to-iteration error accumulation. Under standard mutual incoherence and well-conditioned sparsity assumptions, QOMP provably recovers the exact support of a $K$-sparse state in polynomial time. As an application, we give the first framework for sparse quantum tomography with non-orthogonal dictionaries in $\ell_2$ norm, achieving query complexity $\widetilde{O}(\sqrt{N}/ε)$ in favorable regimes and reducing tomography to estimating only $K$ coefficients instead of $N$ amplitudes. In particular, for pure-state tomography with $m=O(N)$ dictionary vectors and sparsity $K=\widetilde{O}(1)$ on a well-conditioned subdictionary, this circumvents the $\widetildeΩ(N/ε)$ lower bound that holds in the dense, orthonormal-dictionary setting, without contradiction, by leveraging sparsity together with non-orthogonality. Beyond tomography, we analyze QOMP in the QRAM model, where it yields polynomial speedups over classical OMP implementations, and provide a quantum algorithm to estimate the mutual incoherence of a dictionary of $m$ vectors in $O(m/ε)$ queries, improving over both deterministic and quantum-inspired classical methods.

---

### Bayesian Nonparametric Dynamical Clustering of Time Series

Authors: Adrián Pérez-Herrero, Paulo Félix, Jesús Presedo, Carl Henrik Ek
Published: 2025-10-08
Categories: stat.ML, cs.AI, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2510.06919v1

We present a method that models the evolution of an unbounded number of time series clusters by switching among an unknown number of regimes with linear dynamics. We develop a Bayesian non-parametric approach using a hierarchical Dirichlet process as a prior on the parameters of a Switching Linear Dynamical System and a Gaussian process prior to model the statistical variations in amplitude and temporal alignment within each cluster. By modeling the evolution of time series patterns, the method avoids unnecessary proliferation of clusters in a principled manner. We perform inference by formulating a variational lower bound for off-line and on-line scenarios, enabling efficient learning through optimization. We illustrate the versatility and effectiveness of the approach through several case studies of electrocardiogram analysis using publicly available databases.

---

### SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models

Authors: Cheng-Han Chiang, Xiaofei Wang, Linjie Li, Chung-Ching Lin, Kevin Lin, Shujie Liu, Zhendong Wang, Zhengyuan Yang, Hung-yi Lee, Lijuan Wang
Published: 2025-10-08
Categories: cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2510.06917v2

Current large language models (LLMs) and spoken language models (SLMs) begin thinking and taking actions only after the user has finished their turn. This prevents the model from interacting during the user's turn and can lead to high response latency while it waits to think. Consequently, thinking after receiving the full input is not suitable for speech-to-speech interaction, where real-time, low-latency exchange is important. We address this by noting that humans naturally "think while listening." In this paper, we propose SHANKS, a general inference framework that enables SLMs to generate unspoken chain-of-thought reasoning while listening to the user input. SHANKS streams the input speech in fixed-duration chunks and, as soon as a chunk is received, generates unspoken reasoning based on all previous speech and reasoning, while the user continues speaking. SHANKS uses this unspoken reasoning to decide whether to interrupt the user and to make tool calls to complete the task. We demonstrate that SHANKS enhances real-time user-SLM interaction in two scenarios: (1) when the user is presenting a step-by-step solution to a math problem, SHANKS can listen, reason, and interrupt when the user makes a mistake, achieving 37.1% higher interruption accuracy than a baseline that interrupts without thinking; and (2) in a tool-augmented dialogue, SHANKS can complete 56.9% of the tool calls before the user finishes their turn. Overall, SHANKS moves toward models that keep thinking throughout the conversation, not only after a turn ends. Animated illustrations of Shanks can be found at https://d223302.github.io/SHANKS/

---

### LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling

Authors: Zecheng Tang, Baibei Ji, Quantong Qiu, Haitian Wang, Xiaobo Liang, Juntao Li, Min Zhang
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.06915v2

Reward model (RM) plays a pivotal role in aligning large language model (LLM) with human preferences. As real-world applications increasingly involve long history trajectories, e.g., LLM agent, it becomes indispensable to evaluate whether a model's responses are not only high-quality but also grounded in and consistent with the provided context. Yet, current RMs remain confined to short-context settings and primarily focus on response-level attributes (e.g., safety or helpfulness), while largely neglecting the critical dimension of long context-response consistency. In this work, we introduce Long-RewardBench, a benchmark specifically designed for long-context RM evaluation, featuring both Pairwise Comparison and Best-of-N tasks. Our preliminary study reveals that even state-of-the-art generative RMs exhibit significant fragility in long-context scenarios, failing to maintain context-aware preference judgments. Motivated by the analysis of failure patterns observed in model outputs, we propose a general multi-stage training strategy that effectively scales arbitrary models into robust Long-context RMs (LongRMs). Experiments show that our approach not only substantially improves performance on long-context evaluation but also preserves strong short-context capability. Notably, our 8B LongRM outperforms much larger 70B-scale baselines and matches the performance of the proprietary Gemini 2.5 Pro model.

---

### DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning

Authors: Ke Guo, Haochen Liu, Xiaojun Wu, Chen Lv
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.06913v2

Realistic traffic simulation is critical for the development of autonomous driving systems and urban mobility planning, yet existing imitation learning approaches often fail to model realistic traffic behaviors. Behavior cloning suffers from covariate shift, while Generative Adversarial Imitation Learning (GAIL) is notoriously unstable in multi-agent settings. We identify a key source of this instability: irrelevant interaction misguidance, where a discriminator penalizes an ego vehicle's realistic behavior due to unrealistic interactions among its neighbors. To address this, we propose Decomposed Multi-agent GAIL (DecompGAIL), which explicitly decomposes realism into ego-map and ego-neighbor components, filtering out misleading neighbor: neighbor and neighbor: map interactions. We further introduce a social PPO objective that augments ego rewards with distance-weighted neighborhood rewards, encouraging overall realism across agents. Integrated into a lightweight SMART-based backbone, DecompGAIL achieves state-of-the-art performance on the WOMD Sim Agents 2025 benchmark.

---

### Utilizing Large Language Models for Machine Learning Explainability

Authors: Alexandros Vassiliades, Nikolaos Polatidis, Stamatios Samaras, Sotiris Diplaris, Ignacio Cabrera Martin, Yannis Manolopoulos, Stefanos Vrochidis, Ioannis Kompatsiaris
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06912v1

This study explores the explainability capabilities of large language models (LLMs), when employed to autonomously generate machine learning (ML) solutions. We examine two classification tasks: (i) a binary classification problem focused on predicting driver alertness states, and (ii) a multilabel classification problem based on the yeast dataset. Three state-of-the-art LLMs (i.e. OpenAI GPT, Anthropic Claude, and DeepSeek) are prompted to design training pipelines for four common classifiers: Random Forest, XGBoost, Multilayer Perceptron, and Long Short-Term Memory networks. The generated models are evaluated in terms of predictive performance (recall, precision, and F1-score) and explainability using SHAP (SHapley Additive exPlanations). Specifically, we measure Average SHAP Fidelity (Mean Squared Error between SHAP approximations and model outputs) and Average SHAP Sparsity (number of features deemed influential). The results reveal that LLMs are capable of producing effective and interpretable models, achieving high fidelity and consistent sparsity, highlighting their potential as automated tools for interpretable ML pipeline generation. The results show that LLMs can produce effective, interpretable pipelines with high fidelity and consistent sparsity, closely matching manually engineered baselines.

---

### LLM-Assisted Modeling of Semantic Web-Enabled Multi-Agents Systems with AJAN

Authors: Hacane Hechehouche, Andre Antakli, Matthias Klusch
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.06911v1

There are many established semantic Web standards for implementing multi-agent driven applications. The AJAN framework allows to engineer multi-agent systems based on these standards. In particular, agent knowledge is represented in RDF/RDFS and OWL, while agent behavior models are defined with Behavior Trees and SPARQL to access and manipulate this knowledge. However, the appropriate definition of RDF/RDFS and SPARQL-based agent behaviors still remains a major hurdle not only for agent modelers in practice. For example, dealing with URIs is very error-prone regarding typos and dealing with complex SPARQL queries in large-scale environments requires a high learning curve. In this paper, we present an integrated development environment to overcome such hurdles of modeling AJAN agents and at the same time to extend the user community for AJAN by the possibility to leverage Large Language Models for agent engineering.

---

### Vacuum Spiker: A Spiking Neural Network-Based Model for Efficient Anomaly Detection in Time Series

Authors: Iago Xabier Vázquez, Javier Sedano, Muhammad Afzal, Ángel Miguel García-Vico
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06910v1

Anomaly detection is a key task across domains such as industry, healthcare, and cybersecurity. Many real-world anomaly detection problems involve analyzing multiple features over time, making time series analysis a natural approach for such problems. While deep learning models have achieved strong performance in this field, their trend to exhibit high energy consumption limits their deployment in resource-constrained environments such as IoT devices, edge computing platforms, and wearables. To address this challenge, this paper introduces the \textit{Vacuum Spiker algorithm}, a novel Spiking Neural Network-based method for anomaly detection in time series. It incorporates a new detection criterion that relies on global changes in neural activity rather than reconstruction or prediction error. It is trained using Spike Time-Dependent Plasticity in a novel way, intended to induce changes in neural activity when anomalies occur. A new efficient encoding scheme is also proposed, which discretizes the input space into non-overlapping intervals, assigning each to a single neuron. This strategy encodes information with a single spike per time step, improving energy efficiency compared to conventional encoding methods. Experimental results on publicly available datasets show that the proposed algorithm achieves competitive performance while significantly reducing energy consumption, compared to a wide set of deep learning and machine learning baselines. Furthermore, its practical utility is validated in a real-world case study, where the model successfully identifies power curtailment events in a solar inverter. These results highlight its potential for sustainable and efficient anomaly detection.

---

### Emotionally Vulnerable Subtype of Internet Gaming Disorder: Measuring and Exploring the Pathology of Problematic Generative AI Use

Authors: Haocan Sun, Di Wu, Weizi Liu, Guoming Yu, Mike Yao
Published: 2025-10-08
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.06908v2

Concerns over the potential over-pathologization of generative AI (GenAI) use and the lack of conceptual clarity surrounding GenAI addiction call for empirical tools and theoretical refinement. This study developed and validated the PUGenAIS-9 (Problematic Use of Generative Artificial Intelligence Scale-9 items) and examined whether PUGenAIS reflects addiction-like patterns under the Internet Gaming Disorder (IGD) framework. Using samples from China and the United States (N = 1,508), we conducted confirmatory factor analysis and identified a robust 31-item structure across nine IGD-based dimensions. We then derived the PUGenAIS-9 by selecting the highest-loading items from each dimension and validated its structure in an independent sample (N = 1,426). Measurement invariance tests confirmed its stability across nationality and gender. Person-centered (latent profile analysis) and variable-centered (network analysis) approaches revealed a 5-10% prevalence rate, a symptom network structure similar to IGD, and predictive factors related to psychological distress and functional impairment. These findings indicate that PUGenAI shares features of the emotionally vulnerable subtype of IGD rather than the competence-based type. These results support using PUGenAIS-9 to identify problematic GenAI use and show the need to rethink digital addiction with an ICD (infrastructures, content, and device) model. This keeps addiction research responsive to new media while avoiding over-pathologizing.

---

### Angular Constraint Embedding via SpherePair Loss for Constrained Clustering

Authors: Shaojie Zhang, Ke Chen
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.06907v1

Constrained clustering integrates domain knowledge through pairwise constraints. However, existing deep constrained clustering (DCC) methods are either limited by anchors inherent in end-to-end modeling or struggle with learning discriminative Euclidean embedding, restricting their scalability and real-world applicability. To avoid their respective pitfalls, we propose a novel angular constraint embedding approach for DCC, termed SpherePair. Using the SpherePair loss with a geometric formulation, our method faithfully encodes pairwise constraints and leads to embeddings that are clustering-friendly in angular space, effectively separating representation learning from clustering. SpherePair preserves pairwise relations without conflict, removes the need to specify the exact number of clusters, generalizes to unseen data, enables rapid inference of the number of clusters, and is supported by rigorous theoretical guarantees. Comparative evaluations with state-of-the-art DCC methods on diverse benchmarks, along with empirical validation of theoretical insights, confirm its superior performance, scalability, and overall real-world effectiveness. Code is available at \href{https://github.com/spherepaircc/SpherePairCC/tree/main}{our repository}.

---