# Research Papers — 2025-10 · bundle page 88 of 217

> Full-text markdown of papers #4351–4400 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/88
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/87.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/89.md)

### CLIP: Client-Side Invariant Pruning for Mitigating Stragglers in Secure Federated Learning

Authors: Anthony DiMaggio, Raghav Sharma, Gururaj Saileshwar
Published: 2025-10-19
Categories: cs.LG, cs.CR, cs.DC
arXiv: https://arxiv.org/abs/2510.16694v1

Secure federated learning (FL) preserves data privacy during distributed model training. However, deploying such frameworks across heterogeneous devices results in performance bottlenecks, due to straggler clients with limited computational or network capabilities, slowing training for all participating clients. This paper introduces the first straggler mitigation technique for secure aggregation with deep neural networks. We propose CLIP, a client-side invariant neuron pruning technique coupled with network-aware pruning, that addresses compute and network bottlenecks due to stragglers during training with minimal accuracy loss. Our technique accelerates secure FL training by 13% to 34% across multiple datasets (CIFAR10, Shakespeare, FEMNIST) with an accuracy impact of between 1.3% improvement to 2.6% reduction.

---

### Pursuing Minimal Sufficiency in Spatial Reasoning

Authors: Yejie Guo, Yunzhong Hou, Wufei Ma, Meng Tang, Ming-Hsuan Yang
Published: 2025-10-19
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.16688v2

Spatial reasoning, the ability to ground language in 3D understanding, remains a persistent challenge for Vision-Language Models (VLMs). We identify two fundamental bottlenecks: inadequate 3D understanding capabilities stemming from 2D-centric pre-training, and reasoning failures induced by redundant 3D information. To address these, we first construct a Minimal Sufficient Set (MSS) of information before answering a given question: a compact selection of 3D perception results from \textit{expert models}. We introduce MSSR (Minimal Sufficient Spatial Reasoner), a dual-agent framework that implements this principle. A Perception Agent programmatically queries 3D scenes using a versatile perception toolbox to extract sufficient information, including a novel SOG (Situated Orientation Grounding) module that robustly extracts language-grounded directions. A Reasoning Agent then iteratively refines this information to pursue minimality, pruning redundant details and requesting missing ones in a closed loop until the MSS is curated. Extensive experiments demonstrate that our method, by explicitly pursuing both sufficiency and minimality, significantly improves accuracy and achieves state-of-the-art performance across two challenging benchmarks. Furthermore, our framework produces interpretable reasoning paths, offering a promising source of high-quality training data for future models. Source code is available at https://github.com/gyj155/mssr.

---

### High-Dimensional Privacy-Utility Dynamics of Noisy Stochastic Gradient Descent on Least Squares

Authors: Shurong Lin, Eric D. Kolaczyk, Adam Smith, Elliot Paquette
Published: 2025-10-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.16687v1

The interplay between optimization and privacy has become a central theme in privacy-preserving machine learning. Noisy stochastic gradient descent (SGD) has emerged as a cornerstone algorithm, particularly in large-scale settings. These variants of gradient methods inject carefully calibrated noise into each update to achieve differential privacy, the gold standard notion of rigorous privacy guarantees. Prior work primarily provides various bounds on statistical risk and privacy loss for noisy SGD, yet the \textit{exact} behavior of the process remains unclear, particularly in high-dimensional settings. This work leverages a diffusion approach to analyze noisy SGD precisely, providing a continuous-time perspective that captures both statistical risk evolution and privacy loss dynamics in high dimensions. Moreover, we study a variant of noisy SGD that does not require explicit knowledge of gradient sensitivity, unlike existing work that assumes or enforces sensitivity through gradient clipping. Specifically, we focus on the least squares problem with $\ell_2$ regularization.

---

### Investigating the Impact of Rationales for LLMs on Natural Language Understanding

Authors: Wenhang Shi, Shuqing Bian, Yiren Chen, Xinyi Zhang, Zhe Zhao, Pengfei Hu, Wei Lu, Xiaoyong Du
Published: 2025-10-19
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.16686v1

Chain-of-thought (CoT) rationales, which provide step-by-step reasoning to derive final answers, benefit LLMs in both inference and training. Incorporating rationales, either by generating them before answering during inference, or by placing them before or after the original answers during training - significantly improves model performance on mathematical, symbolic and commonsense reasoning tasks. However, most work focuses on the role of rationales in these reasoning tasks, overlooking their potential impact on other important tasks like natural language understanding (NLU) tasks. In this work, we raise the question: Can rationales similarly benefit NLU tasks? To conduct a systematic exploration, we construct NLURC, a comprehensive and high-quality NLU dataset collection with rationales, and develop various rationale-augmented methods. Through exploring the applicability of these methods on NLU tasks using the dataset, we uncover several potentially surprising findings: (1) CoT inference shifts from hindering NLU performance to surpassing direct label prediction as model size grows, indicating a positive correlation. (2) Most rationale-augmented training methods perform worse than label-only training, with one specially designed method consistently achieving improvements. (3) LLMs trained with rationales achieve significant performance gains on unseen NLU tasks, rivaling models ten times their size, while delivering interpretability on par with commercial LLMs.

---

### Structured yet Bounded Temporal Understanding in Large Language Models

Authors: Damin Zhang, Julia Rayz
Published: 2025-10-19
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.16685v2

Large language models (LLMs) increasingly show strong performance on temporally grounded tasks, such as timeline construction, temporal question answering, and event ordering. However, it remains unclear how their behavior depends on the way time is anchored in language. In this work, we study LLMs' temporal understanding through temporal frames of reference (t-FoRs), contrasting deictic framing (past-present-future) and sequential framing (before-after). Using a large-scale dataset of real-world events from Wikidata and similarity judgement task, we examine how LLMs' outputs vary with temporal distance, interval relations, and event duration. Our results show that LLMs systematically adapt to both t-FoRs, but the resulting similarity patterns differ significantly. Under deictic t-FoR, the similarity judgement scores form graded and asymmetric structures centered on the present, with sharper decline for future events and higher variance in the past. Under sequential t-FoR, similarity becomes strongly negative once events are temporally separated. Temporal judgements are also shaped by interval algebra and duration, with instability concentrated in overlap- and containment-based relations, and duration influencing only past events under deictic t-FoR. Overall, these findings characterize how LLMs organize temporal representation under different reference structures and identify the factors that most strongly shape their temporal understanding.

---

### Filtering of Small Components for Isosurface Generation

Authors: Devin Zhao, Rephael Wenger
Published: 2025-10-19
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2510.16684v1

Let $f: \mathbb{R}^3 \rightarrow \mathbb{R}$ be a scalar field. An isosurface is a piecewise linear approximation of a level set $f^{-1}(σ)$ for some $σ\in \mathbb{R}$ built from some regular grid sampling of $f$. Isosurfaces constructed from scanned data such as CT scans or MRIs often contain extremely small components that distract from the visualization and do not form part of any geometric model produced from the data. Simple prefiltering of the data can remove such small components while having no effect on the large components that form the body of the visualization. We present experimental results on such filtering.

---

### Renaissance of RNNs in Streaming Clinical Time Series: Compact Recurrence Remains Competitive with Transformers

Authors: Ran Tong, Jiaqi Liu, Su Liu, Xin Hu, Lanruo Wang
Published: 2025-10-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16677v1

We present a compact, strictly causal benchmark for streaming clinical time series on the MIT--BIH Arrhythmia Database using per-second heart rate. Two tasks are studied under record-level, non-overlapping splits: near-term tachycardia risk (next ten seconds) and one-step heart rate forecasting. We compare a GRU-D (RNN) and a Transformer under matched training budgets against strong non-learned baselines. Evaluation is calibration-aware for classification and proper for forecasting, with temperature scaling and grouped bootstrap confidence intervals. On MIT-BIH, GRU-D slightly surpasses the Transformer for tachycardia risk, while the Transformer clearly lowers forecasting error relative to GRU-D and persistence. Our results show that, in longitudinal monitoring, model choice is task-dependent: compact RNNs remain competitive for short-horizon risk scoring, whereas compact Transformers deliver clearer gains for point forecasting.

---

### Active Target Discovery under Uninformative Prior: The Power of Permanent and Transient Memory

Authors: Anindya Sarkar, Binglin Ji, Yevgeniy Vorobeychik
Published: 2025-10-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.16676v1

In many scientific and engineering fields, where acquiring high-quality data is expensive--such as medical imaging, environmental monitoring, and remote sensing--strategic sampling of unobserved regions based on prior observations is crucial for maximizing discovery rates within a constrained budget. The rise of powerful generative models, such as diffusion models, has enabled active target discovery in partially observable environments by leveraging learned priors--probabilistic representations that capture underlying structure from data. With guidance from sequentially gathered task-specific observations, these models can progressively refine exploration and efficiently direct queries toward promising regions. However, in domains where learning a strong prior is infeasible due to extremely limited data or high sampling cost (such as rare species discovery, diagnostics for emerging diseases, etc.), these methods struggle to generalize. To overcome this limitation, we propose a novel approach that enables effective active target discovery even in settings with uninformative priors, ensuring robust exploration and adaptability in complex real-world scenarios. Our framework is theoretically principled and draws inspiration from neuroscience to guide its design. Unlike black-box policies, our approach is inherently interpretable, providing clear insights into decision-making. Furthermore, it guarantees a strong, monotonic improvement in prior estimates with each new observation, leading to increasingly accurate sampling and reinforcing both reliability and adaptability in dynamic settings. Through comprehensive experiments and ablation studies across various domains, including species distribution modeling and remote sensing, we demonstrate that our method substantially outperforms baseline approaches.

---

### Infinite Neural Operators: Gaussian processes on functions

Authors: Daniel Augusto de Souza, Yuchen Zhu, Harry Jake Cunningham, Yuri Saporito, Diego Mesquita, Marc Peter Deisenroth
Published: 2025-10-19
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.16675v1

A variety of infinitely wide neural architectures (e.g., dense NNs, CNNs, and transformers) induce Gaussian process (GP) priors over their outputs. These relationships provide both an accurate characterization of the prior predictive distribution and enable the use of GP machinery to improve the uncertainty quantification of deep neural networks. In this work, we extend this connection to neural operators (NOs), a class of models designed to learn mappings between function spaces. Specifically, we show conditions for when arbitrary-depth NOs with Gaussian-distributed convolution kernels converge to function-valued GPs. Based on this result, we show how to compute the covariance functions of these NO-GPs for two NO parametrizations, including the popular Fourier neural operator (FNO). With this, we compute the posteriors of these GPs in regression scenarios, including PDE solution operators. This work is an important step towards uncovering the inductive biases of current FNO architectures and opens a path to incorporate novel inductive biases for use in kernel-based operator learning methods.

---

### Evaluating protein binding interfaces with PUMBA

Authors: Azam Shirali, Giri Narasimhan
Published: 2025-10-19
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2510.16674v1

Protein-protein docking tools help in studying interactions between proteins, and are essential for drug, vaccine, and therapeutic development. However, the accuracy of a docking tool depends on a robust scoring function that can reliably differentiate between native and non-native complexes. PIsToN is a state-of-the-art deep learning-based scoring function that uses Vision Transformers in its architecture. Recently, the Mamba architecture has demonstrated exceptional performance in both natural language processing and computer vision, often outperforming Transformer-based models in their domains. In this study, we introduce PUMBA (Protein-protein interface evaluation with Vision Mamba), which improves PIsToN by replacing its Vision Transformer backbone with Vision Mamba. This change allows us to leverage Mamba's efficient long-range sequence modeling for sequences of image patches. As a result, the model's ability to capture both global and local patterns in protein-protein interface features is significantly improved. Evaluation on several widely-used, large-scale public datasets demonstrates that PUMBA consistently outperforms its original Transformer-based predecessor, PIsToN.

---

### All You Need is One: Capsule Prompt Tuning with a Single Vector

Authors: Yiyang Liu, James C. Liang, Heng Fan, Wenhao Yang, Yiming Cui, Xiaotian Han, Lifu Huang, Dongfang Liu, Qifan Wang, Cheng Han
Published: 2025-10-19
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.16670v1

Prompt-based learning has emerged as a parameter-efficient finetuning (PEFT) approach to facilitate Large Language Model (LLM) adaptation to downstream tasks by conditioning generation with task-aware guidance. Despite its successes, current prompt-based learning methods heavily rely on laborious grid searching for optimal prompt length and typically require considerable number of prompts, introducing additional computational burden. Worse yet, our pioneer findings indicate that the task-aware prompt design is inherently limited by its absence of instance-aware information, leading to a subtle attention interplay with the input sequence. In contrast, simply incorporating instance-aware information as a part of the guidance can enhance the prompt-tuned model performance without additional fine-tuning. Moreover, we find an interesting phenomenon, namely "attention anchor", that incorporating instance-aware tokens at the earliest position of the sequence can successfully preserve strong attention to critical structural information and exhibit more active attention interaction with all input tokens. In light of our observation, we introduce Capsule Prompt-Tuning (CaPT), an efficient and effective solution that leverages off-the-shelf, informative instance semantics into prompt-based learning. Our approach innovatively integrates both instance-aware and task-aware information in a nearly parameter-free manner (i.e., one single capsule prompt). Empirical results demonstrate that our method can exhibit superior performance across various language tasks (e.g., 84.03\% average accuracy on T5-Large), serving as an "attention anchor," while enjoying high parameter efficiency (e.g., 0.003\% of model parameters on Llama3.2-1B).

---

### TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation

Authors: Wenbiao Tao, Xinyuan Li, Yunshi Lan, Weining Qian
Published: 2025-10-18
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2601.05254v3

Retrieval-Augmented Generation enhances language models by retrieving external knowledge to support informed and grounded responses. However, traditional RAG methods rely on fragment-level retrieval, limiting their ability to address query-focused summarization queries. GraphRAG introduces a graph-based paradigm for global knowledge reasoning, yet suffers from inefficiencies in information extraction, costly resource consumption, and poor adaptability to incremental updates. To overcome these limitations, we propose TagRAG, a tag-guided hierarchical knowledge graph RAG framework designed for efficient global reasoning and scalable graph maintenance. TagRAG introduces two key components: (1) Tag Knowledge Graph Construction, which extracts object tags and their relationships from documents and organizes them into hierarchical domain tag chains for structured knowledge representation, and (2) Tag-Guided Retrieval-Augmented Generation, which retrieves domain-centric tag chains to localize and synthesize relevant knowledge during inference. This design significantly adapts to smaller language models, improves retrieval granularity, and supports efficient knowledge increment. Extensive experiments on UltraDomain datasets spanning Agriculture, Computer Science, Law, and cross-domain settings demonstrate that TagRAG achieves an average winning rate of 78.36% against baselines while maintaining about 14.6x construction and 1.9x retrieval efficiency compared with GraphRAG.

---

### Reinforcement Learning for Accelerator Beamline Control: a simulation-based approach

Authors: Anwar Ibrahim, Alexey Petrenko, Maxim Kaledin, Ehab Suleiman, Fedor Ratnikov, Denis Derkach
Published: 2025-10-18
Categories: physics.acc-ph, cs.AI
arXiv: https://arxiv.org/abs/2510.26805v1

Particle accelerators play a pivotal role in advancing scientific research, yet optimizing beamline configurations to maximize particle transmission remains a labor-intensive task requiring expert intervention. In this work, we introduce RLABC (Reinforcement Learning for Accelerator Beamline Control), a Python-based library that reframes beamline optimization as a reinforcement learning (RL) problem. Leveraging the Elegant simulation framework, RLABC automates the creation of an RL environment from standard lattice and element input files, enabling sequential tuning of magnets to minimize particle losses. We define a comprehensive state representation capturing beam statistics, actions for adjusting magnet parameters, and a reward function focused on transmission efficiency. Employing the Deep Deterministic Policy Gradient (DDPG) algorithm, we demonstrate RLABC's efficacy on two beamlines, achieving transmission rates of 94% and 91%, comparable to expert manual optimizations. This approach bridges accelerator physics and machine learning, offering a versatile tool for physicists and RL researchers alike to streamline beamline tuning.

---

### Certainty in Uncertainty: Reasoning over Uncertain Knowledge Graphs with Statistical Guarantees

Authors: Yuqicheng Zhu, Jingcheng Wu, Yizhen Wang, Hongkuan Zhou, Jiaoyan Chen, Evgeny Kharlamov, Steffen Staab
Published: 2025-10-18
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.24754v1

Uncertain knowledge graph embedding (UnKGE) methods learn vector representations that capture both structural and uncertainty information to predict scores of unseen triples. However, existing methods produce only point estimates, without quantifying predictive uncertainty-limiting their reliability in high-stakes applications where understanding confidence in predictions is crucial. To address this limitation, we propose \textsc{UnKGCP}, a framework that generates prediction intervals guaranteed to contain the true score with a user-specified level of confidence. The length of the intervals reflects the model's predictive uncertainty. \textsc{UnKGCP} builds on the conformal prediction framework but introduces a novel nonconformity measure tailored to UnKGE methods and an efficient procedure for interval construction. We provide theoretical guarantees for the intervals and empirically verify these guarantees. Extensive experiments on standard benchmarks across diverse UnKGE methods further demonstrate that the intervals are sharp and effectively capture predictive uncertainty.

---

### Multi-Agent Pose Uncertainty: A Differentiable Rendering Cramér-Rao Bound

Authors: Arun Muthukkumar
Published: 2025-10-18
Categories: cs.CV, cs.GR, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2510.21785v1

Pose estimation is essential for many applications within computer vision and robotics. Despite its uses, few works provide rigorous uncertainty quantification for poses under dense or learned models. We derive a closed-form lower bound on the covariance of camera pose estimates by treating a differentiable renderer as a measurement function. Linearizing image formation with respect to a small pose perturbation on the manifold yields a render-aware Cramér-Rao bound. Our approach reduces to classical bundle-adjustment uncertainty, ensuring continuity with vision theory. It also naturally extends to multi-agent settings by fusing Fisher information across cameras. Our statistical formulation has downstream applications for tasks such as cooperative perception and novel view synthesis without requiring explicit keypoint correspondences.

---

### Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models

Authors: Guo Li, Weihong Chen, Yongfu Fan
Published: 2025-10-18
Categories: cs.CV, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.21783v2

Diffusion models have demonstrated powerful performance in generating high-quality images. A typical example is text-to-image generator like Stable Diffusion. However, their widespread use also poses potential privacy risks. A key concern is membership inference attacks, which attempt to determine whether a particular data sample was used in the model training process. Existing membership inference attacks against diffusion models either directly exploit sample loss differences or rely on image-level reconstruction differences. Both approaches commonly ignore the consistency characteristics of noise prediction during the diffusion process, resulting in either low inference accuracy or high computational costs. To address these shortcomings, we propose a membership inference method based on noise aggregation analysis, and introduce a single-step, low-intensity noise injection diffusion strategy to amplify differences between member and non-member samples. Our proposed approach substantially reduces model query requirements while delivering more efficient and accurate membership inference.

---

### Promptable Fire Segmentation: Unleashing SAM2's Potential for Real-Time Mobile Deployment with Strategic Bounding Box Guidance

Authors: Emmanuel U. Ugwu, Zhang Xinming
Published: 2025-10-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21782v1

Fire segmentation remains a critical challenge in computer vision due to flames' irregular boundaries, translucent edges, and highly variable intensities. While the Segment Anything Models (SAM and SAM2) have demonstrated impressive cross-domain generalization capabilities, their effectiveness in fire segmentation -- particularly under mobile deployment constraints -- remains largely unexplored. This paper presents the first comprehensive evaluation of SAM2 variants for fire segmentation, focusing on bounding box prompting strategies to enhance deployment feasibility. We systematically evaluate four SAM2.1 variants (tiny, small, base_plus, large) alongside mobile-oriented variants (TinySAM, MobileSAM) across three fire datasets using multiple prompting strategies: automatic, single positive point (SP), single positive point + single negative point (SP+SN), multiple positive points (MP), bounding box (Box), and hybrid variants (Box+SP and Box+MP). Our experimental results demonstrate that bounding box prompts consistently outperform automatic and single point-based approaches, with Box+MP achieving the highest mean IoU (0.64) and Dice coefficient (0.75) on the Khan dataset. Lightweight variants such as TinySAM and MobileSAM further reduce memory and computational costs, making them more suitable for latency-tolerant edge scenarios. Overall, this work provides critical insights for deploying promptable segmentation models in fire monitoring systems and establishes benchmarks for future research in domain-specific SAM applications. Code is available at: https://github.com/UEmmanuel5/ProFSAM

---

### EdgeSync: Accelerating Edge-Model Updates for Data Drift through Adaptive Continuous Learning

Authors: Runchu Donga, Peng Zhao, Guiqin Wang, Nan Qi, Jie Lin
Published: 2025-10-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.21781v1

Real-time video analytics systems typically deploy lightweight models on edge devices to reduce latency. However, the distribution of data features may change over time due to various factors such as changing lighting and weather conditions, leading to decreased model accuracy. Recent frameworks try to address this issue by leveraging remote servers to continuously train and adapt lightweight edge models using more complex models in the cloud. Despite these advancements, existing methods face two key challenges: first, the retraining process is compute-intensive, causing significant delays in model updates; second, the new model may not align well with the evolving data distribution of the current video stream. To address these challenges, we introduce EdgeSync, an efficient edge-model updating approach that enhances sample filtering by incorporating timeliness and inference results, thus ensuring training samples are more relevant to the current video content while reducing update delays. Additionally, EdgeSync features a dynamic training management module that optimizes the timing and sequencing of model updates to improve their timeliness. Evaluations on diverse and complex real-world datasets demonstrate that EdgeSync improves accuracy by approximately 3.4% compared to existing methods and by about 10% compared to traditional approaches.

---

### Bridging Accuracy and Interpretability: Deep Learning with XAI for Breast Cancer Detection

Authors: Bishal Chhetri, B. V. Rathish Kumar
Published: 2025-10-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.21780v1

In this study, we present an interpretable deep learning framework for the early detection of breast cancer using quantitative features extracted from digitized fine needle aspirate (FNA) images of breast masses. Our deep neural network, using ReLU activations, the Adam optimizer, and a binary cross-entropy loss, delivers state-of-the-art classification performance, achieving an accuracy of 0.992, precision of 1.000, recall of 0.977, and an F1 score of 0.988. These results substantially exceed the benchmarks reported in the literature. We evaluated the model under identical protocols against a suite of well-established algorithms (logistic regression, decision trees, random forests, stochastic gradient descent, K-nearest neighbors, and XGBoost) and found the deep model consistently superior on the same metrics. Recognizing that high predictive accuracy alone is insufficient for clinical adoption due to the black-box nature of deep learning models, we incorporated model-agnostic Explainable AI techniques such as SHAP and LIME to produce feature-level attributions and human-readable visualizations. These explanations quantify the contribution of each feature to individual predictions, support error analysis, and increase clinician trust, thus bridging the gap between performance and interpretability for real-world clinical use. The concave points feature of the cell nuclei is found to be the most influential feature positively impacting the classification task. This insight can be very helpful in improving the diagnosis and treatment of breast cancer by highlighting the key characteristics of breast tumor.

---

### What Causes Postoperative Aspiration?

Authors: Supriya Nagesh, Karina Covarrubias, Robert El-Kareh, Shiva Prasad Kasiviswanathan, Nina Mishra
Published: 2025-10-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.21779v2

Background: Aspiration, the inhalation of foreign material into the lungs, significantly impacts surgical patient morbidity and mortality. This study develops a machine learning (ML) model to predict postoperative aspiration, enabling timely preventative interventions. Methods: From the MIMIC-IV database of over 400,000 hospital admissions, we identified 826 surgical patients (mean age: 62, 55.7\% male) who experienced aspiration within seven days post-surgery, along with a matched non-aspiration cohort. Three ML models: XGBoost, Multilayer Perceptron, and Random Forest were trained using pre-surgical hospitalization data to predict postoperative aspiration. To investigate causation, we estimated Average Treatment Effects (ATE) using Augmented Inverse Probability Weighting. Results: Our ML model achieved an AUROC of 0.86 and 77.3\% sensitivity on a held-out test set. Maximum daily opioid dose, length of stay, and patient age emerged as the most important predictors. ATE analysis identified significant causative factors: opioids (0.25 +/- 0.06) and operative site (neck: 0.20 +/- 0.13, head: 0.19 +/- 0.13). Despite equal surgery rates across genders, men were 1.5 times more likely to aspirate and received 27\% higher maximum daily opioid dosages compared to women. Conclusion: ML models can effectively predict postoperative aspiration risk, enabling targeted preventative measures. Maximum daily opioid dosage and operative site significantly influence aspiration risk. The gender disparity in both opioid administration and aspiration rates warrants further investigation. These findings have important implications for improving postoperative care protocols and aspiration prevention strategies.

---

### Fourier-Based GAN Fingerprint Detection using ResNet50

Authors: Sai Teja Erukude, Viswa Chaitanya Marella, Suhasnadh Reddy Veluru
Published: 2025-10-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.19840v1

The rapid rise of photorealistic images produced from Generative Adversarial Networks (GANs) poses a serious challenge for image forensics and industrial systems requiring reliable content authenticity. This paper uses frequency-domain analysis combined with deep learning to solve the problem of distinguishing StyleGAN-generated images from real ones. Specifically, a two-dimensional Discrete Fourier Transform (2D DFT) was applied to transform images into the Fourier domain, where subtle periodic artifacts become detectable. A ResNet50 neural network is trained on these transformed images to differentiate between real and synthetic ones. The experiments demonstrate that the frequency-domain model achieves a 92.8 percent and an AUC of 0.95, significantly outperforming the equivalent model trained on raw spatial-domain images. These results indicate that the GAN-generated images have unique frequency-domain signatures or "fingerprints". The method proposed highlights the industrial potential of combining signal processing techniques and deep learning to enhance digital forensics and strengthen the trustworthiness of industrial AI systems.

---

### Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory

Authors: Shiqi He, Yue Cui, Xinyu Ma, Yaliang Li, Bolin Ding, Mosharaf Chowdhury
Published: 2025-10-18
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.19838v2

Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions. These agents mark a key step toward practical embodied reasoning in open web environments. However, existing approaches remain limited in reasoning depth and efficiency: vanilla linear methods fail at multi-step reasoning and lack effective backtracking, while other search strategies are coarse-grained and computationally costly. We introduce Branch-and-Browse, a fine-grained web agent framework that unifies structured reasoning-acting, contextual memory, and efficient execution. It (i) employs explicit subtask management with tree-structured exploration for controllable multi-branch reasoning, (ii) bootstraps exploration through efficient web state replay with background reasoning, and (iii) leverages a page action memory to share explored actions within and across sessions. On the WebArena benchmark, Branch-and-Browse achieves a task success rate of 35.8\% and reduces execution time by up to 40.4\% relative to state-of-the-art methods. These results demonstrate that Branch-and-Browse is a reliable and efficient framework for LLM-based web agents.

---

### CodeCRDT: Observation-Driven Coordination for Multi-Agent LLM Code Generation

Authors: Sergey Pugachev
Published: 2025-10-18
Categories: cs.DC, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2510.18893v1

Multi-agent LLM systems fail to realize parallel speedups due to costly coordination. We present CodeCRDT, an observation-driven coordination pattern where agents coordinate by monitoring a shared state with observable updates and deterministic convergence, rather than explicit message passing. Using Conflict-Free Replicated Data Types (CRDTs), CodeCRDT enables lock-free, conflict-free concurrent code generation with strong eventual consistency. Evaluation across 600 trials (6 tasks, 50 runs per mode) shows both benefits and trade-offs: up to 21.1% speedup on some tasks, up to 39.4% slowdown on others, and 100% convergence with zero merge failures. The study formalizes observation-driven coordination for stochastic LLM agents, revealing semantic conflict rates (5-10%) and quality-performance tradeoffs, and provides empirical characterization of when parallel coordination succeeds versus fails based on task structure.

---

### When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs

Authors: Richard J. Young, Brandon Gillins, Alice M. Matthews
Published: 2025-10-18
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.18892v1

Despite widespread deployment of Large Language Models, systematic evaluation of instruction-following capabilities remains challenging. While comprehensive benchmarks exist, focused assessments that quickly diagnose specific instruction adherence patterns are valuable. As newer models may be trained on existing benchmarks, novel evaluation approaches are needed to assess genuine capabilities rather than memorized performance. This paper presents a streamlined evaluation framework using twenty carefully designed prompts to assess LLM instruction-following across diverse task categories. We demonstrate this framework through a large-scale empirical study conducted on October 14, 2025, testing 256 verified working models from 331 available via OpenRouter. To ensure methodological rigor and prevent selection bias, we first verified each model's basic functionality before inclusion. Unlike large-scale benchmarks requiring extensive computational resources, our approach offers a practical diagnostic tool researchers and practitioners can readily apply. Our methodology builds upon verifiable instructions while introducing a compact test suite balancing comprehensiveness with efficiency. Each prompt targets distinct aspects of instruction following, including format compliance, content constraints, logical sequencing, and multi-step task execution. We evaluate models from major providers (OpenAI, Anthropic, Google, Meta, Mistral) and emerging implementations (Qwen, DeepSeek, community models), providing comparative performance analysis. Our findings reveal consistent failure modes and identify specific instruction types posing particular challenges. This work contributes both a practical evaluation tool and one of the most comprehensive empirical analyses of instruction-following capabilities across the contemporary LLM landscape.

---

### Small Language Models Offer Significant Potential for Science Community

Authors: Jian Zhang
Published: 2025-10-18
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.18890v1

Recent advancements in natural language processing, particularly with large language models (LLMs), are transforming how scientists engage with the literature. While the adoption of LLMs is increasing, concerns remain regarding potential information biases and computational costs. Rather than LLMs, I developed a framework to evaluate the feasibility of precise, rapid, and cost-effective information retrieval from extensive geoscience literature using freely available small language models (MiniLMs). A curated corpus of approximately 77 million high-quality sentences, extracted from 95 leading peer-reviewed geoscience journals such as Geophysical Research Letters and Earth and Planetary Science Letters published during years 2000 to 2024, was constructed. MiniLMs enable a computationally efficient approach for extracting relevant domain-specific information from these corpora through semantic search techniques and sentence-level indexing. This approach, unlike LLMs such as ChatGPT-4 that often produces generalized responses, excels at identifying substantial amounts of expert-verified information with established, multi-disciplinary sources, especially for information with quantitative findings. Furthermore, by analyzing emotional tone via sentiment analysis and topical clusters through unsupervised clustering within sentences, MiniLM provides a powerful tool for tracking the evolution of conclusions, research priorities, advancements, and emerging questions within geoscience communities. Overall, MiniLM holds significant potential within the geoscience community for applications such as fact and image retrievals, trend analyses, contradiction analyses, and educational purposes.

---

### Advances in Pre-trained Language Models for Domain-Specific Text Classification: A Systematic Review

Authors: Zhyar Rzgar K. Rostam, Gábor Kertész
Published: 2025-10-18
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17892v1

The exponential increase in scientific literature and online information necessitates efficient methods for extracting knowledge from textual data. Natural language processing (NLP) plays a crucial role in addressing this challenge, particularly in text classification tasks. While large language models (LLMs) have achieved remarkable success in NLP, their accuracy can suffer in domain-specific contexts due to specialized vocabulary, unique grammatical structures, and imbalanced data distributions. In this systematic literature review (SLR), we investigate the utilization of pre-trained language models (PLMs) for domain-specific text classification. We systematically review 41 articles published between 2018 and January 2024, adhering to the PRISMA statement (preferred reporting items for systematic reviews and meta-analyses). This review methodology involved rigorous inclusion criteria and a multi-step selection process employing AI-powered tools. We delve into the evolution of text classification techniques and differentiate between traditional and modern approaches. We emphasize transformer-based models and explore the challenges and considerations associated with using LLMs for domain-specific text classification. Furthermore, we categorize existing research based on various PLMs and propose a taxonomy of techniques used in the field. To validate our findings, we conducted a comparative experiment involving BERT, SciBERT, and BioBERT in biomedical sentence classification. Finally, we present a comparative study on the performance of LLMs in text classification tasks across different domains. In addition, we examine recent advancements in PLMs for domain-specific text classification and offer insights into future directions and limitations in this rapidly evolving domain.

---

### TritonRL: Training LLMs to Think and Code Triton Without Cheating

Authors: Jiin Woo, Shaowei Zhu, Allen Nie, Zhen Jia, Yida Wang, Youngsuk Park
Published: 2025-10-18
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2510.17891v2

The rapid evolution of Large Language Models (LLMs) has driven a growing demand for automated, high-performance system kernels to accelerate machine learning workloads. We introduce TritonRL, a domain-specialized 8B-scale LLM for Triton programming, trained via a novel reinforcement learning (RL) framework. While Triton synthesis faces unique challenges, including data scarcity and a high susceptibility to reward hacking, our approach enables robust kernel generation through two primary innovations. First, we implement a multi-layered verification system that provides high-fidelity reward signals, ensuring that generated kernels are both syntactically and functionally valid. Second, we propose Hierarchical Reward Decomposition (HRD), which decouples reinforcement for high-level reasoning and low-level implementation to resolve the credit assignment problem in long-sequence generation. Comprehensive evaluations on KernelBench demonstrate that TritonRL achieves state-of-the-art correctness and runtime speedup, outperforming concurrent Triton-specific models and matching the performance of frontier models with over 100B parameters. Our results highlight the effectiveness of hardware-aware RL paradigms in specialized domain adaptation.

---

### MIN-Merging: Merge the Important Neurons for Model Merging

Authors: Yunfei Liang
Published: 2025-10-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.17890v2

Recent advances in deep learning have led to a surge of open-source models across diverse domains. While model merging offers a promising way to combine their strengths, existing approaches often suffer from parameter conflicts that degrade performance on domain-specific tasks. We propose MIN-Merging, a router-based framework that selectively merges the most important neurons to reduce such conflicts. Extensive experiments on Computer Vision(CV) and Natural Language Processing(NLP) benchmarks show that MIN-Merging achieves consistent gains on in-domain tasks while retaining the generalization ability of pretrained models on out-of-domain tasks. These results highlight its effectiveness as a practical solution to the parameter conflict problem in model merging.

---

### Hey Pentti, We Did It!: A Fully Vector-Symbolic Lisp

Authors: Eilene Tomkins-Flanagan, Mary A. Kelly
Published: 2025-10-18
Categories: cs.PL, cs.AI
arXiv: https://arxiv.org/abs/2510.17889v1

Kanerva (2014) suggested that it would be possible to construct a complete Lisp out of a vector-symbolic architecture. We present the general form of a vector-symbolic representation of the five Lisp elementary functions, lambda expressions, and other auxiliary functions, found in the Lisp 1.5 specification McCarthy (1960), which is near minimal and sufficient for Turing-completeness. Our specific implementation uses holographic reduced representations Plate (1995), with a lookup table cleanup memory. Lisp, as all Turing-complete languages, is a Cartesian closed category, unusual in its proximity to the mathematical abstraction. We discuss the mathematics, the purpose, and the significance of demonstrating vector-symbolic architectures' Cartesian-closure, as well as the importance of explicitly including cleanup memories in the specification of the architecture.

---

### Shock-Aware Physics-Guided Fusion-DeepONet Operator for Rarefied Micro-Nozzle Flows

Authors: Ehsan Roohi, Amirmehran Mahdavi
Published: 2025-10-18
Categories: cs.LG, physics.flu-dyn
arXiv: https://arxiv.org/abs/2510.17887v1

We present a comprehensive, physics aware deep learning framework for constructing fast and accurate surrogate models of rarefied, shock containing micro nozzle flows. The framework integrates three key components, a Fusion DeepONet operator learning architecture for capturing parameter dependencies, a physics-guided feature space that embeds a shock-aligned coordinate system, and a two-phase curriculum strategy emphasizing high-gradient regions. To demonstrate the generality and inductive bias of the proposed framework, we first validate it on the canonical viscous Burgers equation, which exhibits advective steepening and shock like gradients.

---

### Graphical model for factorization and completion of relatively high rank tensors by sparse sampling

Authors: Angelo Giorgio Cavaliere, Riki Nagasawa, Shuta Yokoi, Tomoyuki Obuchi, Hajime Yoshino
Published: 2025-10-18
Categories: stat.ML, cond-mat.dis-nn, cond-mat.stat-mech, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2510.17886v3

We consider tensor factorizations based on sparse measurements of the components of relatively high rank tensors. The measurements are designed in a way that the underlying graph of interactions is a random graph. The setup will be useful in cases where a substantial amount of data is missing, as in completion of relatively high rank matrices for recommendation systems heavily used in social network services. In order to obtain theoretical insights on the setup, we consider statistical inference of the tensor factorization in a high dimensional limit, which we call as dense limit, where the graphs are large and dense but not fully connected. We build message-passing algorithms and test them in a Bayes optimal teacher-student setting in some specific cases. We also develop a replica theory to examine the performance of statistical inference in the dense limit based on a cumulant expansion. The latter approach allows one to avoid blind usage of Gaussian ansatz which fails in some fully connected systems.

---

### Metrics and evaluations for computational and sustainable AI efficiency

Authors: Hongyuan Liu, Xinyang Liu, Guosheng Hu
Published: 2025-10-18
Categories: cs.PF, cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.17885v1

The rapid advancement of Artificial Intelligence (AI) has created unprecedented demands for computational power, yet methods for evaluating the performance, efficiency, and environmental impact of deployed models remain fragmented. Current approaches often fail to provide a holistic view, making it difficult to compare and optimise systems across heterogeneous hardware, software stacks, and numeric precisions. To address this gap, we propose a unified and reproducible methodology for AI model inference that integrates computational and environmental metrics under realistic serving conditions. Our framework provides a pragmatic, carbon-aware evaluation by systematically measuring latency and throughput distributions, energy consumption, and location-adjusted carbon emissions, all while maintaining matched accuracy constraints for valid comparisons. We apply this methodology to multi-precision models across diverse hardware platforms, from data-centre accelerators like the GH200 to consumer-level GPUs such as the RTX 4090, running on mainstream software stacks including PyTorch, TensorRT, and ONNX Runtime. By systematically categorising these factors, our work establishes a rigorous benchmarking framework that produces decision-ready Pareto frontiers, clarifying the trade-offs between accuracy, latency, energy, and carbon. The accompanying open-source code enables independent verification and facilitates adoption, empowering researchers and practitioners to make evidence-based decisions for sustainable AI deployment.

---

### When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password Cracking

Authors: Mohammad Abdul Rehman, Syed Imad Ali Shah, Abbas Anwar, Noor Islam, Hamid Khan
Published: 2025-10-18
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.17884v3

The remarkable capabilities of Large Language Models (LLMs) in natural language understanding and generation have sparked interest in their potential for cybersecurity applications, including password guessing. In this study, we conduct an empirical investigation into the efficacy of pre-trained LLMs for password cracking using synthetic user profiles. Specifically, we evaluate the performance of state-of-the-art open-source LLMs such as TinyLLaMA, Falcon-RW-1B, and Flan-T5 by prompting them to generate plausible passwords based on structured user attributes (e.g., name, birthdate, hobbies). Our results, measured using Hit@1, Hit@5, and Hit@10 metrics under both plaintext and SHA-256 hash comparisons, reveal consistently poor performance, with all models achieving less than 1.5% accuracy at Hit@10. In contrast, traditional rule-based and combinator-based cracking methods demonstrate significantly higher success rates. Through detailed analysis and visualization, we identify key limitations in the generative reasoning of LLMs when applied to the domain-specific task of password guessing. Our findings suggest that, despite their linguistic prowess, current LLMs lack the domain adaptation and memorization capabilities required for effective password inference, especially in the absence of supervised fine-tuning on leaked password datasets. This study provides critical insights into the limitations of LLMs in adversarial contexts and lays the groundwork for future efforts in secure, privacy-preserving, and robust password modeling.

---

### From Flows to Words: Can Zero-/Few-Shot LLMs Detect Network Intrusions? A Grammar-Constrained, Calibrated Evaluation on UNSW-NB15

Authors: Mohammad Abdul Rehman, Syed Imad Ali Shah, Abbas Anwar, Noor Islam
Published: 2025-10-18
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.17883v2

Large Language Models (LLMs) can reason over natural-language inputs, but their role in intrusion detection without fine-tuning remains uncertain. This study evaluates a prompt-only approach on UNSW-NB15 by converting each network flow to a compact textual record and augmenting it with lightweight, domain-inspired boolean flags (asymmetry, burst rate, TTL irregularities, timer anomalies, rare service/state, short bursts). To reduce output drift and support measurement, the model is constrained to produce structured, grammar-valid responses, and a single decision threshold is calibrated on a small development split. We compare zero-shot, instruction-guided, and few-shot prompting to strong tabular and neural baselines under identical splits, reporting accuracy, precision, recall, F1, and macro scores. Empirically, unguided prompting is unreliable, while instructions plus flags substantially improve detection quality; adding calibrated scoring further stabilizes results. On a balanced subset of two hundred flows, a 7B instruction-tuned model with flags reaches macro-F1 near 0.78; a lighter 3B model with few-shot cues and calibration attains F1 near 0.68 on one thousand examples. As the evaluation set grows to two thousand flows, decision quality decreases, revealing sensitivity to coverage and prompting. Tabular baselines remain more stable and faster, yet the prompt-only pipeline requires no gradient training, produces readable artifacts, and adapts easily through instructions and flags. Contributions include a flow-to-text protocol with interpretable cues, a calibration method for thresholding, a systematic baseline comparison, and a reproducibility bundle with prompts, grammar, metrics, and figures.

---

### Does GenAI Rewrite How We Write? An Empirical Study on Two-Million Preprints

Authors: Minfeng Qi, Zhongmin Cao, Qin Wang, Ningran Li, Tianqing Zhu
Published: 2025-10-18
Categories: cs.CY, cs.AI, cs.CL, cs.DL
arXiv: https://arxiv.org/abs/2510.17882v1

Preprint repositories become central infrastructures for scholarly communication. Their expansion transforms how research is circulated and evaluated before journal publication. Generative large language models (LLMs) introduce a further potential disruption by altering how manuscripts are written. While speculation abounds, systematic evidence of whether and how LLMs reshape scientific publishing remains limited. This paper addresses the gap through a large-scale analysis of more than 2.1 million preprints spanning 2016--2025 (115 months) across four major repositories (i.e., arXiv, bioRxiv, medRxiv, SocArXiv). We introduce a multi-level analytical framework that integrates interrupted time-series models, collaboration and productivity metrics, linguistic profiling, and topic modeling to assess changes in volume, authorship, style, and disciplinary orientation. Our findings reveal that LLMs have accelerated submission and revision cycles, modestly increased linguistic complexity, and disproportionately expanded AI-related topics, while computationally intensive fields benefit more than others. These results show that LLMs act less as universal disruptors than as selective catalysts, amplifying existing strengths and widening disciplinary divides. By documenting these dynamics, the paper provides the first empirical foundation for evaluating the influence of generative AI on academic publishing and highlights the need for governance frameworks that preserve trust, fairness, and accountability in an AI-enabled research ecosystem.

---

### HYDRA: HYbrid knowledge Distillation and spectral Reconstruction Algorithm for high channel hyperspectral camera applications

Authors: Christopher Thirgood, Oscar Mendez, Erin Ling, Jon Storey, Simon Hadfield
Published: 2025-10-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.16664v1

Hyperspectral images (HSI) promise to support a range of new applications in computer vision. Recent research has explored the feasibility of generalizable Spectral Reconstruction (SR), the problem of recovering a HSI from a natural three-channel color image in unseen scenarios. However, previous Multi-Scale Attention (MSA) works have only demonstrated sufficient generalizable results for very sparse spectra, while modern HSI sensors contain hundreds of channels. This paper introduces a novel approach to spectral reconstruction via our HYbrid knowledge Distillation and spectral Reconstruction Architecture (HYDRA). Using a Teacher model that encapsulates latent hyperspectral image data and a Student model that learns mappings from natural images to the Teacher's encoded domain, alongside a novel training method, we achieve high-quality spectral reconstruction. This addresses key limitations of prior SR models, providing SOTA performance across all metrics, including an 18\% boost in accuracy, and faster inference times than current SOTA models at various channel depths.

---

### Robust Dynamic Staffing with Predictions

Authors: Yiding Feng, Vahideh Manshadi, Rad Niazadeh, Saba Neyshabouri
Published: 2025-10-18
Categories: cs.DS, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.16663v1

We consider a natural dynamic staffing problem in which a decision-maker sequentially hires workers over a finite horizon to meet an unknown demand revealed at the end. Predictions about demand arrive over time and become increasingly accurate, while worker availability decreases. This creates a fundamental trade-off between hiring early to avoid understaffing (when workers are more available but forecasts are less reliable) and hiring late to avoid overstaffing (when forecasts are more accurate but availability is lower). This problem is motivated by last-mile delivery operations, where companies such as Amazon rely on gig-economy workers whose availability declines closer to the operating day. To address practical limitations of Bayesian models (in particular, to remain agnostic to the underlying forecasting method), we study this problem under adversarial predictions. In this model, sequential predictions are adversarially chosen uncertainty intervals that (approximately) contain the true demand. The objective is to minimize worst-case staffing imbalance cost. Our main result is a simple and computationally efficient online algorithm that is minimax optimal. We first characterize the minimax cost against a restricted adversary via a polynomial-size linear program, then show how to emulate this solution in the general case. While our base model focuses on a single demand, we extend the framework to multiple demands (with egalitarian/utilitarian objectives), to settings with costly reversals of hiring decisions, and to inconsistent prediction intervals. We also introduce a practical "re-solving" variant of our algorithm, which we prove is also minimax optimal. Finally we conduct numerical experiments showing that our algorithms outperform Bayesian heuristics in both cost and speed, and are competitive with (approximate or exact) Bayesian-optimal policies when those can be computed.

---

### Safire: Similarity Framework for Visualization Retrieval

Authors: Huyen N. Nguyen, Nils Gehlenborg
Published: 2025-10-18
Categories: cs.HC, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2510.16662v1

Effective visualization retrieval necessitates a clear definition of similarity. Despite the growing body of work in specialized visualization retrieval systems, a systematic approach to understanding visualization similarity remains absent. We introduce the Similarity Framework for Visualization Retrieval (Safire), a conceptual model that frames visualization similarity along two dimensions: comparison criteria and representation modalities. Comparison criteria identify the aspects that make visualizations similar, which we divide into primary facets (data, visual encoding, interaction, style, metadata) and derived properties (data-centric and human-centric measures). Safire connects what to compare with how comparisons are executed through representation modalities. We categorize existing representation approaches into four groups based on their levels of information content and visualization determinism: raster image, vector image, specification, and natural language description, together guiding what is computable and comparable. We analyze several visualization retrieval systems using Safire to demonstrate its practical value in clarifying similarity considerations. Our findings reveal how particular criteria and modalities align across different use cases. Notably, the choice of representation modality is not only an implementation detail but also an important decision that shapes retrieval capabilities and limitations. Based on our analysis, we provide recommendations and discuss broader implications for multimodal learning, AI applications, and visualization reproducibility.

---

### Universal and Transferable Attacks on Pathology Foundation Models

Authors: Yuntian Wang, Xilin Yang, Che-Yung Shen, Nir Pillar, Aydogan Ozcan
Published: 2025-10-18
Categories: cs.CV, cs.LG, physics.med-ph
arXiv: https://arxiv.org/abs/2510.16660v1

We introduce Universal and Transferable Adversarial Perturbations (UTAP) for pathology foundation models that reveal critical vulnerabilities in their capabilities. Optimized using deep learning, UTAP comprises a fixed and weak noise pattern that, when added to a pathology image, systematically disrupts the feature representation capabilities of multiple pathology foundation models. Therefore, UTAP induces performance drops in downstream tasks that utilize foundation models, including misclassification across a wide range of unseen data distributions. In addition to compromising the model performance, we demonstrate two key features of UTAP: (1) universality: its perturbation can be applied across diverse field-of-views independent of the dataset that UTAP was developed on, and (2) transferability: its perturbation can successfully degrade the performance of various external, black-box pathology foundation models - never seen before. These two features indicate that UTAP is not a dedicated attack associated with a specific foundation model or image dataset, but rather constitutes a broad threat to various emerging pathology foundation models and their applications. We systematically evaluated UTAP across various state-of-the-art pathology foundation models on multiple datasets, causing a significant drop in their performance with visually imperceptible modifications to the input images using a fixed noise pattern. The development of these potent attacks establishes a critical, high-standard benchmark for model robustness evaluation, highlighting a need for advancing defense mechanisms and potentially providing the necessary assets for adversarial training to ensure the safe and reliable deployment of AI in pathology.

---

### Large-Scale AI and Foundation Models for Neuroscience: A Comprehensive Review

Authors: Shihao Yang, Xiying Huang, Danilo Bernardo, Jun-En Ding, Andrew Michael, Guoan Wang, Jingmei Yang, Alison Anderson, Dinesh Giritharan, Patrick Kwan, Ashish Raj, Yu Zhang et al.
Published: 2025-10-18
Categories: cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2510.16658v3

The development of large-scale artificial intelligence (AI) models is influencing neuroscience research by enabling end-to-end learning from raw brain signals and neural data. In this paper, we review applications of large-scale AI models across four major neuroscience domains: neuroimaging and data processing, brain-computer interfaces and neural decoding, clinical decision support and translational frameworks, and disease-specific applications across neurological and psychiatric disorders. These models show potential to address major computational neuroscience challenges, including multimodal neural data integration, spatiotemporal pattern interpretation, and the development of translational frameworks for clinical research. Moreover, the interaction between neuroscience and AI has become increasingly reciprocal, as biologically informed architectural constraints are now incorporated to develop more interpretable and computationally efficient models. This review highlights both the promise of such technologies and critical implementation considerations, with particular emphasis on rigorous evaluation frameworks, effective integration of domain knowledge, prospective clinical validation, and comprehensive ethical guidelines. Finally, a systematic listing of critical neuroscience datasets used to develop and evaluate large-scale AI models across diverse research applications is provided.

---

### Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence

Authors: Bingji Yi, Qiyuan Liu, Yuwei Cheng, Haifeng Xu
Published: 2025-10-18
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.16657v3

Synthetic data has been increasingly used to train frontier generative models. However, recent studies raise key concerns that iteratively retraining a generative model on its self-generated synthetic data may keep deteriorating model performance, a phenomenon often coined model collapse. In this paper, we investigate ways to modify the synthetic retraining process to avoid model collapse, and even possibly help reverse the trend from collapse to improvement. Our key finding is that by injecting information through an external synthetic data verifier, whether a human or a better model, synthetic retraining will not cause model collapse. Specifically, we situate our theoretical analysis in the fundamental linear regression setting, showing that verifier-guided retraining can yield near-term improvements, but ultimately drives the parameter estimate to the verifier's "knowledge center" in the long run. Our theory further predicts that, unless the verifier is perfectly reliable, these early gains will plateau and may even reverse. Indeed, our experiments across linear regression, Variational Autoencoders (VAEs) trained on MNIST, and fining-tuning SmolLM2-135M on the XSUM task confirm these theoretical insights.

---

### Simulation-free Structure Learning for Stochastic Population Dynamics

Authors: Noah El Rimawi-Fine, Adam Stecklov, Lucas Nelson, Mathieu Blanchette, Alexander Tong, Stephen Y. Zhang, Lazar Atanackovic
Published: 2025-10-18
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2510.16656v2

Modeling dynamical systems and unraveling their underlying structural dependencies is central to many domains in the natural sciences. Various physical systems, such as those arising in cell biology, are inherently high-dimensional and stochastic in nature, and admit only partial, noisy state measurements. Our primary motivating setting is single-cell biology, where destructive measurements yield unpaired population snapshots rather than longitudinal trajectories of the same cells. This poses a significant challenge for addressing the problems of modeling the underlying dynamics and inferring the network structure of these systems. Existing methods are typically tailored either for structure learning or modeling dynamics at the population level, but are limited in their ability to address both problems together. In this work, we address both problems simultaneously: we present StructureFlow, a novel and principled simulation-free training approach for jointly learning the structure and stochastic population dynamics of physical systems. We showcase the utility of StructureFlow for the tasks of structure learning from interventions and dynamical (trajectory) inference of conditional population dynamics. We empirically evaluate our approach on high-dimensional synthetic systems, a set of biologically plausible simulated systems, and an experimental single-cell dataset. We show that StructureFlow can learn the structure of underlying systems while simultaneously modeling their conditional population dynamics --- a key step toward model-based mechanistic understanding of systems behavior.

---

### ARCO-BO: Adaptive Resource-aware COllaborative Bayesian Optimization for Heterogeneous Multi-Agent Design

Authors: Zihan Wang, Yi-Ping Chen, Tuba Dolar, Wei Chen
Published: 2025-10-18
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.16652v1

Modern scientific and engineering design increasingly involves distributed optimization, where agents such as laboratories, simulations, or industrial partners pursue related goals under differing conditions. These agents often face heterogeneities in objectives, evaluation budgets, and accessible design variables, which complicates coordination and can lead to redundancy, poor resource use, and ineffective information sharing. Bayesian Optimization (BO) is a widely used decision-making framework for expensive black box functions, but its single-agent formulation assumes centralized control and full data sharing. Recent collaborative BO methods relax these assumptions, yet they often require uniform resources, fully shared input spaces, and fixed task alignment, conditions rarely satisfied in practice. To address these challenges, we introduce Adaptive Resource Aware Collaborative Bayesian Optimization (ARCO-BO), a framework that explicitly accounts for heterogeneity in multi-agent optimization. ARCO-BO combines three components: a similarity and optima-aware consensus mechanism for adaptive information sharing, a budget-aware asynchronous sampling strategy for resource coordination, and a partial input space sharing for heterogeneous design spaces. Experiments on synthetic and high-dimensional engineering problems show that ARCO-BO consistently outperforms independent BO and existing collaborative BO via consensus approach, achieving robust and efficient performance in complex multi-agent settings.

---

### Unleashing Diverse Thinking Modes in LLMs through Multi-Agent Collaboration

Authors: Zhixuan He, Yue Feng
Published: 2025-10-18
Categories: cs.CL, cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2510.16645v1

Large Language Models (LLMs) demonstrate strong performance but often lack interpretable reasoning. This paper introduces the Multi-Agent Collaboration Framework for Diverse Thinking Modes (DiMo), which enhances both performance and interpretability by simulating a structured debate among four specialized LLM agents. Each agent embodies a distinct reasoning paradigm, allowing the framework to collaboratively explore diverse cognitive approaches. Through iterative debate, agents challenge and refine initial responses, yielding more robust conclusions and an explicit, auditable reasoning chain. Across six benchmarks and under a unified open-source setup, DiMo improves accuracy over widely used single-model and debate baselines, with the largest gains on math. We position DiMo as a semantics-aware, Web-native multi-agent framework: it models human-machine intelligence with LLM agents that produce semantically typed, URL-annotated evidence chains for explanations and user-friendly interactions. Although our experiments use standard reasoning benchmarks, the framework is designed to be instantiated over Web corpora and knowledge graphs, combining retrieval-augmented reasoning with structured justifications that downstream systems can inspect and reuse.

---

### Structured Interfaces for Automated Reasoning with 3D Scene Graphs

Authors: Aaron Ray, Jacob Arkin, Harel Biggie, Chuchu Fan, Luca Carlone, Nicholas Roy
Published: 2025-10-18
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.16643v1

In order to provide a robot with the ability to understand and react to a user's natural language inputs, the natural language must be connected to the robot's underlying representations of the world. Recently, large language models (LLMs) and 3D scene graphs (3DSGs) have become a popular choice for grounding natural language and representing the world. In this work, we address the challenge of using LLMs with 3DSGs to ground natural language. Existing methods encode the scene graph as serialized text within the LLM's context window, but this encoding does not scale to large or rich 3DSGs. Instead, we propose to use a form of Retrieval Augmented Generation to select a subset of the 3DSG relevant to the task. We encode a 3DSG in a graph database and provide a query language interface (Cypher) as a tool to the LLM with which it can retrieve relevant data for language grounding. We evaluate our approach on instruction following and scene question-answering tasks and compare against baseline context window and code generation methods. Our results show that using Cypher as an interface to 3D scene graphs scales significantly better to large, rich graphs on both local and cloud-based models. This leads to large performance improvements in grounded language tasks while also substantially reducing the token count of the scene graph content. A video supplement is available at https://www.youtube.com/watch?v=zY_YI9giZSA.

---

### MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models

Authors: Young-Jun Lee, Byung-Kwan Lee, Jianshu Zhang, Yechan Hwang, Byungsoo Ko, Han-Gyu Kim, Dongyu Yao, Xuankun Rong, Eojin Joo, Seung-Ho Han, Bowon Ko, Ho-Jin Choi
Published: 2025-10-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.16641v1

Vision-and-Language Models (VLMs) have shown impressive capabilities on single-turn benchmarks, yet real-world applications often demand more intricate multi-turn dialogues. Existing multi-turn datasets (e.g, MMDU, ConvBench) only partially capture the breadth and depth of conversational scenarios encountered by users. In this work, we introduce MultiVerse, a novel multi-turn conversation benchmark featuring 647 dialogues - each averaging four turns - derived from a diverse set of 12 popular VLM evaluation benchmarks. With 484 tasks and 484 interaction goals, MultiVerse covers a wide range of topics, from factual knowledge and perception to advanced reasoning tasks such as mathematics and coding. To facilitate robust assessment, we propose a checklist-based evaluation method that leverages GPT-4o as the automated evaluator, measuring performance across 37 key aspects, including perceptual accuracy, linguistic clarity, and factual correctness. We evaluate 18 VLMs on MultiVerse, revealing that even the strongest models (e.g., GPT-4o) achieve only a 50% success rate in complex multi-turn conversations, highlighting the dataset's challenging nature. Notably, we find that providing full dialogue context significantly enhances performance for smaller or weaker models, emphasizing the importance of in-context learning. We believe MultiVerse is a landscape of evaluating multi-turn interaction abilities for VLMs.

---

### A Versatile Framework for Designing Group-Sparse Adversarial Attacks

Authors: Alireza Heshmati, Saman Soleimani Roudi, Sajjad Amini, Shahrokh Ghaemmaghami, Farokh Marvasti
Published: 2025-10-18
Categories: cs.CR, cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2510.16637v1

Existing adversarial attacks often neglect perturbation sparsity, limiting their ability to model structural changes and to explain how deep neural networks (DNNs) process meaningful input patterns. We propose ATOS (Attack Through Overlapping Sparsity), a differentiable optimization framework that generates structured, sparse adversarial perturbations in element-wise, pixel-wise, and group-wise forms. For white-box attacks on image classifiers, we introduce the Overlapping Smoothed L0 (OSL0) function, which promotes convergence to a stationary point while encouraging sparse, structured perturbations. By grouping channels and adjacent pixels, ATOS improves interpretability and helps identify robust versus non-robust features. We approximate the L-infinity gradient using the logarithm of the sum of exponential absolute values to tightly control perturbation magnitude. On CIFAR-10 and ImageNet, ATOS achieves a 100% attack success rate while producing significantly sparser and more structurally coherent perturbations than prior methods. The structured group-wise attack highlights critical regions from the network's perspective, providing counterfactual explanations by replacing class-defining regions with robust features from the target class.

---

### A three-step machine learning approach to predict market bubbles with financial news

Authors: Abraham Atsiwo
Published: 2025-10-18
Categories: q-fin.ST, cs.LG, q-fin.CP
arXiv: https://arxiv.org/abs/2510.16636v1

This study presents a three-step machine learning framework to predict bubbles in the S&P 500 stock market by combining financial news sentiment with macroeconomic indicators. Building on traditional econometric approaches, the proposed approach predicts bubble formation by integrating textual and quantitative data sources. In the first step, bubble periods in the S&P 500 index are identified using a right-tailed unit root test, a widely recognized real-time bubble detection method. The second step extracts sentiment features from large-scale financial news articles using natural language processing (NLP) techniques, which capture investors' expectations and behavioral patterns. In the final step, ensemble learning methods are applied to predict bubble occurrences based on high sentiment-based and macroeconomic predictors. Model performance is evaluated through k-fold cross-validation and compared against benchmark machine learning algorithms. Empirical results indicate that the proposed three-step ensemble approach significantly improves predictive accuracy and robustness, providing valuable early warning insights for investors, regulators, and policymakers in mitigating systemic financial risks.

---

### MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization

Authors: Juhyeon Lee, Wonduk Seo, Junseo Koh, Wonseok Choi, Hyunjin An, Jian Park, Seunghyun lee, Haihua Chen, Yi Bu
Published: 2025-10-18
Categories: cs.MA, cs.AI, cs.CL, cs.HC, cs.IR
arXiv: https://arxiv.org/abs/2510.16635v3

Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without explaining why prompts succeed or fail. Moreover, they involve repetitive trial-and-error refinements that remain implicit, offering limited interpretability or actionable guidance for systematic improvement. In this paper, we propose MA-SAPO: a new Multi-Agent Reasoning for Score Aware Prompt Optimization framework that links evaluation outcomes directly to targeted refinements. Specifically, in the Training Phase, multiple agents interpret evaluation scores, diagnose weaknesses, and generate concrete revision directives, which are stored as reusable reasoning assets. In the Test Phase, an analyzer agent retrieves relevant exemplars and assets for a new prompt, and a refiner agent applies evidence-based edits to improve the prompt and its response. By grounding optimization in structured reasoning, MA-SAPO ensures edits are interpretable, auditable, and controllable. Experiments on the HelpSteer1/2 benchmarks show that our framework consistently outperforms single-pass prompting, retrieval-augmented generation, and prior multi-agent methods across multiple evaluation metrics.

---

### On the Impossibility of Retrain Equivalence in Machine Unlearning

Authors: Jiatong Yu, Yinghui He, Anirudh Goyal, Sanjeev Arora
Published: 2025-10-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.16629v2

Machine unlearning seeks to selectively remove the "influence" of specific training data on a model's outputs. The ideal goal is Retrain Equivalence--behavior identical to a model trained from scratch on only the retained data. This goal was formulated for models trained on i.i.d. data batches, but modern pipelines often involve multi-stage training, with each stage having a distinct data distribution and objective. Examples include LLM fine-tuning for alignment, reasoning ability, etc. Our study shows via theory and experiments that this shift to multi-stage training introduces a fundamental barrier for machine unlearning. The theory indicates that the outcome of local unlearning--methods that only use gradients computed on the forget set--is path-dependent. That is, a model's behavior during unlearning is influenced by the order of its training stages during learning, making it impossible for path-oblivious algorithms to universally achieve Retrain Equivalence. We empirically demonstrate the same phenomenon in LLM post-training across Llama and Qwen models (1B to 14B) with gradient ascent, NPO, and SimNPO local unlearning algorithms. Models fine-tuned via different orderings of identical training stages diverge in behavior during unlearning, with the degradation in GSM8K accuracy after unlearning varying by over 20% across paths. We also observe that some learning paths consistently produce models that unlearn slowly. During unlearning, whether the probability mass gets squeezed into paraphrasing or alternative concepts is also path-dependent. These results consistently show that Retrain Equivalence is an ill-posed target for local unlearning algorithms, so long as the target models are trained in stages. In situations where access to models' training histories is hard, the current work calls for rethinking the definition and desiderata of machine unlearning.

---