# Research Papers — 2025-10 · bundle page 168 of 217

> Full-text markdown of papers #8351–8400 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/168
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/167.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/169.md)

### Distilling Lightweight Language Models for C/C++ Vulnerabilities

Authors: Zhiyuan Wei, Xiaoxuan Yang, Jing Sun, Zijian Zhang
Published: 2025-10-08
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.06645v1

The increasing complexity of modern software systems exacerbates the prevalence of security vulnerabilities, posing risks of severe breaches and substantial economic loss. Consequently, robust code vulnerability detection is essential for software security. While Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing, their potential for automated code vulnerability detection remains underexplored. This paper presents FineSec, a novel framework that harnesses LLMs through knowledge distillation to enable efficient and precise vulnerability identification in C/C++ codebases. FineSec utilizes knowledge distillation to transfer expertise from large teacher models to compact student models, achieving high accuracy with minimal computational cost. By integrating data preparation, training, evaluation, and continuous learning into a unified, single-task workflow, FineSec offers a streamlined approach. Extensive evaluations on C/C++ codebases demonstrate its superiority over both base models and larger LLMs in identifying complex vulnerabilities and logical flaws, establishing FineSec as a practical and scalable solution for real-world software security. To facilitate reproducibility, the datasets, source code, and experimental results are made publicly available at: https://github.com/yangxiaoxuan123/FineSec_detect.

---

### Contextual Representation Flow Across Depth in State-Space and Transformer Architectures

Authors: Nhat M. Hoang, Do Xuan Long, Cong-Duy Nguyen, Chunyan Miao, Min-Yen Kan, Luu Anh Tuan
Published: 2025-10-08
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.06640v3

State Space Models (SSMs) have emerged as efficient, linear-time alternatives to Transformer-Based Models (TBMs) for long-context processing. However, their different mechanisms raise an important question: how does contextual representation flow across depth differ between these model families and their hybrids? We examine this question across twenty-one pretrained models, combining token-wise spectral diversity, layer-wise variation on seven datasets, and answer-location probing on two retrieval tasks. This joint analysis reveals that TBMs retain most of their token diversity at the output, whereas SSMs reach richer intermediate diversity but retain less of it on average, with late-layer compression. Comparisons with reinitialized weights reveal that these profiles depend on pretrained weights, while hybrids combine strong answer-location accessibility with architecture-dependent geometry, showing that high accessibility need not require the steadiest representation flow. Finally, we conduct theoretical case studies connecting these contrasts to mechanism-level differences: query-time token mixing in TBMs, repeated recurrent updates in SSMs, and preserved attention updates in hybrids.

---

### StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering

Authors: Zhihao Wen, Wenkang Wei, Yuan Fang, Xingtong Yu, Hui Zhang, Weicheng Zhu, Xin Zhang
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.06638v3

Knowledge-based Visual Question Answering (KVQA) requires models to ground entities in images and reason over factual knowledge. Recent work has introduced its implicit-knowledge variant, IK-KVQA, where a multimodal large language model (MLLM) is the sole knowledge source and answers are produced without external retrieval. Existing IK-KVQA approaches, however, are typically trained with answer-only supervision: reasoning remains implicit, justifications are often weak or inconsistent, and generalization after standard supervised fine-tuning (SFT) can be brittle. We propose StaR-KVQA, a framework that equips IK-KVQA with dual-path structured reasoning traces - symbolic relation paths over text and vision together with path-grounded natural-language explanations - to provide a stronger inductive bias than generic answer-only supervision. These traces act as modality-aware scaffolds that guide the model toward relevant entities and attributes, offering more structure than generic chain-of-thought supervision while not constraining reasoning to any single fixed path. With a single open-source MLLM, StaR-KVQA constructs and selects traces to build an offline trace-enriched dataset and then performs structure-aware self-distillation; no external retrievers, verifiers, or curated knowledge bases are used, and inference is a single autoregressive pass. Across benchmarks, StaR-KVQA consistently improves both answer accuracy and the transparency of intermediate reasoning, achieving up to +11.3% higher answer accuracy on OK-VQA over the strongest baseline.

---

### Control-Augmented Autoregressive Diffusion for Data Assimilation

Authors: Prakhar Srivastava, Farrin Marouf Sofian, Francesco Immorlano, Kushagra Pandey, Stephan Mandt
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.06637v3

Despite advances in test-time scaling and diffusion finetuning, guidance for Auto-Regressive Diffusion Models (ARDMs) remains underexplored. We introduce an amortized framework that augments a pretrained ARDM with an offline-trained controller. By previewing future rollouts, the controller learns stepwise corrections that anticipate observations under a terminal-cost objective, yielding a reusable policy for guided generation. Motivated by a stochastic optimal control view of ARDM trajectories, our method injects small controls within each denoising sub-step while staying close to the pretrained dynamics. We study this approach for dataassimilation (DA) in chaotic spatiotemporal partial differential equations (PDEs), where existing methods are often computationally expensive and susceptible to forecast drift under sparse observations. At inference, DA becomes a feed-forward rollout with on-the-fly corrections, achieving an order-of-magnitude speedup over strong diffusion-based baselines. Across two canonical PDEs and a compact ECMWF Reanalysis v5 (ERA5) pilot spanning six observation regimes, our method consistently improves stability and accuracy over state-of-the-art alternatives, with similar improvements observed in a larger-scale GenCast study.

---

### StruSR: Structure-Aware Symbolic Regression with Physics-Informed Taylor Guidance

Authors: Yunpeng Gong, Sihan Lan, Can Yang, Kunpeng Xu, Min Jiang
Published: 2025-10-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.06635v1

Symbolic regression aims to find interpretable analytical expressions by searching over mathematical formula spaces to capture underlying system behavior, particularly in scientific modeling governed by physical laws. However, traditional methods lack mechanisms for extracting structured physical priors from time series observations, making it difficult to capture symbolic expressions that reflect the system's global behavior. In this work, we propose a structure-aware symbolic regression framework, called StruSR, that leverages trained Physics-Informed Neural Networks (PINNs) to extract locally structured physical priors from time series data. By performing local Taylor expansions on the outputs of the trained PINN, we obtain derivative-based structural information to guide symbolic expression evolution. To assess the importance of expression components, we introduce a masking-based attribution mechanism that quantifies each subtree's contribution to structural alignment and physical residual reduction. These sensitivity scores steer mutation and crossover operations within genetic programming, preserving substructures with high physical or structural significance while selectively modifying less informative components. A hybrid fitness function jointly minimizes physics residuals and Taylor coefficient mismatch, ensuring consistency with both the governing equations and the local analytical behavior encoded by the PINN. Experiments on benchmark PDE systems demonstrate that StruSR improves convergence speed, structural fidelity, and expression interpretability compared to conventional baselines, offering a principled paradigm for physics-grounded symbolic discovery.

---

### Three Forms of Stochastic Injection for Improved Distribution-to-Distribution Generative Modeling

Authors: Shiye Su, Yuhui Zhang, Linqi Zhou, Rajesh Ranganath, Serena Yeung-Levy
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06634v1

Modeling transformations between arbitrary data distributions is a fundamental scientific challenge, arising in applications like drug discovery and evolutionary simulation. While flow matching offers a natural framework for this task, its use has thus far primarily focused on the noise-to-data setting, while its application in the general distribution-to-distribution setting is underexplored. We find that in the latter case, where the source is also a data distribution to be learned from limited samples, standard flow matching fails due to sparse supervision. To address this, we propose a simple and computationally efficient method that injects stochasticity into the training process by perturbing source samples and flow interpolants. On five diverse imaging tasks spanning biology, radiology, and astronomy, our method significantly improves generation quality, outperforming existing baselines by an average of 9 FID points. Our approach also reduces the transport cost between input and generated samples to better highlight the true effect of the transformation, making flow matching a more practical tool for simulating the diverse distribution transformations that arise in science.

---

### Chem-NMF: Multi-layer $α$-divergence Non-Negative Matrix Factorization for Cardiorespiratory Disease Clustering, with Improved Convergence Inspired by Chemical Catalysts and Rigorous Asymptotic Analysis

Authors: Yasaman Torabi, Shahram Shirani, James P. Reilly
Published: 2025-10-08
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2510.06632v1

Non-Negative Matrix Factorization (NMF) is an unsupervised learning method offering low-rank representations across various domains such as audio processing, biomedical signal analysis, and image recognition. The incorporation of $α$-divergence in NMF formulations enhances flexibility in optimization, yet extending these methods to multi-layer architectures presents challenges in ensuring convergence. To address this, we introduce a novel approach inspired by the Boltzmann probability of the energy barriers in chemical reactions to theoretically perform convergence analysis. We introduce a novel method, called Chem-NMF, with a bounding factor which stabilizes convergence. To our knowledge, this is the first study to apply a physical chemistry perspective to rigorously analyze the convergence behaviour of the NMF algorithm. We start from mathematically proven asymptotic convergence results and then show how they apply to real data. Experimental results demonstrate that the proposed algorithm improves clustering accuracy by 5.6% $\pm$ 2.7% on biomedical signals and 11.1% $\pm$ 7.2% on face images (mean $\pm$ std).

---

### AI-Driven Forecasting and Monitoring of Urban Water System

Authors: Qiming Guo, Bishal Khatri, Hua Zhang, Wenlu Wang
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06631v1

Underground water and wastewater pipelines are vital for city operations but plagued by anomalies like leaks and infiltrations, causing substantial water loss, environmental damage, and high repair costs. Conventional manual inspections lack efficiency, while dense sensor deployments are prohibitively expensive. In recent years, artificial intelligence has advanced rapidly and is increasingly applied to urban infrastructure. In this research, we propose an integrated AI and remote-sensor framework to address the challenge of leak detection in underground water pipelines, through deploying a sparse set of remote sensors to capture real-time flow and depth data, paired with HydroNet - a dedicated model utilizing pipeline attributes (e.g., material, diameter, slope) in a directed graph for higher-precision modeling. Evaluations on a real-world campus wastewater network dataset demonstrate that our system collects effective spatio-temporal hydraulic data, enabling HydroNet to outperform advanced baselines. This integration of edge-aware message passing with hydraulic simulations enables accurate network-wide predictions from limited sensor deployments. We envision that this approach can be effectively extended to a wide range of underground water pipeline networks.

---

### Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks

Authors: Jiachen Li, Bang Wu, Xiaoyu Xia, Xiaoning Liu, Xun Yi, Xiuzhen Zhang
Published: 2025-10-08
Categories: cs.CR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.06629v1

Spiking Neural Networks (SNNs) have gained increasing attention for their superior energy efficiency compared to Artificial Neural Networks (ANNs). However, their security aspects, particularly under backdoor attacks, have received limited attention. Existing defense methods developed for ANNs perform poorly or can be easily bypassed in SNNs due to their event-driven and temporal dependencies. This paper identifies the key blockers that hinder traditional backdoor defenses in SNNs and proposes an unsupervised post-training detection framework, Temporal Membrane Potential Backdoor Detection (TMPBD), to overcome these challenges. TMPBD leverages the maximum margin statistics of temporal membrane potential (TMP) in the final spiking layer to detect target labels without any attack knowledge or data access. We further introduce a robust mitigation mechanism, Neural Dendrites Suppression Backdoor Mitigation (NDSBM), which clamps dendritic connections between early convolutional layers to suppress malicious neurons while preserving benign behaviors, guided by TMP extracted from a small, clean, unlabeled dataset. Extensive experiments on multiple neuromorphic benchmarks and state-of-the-art input-aware dynamic trigger attacks demonstrate that TMPBD achieves 100% detection accuracy, while NDSBM reduces the attack success rate from 100% to 8.44%, and to 2.81% when combined with detection, without degrading clean accuracy.

---

### POME: Post Optimization Model Edit via Muon-style Projection

Authors: Yong Liu, Di Fu, Yang Luo, Zirui Zhu, Minhao Cheng, Cho-Jui Hsieh, Yang You
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06627v1

We introduce Post-Optimization Model Edit (POME), a new algorithm that enhances the performance of fine-tuned large language models using only their pretrained and fine-tuned checkpoints, without requiring extra data or further optimization. The core idea is to apply a muon-style projection to $ΔW$, the difference between the fine-tuned and pretrained weights. This projection uses truncated singular value decomposition (SVD) to equalize the influence of dominant update directions and prune small singular values, which often represent noise. As a simple post-processing step, POME is completely decoupled from the training pipeline. It requires zero modifications and imposes no overhead, making it universally compatible with any optimizer or distributed framework. POME delivers consistent gains, boosting average performance by +2.5\% on GSM8K and +1.0\% on code generation. Its broad applicability -- from 7B foundation models to 72B RLHF-instructed models -- establishes it as a practical, zero-cost enhancement for any fine-tuning pipeline. Code is available at https://github.com/NUS-HPC-AI-Lab/POME.

---

### DPA-Net: A Dual-Path Attention Neural Network for Inferring Glycemic Control Metrics from Self-Monitored Blood Glucose Data

Authors: Canyu Lei, Benjamin Lobo, Jianxin Xie
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06623v1

Continuous glucose monitoring (CGM) provides dense and dynamic glucose profiles that enable reliable estimation of Ambulatory Glucose Profile (AGP) metrics, such as Time in Range (TIR), Time Below Range (TBR), and Time Above Range (TAR). However, the high cost and limited accessibility of CGM restrict its widespread adoption, particularly in low- and middle-income regions. In contrast, self-monitoring of blood glucose (SMBG) is inexpensive and widely available but yields sparse and irregular data that are challenging to translate into clinically meaningful glycemic metrics. In this work, we propose a Dual-Path Attention Neural Network (DPA-Net) to estimate AGP metrics directly from SMBG data. DPA-Net integrates two complementary paths: (1) a spatial-channel attention path that reconstructs a CGM-like trajectory from sparse SMBG observations, and (2) a multi-scale ResNet path that directly predicts AGP metrics. An alignment mechanism between the two paths is introduced to reduce bias and mitigate overfitting. In addition, we develop an active point selector to identify realistic and informative SMBG sampling points that reflect patient behavioral patterns. Experimental results on a large, real-world dataset demonstrate that DPA-Net achieves robust accuracy with low errors while reducing systematic bias. To the best of our knowledge, this is the first supervised machine learning framework for estimating AGP metrics from SMBG data, offering a practical and clinically relevant decision-support tool in settings where CGM is not accessible.

---

### FEAorta: A Fully Automated Framework for Finite Element Analysis of the Aorta From 3D CT Images

Authors: Jiasong Chen, Linchen Qian, Ruonan Gong, Christina Sun, Tongran Qin, Thuy Pham, Caitlin Martin, Mohammad Zafar, John Elefteriades, Wei Sun, Liang Liang
Published: 2025-10-08
Categories: eess.IV, cs.CE, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.06621v1

Aortic aneurysm disease ranks consistently in the top 20 causes of death in the U.S. population. Thoracic aortic aneurysm is manifested as an abnormal bulging of thoracic aortic wall and it is a leading cause of death in adults. From the perspective of biomechanics, rupture occurs when the stress acting on the aortic wall exceeds the wall strength. Wall stress distribution can be obtained by computational biomechanical analyses, especially structural Finite Element Analysis. For risk assessment, probabilistic rupture risk of TAA can be calculated by comparing stress with material strength using a material failure model. Although these engineering tools are currently available for TAA rupture risk assessment on patient specific level, clinical adoption has been limited due to two major barriers: labor intensive 3D reconstruction current patient specific anatomical modeling still relies on manual segmentation, making it time consuming and difficult to scale to a large patient population, and computational burden traditional FEA simulations are resource intensive and incompatible with time sensitive clinical workflows. The second barrier was successfully overcome by our team through the development of the PyTorch FEA library and the FEA DNN integration framework. By incorporating the FEA functionalities within PyTorch FEA and applying the principle of static determinacy, we reduced the FEA based stress computation time to approximately three minutes per case. Moreover, by integrating DNN and FEA through the PyTorch FEA library, our approach further decreases the computation time to only a few seconds per case. This work focuses on overcoming the first barrier through the development of an end to end deep neural network capable of generating patient specific finite element meshes of the aorta directly from 3D CT images.

---

### MSITrack: A Challenging Benchmark for Multispectral Single Object Tracking

Authors: Tao Feng, Tingfa Xu, Haolin Qin, Tianhao Li, Shuaihao Han, Xuyang Zou, Zhan Lv, Jianan Li
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06619v1

Visual object tracking in real-world scenarios presents numerous challenges including occlusion, interference from similar objects and complex backgrounds-all of which limit the effectiveness of RGB-based trackers. Multispectral imagery, which captures pixel-level spectral reflectance, enhances target discriminability. However, the availability of multispectral tracking datasets remains limited. To bridge this gap, we introduce MSITrack, the largest and most diverse multispectral single object tracking dataset to date. MSITrack offers the following key features: (i) More Challenging Attributes-including interference from similar objects and similarity in color and texture between targets and backgrounds in natural scenarios, along with a wide range of real-world tracking challenges; (ii) Richer and More Natural Scenes-spanning 55 object categories and 300 distinct natural scenes, MSITrack far exceeds the scope of existing benchmarks. Many of these scenes and categories are introduced to the multispectral tracking domain for the first time; (iii) Larger Scale-300 videos comprising over 129k frames of multispectral imagery. To ensure annotation precision, each frame has undergone meticulous processing, manual labeling and multi-stage verification. Extensive evaluations using representative trackers demonstrate that the multispectral data in MSITrack significantly improves performance over RGB-only baselines, highlighting its potential to drive future advancements in the field. The MSITrack dataset is publicly available at: https://github.com/Fengtao191/MSITrack.

---

### A Bridge from Audio to Video: Phoneme-Viseme Alignment Allows Every Face to Speak Multiple Languages

Authors: Zibo Su, Kun Wei, Jiahua Li, Jing Kong, Xu Yang, Cheng Deng
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06612v2

Speech-driven talking face synthesis (TFS) focuses on generating lifelike facial animations from speech input. Current TFS models perform well in English but struggle with non-English languages, producing inaccurate mouth shapes and rigid facial expressions. These limitations are mainly caused by English-dominated training datasets and the lack of cross-language generalization ability.To address these challenges, we propose Multilingual Experts (MuEx), a novel framework featuring a Phoneme-Guided Mixture-of-Experts (PG-MoE) architecture that employs phonemes and visemes as universal intermediaries to bridge the gap between audio and visual modalities, enabling lifelike multilingual TFS. We extract speech and visual features as phonemes and visemes, respectively, which represent the basic units of speech sounds and mouth movements, to alleviate linguistic differences and dataset bias.Furthermore, we introduce the Phoneme-Viseme Alignment Mechanism (PV-Align), which establishes robust cross-modal correspondences between phonemes and visemes to improve audiovisual synchronization. In addition, we construct a Multilingual Talking Face Dataset (MTFD) comprising 12 diverse languages with 95.04 hours of high-quality videos for training and evaluating multilingual TFS performance.Extensive experiments demonstrate that MuEx achieves superior performance across all languages in MTFD and exhibits effective zero-shot generalization to unseen languages without additional training.

---

### Self-supervised Deep Unrolled Model with Implicit Neural Representation Regularization for Accelerating MRI Reconstruction

Authors: Jingran Xu, Yuanyuan Liu, Yuanbiao Yang, Zhuo-Xu Cui, Jing Cheng, Qingyong Zhu, Nannan Zhang, Yihang Zhou, Dong Liang, Yanjie Zhu
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06611v2

Magnetic resonance imaging (MRI) is a vital clinical diagnostic tool, yet its application is limited by prolonged scan times. Accelerating MRI reconstruction addresses this issue by reconstructing high-fidelity MR images from undersampled k-space measurements. In recent years, deep learning-based methods have demonstrated remarkable progress. However, most methods rely on supervised learning, which requires large amounts of fully-sampled training data that are difficult to obtain. This paper proposes a novel zero-shot self-supervised reconstruction method named UnrollINR, which enables scan-specific MRI reconstruction without external training data. UnrollINR adopts a physics-guided unrolled reconstruction architecture and introduces implicit neural representation (INR) as a regularization prior to effectively constrain the solution space. This method overcomes the local bias limitation of CNNs in traditional deep unrolled methods and avoids the instability associated with relying solely on INR's implicit regularization in highly ill-posed scenarios. Consequently, UnrollINR significantly improves MRI reconstruction performance under high acceleration rates. Experimental results show that even at a high acceleration rate of 10, UnrollINR achieves superior reconstruction performance compared to supervised and self-supervised learning methods, validating its effectiveness and superiority.

---

### Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation

Authors: Shuo Shao, Yiming Li, Hongwei Yao, Yifei Chen, Yuchen Yang, Zhan Qin
Published: 2025-10-08
Categories: cs.CR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.06605v2

The substantial investment required to develop Large Language Models (LLMs) makes them valuable intellectual property, raising significant concerns about copyright protection. LLM fingerprinting has emerged as a key technique to address this, which aims to verify a model's origin by extracting an intrinsic, unique signature (a "fingerprint") and comparing it to that of a source model to identify illicit copies. However, existing black-box fingerprinting methods often fail to generate distinctive LLM fingerprints. This ineffectiveness arises because black-box methods typically rely on model outputs, which lose critical information about the model's unique parameters due to the usage of non-linear functions. To address this, we first leverage Fisher Information Theory to formally demonstrate that the gradient of the model's input is a more informative feature for fingerprinting than the output. Based on this insight, we propose ZeroPrint, a novel method that approximates these information-rich gradients in a black-box setting using zeroth-order estimation. ZeroPrint overcomes the challenge of applying this to discrete text by simulating input perturbations via semantic-preserving word substitutions. This operation allows ZeroPrint to estimate the model's Jacobian matrix as a unique fingerprint. Experiments on the standard benchmark show ZeroPrint achieves a state-of-the-art effectiveness and robustness, significantly outperforming existing black-box methods.

---

### AIM 2025 Challenge on Real-World RAW Image Denoising

Authors: Feiran Li, Jiacheng Li, Marcos V. Conde, Beril Besbinar, Vlad Hosu, Daisuke Iso, Radu Timofte
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06601v1

We introduce the AIM 2025 Real-World RAW Image Denoising Challenge, aiming to advance efficient and effective denoising techniques grounded in data synthesis. The competition is built upon a newly established evaluation benchmark featuring challenging low-light noisy images captured in the wild using five different DSLR cameras. Participants are tasked with developing novel noise synthesis pipelines, network architectures, and training methodologies to achieve high performance across different camera models. Winners are determined based on a combination of performance metrics, including full-reference measures (PSNR, SSIM, LPIPS), and non-reference ones (ARNIQA, TOPIQ). By pushing the boundaries of camera-agnostic low-light RAW image denoising trained on synthetic data, the competition promotes the development of robust and practical models aligned with the rapid progress in digital photography. We expect the competition outcomes to influence multiple domains, from image restoration to night-time autonomous driving.

---

### Fine-Grained Emotion Recognition via In-Context Learning

Authors: Zhaochun Ren, Zhou Yang, Chenglong Ye, Haizhou Sun, Chao Chen, Xiaofei Zhu, Xiangwen Liao
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.06600v1

Fine-grained emotion recognition aims to identify the emotional type in queries through reasoning and decision-making processes, playing a crucial role in various systems. Recent methods use In-Context Learning (ICL), enhancing the representation of queries in the reasoning process through semantically similar examples, while further improving emotion recognition by explaining the reasoning mechanisms. However, these methods enhance the reasoning process but overlook the decision-making process. This paper investigates decision-making in fine-grained emotion recognition through prototype theory. We show that ICL relies on similarity matching between query representations and emotional prototypes within the model, where emotion-accurate representations are critical. However, semantically similar examples often introduce emotional discrepancies, hindering accurate representations and causing errors. To address this, we propose Emotion In-Context Learning (EICL), which introduces emotionally similar examples and uses a dynamic soft-label strategy to improve query representations in the emotion reasoning process. A two-stage exclusion strategy is then employed to assess similarity from multiple angles, further optimizing the decision-making process. Extensive experiments show that EICL significantly outperforms ICL on multiple datasets.

---

### SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation

Authors: Ayush Zenith, Arnold Zumbrun, Neel Raut, Jing Lin
Published: 2025-10-08
Categories: cs.CV, cs.AI, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2510.06596v2

The performance of machine learning models depends heavily on training data. The scarcity of large-scale, well-annotated datasets poses significant challenges in creating robust models. To address this, synthetic data generated through simulations and generative models has emerged as a promising solution, enhancing dataset diversity and improving the performance, reliability, and resilience of models. However, evaluating the quality of this generated data requires an effective metric. We introduce the Synthetic Dataset Quality Metric (SDQM) to assess data quality for object detection tasks without requiring model training to converge. This metric enables more efficient generation and selection of synthetic datasets, addressing a key challenge in resource-constrained object detection tasks. In our experiments, SDQM demonstrated a strong correlation with the mean average precision (mAP) scores of YOLO11, a leading object detection model, whereas previous metrics only exhibited moderate or weak correlations. In addition, it provides actionable insights into improving dataset quality, minimizing the need for costly iterative training. This scalable and efficient metric sets a new standard for evaluating synthetic data. The code for SDQM is available at https://github.com/ayushzenith/SDQM

---

### Do Internal Layers of LLMs Reveal Patterns for Jailbreak Detection?

Authors: Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06594v2

Jailbreaking large language models (LLMs) has emerged as a pressing concern with the increasing prevalence and accessibility of conversational LLMs. Adversarial users often exploit these models through carefully engineered prompts to elicit restricted or sensitive outputs, a strategy widely referred to as jailbreaking. While numerous defense mechanisms have been proposed, attackers continuously develop novel prompting techniques, and no existing model can be considered fully resistant. In this study, we investigate the jailbreak phenomenon by examining the internal representations of LLMs, with a focus on how hidden layers respond to jailbreak versus benign prompts. Specifically, we analyze the open-source LLM GPT-J and the state-space model Mamba2, presenting preliminary findings that highlight distinct layer-wise behaviors. Our results suggest promising directions for further research on leveraging internal model dynamics for robust jailbreak detection and defense.

---

### Adaptive Stain Normalization for Cross-Domain Medical Histology

Authors: Tianyue Xu, Yanlin Wu, Abhai K. Tripathi, Matthew M. Ippolito, Benjamin D. Haeffele
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06592v1

Deep learning advances have revolutionized automated digital pathology analysis. However, differences in staining protocols and imaging conditions can introduce significant color variability. In deep learning, such color inconsistency often reduces performance when deploying models on data acquired under different conditions from the training data, a challenge known as domain shift. Many existing methods attempt to address this problem via color normalization but suffer from several notable drawbacks such as introducing artifacts or requiring careful choice of a template image for stain mapping. To address these limitations, we propose a trainable color normalization model that can be integrated with any backbone network for downstream tasks such as object detection and classification. Based on the physics of the imaging process per the Beer-Lambert law, our model architecture is derived via algorithmic unrolling of a nonnegative matrix factorization (NMF) model to extract stain-invariant structural information from the original pathology images, which serves as input for further processing. Experimentally, we evaluate the method on publicly available pathology datasets and an internally curated collection of malaria blood smears for cross-domain object detection and classification, where our method outperforms many state-of-the-art stain normalization methods. Our code is available at https://github.com/xutianyue/BeerLaNet.

---

### Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer

Authors: Ziyuan Huang, DanDan Zheng, Cheng Zou, Rui Liu, Xiaolong Wang, Kaixiang Ji, Weilong Chai, Jianxin Sun, Libin Wang, Yongjie Lv, Taozhi Huang, Jiajia Liu et al.
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06590v1

Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in discrete latent spaces to align with the tokens from large language models, where the quantization errors can limit semantic expressiveness and degrade the capability of vision-language understanding. To address this, we introduce MingTok, a new family of visual tokenizers with a continuous latent space, for unified autoregressive generation and understanding. While understanding tasks favor discriminative high-dimensional features, generation tasks prefer compact low-level codes. Thus, to reconcile these competing demands, MingTok adopts a three-stage sequential architecture involving low-level encoding, semantic expansion, and visual reconstruction. Built on top of it, Ming-UniVision eliminates the need for task-specific visual representations, and unifies diverse vision-language tasks under a single autoregrsssive prediction paradigm. By formulating both understanding and generation as next-token prediction in a shared continuous space, it seamlessly supports multi-round, in-context tasks such as iterative understanding, generation and editing. Empirically, we find that using a unified continuous visual representation reconciles the competing requirements on the tokenizers by the understanding and generation tasks, thereby leading to state-of-the-art level performance across both domains. We hope our findings will facilitate unified visual tokenization in the continuous domain. Inference code and model weights are released to benefit community.

---

### WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks

Authors: Jingbo Yang, Bairu Hou, Wei Wei, Shiyu Chang, Yujia Bao
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.06587v1

Large language model (LLM) agents are becoming competent at straightforward web tasks, such as opening an item page or submitting a form, but still struggle with objectives that require long horizon navigation, large scale information extraction, and reasoning under constraints. We present WebDART, a general framework that enables a single LLM to handle such complex chores. WebDART (i) dynamically decomposes each objective into three focused subtasks: navigation, information extraction, and execution, so the model concentrates on one skill at a time, and (ii) continuously replans the decomposition as new webpages are revealed, taking advantage of newly discovered filters or shortcuts and avoiding redundant exploration. Evaluated on WebChoreArena, WebDART lifts success rates by up to 13.7 percentage points over previous SOTA agents, while matching their performance on the easier WebArena suite and completing tasks with up to 14.7 fewer navigation steps.

---

### Improving Artifact Robustness for CT Deep Learning Models Without Labeled Artifact Images via Domain Adaptation

Authors: Justin Cheung, Samuel Savine, Calvin Nguyen, Lin Lu, Alhassan S. Yasin
Published: 2025-10-08
Categories: cs.CV, q-bio.TO
arXiv: https://arxiv.org/abs/2510.06584v2

If a CT scanner introduces a new artifact not present in the training labels, the model may misclassify the images. Although modern CT scanners include design features which mitigate these artifacts, unanticipated or difficult-to-mitigate artifacts can still appear in practice. The direct solution of labeling images from this new distribution can be costly. As a more accessible alternative, this study evaluates domain adaptation as an approach for training models that maintain classification performance despite new artifacts, even without corresponding labels. We simulate ring artifacts from detector gain error in sinogram space and evaluate domain adversarial neural networks (DANN) against baseline and augmentation-based approaches on the OrganAMNIST abdominal CT dataset. We simulate the absence of labels from an unseen distribution via masking in the loss function and selectively detaching unlabeled instances from the computational graph. Our results demonstrate that baseline models trained only on clean images fail to generalize to images with ring artifacts, and traditional augmentation with other distortion types provides no improvement on unseen artifact domains. In contrast, the DANN approach improves classification accuracy on ring artifact images using only unlabeled artifact data during training, demonstrating the viability of domain adaptation for artifact robustness. The domain-adapted model achieved a classification accuracy of 77.4% on ring artifact test data, 38.7% higher than a baseline model only trained on images with no artifact. These findings provide empirical evidence that domain adaptation can effectively address distribution shift in medical imaging without requiring expensive expert labeling of new artifact distributions, suggesting promise for deployment in clinical settings where novel artifacts may emerge.

---

### Through the Perspective of LiDAR: A Feature-Enriched and Uncertainty-Aware Annotation Pipeline for Terrestrial Point Cloud Segmentation

Authors: Fei Zhang, Rob Chancia, Josie Clapp, Amirhossein Hassanzadeh, Dimah Dera, Richard MacKenzie, Jan van Aardt
Published: 2025-10-08
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.06582v3

Accurate semantic segmentation of terrestrial laser scanning (TLS) point clouds is limited by costly manual annotation. We propose a semi-automated, uncertainty-aware pipeline that integrates spherical projection, feature enrichment, ensemble learning, and targeted annotation to reduce labeling effort, while sustaining high accuracy. Our approach projects 3D points to a 2D spherical grid, enriches pixels with multi-source features, and trains an ensemble of segmentation networks to produce pseudo-labels and uncertainty maps, the latter guiding annotation of ambiguous regions. The 2D outputs are back-projected to 3D, yielding densely annotated point clouds supported by a three-tier visualization suite (2D feature maps, 3D colorized point clouds, and compact virtual spheres) for rapid triage and reviewer guidance. Using this pipeline, we build Mangrove3D, a semantic segmentation TLS dataset for mangrove forests. We further evaluate data efficiency and feature importance to address two key questions: (1) how much annotated data are needed and (2) which features matter most. Results show that performance saturates after ~12 annotated scans, geometric features contribute the most, and compact nine-channel stacks capture nearly all discriminative power, with the mean Intersection over Union (mIoU) plateauing at around 0.76. Finally, we confirm the generalization of our feature-enrichment strategy through cross-dataset tests on ForestSemantic and Semantic3D. Our contributions include: (i) a robust, uncertainty-aware TLS annotation pipeline with visualization tools; (ii) the Mangrove3D dataset; and (iii) empirical guidance on data efficiency and feature importance, thus enabling scalable, high-quality segmentation of TLS point clouds for ecological monitoring and beyond. The dataset and processing scripts are publicly available at https://fz-rit.github.io/through-the-lidars-eye/.

---

### TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents

Authors: Haofei Yu, Keyang Xuan, Fenghai Li, Kunlun Zhu, Zijie Lei, Jiaxun Zhang, Ziheng Qi, Kyle Richardson, Jiaxuan You
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06579v1

Automatic research with Large Language Models (LLMs) is rapidly gaining importance, driving the development of increasingly complex workflows involving multi-agent systems, planning, tool usage, code execution, and human-agent interaction to accelerate research processes. However, as more researchers and developers begin to use and build upon these tools and platforms, the complexity and difficulty of extending and maintaining such agentic workflows have become a significant challenge, particularly as algorithms and architectures continue to advance. To address this growing complexity, TinyScientist identifies the essential components of the automatic research workflow and proposes an interactive, extensible, and controllable framework that easily adapts to new tools and supports iterative growth. We provide an open-source codebase, an interactive web demonstration, and a PyPI Python package to make state-of-the-art auto-research pipelines broadly accessible to every researcher and developer.

---

### The Framework That Survives Bad Models: Human-AI Collaboration For Clinical Trials

Authors: Yao Chen, David Ohlssen, Aimee Readie, Gregory Ligozio, Ruvie Martin, Thibaud Coroller
Published: 2025-10-08
Categories: cs.LG, cs.AI, eess.IV
arXiv: https://arxiv.org/abs/2510.06567v1

Artificial intelligence (AI) holds great promise for supporting clinical trials, from patient recruitment and endpoint assessment to treatment response prediction. However, deploying AI without safeguards poses significant risks, particularly when evaluating patient endpoints that directly impact trial conclusions. We compared two AI frameworks against human-only assessment for medical image-based disease evaluation, measuring cost, accuracy, robustness, and generalization ability. To stress-test these frameworks, we injected bad models, ranging from random guesses to naive predictions, to ensure that observed treatment effects remain valid even under severe model degradation. We evaluated the frameworks using two randomized controlled trials with endpoints derived from spinal X-ray images. Our findings indicate that using AI as a supporting reader (AI-SR) is the most suitable approach for clinical trials, as it meets all criteria across various model types, even with bad models. This method consistently provides reliable disease estimation, preserves clinical trial treatment effect estimates and conclusions, and retains these advantages when applied to different populations.

---

### HSNet: Heterogeneous Subgraph Network for Single Image Super-resolution

Authors: Qiongyang Hu, Wenyang Liu, Wenbin Zou, Yuejiao Su, Lap-Pui Chau, Yi Wang
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.06564v1

Existing deep learning approaches for image super-resolution, particularly those based on CNNs and attention mechanisms, often suffer from structural inflexibility. Although graph-based methods offer greater representational adaptability, they are frequently impeded by excessive computational complexity. To overcome these limitations, this paper proposes the Heterogeneous Subgraph Network (HSNet), a novel framework that efficiently leverages graph modeling while maintaining computational feasibility. The core idea of HSNet is to decompose the global graph into manageable sub-components. First, we introduce the Constructive Subgraph Set Block (CSSB), which generates a diverse set of complementary subgraphs. Rather than relying on a single monolithic graph, CSSB captures heterogeneous characteristics of the image by modeling different relational patterns and feature interactions, producing a rich ensemble of both local and global graph structures. Subsequently, the Subgraph Aggregation Block (SAB) integrates the representations embedded across these subgraphs. Through adaptive weighting and fusion of multi-graph features, SAB constructs a comprehensive and discriminative representation that captures intricate interdependencies. Furthermore, a Node Sampling Strategy (NSS) is designed to selectively retain the most salient features, thereby enhancing accuracy while reducing computational overhead. Extensive experiments demonstrate that HSNet achieves state-of-the-art performance, effectively balancing reconstruction quality with computational efficiency. The code will be made publicly available.

---

### Adapting Quantum Machine Learning for Energy Dissociation of Bonds

Authors: Swathi Chandrasekhar, Shiva Raj Pokhrel, Navneet Singh
Published: 2025-10-08
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.06563v1

Accurate prediction of bond dissociation energies (BDEs) underpins mechanistic insight and the rational design of molecules and materials. We present a systematic, reproducible benchmark comparing quantum and classical machine learning models for BDE prediction using a chemically curated feature set encompassing atomic properties (atomic numbers, hybridization), bond characteristics (bond order, type), and local environmental descriptors. Our quantum framework, implemented in Qiskit Aer on six qubits, employs ZZFeatureMap encodings with variational ansatz (RealAmplitudes) across multiple architectures Variational Quantum Regressors (VQR), Quantum Support Vector Regressors (QSVR), Quantum Neural Networks (QNN), Quantum Convolutional Neural Networks (QCNN), and Quantum Random Forests (QRF). These are rigorously benchmarked against strong classical baselines, including Support Vector Regression (SVR), Random Forests (RF), and Multi-Layer Perceptrons (MLP). Comprehensive evaluation spanning absolute and relative error metrics, threshold accuracies, and error distributions shows that top-performing quantum models (QCNN, QRF) match the predictive accuracy and robustness of classical ensembles and deep networks, particularly within the chemically prevalent mid-range BDE regime. These findings establish a transparent baseline for quantum-enhanced molecular property prediction and outline a practical foundation for advancing quantum computational chemistry toward near chemical accuracy.

---

### The Algebra of Meaning: Why Machines Need Montague More Than Moore's Law

Authors: Cheonkam Jeong, Sungdo Kim, Jewoo Park
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2510.06559v1

Contemporary language models are fluent yet routinely mis-handle the types of meaning their outputs entail. We argue that hallucination, brittle moderation, and opaque compliance outcomes are symptoms of missing type-theoretic semantics rather than data or scale limitations. Building on Montague's view of language as typed, compositional algebra, we recast alignment as a parsing problem: natural-language inputs must be compiled into structures that make explicit their descriptive, normative, and legal dimensions under context. We present Savassan, a neuro-symbolic architecture that compiles utterances into Montague-style logical forms and maps them to typed ontologies extended with deontic operators and jurisdictional contexts. Neural components extract candidate structures from unstructured inputs; symbolic components perform type checking, constraint reasoning, and cross-jurisdiction mapping to produce compliance-aware guidance rather than binary censorship. In cross-border scenarios, the system "parses once" (e.g., defect claim(product x, company y)) and projects the result into multiple legal ontologies (e.g., defamation risk in KR/JP, protected opinion in US, GDPR checks in EU), composing outcomes into a single, explainable decision. This paper contributes: (i) a diagnosis of hallucination as a type error; (ii) a formal Montague-ontology bridge for business/legal reasoning; and (iii) a production-oriented design that embeds typed interfaces across the pipeline. We outline an evaluation plan using legal reasoning benchmarks and synthetic multi-jurisdiction suites. Our position is that trustworthy autonomy requires compositional typing of meaning, enabling systems to reason about what is described, what is prescribed, and what incurs liability within a unified algebra of meaning.

---

### The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning

Authors: Milad Aghajohari, Kamran Chitsaz, Amirhossein Kazemnejad, Sarath Chandar, Alessandro Sordoni, Aaron Courville, Siva Reddy
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.06557v3

Reinforcement learning (RL) has recently become a strong recipe for training reasoning LLMs that produce long chains of thought (LongCoT). Yet the standard RL "thinking environment", where the state is the prompt plus all prior reasoning tokens, makes the state unbounded and forces attention-based policies to pay quadratic compute as thoughts lengthen. We revisit the environment itself. We propose Markovian Thinking, a paradigm in which the policy advances reasoning while conditioning on a constant-size state, decoupling thinking length from context size. As an immediate consequence this yields linear compute with constant memory. We instantiate this idea with Delethink, an RL environment that structures reasoning into fixed-size chunks. Within each chunk, the model thinks as usual; at the boundary, the environment resets the context and reinitializes the prompt with a short carryover. Through RL, the policy learns to write a textual state near the end of each chunk sufficient for seamless continuation of reasoning after reset. Trained in this environment, an R1-Distill 1.5B model reasons in 8K-token chunks yet thinks up to 24K tokens, matching or surpassing LongCoT-RL trained with a 24K budget. With test-time scaling, Delethink continues to improve where LongCoT plateaus. The effect of linear compute is substantial: we empirically estimate at 96K average thinking length LongCoT-RL costs 27 H100-months vs. 7 for Delethink. Analysis at RL initialization shows off-the-shelf reasoning models (1.5B-120B) often sample Markovian traces zero-shot across diverse benchmarks, providing positive samples that make RL effective at scale. Our results show that redesigning the thinking environment is a powerful lever: it enables very long reasoning without quadratic overhead and opens a path toward efficient, scalable reasoning LLMs.

---

### Flipping the Dialogue: Training and Evaluating User Language Models

Authors: Tarek Naous, Philippe Laban, Wei Xu, Jennifer Neville
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06552v2

Conversations with LMs involve two participants: a human user leading the conversation, and an LM assistant responding to the user's request. To satisfy this specific role, LMs are post-trained to be helpful assistants -- optimized to produce exhaustive and well-structured responses, free of ambiguity and grammar errors. User utterances, on the other hand, are rarely perfected, with each user phrasing requests in unique ways, sometimes putting in partial effort at each turn and refining on the fly. To evaluate LM performance in realistic settings, prior work simulated users in multi-turn conversations, often by prompting an LM originally trained to be a helpful assistant to act as a user. However, we show that assistant LMs make for poor user simulators, with the surprising finding that better assistants yield worse simulators. Instead, we introduce purpose-built User Language Models (User LMs) - models post-trained to simulate human users in multi-turn conversations. Through various evaluations, we show how User LMs align better with human behavior and achieve better simulation robustness than existing simulation methods. When leveraging User LMs to simulate coding and math conversations, the performance of a strong assistant (GPT-4o) drops from 74.6% to 57.4%, confirming that more realistic simulation environments lead to assistant struggles as they fail to cope with the nuances of users in multi-turn setups.

---

### Reusing Overtrained Language Models Saturates Scaling

Authors: Seng Pei Liew, Takuya Kato
Published: 2025-10-08
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.06548v2

Reusing pretrained base models for further pretraining, such as continual pretraining or model growth, is promising at reducing the cost of training language models from scratch. However, the effectiveness remains unclear, especially when applied to overtrained base models. In this work, we empirically study the scaling properties of model reuse and find that the scaling efficiency diminishes in a predictable manner: The scaling exponent with respect to second-stage training tokens decreases logarithmically with the number of tokens used to pretrain the base model. The joint dependence on first- and second-stage tokens is accurately modeled by a simple scaling law. Such saturation effect reveals a fundamental trade-off in multi-stage pretraining strategies: the more extensively a base model is pretrained, the less benefit additional pretraining provides. Our findings provide practical insights for efficient language model training and raise important considerations for the reuse of overtrained models.

---

### Incoherence in Goal-Conditioned Autoregressive Models

Authors: Jacek Karwowski, Raymond Douglas
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06545v2

We investigate mathematically the notion of incoherence: a structural issue with reinforcement learning policies derived by naive goal-conditioning of autoregressive models. We focus on the process of re-training models on their own actions, that is, fine-tuning offline-learned policies with online RL. We prove that it decreases incoherence and leads to an improvement in return, and we aim to characterize the resulting trajectory of policies. By re-framing standard notions of control-as-inference and soft Q learning, we establish a three-way correspondence with two other ways of understanding the iterative re-training process: as folding the posterior into the reward and, in the deterministic case, as decreasing the temperature parameter; the correspondence has computational content via the training-inference trade-off. Through soft-conditioning generative models, we discuss the link between incoherence and the effective horizon.

---

### Associative Memory Model with Neural Networks: Memorizing multiple images with one neuron

Authors: Hiroshi Inazawa
Published: 2025-10-08
Categories: cs.NE
arXiv: https://arxiv.org/abs/2510.06542v1

This paper presents a neural network model (associative memory model) for memory and recall of images. In this model, only a single neuron can memorize multi-images and when that neuron is activated, it is possible to recall all the memorized images at the same time. The system is composed of a single cluster of numerous neurons, referred to as the "Cue Ball," and multiple neural network layers, collectively called the "Recall Net." One of the features of this model is that several different images are stored simultaneously in one neuron, and by presenting one of the images stored in that neuron, all stored images are recalled. Furthermore, this model allows for complete recall of an image even when an incomplete image is presented

---

### Cluster Paths: Navigating Interpretability in Neural Networks

Authors: Nicholas M. Kroeger, Vincent Bindschaedler
Published: 2025-10-08
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.06541v1

While modern deep neural networks achieve impressive performance in vision tasks, they remain opaque in their decision processes, risking unwarranted trust, undetected biases and unexpected failures. We propose cluster paths, a post-hoc interpretability method that clusters activations at selected layers and represents each input as its sequence of cluster IDs. To assess these cluster paths, we introduce four metrics: path complexity (cognitive load), weighted-path purity (class alignment), decision-alignment faithfulness (predictive fidelity), and path agreement (stability under perturbations). In a spurious-cue CIFAR-10 experiment, cluster paths identify color-based shortcuts and collapse when the cue is removed. On a five-class CelebA hair-color task, they achieve 90% faithfulness and maintain 96% agreement under Gaussian noise without sacrificing accuracy. Scaling to a Vision Transformer pretrained on ImageNet, we extend cluster paths to concept paths derived from prompting a large language model on minimal path divergences. Finally, we show that cluster paths can serve as an effective out-of-distribution (OOD) detector, reliably flagging anomalous samples before the model generates over-confident predictions. Cluster paths uncover visual concepts, such as color palettes, textures, or object contexts, at multiple network depths, demonstrating that cluster paths scale to large vision models while generating concise and human-readable explanations.

---

### Scalable Policy-Based RL Algorithms for POMDPs

Authors: Ameya Anjarlekar, Rasoul Etesami, R Srikant
Published: 2025-10-08
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.06540v2

The continuous nature of belief states in POMDPs presents significant computational challenges in learning the optimal policy. In this paper, we consider an approach that solves a Partially Observable Reinforcement Learning (PORL) problem by approximating the corresponding POMDP model into a finite-state Markov Decision Process (MDP) (called Superstate MDP). We first derive theoretical guarantees that improve upon prior work that relate the optimal value function of the transformed Superstate MDP to the optimal value function of the original POMDP. Next, we propose a policy-based learning approach with linear function approximation to learn the optimal policy for the Superstate MDP. Consequently, our approach shows that a POMDP can be approximately solved using TD-learning followed by Policy Optimization by treating it as an MDP, where the MDP state corresponds to a finite history. We show that the approximation error decreases exponentially with the length of this history. To the best of our knowledge, our finite-time bounds are the first to explicitly quantify the error introduced when applying standard TD learning to a setting where the true dynamics are not Markovian.

---

### Auto-Prompt Ensemble for LLM Judge

Authors: Jiajie Li, Huayi Zhang, Peng Lin, Jinjun Xiong, Wei Xu
Published: 2025-10-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.06538v1

We present a novel framework that improves the reliability of LLM judges by selectively augmenting LLM with auxiliary evaluation dimensions. Existing LLM judges often miss crucial evaluation dimensions because they fail to recognize the implicit standards underlying human assessments. To address this challenge, we propose the Auto-Prompt Ensemble (APE), an adaptive framework that automatically learns evaluation dimensions from its failure cases. APE incorporates a confidence-based ensemble mechanism to decide when to adopt the judgments from additional evaluation dimensions through a novel confidence estimation approach called Collective Confidence. Extensive experiments demonstrate that APE improves the reliability of LLM Judge across diverse standard benchmarks. For instance, APE enhances GPT-4o agreement rate on Reward Bench from 87.2% to 90.5% in the zero-shot setting. Overall, APE provides a principled approach for LLM Judge to leverage test-time computation, and bridge the evaluation gap between human and LLM judges.

---

### Beneficial Reasoning Behaviors in Agentic Search and Effective Post-training to Obtain Them

Authors: Jiahe Jin, Abhijay Paladugu, Chenyan Xiong
Published: 2025-10-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.06534v3

Agentic search requires large language models (LLMs) to perform multi-step search to solve complex information-seeking tasks, imposing unique challenges on their reasoning capabilities. However, what constitutes effective reasoning for agentic search and how it can be learned remains unclear. In this work, we first investigate the reasoning behaviors that enable success in agentic search. By comparing successful and failed trajectories via an LLM-based analysis pipeline, we identify four beneficial behaviors: Information Verification, Authority Evaluation, Adaptive Search, and Error Recovery. Building on this, we propose Behavior Priming, a training approach that equips agentic search models with these reasoning behaviors before reinforcement learning (RL). Specifically, it first performs supervised fine-tuning (SFT) on collected trajectories exhibiting the identified behaviors to cultivate these behaviors, and then applies standard RL to further improve task performance. Experiments on Qwen3-1.7B and Llama3.2-3B-Instruct show that Behavior Priming yields relative improvements over direct RL by 37.2\% on three web benchmarks and 6.2\% on seven multi-hop QA benchmarks, and outperforms the SFT-then-RL baseline using outcome-correct trajectories for fine-tuning. Crucially, we show that these reasoning behaviors matter more than outcome correctness in the priming stage prior to RL. Further analysis reveals that Behavior Priming enhances exploration (pass@8) and test-time scaling (search step number), providing a robust foundation for RL. Our code are avalible at https://github.com/cxcscmu/Behavior-Priming-for-Agentic-Search.

---

### CLAQS: Compact Learnable All-Quantum Token Mixer with Shared-ansatz for Text Classification

Authors: Junhao Chen, Yifan Zhou, Hanqi Jiang, Yi Pan, Yiwei Li, Huaqin Zhao, Wei Zhang, Yingfeng Wang, Tianming Liu
Published: 2025-10-08
Categories: quant-ph, cs.AI
arXiv: https://arxiv.org/abs/2510.06532v1

Quantum compute is scaling fast, from cloud QPUs to high throughput GPU simulators, making it timely to prototype quantum NLP beyond toy tasks. However, devices remain qubit limited and depth limited, training can be unstable, and classical attention is compute and memory heavy. This motivates compact, phase aware quantum token mixers that stabilize amplitudes and scale to long sequences. We present CLAQS, a compact, fully quantum token mixer for text classification that jointly learns complex-valued mixing and nonlinear transformations within a unified quantum circuit. To enable stable end-to-end optimization, we apply l1 normalization to regulate amplitude scaling and introduce a two-stage parameterized quantum architecture that decouples shared token embeddings from a window-level quantum feed-forward module. Operating under a sliding-window regime with document-level aggregation, CLAQS requires only eight data qubits and shallow circuits, yet achieves 91.64% accuracy on SST-2 and 87.08% on IMDB, outperforming both classical Transformer baselines and strong hybrid quantum-classical counterparts.

---

### From Description to Detection: LLM based Extendable O-RAN Compliant Blind DoS Detection in 5G and Beyond

Authors: Thusitha Dayaratne, Ngoc Duy Pham, Viet Vo, Shangqi Lai, Sharif Abuadbba, Hajime Suzuki, Xingliang Yuan, Carsten Rudolph
Published: 2025-10-08
Categories: cs.CR, cs.ET, cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2510.06530v1

The quality and experience of mobile communication have significantly improved with the introduction of 5G, and these improvements are expected to continue beyond the 5G era. However, vulnerabilities in control-plane protocols, such as Radio Resource Control (RRC) and Non-Access Stratum (NAS), pose significant security threats, such as Blind Denial of Service (DoS) attacks. Despite the availability of existing anomaly detection methods that leverage rule-based systems or traditional machine learning methods, these methods have several limitations, including the need for extensive training data, predefined rules, and limited explainability. Addressing these challenges, we propose a novel anomaly detection framework that leverages the capabilities of Large Language Models (LLMs) in zero-shot mode with unordered data and short natural language attack descriptions within the Open Radio Access Network (O-RAN) architecture. We analyse robustness to prompt variation, demonstrate the practicality of automating the attack descriptions and show that detection quality relies on the semantic completeness of the description rather than its phrasing or length. We utilise an RRC/NAS dataset to evaluate the solution and provide an extensive comparison of open-source and proprietary LLM implementations to demonstrate superior performance in attack detection. We further validate the practicality of our framework within O-RAN's real-time constraints, illustrating its potential for detecting other Layer-3 attacks.

---

### VUGEN: Visual Understanding priors for GENeration

Authors: Xiangyi Chen, Théophane Vallaeys, Maha Elbayad, John Nguyen, Jakob Verbeek
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06529v1

Recent advances in Vision-Language Models (VLMs) have enabled unified understanding across text and images, yet equipping these models with robust image generation capabilities remains challenging. Existing approaches often rely on reconstruction-oriented autoencoders or complex bridging mechanisms, leading to misalignment between understanding and generation representations, or architectural complexity. In this work, we propose VUGEN, a novel framework that explicitly leverages VLM's pretrained visual understanding priors for efficient and high-quality image generation. Our approach first transforms the high-dimensional latent space of the VLM's native vision encoder into a lower-dimensional, tractable distribution that maximally preserves visual information. The VLM is then trained to sample within this reduced latent space, ensuring alignment with its visual understanding capabilities. Finally, a dedicated pixel decoder maps these generated latents back to the image space. We find that a VAE-free pixel diffusion decoder to be on par or better than commonly used complex latent diffusion decoders that internally rely on VAE latents. Extensive experiments demonstrate that VUGEN achieves superior image generation performance, improving DPG Bench from 71.17 to 74.32 and FID from 11.86 to 9.06 on COCO, while fully preserving the VLM's original understanding capabilities.

---

### BACHI: Boundary-Aware Symbolic Chord Recognition Through Masked Iterative Decoding on Pop and Classical Music

Authors: Mingyang Yao, Ke Chen, Shlomo Dubnov, Taylor Berg-Kirkpatrick
Published: 2025-10-08
Categories: cs.SD, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2510.06528v2

Automatic chord recognition (ACR) via deep learning models has gradually achieved promising recognition accuracy, yet two key challenges remain. First, prior work has primarily focused on audio-domain ACR, while symbolic music (e.g., score) ACR has received limited attention due to data scarcity. Second, existing methods still overlook strategies that are aligned with human music analytical practices. To address these challenges, we make two contributions: (1) we introduce POP909-CL, an enhanced version of POP909 dataset with tempo-aligned content and human-corrected labels of chords, beats, keys, and time signatures; and (2) We propose BACHI, a symbolic chord recognition model that decomposes the task into different decision steps, namely boundary detection and iterative ranking of chord root, quality, and bass (inversion). This mechanism mirrors the human ear-training practices. Experiments demonstrate that BACHI achieves state-of-the-art chord recognition performance on both classical and pop music benchmarks, with ablation studies validating the effectiveness of each module.

---

### Wide Neural Networks as a Baseline for the Computational No-Coincidence Conjecture

Authors: John Dunbar, Scott Aaronson
Published: 2025-10-08
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.06527v2

We establish that randomly initialized neural networks, with large width and a natural choice of hyperparameters, have nearly independent outputs exactly when their activation function is nonlinear with zero mean under the Gaussian measure: $\mathbb{E}_{z \sim \mathcal{N}(0,1)}(σ(z))=0$. For example, this includes ReLU and GeLU with an additive shift, as well as tanh, but not ReLU or GeLU by themselves. Because of their nearly independent outputs, we propose neural networks with zero-mean activation functions as a promising candidate for the Alignment Research Center's computational no-coincidence conjecture -- a conjecture that aims to measure the limits of AI interpretability.

---

### Domain-Grounded Evaluation of LLMs in International Student Knowledge

Authors: Claudinei Daitx, Haitham Amar
Published: 2025-10-07
Categories: cs.HC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.20653v1

Large language models (LLMs) are increasingly used to answer high-stakes study-abroad questions about admissions, visas, scholarships, and eligibility. Yet it remains unclear how reliably they advise students, and how often otherwise helpful answers drift into unsupported claims (``hallucinations''). This work provides a clear, domain-grounded overview of how current LLMs behave in this setting. Using realistic questions set drawn from ApplyBoard's advising workflows -- an EdTech platform that supports students from discovery to enrolment -- we evaluate two essentials side by side: accuracy (is the information correct and complete?) and hallucination (does the model add content not supported by the question or domain evidence). These questions are categorized by domain scope which can be a single-domain or multi-domain -- when it must integrate evidence across areas such as admissions, visas, and scholarships. To reflect real advising quality, we grade answers with a simple rubric which is correct, partial, or wrong. The rubric is domain-coverage-aware: an answer can be partial if it addresses only a subset of the required domains, and it can be over-scoped if it introduces extra, unnecessary domains; both patterns are captured in our scoring as under-coverage or reduced relevance/hallucination. We also report measures of faithfulness and answer relevance, alongside an aggregate hallucination score, to capture relevance and usefulness. All models are tested with the same questions for a fair, head-to-head comparison. Our goals are to: (1) give a clear picture of which models are most dependable for study-abroad advising, (2) surface common failure modes -- where answers are incomplete, off-topic, or unsupported, and (3) offer a practical, reusable protocol for auditing LLMs before deployment in education and advising contexts.

---

### When LLMs Can't Help: Real-World Evaluation of LLMs in Nutrition

Authors: Karen Jia-Hui Li, Simone Balloccu, Ondrej Dusek, Ehud Reiter
Published: 2025-10-07
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2511.20652v1

The increasing trust in large language models (LLMs), especially in the form of chatbots, is often undermined by the lack of their extrinsic evaluation. This holds particularly true in nutrition, where randomised controlled trials (RCTs) are the gold standard, and experts demand them for evidence-based deployment. LLMs have shown promising results in this field, but these are limited to intrinsic setups. We address this gap by running the first RCT involving LLMs for nutrition. We augment a rule-based chatbot with two LLM-based features: (1) message rephrasing for conversational variety and engagement, and (2) nutritional counselling through a fine-tuned model. In our seven-week RCT (n=81), we compare chatbot variants with and without LLM integration. We measure effects on dietary outcome, emotional well-being, and engagement. Despite our LLM-based features performing well in intrinsic evaluation, we find that they did not yield consistent benefits in real-world deployment. These results highlight critical gaps between intrinsic evaluations and real-world impact, emphasising the need for interdisciplinary, human-centred approaches.\footnote{We provide all of our code and results at: \\ \href{https://github.com/saeshyra/diet-chatbot-trial}{https://github.com/saeshyra/diet-chatbot-trial}}

---

### Embedding Generative AI into Systems Analysis and Design Curriculum: Framework, Case Study, and Cross-Campus Empirical Evidence

Authors: Mahmoud Elkhodr, Ergun Gide
Published: 2025-10-07
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.17515v1

Systems analysis students increasingly use Generative AI, yet current pedagogy lacks systematic approaches for teaching responsible AI orchestration that fosters critical thinking whilst meeting educational outcomes. Students risk accepting AI suggestions blindly or uncritically without assessing alignment with user needs or contextual appropriateness. SAGE (Structured AI-Guided Education) addresses this gap by embedding GenAI into curriculum design, training students when to accept, modify, or reject AI contributions. Implementation with 18 student groups across four Australian universities revealed how orchestration skills develop. Most groups (84\%) moved beyond passive acceptance, showing selective judgment, yet none proactively identified gaps overlooked by both human and AI analysis, indicating a competency ceiling. Students strong at explaining decisions also performed well at integrating sources, and those with deep domain understanding consistently considered accessibility considerations. Accessibility awareness proved fragile. When writing requirements, 85\% of groups explicitly considered elderly users and cultural needs. Notably, 55\% of groups struggled identifying when AI misclassified system boundaries (what belongs inside versus outside the system), 45\% missed data management errors (how information is stored and updated), and 55\% overlooked missing exception handling. Three implications emerge for educators: (i) require students to document why they accepted, modified, or rejected each AI suggestion, making reasoning explicit; (ii) embed accessibility prompts at each development stage because awareness collapses without continuous scaffolding; and (iii) have students create their own specifications before using AI, then compare versions, and anchor to research or standards to identify gaps.

---

### XAI-on-RAN: Explainable, AI-native, and GPU-Accelerated RAN Towards 6G

Authors: Osman Tugay Basaran, Falko Dressler
Published: 2025-10-07
Categories: cs.NI, cs.AI, cs.IT
arXiv: https://arxiv.org/abs/2511.17514v1

Artificial intelligence (AI)-native radio access networks (RANs) will serve vertical industries with stringent requirements: smart grids, autonomous vehicles, remote healthcare, industrial automation, etc. To achieve these requirements, modern 5G/6G design increasingly leverage AI for network optimization, but the opacity of AI decisions poses risks in mission-critical domains. These use cases are often delivered via non-public networks (NPNs) or dedicated network slices, where reliability and safety are vital. In this paper, we motivate the need for transparent and trustworthy AI in high-stakes communications (e.g., healthcare, industrial automation, and robotics) by drawing on 3rd generation partnership project (3GPP)'s vision for non-public networks. We design a mathematical framework to model the trade-offs between transparency (explanation fidelity and fairness), latency, and graphics processing unit (GPU) utilization in deploying explainable AI (XAI) models. Empirical evaluations demonstrate that our proposed hybrid XAI model xAI-Native, consistently surpasses conventional baseline models in performance.

---

### The Anatomy of a Triton Attention Kernel

Authors: Burkhard Ringlein, Jan van Lunteren, Radu Stoica, Thomas Parnell
Published: 2025-10-07
Categories: cs.LG, cs.AI, cs.CL, cs.DC, cs.PL
arXiv: https://arxiv.org/abs/2511.11581v1

A long-standing goal in both industry and academia is to develop an LLM inference platform that is portable across hardware architectures, eliminates the need for low-level hand-tuning, and still delivers best-in-class efficiency. In this work, we demonstrate that portable, efficient cross-platform LLM inference is indeed possible and share our experience. We develop a state-of-the-art paged attention kernel, the core performance-critical component of many LLM deployments, that builds exclusively on the domain-specific just-in-time compiled language Triton to achieve state-of-the-art performance on both NVIDIA and AMD GPUs. We describe our high-level approach, the key algorithmic and system-level improvements, the parameter auto-tuning required to unlock efficiency, and the integrations into a popular inference server that are necessary to bring the performance of a generic Triton attention kernel from 19.7% of the state-of-the-art to 105.9%. Our results highlight how open-source domain-specific languages can be leveraged to unlock model portability across different GPU vendors.

---

### Digital Transformation Chatbot (DTchatbot): Integrating Large Language Model-based Chatbot in Acquiring Digital Transformation Needs

Authors: Jiawei Zheng, Gokcen Yilmaz, Ji Han, Saeema Ahmed-Kristensen
Published: 2025-10-07
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.02842v1

Many organisations pursue digital transformation to enhance operational efficiency, reduce manual efforts, and optimise processes by automation and digital tools. To achieve this, a comprehensive understanding of their unique needs is required. However, traditional methods, such as expert interviews, while effective, face several challenges, including scheduling conflicts, resource constraints, inconsistency, etc. To tackle these issues, we investigate the use of a Large Language Model (LLM)-powered chatbot to acquire organisations' digital transformation needs. Specifically, the chatbot integrates workflow-based instruction with LLM's planning and reasoning capabilities, enabling it to function as a virtual expert and conduct interviews. We detail the chatbot's features and its implementation. Our preliminary evaluation indicates that the chatbot performs as designed, effectively following predefined workflows and supporting user interactions with areas for improvement. We conclude by discussing the implications of employing chatbots to elicit user information, emphasizing their potential and limitations.

---