# Research Papers — 2025-10 · bundle page 62 of 217

> Full-text markdown of papers #3051–3100 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/62
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/61.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/63.md)

### SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization

Authors: Kaiyi Xu, Junchao Gong, Wenlong Zhang, Ben Fei, Lei Bai, Wanli Ouyang
Published: 2025-10-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21847v1

Precipitation nowcasting based on radar echoes plays a crucial role in monitoring extreme weather and supporting disaster prevention. Although deep learning approaches have achieved significant progress, they still face notable limitations. For example, deterministic models tend to produce over-smoothed predictions, which struggle to capture extreme events and fine-scale precipitation patterns. Probabilistic generative models, due to their inherent randomness, often show fluctuating performance across different metrics and rarely achieve consistently optimal results. Furthermore, precipitation nowcasting is typically evaluated using multiple metrics, some of which are inherently conflicting. For instance, there is often a trade-off between the Critical Success Index (CSI) and the False Alarm Ratio (FAR), making it challenging for existing models to deliver forecasts that perform well on both metrics simultaneously. To address these challenges, we introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models. Specifically, we propose SynCast, a method that employs the two-stage post-training framework of Diffusion Sequential Preference Optimization (Diffusion-SPO), to progressively align conflicting metrics and consistently achieve superior performance. In the first stage, the framework focuses on reducing FAR, training the model to effectively suppress false alarms. Building on this foundation, the second stage further optimizes CSI with constraints that preserve FAR alignment, thereby achieving synergistic improvements across these conflicting metrics.

---

### Training data membership inference via Gaussian process meta-modeling: a post-hoc analysis approach

Authors: Yongchao Huang, Pengfei Zhang, Shahzad Mumtaz
Published: 2025-10-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.21846v1

Membership inference attacks (MIAs) test whether a data point was part of a model's training set, posing serious privacy risks. Existing methods often depend on shadow models or heavy query access, which limits their practicality. We propose GP-MIA, an efficient and interpretable approach based on Gaussian process (GP) meta-modeling. Using post-hoc metrics such as accuracy, entropy, dataset statistics, and optional sensitivity features (e.g. gradients, NTK measures) from a single trained model, GP-MIA trains a GP classifier to distinguish members from non-members while providing calibrated uncertainty estimates. Experiments on synthetic data, real-world fraud detection data, CIFAR-10, and WikiText-2 show that GP-MIA achieves high accuracy and generalizability, offering a practical alternative to existing MIAs.

---

### KARIPAP: Quantum-Inspired Tensor Network Compression of Large Language Models Using Infinite Projected Entangled Pair States and Tensor Renormalization Group

Authors: Azree Nazri
Published: 2025-10-22
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2510.21844v1

Large Language Models (LLMs) like ChatGPT and LLaMA drive rapid progress in generative AI, yet their huge parameter scales create severe computational and environmental burdens. High training costs, energy use, and limited device deployment hinder accessibility. Existing compression - pruning, distillation, low-rank, and quantization - reduces size but ignores complex inter-layer correlations. We propose KARIPAP, a quantum-inspired tensor network compression using Infinite Projected Entangled Pair States (iPEPS) and Tensor Renormalization Group (TRG) contraction. Unlike 1D Matrix Product States, iPEPS captures multi-directional entanglement in attention and deep transformer layers. TRG ensures polynomial-time contraction, making tensorization feasible while preserving key correlation geometry. Experiments on LLaMA-2 7B show up to 93% memory and 70% parameter reduction, with 50% faster training, 25% faster inference, and only 2-3% accuracy loss. Layer-wise entanglement profiling reveals redundancy in deeper layers, confirming their suitability for tensor factorization. KARIPAP demonstrates that modern LLMs occupy low-dimensional entanglement manifolds, enabling scalable, energy-efficient, and quantum-aware AI architectures.

---

### Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?

Authors: Michael Aerni, Joshua Swanson, Kristina Nikolić, Florian Tramèr
Published: 2025-10-22
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2510.21842v2

We present modal aphasia, a systematic dissociation in which current unified multimodal models accurately memorize concepts visually but fail to articulate them in writing, despite being trained on images and text simultaneously. For one, we show that leading frontier models can generate near-perfect reproductions of iconic movie artwork, but confuse crucial details when asked for textual descriptions. We corroborate those findings through controlled experiments on synthetic datasets in multiple architectures. Our experiments confirm that modal aphasia reliably emerges as a fundamental property of current unified multimodal models, not just as a training artifact. In practice, modal aphasia can introduce vulnerabilities in AI safety frameworks, as safeguards applied to one modality may leave harmful concepts accessible in other modalities. We demonstrate this risk by showing how a model aligned solely on text remains capable of generating unsafe images.

---

### RatioWaveNet: A Learnable RDWT Front-End for Robust and Interpretable EEG Motor-Imagery Classification

Authors: Marco Siino, Giuseppe Bonomo, Rosario Sorbello, Ilenia Tinnirello
Published: 2025-10-22
Categories: cs.CV, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2510.21841v1

Brain-computer interfaces (BCIs) based on motor imagery (MI) translate covert movement intentions into actionable commands, yet reliable decoding from non-invasive EEG remains challenging due to nonstationarity, low SNR, and subject variability. We present RatioWaveNet, which augments a strong temporal CNN-Transformer backbone (TCFormer) with a trainable, Rationally-Dilated Wavelet Transform (RDWT) front end. The RDWT performs an undecimated, multi-resolution subband decomposition that preserves temporal length and shift-invariance, enhancing sensorimotor rhythms while mitigating jitter and mild artifacts; subbands are fused via lightweight grouped 1-D convolutions and passed to a multi-kernel CNN for local temporal-spatial feature extraction, a grouped-query attention encoder for long-range context, and a compact TCN head for causal temporal integration. Our goal is to test whether this principled wavelet front end improves robustness precisely where BCIs typically fail - on the hardest subjects - and whether such gains persist on average across seeds under both intra- and inter-subject protocols. On BCI-IV-2a and BCI-IV-2b, across five seeds, RatioWaveNet improves worst-subject accuracy over the Transformer backbone by +0.17 / +0.42 percentage points (Sub-Dependent / LOSO) on 2a and by +1.07 / +2.54 percentage points on 2b, with consistent average-case gains and modest computational overhead. These results indicate that a simple, trainable wavelet front end is an effective plug-in to strengthen Transformer-based BCIs, improving worst-case reliability without sacrificing efficiency.

---

### Improving the Physics of Video Generation with VJEPA-2 Reward Signal

Authors: Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich, Nicolas Beltran-Velez, Melissa Hall, Reyhane Askari-Hemmat, Xiaochuang Han, Nicolas Ballas, Michal Drozdzal, Adriana Romero-Soriano
Published: 2025-10-22
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2510.21840v1

This is a short technical report describing the winning entry of the PhysicsIQ Challenge, presented at the Perception Test Workshop at ICCV 2025. State-of-the-art video generative models exhibit severely limited physical understanding, and often produce implausible videos. The Physics IQ benchmark has shown that visual realism does not imply physics understanding. Yet, intuitive physics understanding has shown to emerge from SSL pretraining on natural videos. In this report, we investigate whether we can leverage SSL-based video world models to improve the physics plausibility of video generative models. In particular, we build ontop of the state-of-the-art video generative model MAGI-1 and couple it with the recently introduced Video Joint Embedding Predictive Architecture 2 (VJEPA-2) to guide the generation process. We show that by leveraging VJEPA-2 as reward signal, we can improve the physics plausibility of state-of-the-art video generative models by ~6%.

---

### Evaluating ChatGPT's Performance in Classifying Pneumonia from Chest X-Ray Images

Authors: Pragna Prahallad, Pranathi Prahallad
Published: 2025-10-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.21839v1

In this study, we evaluate the ability of OpenAI's gpt-4o model to classify chest X-ray images as either NORMAL or PNEUMONIA in a zero-shot setting, without any prior fine-tuning. A balanced test set of 400 images (200 from each class) was used to assess performance across four distinct prompt designs, ranging from minimal instructions to detailed, reasoning-based prompts. The results indicate that concise, feature-focused prompts achieved the highest classification accuracy of 74\%, whereas reasoning-oriented prompts resulted in lower performance. These findings highlight that while ChatGPT exhibits emerging potential for medical image interpretation, its diagnostic reliability remains limited. Continued advances in visual reasoning and domain-specific adaptation are required before such models can be safely applied in clinical practice.

---

### Quantum Autoencoders for Anomaly Detection in Cybersecurity

Authors: Rohan Senthil, Swee Liang Wong
Published: 2025-10-22
Categories: cs.ET, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.21837v1

Anomaly detection in cybersecurity is a challenging task, where normal events far outnumber anomalous ones with new anomalies occurring frequently. Classical autoencoders have been used for anomaly detection, but struggles in data-limited settings which quantum counterparts can potentially overcome. In this work, we apply Quantum Autoencoders (QAEs) for anomaly detection in cybersecurity, specifically on the BPF-extended tracking honeypot (BETH) dataset. QAEs are evaluated across multiple encoding techniques, ansatz types, repetitions, and feature selection strategies. Our results demonstrate that an 8-feature QAE using Dense-Angle encoding with a RealAmplitude ansatz can outperform Classical Autoencoders (CAEs), even when trained on substantially fewer samples. The effects of quantum encoding and feature selection for developing quantum models are demonstrated and discussed. In a data-limited setting, the best performing QAE model has a F1 score of 0.87, better than that of CAE (0.77). These findings suggest that QAEs may offer practical advantages for anomaly detection in data-limited scenarios.

---

### COLA: Continual Learning via Autoencoder Retrieval of Adapters

Authors: Jaya Krishna Mandivarapu
Published: 2025-10-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21836v1

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence due to catastrophic forgetting. Large language models (LLMs) are often impractical to frequent re-training and continual learning , due to high cost of computational resources for training. Moreover, LLM are not suitable for continual learning as updating these models over time for acquiring new knowledge leads to overwrites existing knowledge leading to common phenomenon know as \textit{catastrophic forgetting}. In this paper, we aim to address these concerns using a novel framework , COLA that employs an autoencoder to learn capture low-dimensional embeddings of the weights associated with various tasks. Our approach facilitates the transfer of knowledge to new tasks while preventing catastrophic forgetting, all without using data replay or a substantial set of task-specific parameters. Our approach, COLA, makes the LLM efficiently learn new tasks with minimal training, insignificant performance degradation on previous tasks, and eliminates the need for retaining earlier training data. Empirical evaluation on different datasets ranging from task oriented dialouge system to intent classsfication datasets showcases that our method not only overcomes catastrophic forgetting but also achieves significant reduction in parameter usage and memory size, across multiple tasks and outperforming the existing state of the art methods across multiple datasets.

---

### A Multimodal, Multitask System for Generating E Commerce Text Listings from Images

Authors: Nayan Kumar Singh
Published: 2025-10-22
Categories: cs.LG, cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.21835v1

Manually generating catchy descriptions and names is labor intensive and a slow process for retailers. Although generative AI provides an automation solution in form of Vision to Language Models (VLM), the current VLMs are prone to factual "hallucinations". Siloed, single task models are not only inefficient but also fail to capture interdependent relationships between features. To address these challenges, we propose an end to end, multi task system that generates factually grounded textual listings from a single image. The contributions of this study are two proposals for the model architecture. First, application of multi task learning approach for fine tuning a vision encoder where a single vision backbone is jointly trained on attribute prediction such as color, hemline and neck style and price regression. Second, introduction of a hierarchical generation process where the model's own predicted attributes are embedded in a prompt and fed to the text decoder to improve factual consistency. The experiments demonstrate the superiority of this architecture. The multi tasking approach outperforms both the independent price regression, with a 3.6% better R2 Value and attribute classification, with a 6.6% improvement F1 score. Critically, the hierarchical generation process proves highly effective, slashing the factual hallucination rate from 12.7% to 7.1%, a 44.5% relative reduction, compared to a non hierarchical ablation. The hierarchical approach also reduces the latency of the autoregressive text generation process by a factor of 3.5 when compared to direct vision to language model of similar size. One minor caveat is that the model does perform 3.5% worse than direct vision-to-language model on ROUGE-L score.

---

### Restoring Pruned Large Language Models via Lost Component Compensation

Authors: Zijian Feng, Hanzhang Zhou, Zixiao Zhu, Tianjiao Li, Jia Jim Deryl Chua, Lee Onn Mak, Gee Wah Ng, Kezhi Mao
Published: 2025-10-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21834v1

Pruning is a widely used technique to reduce the size and inference cost of large language models (LLMs), but it often causes performance degradation. To mitigate this, existing restoration methods typically employ parameter-efficient fine-tuning (PEFT), such as LoRA, to recover the pruned model's performance. However, most PEFT methods are designed for dense models and overlook the distinct properties of pruned models, often resulting in suboptimal recovery. In this work, we propose a targeted restoration strategy for pruned models that restores performance while preserving their low cost and high efficiency. We observe that pruning-induced information loss is reflected in attention activations, and selectively reintroducing components of this information can significantly recover model performance. Based on this insight, we introduce RestoreLCC (Restoring Pruned LLMs via Lost Component Compensation), a plug-and-play method that contrastively probes critical attention heads via activation editing, extracts lost components from activation differences, and finally injects them back into the corresponding pruned heads for compensation and recovery. RestoreLCC is compatible with structured, semi-structured, and unstructured pruning schemes. Extensive experiments demonstrate that RestoreLCC consistently outperforms state-of-the-art baselines in both general and task-specific performance recovery, without compromising the sparsity or inference efficiency of pruned models.

---

### Towards Accurate and Efficient Waste Image Classification: A Hybrid Deep Learning and Machine Learning Approach

Authors: Ngoc-Bao-Quang Nguyen, Tuan-Minh Do, Cong-Tam Phan, Thi-Thu-Hong Phan
Published: 2025-10-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21833v1

Automated image-based garbage classification is a critical component of global waste management; however, systematic benchmarks that integrate Machine Learning (ML), Deep Learning (DL), and efficient hybrid solutions remain underdeveloped. This study provides a comprehensive comparison of three paradigms: (1) machine learning algorithms using handcrafted features, (2) deep learning architectures, including ResNet variants and EfficientNetV2S, and (3) a hybrid approach that utilizes deep models for feature extraction combined with classical classifiers such as Support Vector Machine and Logistic Regression to identify the most effective strategy. Experiments on three public datasets - TrashNet, Garbage Classification, and a refined Household Garbage Dataset (with 43 corrected mislabels)- demonstrate that the hybrid method consistently outperforms the others, achieving up to 100% accuracy on TrashNet and the refined Household set, and 99.87% on Garbage Classification, thereby surpassing state-of-the-art benchmarks. Furthermore, feature selection reduces feature dimensionality by over 95% without compromising accuracy, resulting in faster training and inference. This work establishes more reliable benchmarks for waste classification and introduces an efficient hybrid framework that achieves high accuracy while reducing inference cost, making it suitable for scalable deployment in resource-constrained environments.

---

### GAPO: Robust Advantage Estimation for Real-World Code LLMs

Authors: Jianqing Zhang, Zhezheng Hao, Wei Xia, Hande Dong, Hong Wang, Chenxing Wei, Yuyan Zhou, Yubin Qi, Qiang Lin, Jian Cao
Published: 2025-10-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.21830v4

Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, where group-relative methods, such as GRPO, are popular due to their critic-free and normalized advantage estimation. However, in real-world code-editing scenarios, reward distributions are often skewed with unpredictable noise, leading to distorted advantage computation and increased rollout outliers. To address this issue, we propose Group Adaptive Policy Optimization (GAPO), which adaptively finds an interval with the highest SNR (Signal to Noise Ratio) per prompt and uses the median of that interval as an adaptive Q to replace the group mean in advantage calculation to reduce noise further. This adaptive Q robustly handles rollout noise while remaining plug-and-play and efficient. We evaluate GAPO on nine instruction-tuned LLMs (3B-14B) using a collected large dataset of 51,844 real-world, history-aware code-editing tasks spanning 10 programming languages. GAPO yields up to 4.35 in-domain (ID) and 5.30 out-of-domain (OOD) exact-match improvements over GRPO and its variant DAPO, while achieving lower clipping ratios and higher GPU throughput. Code: https://github.com/TsingZ0/verl-GAPO.

---

### A Flow Model with Low-Rank Transformers for Incomplete Multimodal Survival Analysis

Authors: Yi Yin, Yuntao Shou, Zao Dai, Yun Peng, Tao Meng, Wei Ai, Keqin Li
Published: 2025-10-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21829v1

In recent years, multimodal medical data-based survival analysis has attracted much attention. However, real-world datasets often suffer from the problem of incomplete modality, where some patient modality information is missing due to acquisition limitations or system failures. Existing methods typically infer missing modalities directly from observed ones using deep neural networks, but they often ignore the distributional discrepancy across modalities, resulting in inconsistent and unreliable modality reconstruction. To address these challenges, we propose a novel framework that combines a low-rank Transformer with a flow-based generative model for robust and flexible multimodal survival prediction. Specifically, we first formulate the concerned problem as incomplete multimodal survival analysis using the multi-instance representation of whole slide images (WSIs) and genomic profiles. To realize incomplete multimodal survival analysis, we propose a class-specific flow for cross-modal distribution alignment. Under the condition of class labels, we model and transform the cross-modal distribution. By virtue of the reversible structure and accurate density modeling capabilities of the normalizing flow model, the model can effectively construct a distribution-consistent latent space of the missing modality, thereby improving the consistency between the reconstructed data and the true distribution. Finally, we design a lightweight Transformer architecture to model intra-modal dependencies while alleviating the overfitting problem in high-dimensional modality fusion by virtue of the low-rank Transformer. Extensive experiments have demonstrated that our method not only achieves state-of-the-art performance under complete modality settings, but also maintains robust and superior accuracy under the incomplete modalities scenario.

---

### Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images

Authors: Yichi Zhang, Zhuo Chen, Lingbing Guo, Wen Zhang, Huajun Chen
Published: 2025-10-22
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.21828v2

Understanding and reasoning with abstractive information from the visual modality presents significant challenges for current multi-modal large language models (MLLMs). Among the various forms of abstractive information, Multi-Modal Relational Knowledge (MMRK), which represents abstract relational structures between multi-modal entities using node-edge formats, remains largely under-explored. In particular, STructured and Abstractive Reasoning (STAR) on such data has received little attention from the research community. To bridge the dual gaps in large-scale high-quality data and capability enhancement methodologies, this paper makes the following key contributions: (i). An automatic STAR data engine capable of synthesizing images with MMRK to build multi-modal instruction data with reliable chain-of-thought thinking for various STAR tasks and (ii). A comprehsive two-stage capability enhancement training framework, accompanied by a suite of evaluation protocols tailored to different STAR tasks. Based upon these contributions, we introduce STAR-64K, a dataset comprising 64K high-quality multi-modal instruction samples, and conduct experiments across 5 open-source MLLMs. Experimental results show that our two-stage enhancement framework enables smaller 3B/7B models to significantly outperform GPT-4o in STAR. Additionally, we provide in-depth analysis regarding the effectiveness of various designs, data transferability, and scalability.

---

### Precise classification of low quality G-banded Chromosome Images by reliability metrics and data pruning classifier

Authors: Mojtaba Moattari
Published: 2025-10-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.21827v1

In the last decade, due to high resolution cameras and accurate meta-phase analyzes, the accuracy of chromosome classification has improved substantially. However, current Karyotyping systems demand large number of high quality train data to have an adequately plausible Precision per each chromosome. Such provision of high quality train data with accurate devices are not yet accomplished in some out-reached pathological laboratories. To prevent false positive detections in low-cost systems and low-quality images settings, this paper improves the classification Precision of chromosomes using proposed reliability thresholding metrics and deliberately engineered features. The proposed method has been evaluated using a variation of deep Alex-Net neural network, SVM, K Nearest-Neighbors, and their cascade pipelines to an automated filtering of semi-straight chromosome. The classification results have highly improved over 90% for the chromosomes with more common defections and translocations. Furthermore, a comparative analysis over the proposed thresholding metrics has been conducted and the best metric is bolded with its salient characteristics. The high Precision results provided for a very low-quality G-banding database verifies suitability of the proposed metrics and pruning method for Karyotyping facilities in poor countries and lowbudget pathological laboratories.

---

### Fuzzy numbers revisited: operations on extensional fuzzy numbers

Authors: Krzysztof Siminski
Published: 2025-10-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20861v1

Fuzzy numbers are commonly represented with fuzzy sets. Their objective is to better represent imprecise data. However, operations on fuzzy numbers are not as straightforward as maths on crisp numbers. Commonly, the Zadeh's extension rule is applied to elaborate a result. This can produce two problems: (1) high computational complexity and (2) for some fuzzy sets and some operations the results is not a fuzzy set with the same features (eg. multiplication of two triangular fuzzy sets does not produce a triangular fuzzy set). One more problem is the fuzzy spread -- fuzziness of the result increases with the number of operations. These facts can severely limit the application field of fuzzy numbers. In this paper we would like to revisite this problem with a different kind of fuzzy numbers -- extensional fuzzy numbers. The paper defines operations on extensional fuzzy numbers and relational operators (=, >, >=, <, <=) for them. The proposed approach is illustrated with several applicational examples. The C++ implementation is available from a public GitHub repository.

---

### Data-Centric Lessons To Improve Speech-Language Pretraining

Authors: Vishaal Udandarao, Zhiyun Lu, Xuankai Chang, Yongqiang Wang, Violet Z. Yao, Albin Madapally Jose, Fartash Faghri, Josh Gardner, Chung-Cheng Chiu
Published: 2025-10-22
Categories: eess.AS, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.20860v1

Spoken Question-Answering (SQA) is a core capability for useful and interactive artificial intelligence systems. Recently, several speech-language models (SpeechLMs) have been released with a specific focus on improving their SQA performance. However, a lack of controlled ablations of pretraining data processing and curation makes it challenging to understand what factors account for performance, despite substantial gains from similar studies in other data modalities. In this work, we address this gap by conducting a data-centric exploration for pretraining SpeechLMs. We focus on three research questions fundamental to speech-language pretraining data: (1) how to process raw web-crawled audio content for speech-text pretraining, (2) how to construct synthetic pretraining datasets to augment web-crawled data and (3) how to interleave (text, audio) segments into training sequences. We apply the insights from our controlled data-centric ablations to pretrain a 3.8B-parameter SpeechLM, called SpeLangy, that outperforms models that are up to 3x larger by 10.2% absolute performance. We hope our findings highlight the impact of effective data curation for speech-language pretraining and guide future data-centric exploration in SpeechLMs.

---

### Lightweight Classifier for Detecting Intracranial Hemorrhage in Ultrasound Data

Authors: Phat Tran, Enbai Kuang, Fred Xu
Published: 2025-10-22
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2510.20857v1

Intracranial hemorrhage (ICH) secondary to Traumatic Brain Injury (TBI) represents a critical diagnostic challenge, with approximately 64,000 TBI-related deaths annually in the United States. Current diagnostic modalities including Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) have significant limitations: high cost, limited availability, and infrastructure dependence, particularly in resource-constrained environments. This study investigates machine learning approaches for automated ICH detection using Ultrasound Tissue Pulsatility Imaging (TPI), a portable technique measuring tissue displacement from hemodynamic forces during cardiac cycles. We analyze ultrasound TPI signals comprising 30 temporal frames per cardiac cycle with recording angle information, collected from TBI patients with CT-confirmed ground truth labels. Our preprocessing pipeline employs z-score normalization and Principal Component Analysis (PCA) for dimensionality reduction, retaining components explaining 95% of cumulative variance. We systematically evaluate multiple classification algorithms spanning probabilistic, kernel-based, neural network, and ensemble learning approaches across three feature representations: original 31-dimensional space, reduced subset, and PCA-transformed space. Results demonstrate that PCA transformation substantially improves classifier performance, with ensemble methods achieving 98.0% accuracy and F1-score of 0.890, effectively balancing precision and recall despite class imbalance. These findings establish the feasibility of machine learning-based ICH detection in TBI patients using portable ultrasound devices, with applications in emergency medicine, rural healthcare, and military settings where traditional imaging is unavailable.

---

### Beyond Hearing: Learning Task-Agnostic ExG Representations from Earphones via Physiology-Informed Tokenization

Authors: Hyungjun Yoon, Seungjoo Lee, Yu Yvonne Wu, Xiaomeng Chen, Taiting Lu, Freddy Yifei Liu, Taeckyung Lee, Hyeongheon Cha, Haochen Zhao, Gaoteng Zhao, Dongyao Chen, Cecilia Mascolo et al.
Published: 2025-10-22
Categories: eess.AS, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2510.20853v2

Electrophysiological (ExG) signals offer valuable insights into human physiology, yet building foundation models that generalize across everyday tasks remains challenging due to two key limitations: (i)~insufficient data diversity, as most ExG recordings are collected in controlled labs with bulky, expensive devices; and (ii)~task-specific model designs that require tailored processing (i.e., targeted frequency filters) and architectures, which limit generalization across tasks. To address these challenges, we introduce an approach for scalable, task-agnostic ExG monitoring in the wild. We collected 50 hours of unobtrusive free-living ExG data with an earphone-based hardware prototype to narrow the data diversity gap. At the core of our approach is Physiology-informed Multi-band Tokenization (PiMT), which decomposes ExG signals into 12 physiology-informed tokens, followed by a reconstruction task to learn robust representations. This enables adaptive feature recognition across the full frequency spectrum while capturing task-relevant information. Experiments on our new DailySense dataset, the first to enable ExG-based analysis across five human senses, together with four public ExG benchmarks, demonstrate that PiMT consistently outperforms state-of-the-art methods across diverse tasks.

---

### Alternatives to the Laplacian for Scalable Spectral Clustering with Group Fairness Constraints

Authors: Iván Ojeda-Ruiz, Young Ju Lee, Malcolm Dickens, Leonardo Cambisaca
Published: 2025-10-22
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2510.20220v3

Recent research has focused on mitigating algorithmic bias in clustering by incorporating fairness constraints into algorithmic design. Notions such as disparate impact, community cohesion, and cost per population have been implemented to enforce equitable outcomes. Among these, group fairness (balance) ensures that each protected group is proportionally represented within every cluster. However, incorporating balance as a metric of fairness into spectral clustering algorithms has led to computational times that can be improved. This study aims to enhance the efficiency of spectral clustering algorithms by reformulating the constrained optimization problem using a new formulation derived from the Lagrangian method and the Sherman-Morrison-Woodbury (SMW) identity, resulting in the Fair-SMW algorithm. Fair-SMW employs three alternatives to the Laplacian matrix with different spectral gaps to generate multiple variations of Fair-SMW, achieving clustering solutions with comparable balance to existing algorithms while offering improved runtime performance. We present the results of Fair-SMW, evaluated using the Stochastic Block Model (SBM) to measure both runtime efficiency and balance across real-world network datasets, including LastFM, FacebookNet, Deezer, and German. We achieve an improvement in computation time that is twice as fast as the state-of-the-art, and also flexible enough to achieve twice as much balance.

---

### Data-Adaptive Transformed Bilateral Tensor Low-Rank Representation for Clustering

Authors: Hui Chen, Xinjie Wang, Xianchao Xiu, Wanquan Liu
Published: 2025-10-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20077v1

Tensor low-rank representation (TLRR) has demonstrated significant success in image clustering. However, most existing methods rely on fixed transformations and suffer from poor robustness to noise. In this paper, we propose a novel transformed bilateral tensor low-rank representation model called TBTLRR, which introduces a data-adaptive tensor nuclear norm by learning arbitrary unitary transforms, allowing for more effective capture of global correlations. In addition, by leveraging the bilateral structure of latent tensor data, TBTLRR is able to exploit local correlations between image samples and features. Furthermore, TBTLRR integrates the $\ell_{1/2}$-norm and Frobenius norm regularization terms for better dealing with complex noise in real-world scenarios. To solve the proposed nonconvex model, we develop an efficient optimization algorithm inspired by the alternating direction method of multipliers (ADMM) and provide theoretical convergence. Extensive experiments validate its superiority over the state-of-the-art methods in clustering. The code will be available at https://github.com/xianchaoxiu/TBTLRR.

---

### LLMs can hide text in other text of the same length

Authors: Antonio Norelli, Michael Bronstein
Published: 2025-10-22
Categories: cs.AI, cs.CL, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.20075v6

A meaningful text can be hidden inside another, completely different yet still coherent and plausible, text of the same length. For example, a tweet containing a harsh political critique could be embedded in a tweet that celebrates the same political leader, or an ordinary product review could conceal a secret manuscript. This uncanny state of affairs is now possible thanks to Large Language Models, and in this paper we present Calgacus, a simple and efficient protocol to achieve it. We show that even modest 8-billion-parameter open-source LLMs are sufficient to obtain high-quality results, and a message as long as this abstract can be encoded and decoded locally on a laptop in seconds. The existence of such a protocol demonstrates a radical decoupling of text from authorial intent, further eroding trust in written communication, already shaken by the rise of LLM chatbots. We illustrate this with a concrete scenario: a company could covertly deploy an unfiltered LLM by encoding its answers within the compliant responses of a safe model. This possibility raises urgent questions for AI safety and challenges our understanding of what it means for a Large Language Model to know something.

---

### Filter-Based Reconstruction of Images from Events

Authors: Bernd Pfrommer
Published: 2025-10-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20071v1

Reconstructing an intensity image from the events of a moving event camera is a challenging task that is typically approached with neural networks deployed on graphics processing units. This paper presents a much simpler, FIlter Based Asynchronous Reconstruction method (FIBAR). First, intensity changes signaled by events are integrated with a temporal digital IIR filter. To reduce reconstruction noise, stale pixels are detected by a novel algorithm that regulates a window of recently updated pixels. Arguing that for a moving camera, the absence of events at a pixel location likely implies a low image gradient, stale pixels are then blurred with a Gaussian filter. In contrast to most existing methods, FIBAR is asynchronous and permits image read-out at an arbitrary time. It runs on a modern laptop CPU at about 42(140) million events/s with (without) spatial filtering enabled. A few simple qualitative experiments are presented that show the difference in image reconstruction between FIBAR and a neural network-based approach (FireNet). FIBAR's reconstruction is noisier than neural network-based methods and suffers from ghost images. However, it is sufficient for certain tasks such as the detection of fiducial markers. Code is available at https://github.com/ros-event-camera/event_image_reconstruction_fibar

---

### Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamics

Authors: Ram Dyuthi Sristi, Sowmya Manojna Narasimha, Jingya Huang, Alice Despatin, Simon Musall, Vikash Gilja, Gal Mishne
Published: 2025-10-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20068v1

Simultaneous recordings from thousands of neurons across multiple brain areas reveal rich mixtures of activity that are shared between regions and dynamics that are unique to each region. Existing alignment or multi-view methods neglect temporal structure, whereas dynamical latent variable models capture temporal dependencies but are usually restricted to a single area, assume linear read-outs, or conflate shared and private signals. We introduce the Coupled Transformer Autoencoder (CTAE) - a sequence model that addresses both (i) non-stationary, non-linear dynamics and (ii) separation of shared versus region-specific structure in a single framework. CTAE employs transformer encoders and decoders to capture long-range neural dynamics and explicitly partitions each region's latent space into orthogonal shared and private subspaces. We demonstrate the effectiveness of CTAE on two high-density electrophysiology datasets with simultaneous recordings from multiple regions, one from motor cortical areas and the other from sensory areas. CTAE extracts meaningful representations that better decode behavioral variables compared to existing approaches.

---

### A Multi-Layer Machine Learning and Econometric Pipeline for Forecasting Market Risk: Evidence from Cryptoasset Liquidity Spillovers

Authors: Yimeng Qiu, Feihuang Fang
Published: 2025-10-22
Categories: cs.LG, cs.CE, econ.EM
arXiv: https://arxiv.org/abs/2510.20066v1

We study whether liquidity and volatility proxies of a core set of cryptoassets generate spillovers that forecast market-wide risk. Our empirical framework integrates three statistical layers: (A) interactions between core liquidity and returns, (B) principal-component relations linking liquidity and returns, and (C) volatility-factor projections that capture cross-sectional volatility crowding. The analysis is complemented by vector autoregression impulse responses and forecast error variance decompositions (see Granger 1969; Sims 1980), heterogeneous autoregressive models with exogenous regressors (HAR-X, Corsi 2009), and a leakage-safe machine learning protocol using temporal splits, early stopping, validation-only thresholding, and SHAP-based interpretation. Using daily data from 2021 to 2025 (1462 observations across 74 assets), we document statistically significant Granger-causal relationships across layers and moderate out-of-sample predictive accuracy. We report the most informative figures, including the pipeline overview, Layer A heatmap, Layer C robustness analysis, vector autoregression variance decompositions, and the test-set precision-recall curve. Full data and figure outputs are provided in the artifact repository.

---

### Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs

Authors: Hongyi Liu, Jiaji Huang, Zhen Jia, Youngsuk Park, Yu-Xiang Wang
Published: 2025-10-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20064v2

Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding. We design an algorithm that provably competes with the best draft model in hindsight for each query in terms of either the token acceptance probability or expected acceptance length. In particular, we show that we can accurately evaluate all draft models, instead of only the chosen model without incurring additional queries to the target model, which allows us to improve exponentially over the existing bandit-based approach as the number of draft models increases. Our approach is generically applicable with any speculative decoding methods (single draft, multi-drafts and draft-trees). Moreover, we design system-efficient versions of online learners and demonstrate that the overhead in computation and latency can be substantially reduced. We conduct extensive experiments on open-source LLMs and diverse datasets, demonstrating that our methods substantially outperform the state-of-the-art EAGLE3 and the BanditSpec baseline in a variety of domains where specialized domain-expert drafters are available, especially when long reasoning chains are required.

---

### Ask What Your Country Can Do For You: Towards a Public Red Teaming Model

Authors: Wm. Matthew Kennedy, Cigdem Patlak, Jayraj Dave, Blake Chambers, Aayush Dhanotiya, Darshini Ramiah, Reva Schwartz, Jack Hagen, Akash Kundu, Mouni Pendharkar, Liam Baisley, Theodora Skeadas et al.
Published: 2025-10-22
Categories: cs.CY, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.20061v1

AI systems have the potential to produce both benefits and harms, but without rigorous and ongoing adversarial evaluation, AI actors will struggle to assess the breadth and magnitude of the AI risk surface. Researchers from the field of systems design have developed several effective sociotechnical AI evaluation and red teaming techniques targeting bias, hate speech, mis/disinformation, and other documented harm classes. However, as increasingly sophisticated AI systems are released into high-stakes sectors (such as education, healthcare, and intelligence-gathering), our current evaluation and monitoring methods are proving less and less capable of delivering effective oversight. In order to actually deliver responsible AI and to ensure AI's harms are fully understood and its security vulnerabilities mitigated, pioneering new approaches to close this "responsibility gap" are now more urgent than ever. In this paper, we propose one such approach, the cooperative public AI red-teaming exercise, and discuss early results of its prior pilot implementations. This approach is intertwined with CAMLIS itself: the first in-person public demonstrator exercise was held in conjunction with CAMLIS 2024. We review the operational design and results of this exercise, the prior National Institute of Standards and Technology (NIST)'s Assessing the Risks and Impacts of AI (ARIA) pilot exercise, and another similar exercise conducted with the Singapore Infocomm Media Development Authority (IMDA). Ultimately, we argue that this approach is both capable of delivering meaningful results and is also scalable to many AI developing jurisdictions.

---

### Enhancing Reasoning Skills in Small Persian Medical Language Models Can Outperform Large-Scale Data Training

Authors: Mehrdad Ghassabi, Sadra Hakim, Hamidreza Baradaran Kashani, Pedram Rostami
Published: 2025-10-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.20059v5

Enhancing reasoning capabilities in small language models is critical for specialized applications such as medical question answering, particularly in underrepresented languages like Persian. In this study, we employ Reinforcement Learning with AI Feedback (RLAIF) and Direct preference optimization (DPO) to improve the reasoning skills of a general-purpose Persian language model. To achieve this, we translated a multiple-choice medical question-answering dataset into Persian and used RLAIF to generate rejected-preferred answer pairs, which are essential for DPO training. By prompting both teacher and student models to produce Chain-of-Thought (CoT) reasoning responses, we compiled a dataset containing correct and incorrect reasoning trajectories. This dataset, comprising 2 million tokens in preferred answers and 2.5 million tokens in rejected ones, was used to train a baseline model, significantly enhancing its medical reasoning capabilities in Persian. Remarkably, the resulting model outperformed its predecessor, gaokerena-V, which was trained on approximately 57 million tokens, despite leveraging a much smaller dataset. These results highlight the efficiency and effectiveness of reasoning-focused training approaches in developing domain-specific language models with limited data availability.

---

### Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards

Authors: Yuwei Cheng, Zifeng Zhao, Haifeng Xu
Published: 2025-10-22
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.20055v1

Online advertising platforms use automated auctions to connect advertisers with potential customers, requiring effective bidding strategies to maximize profits. Accurate ad impact estimation requires considering three key factors: delayed and long-term effects, cumulative ad impacts such as reinforcement or fatigue, and customer heterogeneity. However, these effects are often not jointly addressed in previous studies. To capture these factors, we model ad bidding as a Contextual Markov Decision Process (CMDP) with delayed Poisson rewards. For efficient estimation, we propose a two-stage maximum likelihood estimator combined with data-splitting strategies, ensuring controlled estimation error based on the first-stage estimator's (in)accuracy. Building on this, we design a reinforcement learning algorithm to derive efficient personalized bidding strategies. This approach achieves a near-optimal regret bound of $\tilde{O}{(dH^2\sqrt{T})}$, where $d$ is the contextual dimension, $H$ is the number of rounds, and $T$ is the number of customers. Our theoretical findings are validated by simulation experiments.

---

### Endogenous Aggregation of Multiple Data Envelopment Analysis Scores for Large Data Sets

Authors: Hashem Omrani, Raha Imanirad, Adam Diamant, Utkarsh Verma, Amol Verma, Fahad Razak
Published: 2025-10-22
Categories: math.OC, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.20052v2

We propose an approach for dynamic efficiency evaluation across multiple organizational dimensions using data envelopment analysis (DEA). The method generates both dimension-specific and aggregate efficiency scores, incorporates desirable and undesirable outputs, and is suitable for large-scale problem settings. Two regularized DEA models are introduced: a slack-based measure (SBM) and a linearized version of a nonlinear goal programming model (GP-SBM). While SBM estimates an aggregate efficiency score and then distributes it across dimensions, GP-SBM first estimates dimension-level efficiencies and then derives an aggregate score. Both models utilize a regularization parameter to enhance discriminatory power while also directly integrating both desirable and undesirable outputs. We demonstrate the computational efficiency and validity of our approach on multiple datasets and apply it to a case study of twelve hospitals in Ontario, Canada, evaluating three theoretically grounded dimensions of organizational effectiveness over a 24-month period from January 2018 to December 2019: technical efficiency, clinical efficiency, and patient experience. Our numerical results show that SBM and GP-SBM better capture correlations among input/output variables and outperform conventional benchmarking methods that separately evaluate dimensions before aggregation.

---

### From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge

Authors: Nafis Chowdhury, Moinul Haque, Anika Ahmed, Nazia Tasnim, Md. Istiak Hossain Shihab, Sajjadur Rahman, Farig Sadeque
Published: 2025-10-22
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.20043v1

Recent progress in NLP research has demonstrated remarkable capabilities of large language models (LLMs) across a wide range of tasks. While recent multilingual benchmarks have advanced cultural evaluation for LLMs, critical gaps remain in capturing the nuances of low-resource cultures. Our work addresses these limitations through a Bengali Language Cultural Knowledge (BLanCK) dataset including folk traditions, culinary arts, and regional dialects. Our investigation of several multilingual language models shows that while these models perform well in non-cultural categories, they struggle significantly with cultural knowledge and performance improves substantially across all models when context is provided, emphasizing context-aware architectures and culturally curated training data.

---

### Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models

Authors: Huichan Seo, Sieun Choi, Minki Hong, Yi Zhou, Junseo Kim, Lukman Ismaila, Naome Etori, Mehul Agarwal, Zhixuan Liu, Jihie Kim, Jean Oh
Published: 2025-10-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20042v3

Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I) systems, leaving image-to-image (I2I) editors underexplored. We bridge this gap with a unified evaluation across six countries, an 8-category/36-subcategory schema, and era-aware prompts, auditing both T2I generation and I2I editing under a standardized protocol that yields comparable diagnostics. Using open models with fixed settings, we derive cross-country, cross-era, and cross-category evaluations. Our framework combines standard automatic metrics, a culture-aware retrieval-augmented VQA, and expert human judgments collected from native reviewers. To enable reproducibility, we release the complete image corpus, prompts, and configurations. Our study reveals three findings: (1) under country-agnostic prompts, models default to Global-North, modern-leaning depictions that flatten cross-country distinctions; (2) iterative I2I editing erodes cultural fidelity even when conventional metrics remain flat or improve; and (3) I2I models apply superficial cues (palette shifts, generic props) rather than era-consistent, context-aware changes, often retaining source identity for Global-South targets. These results highlight that culture-sensitive edits remain unreliable in current systems. By releasing standardized data, prompts, and human evaluation protocols, we provide a reproducible, culture-centered benchmark for diagnosing and tracking cultural bias in generative image models. Project page: https://seochan99.github.io/ECB

---

### Approximate Model Predictive Control for Microgrid Energy Management via Imitation Learning

Authors: Changrui Liu, Shengling Shi, Anil Alan, Ganesh Kumar Venayagamoorthy, Bart De Schutter
Published: 2025-10-22
Categories: eess.SY, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2510.20040v2

Efficient energy management is essential for reliable and sustainable microgrid operation amid increasing renewable integration. In this paper, an imitation learning-based framework to approximate mixed-integer Economic Model Predictive Control (EMPC) is proposed for microgrid energy management, considering fuel generators, renewable energy resources, a unified energy storage unit, and curtailable loads. Within the proposed framework, a neural network is trained to imitate expert EMPC control actions from offline trajectories, thereby enabling fast real-time decision making without solving online mixed-integer optimization problems, which often exhibit highly variable solution times across instances and do not scale well to large problem sizes; in particular, worst-case solve times can be excessively large and therefore unsuitable for real-time deployment. In contrast, the learned policy provides predictable and consistently low computation times. To enhance robustness and generalization, the learning process incorporates noise injection during training to mitigate distribution shift and explicitly accounts for forecast uncertainty in renewable generation and demand. Furthermore, a constraint-tightening approach combined with a projection layer is proposed to ensure recursive feasibility and constraint satisfaction of the learned controller. Simulation results demonstrate that the learned policy achieves economic performance comparable to EMPC, while reducing computation time by approximately one order of magnitude relative to the optimization-based EMPC.

---

### Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactions

Authors: Yuyang Jiang, Longjie Guo, Yuchen Wu, Aylin Caliskan, Tanu Mitra, Hua Shen
Published: 2025-10-22
Categories: cs.HC, cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2510.20039v1

Large language model (LLM)-powered chatbots are increasingly used for opinion exploration. Prior research examined how LLMs alter user views, yet little work extended beyond one-way influence to address how user input can affect LLM responses and how such bi-directional influence manifests throughout the multi-turn conversations. This study investigates this dynamic through 50 controversial-topic discussions with participants (N=266) across three conditions: static statements, standard chatbot, and personalized chatbot. Results show that human opinions barely shifted, while LLM outputs changed more substantially, narrowing the gap between human and LLM stance. Personalization amplified these shifts in both directions compared to the standard setting. Analysis of multi-turn conversations further revealed that exchanges involving participants' personal stories were most likely to trigger stance changes for both humans and LLMs. Our work highlights the risk of over-alignment in human-LLM interaction and the need for careful design of personalized chatbots to more thoughtfully and stably align with users.

---

### ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering

Authors: Marianne Menglin Liu, Daniel Garcia, Fjona Parllaku, Vikas Upadhyay, Syed Fahad Allam Shah, Dan Roth
Published: 2025-10-22
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2510.20036v2

Large language model (LLM) agents rely on external tools to solve complex tasks, but real-world toolsets often contain redundant tools with overlapping names and descriptions, introducing ambiguity and reducing selection accuracy. LLMs also face strict input context limits, preventing efficient consideration of large toolsets. To address these challenges, we propose ToolScope, which includes: (1) ToolScopeMerger with Auto-Correction to automatically audit and fix tool merges, reducing redundancy, and (2) ToolScopeRetriever to rank and select only the most relevant tools for each query, compressing toolsets to fit within context limits without sacrificing accuracy. Evaluations on three state-of-the-art LLMs and three open-source tool-use benchmarks show gains of 8.38% to 38.6% in tool selection accuracy, demonstrating ToolScope's effectiveness in enhancing LLM tool use.

---

### Throwing Vines at the Wall: Structure Learning via Random Search

Authors: Thibault Vatter, Thomas Nagler
Published: 2025-10-22
Categories: stat.ME, cs.LG
arXiv: https://arxiv.org/abs/2510.20035v3

Vine copulas offer flexible multivariate dependence modeling and have become widely used in machine learning. Yet, structure learning remains a key challenge. Early heuristics, such as Dissmann's greedy algorithm, are still considered the gold standard but are often suboptimal. We propose random search algorithms and a statistical framework based on model confidence sets, to improve structure selection, provide theoretical guarantees on selection probabilities and excess risk, as well as serve as a foundation for ensembling. Empirical results on real-world data sets show that our methods consistently outperform state-of-the-art approaches.

---

### Improving Transfer Learning for Sequence Labeling Tasks by Adapting Pre-trained Neural Language Models

Authors: David Dukić
Published: 2025-10-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.20033v1

This doctoral thesis improves the transfer learning for sequence labeling tasks by adapting pre-trained neural language models. The proposed improvements in transfer learning involve introducing a multi-task model that incorporates an additional signal, a method based on architectural modifications in autoregressive large language models, and a sequence labeling framework for autoregressive large language models utilizing supervised in-context fine-tuning combined with response-oriented adaptation strategies. The first improvement is given in the context of domain transfer for the event trigger detection task. The domain transfer of the event trigger detection task can be improved by incorporating an additional signal obtained from a domain-independent text processing system into a multi-task model. The second improvement involves modifying the model's architecture. For that purpose, a method is proposed to enable bidirectional information flow across layers of autoregressive large language models. The third improvement utilizes autoregressive large language models as text generators through a generative supervised in-context fine-tuning framework. The proposed model, method, and framework demonstrate that pre-trained neural language models achieve their best performance on sequence labeling tasks when adapted through targeted transfer learning paradigms.

---

### Speculative Sampling for Parametric Temporal Point Processes

Authors: Marin Biloš, Anderson Schneider, Yuriy Nevmyvaka
Published: 2025-10-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20031v1

Temporal point processes are powerful generative models for event sequences that capture complex dependencies in time-series data. They are commonly specified using autoregressive models that learn the distribution of the next event from the previous events. This makes sampling inherently sequential, limiting efficiency. In this paper, we propose a novel algorithm based on rejection sampling that enables exact sampling of multiple future values from existing TPP models, in parallel, and without requiring any architectural changes or retraining. Besides theoretical guarantees, our method demonstrates empirical speedups on real-world datasets, bridging the gap between expressive modeling and efficient parallel generation for large-scale TPP applications.

---

### On Encoding Matrices using Quantum Circuits

Authors: Liron Mor Yosef, Haim Avron
Published: 2025-10-22
Categories: quant-ph, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2510.20030v2

Over a decade ago, it was demonstrated that quantum computing has the potential to revolutionize numerical linear algebra by enabling algorithms with complexity superior to what is classically achievable, e.g., the seminal HHL algorithm for solving linear systems. Efficient execution of such algorithms critically depends on representing inputs (matrices and vectors) as quantum circuits that encode or implement these inputs. For that task, two common circuit representations emerged in the literature: block encodings and state preparation circuits. In this paper, we systematically study encodings matrices in the form of block encodings and state preparation circuits. We examine methods for constructing these representations from matrices given in classical form, as well as quantum two-way conversions between circuit representations. Two key results we establish (among others) are: (a) a general method for efficiently constructing a block encoding of an arbitrary matrix given in classical form (entries stored in classical random access memory); and (b) low-overhead, bidirectional conversion algorithms between block encodings and state preparation circuits, showing that these models are essentially equivalent. From a technical perspective, two central components of our constructions are: (i) a special constant-depth multiplexer that simultaneously multiplexes all higher-order Pauli matrices of a given size, and (ii) an algorithm for performing a quantum conversion between a matrix's expansion in the standard basis and its expansion in the basis of higher-order Pauli matrices.

---

### BrainPuzzle: Hybrid Physics and Data-Driven Reconstruction for Transcranial Ultrasound Tomography

Authors: Shengyu Chen, Shihang Feng, Yi Luo, Xiaowei Jia, Youzuo Lin
Published: 2025-10-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20029v2

Ultrasound brain imaging remains challenging due to the large difference in sound speed between the skull and brain tissues and the difficulty of coupling large probes to the skull. This work aims to achieve quantitative transcranial ultrasound by reconstructing an accurate speed-of-sound (SoS) map of the brain. Traditional physics-based full-waveform inversion (FWI) is limited by weak signals caused by skull-induced attenuation, mode conversion, and phase aberration, as well as incomplete spatial coverage since full-aperture arrays are clinically impractical. In contrast, purely data-driven methods that learn directly from raw ultrasound data often fail to model the complex nonlinear and nonlocal wave propagation through bone, leading to anatomically plausible but quantitatively biased SoS maps under low signal-to-noise and sparse-aperture conditions. To address these issues, we propose BrainPuzzle, a hybrid two-stage framework that combines physical modeling with machine learning. In the first stage, reverse time migration (time-reversal acoustics) is applied to multi-angle acquisitions to produce migration fragments that preserve structural details even under low SNR. In the second stage, a transformer-based super-resolution encoder-decoder with a graph-based attention unit (GAU) fuses these fragments into a coherent and quantitatively accurate SoS image. A partial-array acquisition strategy using a movable low-count transducer set improves feasibility and coupling, while the hybrid algorithm compensates for the missing aperture. Experiments on two synthetic datasets show that BrainPuzzle achieves superior SoS reconstruction accuracy and image completeness, demonstrating its potential for advancing quantitative ultrasound brain imaging.

---

### The Temporal Graph of Bitcoin Transactions

Authors: Vahid Jalili
Published: 2025-10-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.20028v1

Since its 2009 genesis block, the Bitcoin network has processed >1.08 billion (B) transactions representing >8.72B BTC, offering rich potential for machine learning (ML); yet, its pseudonymity and obscured flow of funds inherent in its UTxO-based design, have rendered this data largely inaccessible for ML research. Addressing this gap, we present an ML-compatible graph modeling the Bitcoin's economic topology by reconstructing the flow of funds. This temporal, heterogeneous graph encompasses complete transaction history up to block 863000, consisting of >2.4B nodes and >39.72B edges. Additionally, we provide custom sampling methods yielding node and edge feature vectors of sampled communities, tools to load and analyze the Bitcoin graph data within specialized graph databases, and ready-to-use database snapshots. This comprehensive dataset and toolkit empower the ML community to tackle Bitcoin's intricate ecosystem at scale, driving progress in applications such as anomaly detection, address classification, market analysis, and large-scale graph ML benchmarking. Dataset and code available at https://github.com/B1AAB/EBA

---

### Extreme Views: 3DGS Filter for Novel View Synthesis from Out-of-Distribution Camera Poses

Authors: Damian Bowness, Charalambos Poullis
Published: 2025-10-22
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2510.20027v1

When viewing a 3D Gaussian Splatting (3DGS) model from camera positions significantly outside the training data distribution, substantial visual noise commonly occurs. These artifacts result from the lack of training data in these extrapolated regions, leading to uncertain density, color, and geometry predictions from the model. To address this issue, we propose a novel real-time render-aware filtering method. Our approach leverages sensitivity scores derived from intermediate gradients, explicitly targeting instabilities caused by anisotropic orientations rather than isotropic variance. This filtering method directly addresses the core issue of generative uncertainty, allowing 3D reconstruction systems to maintain high visual fidelity even when users freely navigate outside the original training viewpoints. Experimental evaluation demonstrates that our method substantially improves visual quality, realism, and consistency compared to existing Neural Radiance Field (NeRF)-based approaches such as BayesRays. Critically, our filter seamlessly integrates into existing 3DGS rendering pipelines in real-time, unlike methods that require extensive post-hoc retraining or fine-tuning. Code and results at https://damian-bowness.github.io/EV3DGS

---

### SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph

Authors: Jiazheng Li, Yawei Wang, David Yan, Yijun Tian, Zhichao Xu, Huan Song, Panpan Xu, Lin Lee Cheong
Published: 2025-10-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20022v1

Large Language Models (LLMs) have demonstrated remarkable capabilities, enabling language agents to excel at single-turn tasks. However, their application to complex, multi-step, and long-horizon tasks remains challenging. While reinforcement learning (RL) offers a promising avenue for addressing these challenges, mainstream approaches typically rely solely on sparse, outcome-based rewards, a limitation that becomes especially problematic for group-based RL algorithms lacking critic models, such as Group Relative Policy Optimization (GRPO). In such methods, uniformly rewarding or penalizing all actions within a trajectory can lead to training instability and suboptimal policies, because beneficial and detrimental actions are often entangled across multi-step interactions. To address this challenge, we propose SALT, a novel and lightweight framework that provides a finer-grained advantage assignment, derived solely from outcome rewards. We achieve this by constructing a graph from trajectories of the same prompt, which allows us to quantify the quality of each step and assign advantages accordingly. Crucially, SALT is designed as a plug-and-play module that seamlessly integrates with existing group-based RL algorithms, requiring no modifications to the rollout procedure and introducing negligible computational overhead. Extensive experiments on the WebShop, ALFWorld, and AppWorld benchmarks with various model sizes demonstrate that SALT consistently improves performance. We also conduct a thorough analysis to validate the design choices behind SALT and offer actionable insights.

---

### Optimized Distortion in Linear Social Choice

Authors: Luise Ge, Gregory Kehne, Yevgeniy Vorobeychik
Published: 2025-10-22
Categories: cs.GT, cs.AI
arXiv: https://arxiv.org/abs/2510.20020v1

Social choice theory offers a wealth of approaches for selecting a candidate on behalf of voters based on their reported preference rankings over options. When voters have underlying utilities for these options, however, using preference rankings may lead to suboptimal outcomes vis-à-vis utilitarian social welfare. Distortion is a measure of this suboptimality, and provides a worst-case approach for developing and analyzing voting rules when utilities have minimal structure. However in many settings, such as common paradigms for value alignment, alternatives admit a vector representation, and it is natural to suppose that utilities are parametric functions thereof. We undertake the first study of distortion for linear utility functions. Specifically, we investigate the distortion of linear social choice for deterministic and randomized voting rules. We obtain bounds that depend only on the dimension of the candidate embedding, and are independent of the numbers of candidates or voters. Additionally, we introduce poly-time instance-optimal algorithms for minimizing distortion given a collection of candidates and votes. We empirically evaluate these in two real-world domains: recommendation systems using collaborative filtering embeddings, and opinion surveys utilizing language model embeddings, benchmarking several standard rules against our instance-optimal algorithms.

---

### Machine Learning-Based Localization Accuracy of RFID Sensor Networks via RSSI Decision Trees and CAD Modeling for Defense Applications

Authors: Curtis Lee Shull, Merrick Green
Published: 2025-10-22
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2510.20019v1

Radio Frequency Identification (RFID) tracking may be a viable solution for defense assets that must be stored in accordance with security guidelines. However, poor sensor specificity (vulnerabilities include long range detection, spoofing, and counterfeiting) can lead to erroneous detection and operational security events. We present a supervised learning simulation with realistic Received Signal Strength Indicator (RSSI) data and Decision Tree classification in a Computer Assisted Design (CAD)-modeled floor plan that encapsulates some of the challenges encountered in defense storage. In this work, we focused on classifying 12 lab zones (LabZoneA-L) to perform location inference. The raw dataset had approximately 980,000 reads. Class frequencies were imbalanced, and class weights were calculated to account for class imbalance in this multi-class setting. The model, trained on stratified subsamples to 5,000 balanced observations, yielded an overall accuracy of 34.2% and F1-scores greater than 0.40 for multiple zones (Zones F, G, H, etc.). However, rare classes (most notably LabZoneC) were often misclassified, even with the use of class weights. An adjacency-aware confusion matrix was calculated to allow better interpretation of physically adjacent zones. These results suggest that RSSI-based decision trees can be applied in realistic simulations to enable zone-level anomaly detection or misplacement monitoring for defense supply logistics. Reliable classification performance in low-coverage and low-signal zones could be improved with better antenna placement or additional sensors and sensor fusion with other modalities.

---

### Simultaneously Solving Infinitely Many LQ Mean Field Games In Hilbert Spaces: The Power of Neural Operators

Authors: Dena Firoozi, Anastasis Kratsios, Xuwei Yang
Published: 2025-10-22
Categories: math.OC, cs.LG, math.NA, math.PR, q-fin.MF
arXiv: https://arxiv.org/abs/2510.20017v1

Traditional mean-field game (MFG) solvers operate on an instance-by-instance basis, which becomes infeasible when many related problems must be solved (e.g., for seeking a robust description of the solution under perturbations of the dynamics or utilities, or in settings involving continuum-parameterized agents.). We overcome this by training neural operators (NOs) to learn the rules-to-equilibrium map from the problem data (``rules'': dynamics and cost functionals) of LQ MFGs defined on separable Hilbert spaces to the corresponding equilibrium strategy. Our main result is a statistical guarantee: an NO trained on a small number of randomly sampled rules reliably solves unseen LQ MFG variants, even in infinite-dimensional settings. The number of NO parameters needed remains controlled under appropriate rule sampling during training. Our guarantee follows from three results: (i) local-Lipschitz estimates for the highly nonlinear rules-to-equilibrium map; (ii) a universal approximation theorem using NOs with a prespecified Lipschitz regularity (unlike traditional NO results where the NO's Lipschitz constant can diverge as the approximation error vanishes); and (iii) new sample-complexity bounds for $L$-Lipschitz learners in infinite dimensions, directly applicable as the Lipschitz constants of our approximating NOs are controlled in (ii).

---

### A Unified Detection Pipeline for Robust Object Detection in Fisheye-Based Traffic Surveillance

Authors: Neema Jakisa Owor, Joshua Kofi Asamoah, Tanner Wambui Muturi, Anneliese Jakisa Owor, Blessing Agyei Kyem, Andrews Danyo, Yaw Adu-Gyamfi, Armstrong Aboah
Published: 2025-10-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20016v1

Fisheye cameras offer an efficient solution for wide-area traffic surveillance by capturing large fields of view from a single vantage point. However, the strong radial distortion and nonuniform resolution inherent in fisheye imagery introduce substantial challenges for standard object detectors, particularly near image boundaries where object appearance is severely degraded. In this work, we present a detection framework designed to operate robustly under these conditions. Our approach employs a simple yet effective pre and post processing pipeline that enhances detection consistency across the image, especially in regions affected by severe distortion. We train several state-of-the-art detection models on the fisheye traffic imagery and combine their outputs through an ensemble strategy to improve overall detection accuracy. Our method achieves an F1 score of0.6366 on the 2025 AI City Challenge Track 4, placing 8thoverall out of 62 teams. These results demonstrate the effectiveness of our framework in addressing issues inherent to fisheye imagery.

---

### AI Pose Analysis and Kinematic Profiling of Range-of-Motion Variations in Resistance Training

Authors: Adam Diamant
Published: 2025-10-22
Categories: stat.AP, cs.CV
arXiv: https://arxiv.org/abs/2510.20012v2

This study develops an AI-based pose estimation pipeline for quantifying movement kinematics in resistance training. Using videos from Wolf et al. (2025), comprising 303 recordings of 26 participants performing eight upper-body exercises under full (fROM) and lengthened partial (pROM) conditions, we extract joint-angle trajectories using five distinct deep-learning pose estimation models and a unified signal-processing framework. From these trajectories, we derive repetition-level metrics including range of motion (ROM) and repetition duration. We use these outputs as dependent variables in a crossed random-effects model that accounts for participant-, exercise-, and model-level variability to assess systematic differences between ROM conditions. Results indicate that pROM reduces range of motion without significantly affecting repetition duration. Variance decomposition shows that pROM increases both between-participant and between-exercise variability, suggesting reduced consistency in execution. To enable cross-exercise comparison, we model ROM on a logarithmic scale and define %ROM as the proportion of fROM achieved under pROM. While the estimated mean is approximately 56\%, significant heterogeneity across exercises indicates that lengthened partials are not characterized by a fixed proportion of full ROM. The results demonstrate that AI-based motion analysis can provide reliable kinematic insights to inform evidence-based training recommendations.

---

### Improving Predictive Confidence in Medical Imaging via Online Label Smoothing

Authors: Kushan Choudhury, Shubhrodeep Roy, Ankur Chanda, Shubhajit Biswas, Somenath Kuiry
Published: 2025-10-22
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.20011v1

Deep learning models, especially convolutional neural networks, have achieved impressive results in medical image classification. However, these models often produce overconfident predictions, which can undermine their reliability in critical healthcare settings. While traditional label smoothing offers a simple way to reduce such overconfidence, it fails to consider relationships between classes by treating all non-target classes equally. In this study, we explore the use of Online Label Smoothing (OLS), a dynamic approach that adjusts soft labels throughout training based on the model's own prediction patterns. We evaluate OLS on the large-scale RadImageNet dataset using three widely used architectures: ResNet-50, MobileNetV2, and VGG-19. Our results show that OLS consistently improves both Top-1 and Top-5 classification accuracy compared to standard training methods, including hard labels, conventional label smoothing, and teacher-free knowledge distillation. In addition to accuracy gains, OLS leads to more compact and well-separated feature embeddings, indicating improved representation learning. These findings suggest that OLS not only strengthens predictive performance but also enhances calibration, making it a practical and effective solution for developing trustworthy AI systems in the medical imaging domain.

---