# Research Papers — 2025-10 · bundle page 38 of 217

> Full-text markdown of papers #1851–1900 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/38
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/37.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/39.md)

### On the Structure of Floating-Point Noise in Batch-Invariant GPU Matrix Multiplication

Authors: Tadisetty Sai Yashwanth
Published: 2025-10-26
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2511.00025v1

Floating-point non-associativity makes fundamental deep learning operations, such as matrix multiplication (matmul) on GPUs, inherently non-deterministic. Despite this, the statistical structure of the resulting numerical error remains poorly understood. A common working assumption is that these errors behave as independent and identically distributed (i.i.d.) Gaussian noise. In this paper, we empirically test this assumption and show that it fails to describe real GPU behavior. By comparing outputs of single-input and batched matmuls, we find that while the i.i.d. model predicts non-zero output instability, empirical results show a 0.00% prediction flip rate. Through covariance analysis, we uncover the cause: the floating-point error is structured and highly correlated. For float16, nearly 50% of the total error variance lies in off-diagonal terms, revealing that the noise behaves as a coordinated, directional perturbation rather than random static. This result challenges the prevailing stochastic view of numerical noise and provides a principled foundation for analyzing deep learning reliability under hardware non-determinism.

---

### Chitchat with AI: Understand the supply chain carbon disclosure of companies worldwide through Large Language Model

Authors: Haotian Hang, Yueyang Shen, Vicky Zhu, Jose Cruz, Michelle Li
Published: 2025-10-26
Categories: cs.CY, cs.AI, cs.CL, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2511.00024v1

In the context of global sustainability mandates, corporate carbon disclosure has emerged as a critical mechanism for aligning business strategy with environmental responsibility. The Carbon Disclosure Project (CDP) hosts the world's largest longitudinal dataset of climate-related survey responses, combining structured indicators with open-ended narratives, but the heterogeneity and free-form nature of these disclosures present significant analytical challenges for benchmarking, compliance monitoring, and investment screening. This paper proposes a novel decision-support framework that leverages large language models (LLMs) to assess corporate climate disclosure quality at scale. It develops a master rubric that harmonizes narrative scoring across 11 years of CDP data (2010-2020), enabling cross-sector and cross-country benchmarking. By integrating rubric-guided scoring with percentile-based normalization, our method identifies temporal trends, strategic alignment patterns, and inconsistencies in disclosure across industries and regions. Results reveal that sectors such as technology and countries like Germany consistently demonstrate higher rubric alignment, while others exhibit volatility or superficial engagement, offering insights that inform key decision-making processes for investors, regulators, and corporate environmental, social, and governance (ESG) strategists. The proposed LLM-based approach transforms unstructured disclosures into quantifiable, interpretable, comparable, and actionable intelligence, advancing the capabilities of AI-enabled decision support systems (DSSs) in the domain of climate governance.

---

### Towards Piece-by-Piece Explanations for Chess Positions with SHAP

Authors: Francesco Spinnato
Published: 2025-10-26
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.25775v1

Contemporary chess engines offer precise yet opaque evaluations, typically expressed as centipawn scores. While effective for decision-making, these outputs obscure the underlying contributions of individual pieces or patterns. In this paper, we explore adapting SHAP (SHapley Additive exPlanations) to the domain of chess analysis, aiming to attribute a chess engines evaluation to specific pieces on the board. By treating pieces as features and systematically ablating them, we compute additive, per-piece contributions that explain the engines output in a locally faithful and human-interpretable manner. This method draws inspiration from classical chess pedagogy, where players assess positions by mentally removing pieces, and grounds it in modern explainable AI techniques. Our approach opens new possibilities for visualization, human training, and engine comparison. We release accompanying code and data to foster future research in interpretable chess AI.

---

### Pulsar Detection with Deep Learning

Authors: Manideep Pendyala
Published: 2025-10-26
Categories: astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2510.25774v1

Pulsar surveys generate millions of candidates per run, overwhelming manual inspection. This thesis builds a deep learning pipeline for radio pulsar candidate selection that fuses array-derived features with image diagnostics. From approximately 500 GB of Giant Metrewave Radio Telescope (GMRT) data, raw voltages are converted to filterbanks (SIGPROC), then de-dispersed and folded across trial dispersion measures (PRESTO) to produce approximately 32,000 candidates. Each candidate yields four diagnostics--summed profile, time vs. phase, subbands vs. phase, and DM curve--represented as arrays and images. A baseline stacked model (ANNs for arrays + CNNs for images with logistic-regression fusion) reaches 68% accuracy. We then refine the CNN architecture and training (regularization, learning-rate scheduling, max-norm constraints) and mitigate class imbalance via targeted augmentation, including a GAN-based generator for the minority class. The enhanced CNN attains 87% accuracy; the final GAN+CNN system achieves 94% accuracy with balanced precision and recall on a held-out test set, while remaining lightweight enough for near--real-time triage. The results show that combining array and image channels improves separability over image-only approaches, and that modest generative augmentation substantially boosts minority (pulsar) recall. The methods are survey-agnostic and extensible to forthcoming high-throughput facilities.

---

### Sub-microsecond Transformers for Jet Tagging on FPGAs

Authors: Lauri Laatu, Chang Sun, Arianna Cox, Abhijith Gandrakota, Benedikt Maier, Jennifer Ngadiuba, Zhiqiang Que, Wayne Luk, Maria Spiropulu, Alexander Tapper
Published: 2025-10-26
Categories: physics.ins-det, cs.LG, cs.PF, hep-ex
arXiv: https://arxiv.org/abs/2510.24784v1

We present the first sub-microsecond transformer implementation on an FPGA achieving competitive performance for state-of-the-art high-energy physics benchmarks. Transformers have shown exceptional performance on multiple tasks in modern machine learning applications, including jet tagging at the CERN Large Hadron Collider (LHC). However, their computational complexity prohibits use in real-time applications, such as the hardware trigger system of the collider experiments up until now. In this work, we demonstrate the first application of transformers for jet tagging on FPGAs, achieving $\mathcal{O}(100)$ nanosecond latency with superior performance compared to alternative baseline models. We leverage high-granularity quantization and distributed arithmetic optimization to fit the entire transformer model on a single FPGA, achieving the required throughput and latency. Furthermore, we add multi-head attention and linear attention support to hls4ml, making our work accessible to the broader fast machine learning community. This work advances the next-generation trigger systems for the High Luminosity LHC, enabling the use of transformers for real-time applications in high-energy physics and beyond.

---

### AI & Data Competencies: Scaffolding holistic AI literacy in Higher Education

Authors: Kathleen Kennedy, Anuj Gupta
Published: 2025-10-26
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.24783v1

This chapter introduces the AI & Data Acumen Learning Outcomes Framework, a comprehensive tool designed to guide the integration of AI literacy across higher education. Developed through a collaborative process, the framework defines key AI and data-related competencies across four proficiency levels and seven knowledge dimensions. It provides a structured approach for educators to scaffold student learning in AI, balancing technical skills with ethical considerations and sociocultural awareness. The chapter outlines the framework's development process, its structure, and practical strategies for implementation in curriculum design, learning activities, and assessment. We address challenges in implementation and future directions for AI education. By offering a roadmap for developing students' holistic AI literacy, this framework prepares learners to leverage generative AI capabilities in both academic and professional contexts.

---

### Sparsity and Superposition in Mixture of Experts

Authors: Marmik Chaudhari, Jeremi Nuer, Rome Thorstenson
Published: 2025-10-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.23671v2

Mixture of Experts (MoE) models have become central to scaling large language models, yet their mechanistic differences from dense networks remain poorly understood. Previous work has explored how dense models use \textit{superposition} to represent more features than dimensions, and how superposition is a function of feature sparsity and feature importance. MoE models cannot be explained mechanistically through the same lens. We find that neither feature sparsity nor feature importance cause discontinuous phase changes, and that network sparsity (the ratio of active to total experts) better characterizes MoEs. We develop new metrics for measuring superposition across experts. Our findings demonstrate that models with greater network sparsity exhibit greater \emph{monosemanticity}. We propose a new definition of expert specialization based on monosemantic feature representation rather than load balancing, showing that experts naturally organize around coherent feature combinations when initialized appropriately. These results suggest that network sparsity in MoEs may enable more interpretable models without sacrificing performance, challenging the common assumption that interpretability and capability are fundamentally at odds.

---

### What Work is AI Actually Doing? Uncovering the Drivers of Generative AI Adoption

Authors: Peeyush Agarwal, Harsh Agarwal, Akshat Rana
Published: 2025-10-26
Categories: econ.GN, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.23669v2

Purpose: The rapid integration of artificial intelligence (AI) systems like ChatGPT, Claude AI, etc., has a deep impact on how work is done. Predicting how AI will reshape work requires understanding not just its capabilities, but how it is actually being adopted. This study investigates which intrinsic task characteristics drive users' decisions to delegate work to AI systems. Methodology: This study utilizes the Anthropic Economic Index dataset of four million Claude AI interactions mapped to O*NET tasks. We systematically scored each task across seven key dimensions: Routine, Cognitive, Social Intelligence, Creativity, Domain Knowledge, Complexity, and Decision Making using 35 parameters. We then employed multivariate techniques to identify latent task archetypes and analyzed their relationship with AI usage. Findings: Tasks requiring high creativity, complexity, and cognitive demand, but low routineness, attracted the most AI engagement. Furthermore, we identified three task archetypes: Dynamic Problem Solving, Procedural & Analytical Work, and Standardized Operational Tasks, demonstrating that AI applicability is best predicted by a combination of task characteristics, over individual factors. Our analysis revealed highly concentrated AI usage patterns, with just 5% of tasks accounting for 59% of all interactions. Originality: This research provides the first systematic evidence linking real-world generative AI usage to a comprehensive, multi-dimensional framework of intrinsic task characteristics. It introduces a data-driven classification of work archetypes that offers a new framework for analyzing the emerging human-AI division of labor.

---

### Traffic flow forecasting, STL decomposition, Hybrid model, LSTM, ARIMA, XGBoost, Intelligent transportation systems

Authors: Fujiang Yuan, Yangrui Fan, Xiaohuan Bing, Zhen Tian, Chunhong Yuan, Yankang Li
Published: 2025-10-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.23668v1

Accurate traffic flow forecasting is essential for intelligent transportation systems and urban traffic management. However, single model approaches often fail to capture the complex, nonlinear, and multi scale temporal patterns in traffic flow data. This study proposes a decomposition driven hybrid framework that integrates Seasonal Trend decomposition using Loess (STL) with three complementary predictive models. STL first decomposes the original time series into trend, seasonal, and residual components. Then, a Long Short Term Memory (LSTM) network models long term trends, an Autoregressive Integrated Moving Average (ARIMA) model captures seasonal periodicity, and an Extreme Gradient Boosting (XGBoost) algorithm predicts nonlinear residual fluctuations. The final forecast is obtained through multiplicative integration of the sub model predictions. Using 998 traffic flow records from a New York City intersection between November and December 2015, results show that the LSTM ARIMA XGBoost hybrid model significantly outperforms standalone models including LSTM, ARIMA, and XGBoost across MAE, RMSE, and R squared metrics. The decomposition strategy effectively isolates temporal characteristics, allowing each model to specialize, thereby improving prediction accuracy, interpretability, and robustness.

---

### Optimize Any Topology: A Foundation Model for Shape- and Resolution-Free Structural Topology Optimization

Authors: Amin Heyrani Nobari, Lyle Regenwetter, Cyril Picard, Ligong Han, Faez Ahmed
Published: 2025-10-26
Categories: cs.LG, cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2510.23667v1

Structural topology optimization (TO) is central to engineering design but remains computationally intensive due to complex physics and hard constraints. Existing deep-learning methods are limited to fixed square grids, a few hand-coded boundary conditions, and post-hoc optimization, preventing general deployment. We introduce Optimize Any Topology (OAT), a foundation-model framework that directly predicts minimum-compliance layouts for arbitrary aspect ratios, resolutions, volume fractions, loads, and fixtures. OAT combines a resolution- and shape-agnostic autoencoder with an implicit neural-field decoder and a conditional latent-diffusion model trained on OpenTO, a new corpus of 2.2 million optimized structures covering 2 million unique boundary-condition configurations. On four public benchmarks and two challenging unseen tests, OAT lowers mean compliance up to 90% relative to the best prior models and delivers sub-1 second inference on a single GPU across resolutions from 64 x 64 to 256 x 256 and aspect ratios as high as 10:1. These results establish OAT as a general, fast, and resolution-free framework for physics-aware topology optimization and provide a large-scale dataset to spur further research in generative modeling for inverse design. Code & data can be found at https://github.com/ahnobari/OptimizeAnyTopology.

---

### Beyond Normality: Reliable A/B Testing with Non-Gaussian Data

Authors: Junpeng Gong, Chunkai Wang, Hao Li, Jinyong Ma, Haoxuan Li, Xu He
Published: 2025-10-26
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2510.23666v1

A/B testing has become the cornerstone of decision-making in online markets, guiding how platforms launch new features, optimize pricing strategies, and improve user experience. In practice, we typically employ the pairwise $t$-test to compare outcomes between the treatment and control groups, thereby assessing the effectiveness of a given strategy. To be trustworthy, these experiments must keep Type I error (i.e., false positive rate) under control; otherwise, we may launch harmful strategies. However, in real-world applications, we find that A/B testing often fails to deliver reliable results. When the data distribution departs from normality or when the treatment and control groups differ in sample size, the commonly used pairwise $t$-test is no longer trustworthy. In this paper, we quantify how skewed, long tailed data and unequal allocation distort error rates and derive explicit formulas for the minimum sample size required for the $t$-test to remain valid. We find that many online feedback metrics require hundreds of millions samples to ensure reliable A/B testing. Thus we introduce an Edgeworth-based correction that provides more accurate $p$-values when the available sample size is limited. Offline experiments on a leading A/B testing platform corroborate the practical value of our theoretical minimum sample size thresholds and demonstrate that the corrected method substantially improves the reliability of A/B testing in real-world conditions.

---

### Transformers from Compressed Representations

Authors: Juan C. Leon Alcazar, Mattia Soldan, Mohammad Saatialsoruji, Alejandro Pardo, Hani Itani, Juan Camilo Perez, Bernard Ghanem
Published: 2025-10-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.23665v2

Compressed file formats are the corner stone of efficient data storage and transmission, yet their potential for representation learning remains largely underexplored. We introduce TEMPEST (TransformErs froM comPressed rEpreSenTations), a method that exploits the inherent byte-stream structure of compressed files to design an effective tokenization and encoding strategy. By leveraging this compact encoding, a standard transformer can directly learn semantic representations from compressed data streams, bypassing the need for raw byte-level processing or full media decoding. Our proposal substantially reduces the number of tokens required for semantic classification, thereby lowering both computational complexity and memory usage. Through extensive experiments across diverse datasets, coding schemes, and modalities, we show that TEMPEST achieves accuracy competitive wit the state-of-the-art while delivering efficiency gains in memory and compute.

---

### Agentsway -- Software Development Methodology for AI Agents-based Teams

Authors: Eranga Bandara, Ross Gore, Xueping Liang, Sachini Rajapakse, Isurunima Kularathne, Pramoda Karunarathna, Peter Foytik, Sachin Shetty, Ravi Mukkamala, Abdul Rahman, Amin Hass, Ng Wee Keong et al.
Published: 2025-10-26
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.23664v1

The emergence of Agentic AI is fundamentally transforming how software is designed, developed, and maintained. Traditional software development methodologies such as Agile, Kanban, ShapeUp, etc, were originally designed for human-centric teams and are increasingly inadequate in environments where autonomous AI agents contribute to planning, coding, testing, and continuous learning. To address this methodological gap, we present "Agentsway" a novel software development framework designed for ecosystems where AI agents operate as first-class collaborators. Agentsway introduces a structured lifecycle centered on human orchestration, and privacy-preserving collaboration among specialized AI agents. The framework defines distinct roles for planning, prompting, coding, testing, and fine-tuning agents, each contributing to iterative improvement and adaptive learning throughout the development process. By integrating fine-tuned LLMs that leverage outputs and feedback from different agents throughout the development cycle as part of a retrospective learning process, Agentsway enhances domain-specific reasoning, and explainable decision-making across the entire software development lifecycle. Responsible AI principles are further embedded across the agents through the coordinated use of multiple fine-tuned LLMs and advanced reasoning models, ensuring balanced, transparent, and accountable decision-making. This work advances software engineering by formalizing agent-centric collaboration, integrating privacy-by-design principles, and defining measurable metrics for productivity and trust. Agentsway represents a foundational step toward the next generation of AI-native, self-improving software development methodologies. To the best of our knowledge, this is the first research effort to introduce a dedicated methodology explicitly designed for AI agent-based software engineering teams.

---

### AI-Driven Carbon Monitoring: Transformer-Based Reconstruction of Atmospheric CO2 in Canadian Poultry Regions

Authors: Padmanabhan Jagannathan Prajesh, Kaliaperumal Ragunath, Miriam Gordon, Bruce Rathgeber, Suresh Neethirajan
Published: 2025-10-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.23663v1

Accurate mapping of column-averaged CO2 (XCO2) over agricultural landscapes is essential for guiding emission mitigation strategies. We present a Spatiotemporal Vision Transformer with Wavelets (ST-ViWT) framework that reconstructs continuous, uncertainty-quantified XCO2 fields from OCO-2 across southern Canada, emphasizing poultry-intensive regions. The model fuses wavelet time-frequency representations with transformer attention over meteorology, vegetation indices, topography, and land cover. On 2024 OCO-2 data, ST-ViWT attains R2 = 0.984 and RMSE = 0.468 ppm; 92.3 percent of gap-filled predictions lie within +/-1 ppm. Independent validation with TCCON shows robust generalization (bias = -0.14 ppm; r = 0.928), including faithful reproduction of the late-summer drawdown. Spatial analysis across 14 poultry regions reveals a moderate positive association between facility density and XCO2 (r = 0.43); high-density areas exhibit larger seasonal amplitudes (9.57 ppm) and enhanced summer variability. Compared with conventional interpolation and standard machine-learning baselines, ST-ViWT yields seamless 0.25 degree CO2 surfaces with explicit uncertainties, enabling year-round coverage despite sparse observations. The approach supports integration of satellite constraints with national inventories and precision livestock platforms to benchmark emissions, refine region-specific factors, and verify interventions. Importantly, transformer-based Earth observation enables scalable, transparent, spatially explicit carbon accounting, hotspot prioritization, and policy-relevant mitigation assessment.

---

### JiuTian Chuanliu: A Large Spatiotemporal Model for General-purpose Dynamic Urban Sensing

Authors: Liangzhe Han, Leilei Sun, Tongyu Zhu, Tao Tao, Jibin Wang, Weifeng Lv
Published: 2025-10-26
Categories: cs.SI, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2510.23662v1

As a window for urban sensing, human mobility contains rich spatiotemporal information that reflects both residents' behavior preferences and the functions of urban areas. The analysis of human mobility has attracted the attention of many researchers. However, existing methods often address specific tasks from a particular perspective, leading to insufficient modeling of human mobility and limited applicability of the learned knowledge in various downstream applications. To address these challenges, this paper proposes to push massive amounts of human mobility data into a spatiotemporal model, discover latent semantics behind mobility behavior and support various urban sensing tasks. Specifically, a large-scale and widely covering human mobility data is collected through the ubiquitous base station system and a framework named General-purpose and Dynamic Human Mobility Embedding (GDHME) for urban sensing is introduced. The framework follows the self-supervised learning idea and contains two major stages. In stage 1, GDHME treats people and regions as nodes within a dynamic graph, unifying human mobility data as people-region-time interactions. An encoder operating in continuous-time dynamically computes evolving node representations, capturing dynamic states for both people and regions. Moreover, an autoregressive self-supervised task is specially designed to guide the learning of the general-purpose node embeddings. In stage 2, these representations are utilized to support various tasks. To evaluate the effectiveness of our GDHME framework, we further construct a multi-task urban sensing benchmark. Offline experiments demonstrate GDHME's ability to automatically learn valuable node features from vast amounts of data. Furthermore, our framework is used to deploy the JiuTian ChuanLiu Big Model, a system that has been presented at the 2023 China Mobile Worldwide Partner Conference.

---

### Quanvolutional Neural Networks for Pneumonia Detection: An Efficient Quantum-Assisted Feature Extraction Paradigm

Authors: Gazi Tanbhir, Md. Farhan Shahriyar, Abdullah Md Raihan Chy
Published: 2025-10-26
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.23660v1

Pneumonia poses a significant global health challenge, demanding accurate and timely diagnosis. While deep learning, particularly Convolutional Neural Networks (CNNs), has shown promise in medical image analysis for pneumonia detection, CNNs often suffer from high computational costs, limitations in feature representation, and challenges in generalizing from smaller datasets. To address these limitations, we explore the application of Quanvolutional Neural Networks (QNNs), leveraging quantum computing for enhanced feature extraction. This paper introduces a novel hybrid quantum-classical model for pneumonia detection using the PneumoniaMNIST dataset. Our approach utilizes a quanvolutional layer with a parameterized quantum circuit (PQC) to process 2x2 image patches, employing rotational Y-gates for data encoding and entangling layers to generate non-classical feature representations. These quantum-extracted features are then fed into a classical neural network for classification. Experimental results demonstrate that the proposed QNN achieves a higher validation accuracy of 83.33 percent compared to a comparable classical CNN which achieves 73.33 percent. This enhanced convergence and sample efficiency highlight the potential of QNNs for medical image analysis, particularly in scenarios with limited labeled data. This research lays the foundation for integrating quantum computing into deep-learning-driven medical diagnostic systems, offering a computationally efficient alternative to traditional approaches.

---

### Quantum Machine Learning for Image Classification: A Hybrid Model of Residual Network with Quantum Support Vector Machine

Authors: Md. Farhan Shahriyar, Gazi Tanbhir, Abdullah Md Raihan Chy
Published: 2025-10-26
Categories: cs.LG, cs.CV, cs.ET
arXiv: https://arxiv.org/abs/2510.23659v1

Recently, there has been growing attention on combining quantum machine learning (QML) with classical deep learning approaches, as computational techniques are key to improving the performance of image classification tasks. This study presents a hybrid approach that uses ResNet-50 (Residual Network) for feature extraction and Quantum Support Vector Machines (QSVM) for classification in the context of potato disease detection. Classical machine learning as well as deep learning models often struggle with high-dimensional and complex datasets, necessitating advanced techniques like quantum computing to improve classification efficiency. In our research, we use ResNet-50 to extract deep feature representations from RGB images of potato diseases. These features are then subjected to dimensionality reduction using Principal Component Analysis (PCA). The resulting features are processed through QSVM models which apply various quantum feature maps such as ZZ, Z, and Pauli-X to transform classical data into quantum states. To assess the model performance, we compared it with classical machine learning algorithms such as Support Vector Machine (SVM) and Random Forest (RF) using five-fold stratified cross-validation for comprehensive evaluation. The experimental results demonstrate that the Z-feature map-based QSVM outperforms classical models, achieving an accuracy of 99.23 percent, surpassing both SVM and RF models. This research highlights the advantages of integrating quantum computing into image classification and provides a potential disease detection solution through hybrid quantum-classical modeling.

---

### Aligning Diffusion Language Models via Unpaired Preference Optimization

Authors: Vaibhav Jindal, Hejian Sang, Chun-Mao Lai, Yanning Chen, Zhipeng Wang
Published: 2025-10-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.23658v2

Diffusion language models (dLLMs) are an emerging alternative to autoregressive (AR) generators, but aligning them to human preferences is challenging because sequence log-likelihoods are intractable and pairwise preference data are costly to collect. We introduce ELBO-KTO, which combines an ELBO surrogate for diffusion log-likelihoods with a prospect-theoretic, unpaired preference objective (Kahneman Tversky Optimization, KTO). We analyze the bias and variance induced by the ELBO substitution and employ variance-reduction practices that stabilize gradients during training. Applied to LLaDA-8B-Instruct, ELBO-KTO yields 65.9% and 62.3% adjusted win rates on kto-mix-14k and UltraFeedback-Binary, respectively, versus the base model under an automatic LLM judge. Across downstream tasks, including GSM8K, MMLU, and additional reasoning/knowledge benchmarks, ELBO-KTO trained on UltraFeedback-Binary performs on par with or better than the base model under identical decoding. This establishes unpaired preference optimization as a viable alternative to pairwise alignment in diffusion LLMs.

---

### A machine learning framework integrating seed traits and plasma parameters for predicting germination uplift in crops

Authors: Saklain Niam, Tashfiqur Rahman, Md. Amjad Patwary, Mukarram Hossain
Published: 2025-10-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.23657v1

Cold plasma (CP) is an eco-friendly method to enhance seed germination, yet outcomes remain difficult to predict due to complex seed--plasma--environment interactions. This study introduces the first machine learning framework to forecast germination uplift in soybean, barley, sunflower, radish, and tomato under dielectric barrier discharge (DBD) plasma. Among the models tested (GB, XGB, ET, and hybrids), Extra Trees (ET) performed best (R\textsuperscript{2} = 0.919; RMSE = 3.21; MAE = 2.62), improving to R\textsuperscript{2} = 0.925 after feature reduction. Engineering analysis revealed a hormetic response: negligible effects at $<$7 kV or $<$200 s, maximum germination at 7--15 kV for 200--500 s, and reduced germination beyond 20 kV or prolonged exposures. Discharge power was also a dominant factor, with germination rate maximizing at $\geq$100 W with low exposure time. Species and cultivar-level predictions showed radish (MAE = 1.46) and soybean (MAE = 2.05) were modeled with high consistency, while sunflower remained slightly higher variable (MAE = 3.80). Among cultivars, Williams (MAE = 1.23) and Sari (1.33) were well predicted, while Arian (2.86) and Nyírségi fekete (3.74) were comparatively poorly captured. This framework was also embedded into MLflow, providing a decision-support tool for optimizing CP seed germination in precision agriculture.

---

### Correctness Forensics for Batch Speculative Decoding: Diagnosing the Ragged Tensor Problem

Authors: Ranran Haoran Zhang, Soumik Dey, Ashirbad Mishra, Hansi Wu, Binbin Li, Rui Zhang
Published: 2025-10-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.22876v4

Inference optimizations are routinely evaluated by throughput alone, without verifying output correctness. We conduct a forensic analysis of batch speculative decoding and find that several widely-used implementations silently produce corrupted outputs (repetitive tokens, <unk> symbols) while reporting competitive speed; failures invisible to metrics like ROUGE. We trace the root cause to the ragged tensor problem: variable token acceptance desynchronizes position IDs, attention masks, and KV-cache across a batch. We formalize the synchronization invariants (rectangular alignment and position-ID contiguity) that valid batched inference must preserve and show that maintaining them incurs superlinear alignment overhead under contiguous layouts. EQSPEC enforces the invariants without custom kernels; EXSPEC schedules same-length sequences to bypass realignment. On SpecBench across three model families, EXSPEC reaches 3 x throughput at batch size 8 with 95% exact match to standard decoding; residual divergence traces to floating-point non-determinism, not synchronization error. Code:https://github.com/eBay/spec_dec

---

### A Comprehensive Dataset for Human vs. AI Generated Text Detection

Authors: Rajarshi Roy, Gurpreet Singh, Ashhar Aziz, Shashwat Bajpai, Nasrin Imanpour, Shwetangshu Biswas, Kapil Wanaskar, Parth Patwa, Subhankar Ghosh, Shreyas Dixit, Nilesh Ranjan Pal, Vipula Rawte et al.
Published: 2025-10-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.22874v3

The rapid advancement of large language models (LLMs) has led to increasingly human-like AI-generated text, raising concerns about content authenticity, misinformation, and trustworthiness. Addressing the challenge of reliably detecting AI-generated text and attributing it to specific models requires large-scale, diverse, and well-annotated datasets. In this work, we present a comprehensive dataset comprising over 73,193 text samples that combine authentic New York Times articles with synthetic versions generated by multiple state-of-the-art LLMs including Gemma-2-9b, Mistral-7B, Qwen-2-72B, LLaMA-8B, Yi-Large, and GPT-4-o. The dataset provides original article abstracts as prompts, full human-authored narratives. We establish baseline results for two key tasks: distinguishing human-written from AI-generated text, achieving an accuracy of 58.35\%, and attributing AI texts to their generating models with an accuracy of 8.92\%. By bridging real-world journalistic content with modern generative models, the dataset aims to catalyze the development of robust detection and attribution methods, fostering trust and transparency in the era of generative AI. Our dataset is available at: https://huggingface.co/datasets/Rajarshi-Roy-research/Defactify_Text_Dataset

---

### Seeing the Unseen: Towards Training-Free Inspection for Wind Turbine Blades Using Knowledge-Augmented Vision Language Models

Authors: Yang Zhang, Qianyu Zhou, Farhad Imani, Jiong Tang
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22868v2

Wind turbine blades operate in harsh environments, making timely damage detection essential for preventing failures and optimizing maintenance. Drone-based inspection and deep learning are promising, but typically depend on large, labeled datasets, which limit their ability to detect rare or evolving damage types. To address this, we propose a zero-shot-oriented inspection framework that integrates Retrieval-Augmented Generation (RAG) with Vision-Language Models (VLM). A multimodal knowledge base is constructed, comprising technical documentation, representative reference images, and domain-specific guidelines. A hybrid text-image retriever with keyword-aware reranking assembles the most relevant context to condition the VLM at inference, injecting domain knowledge without task-specific training. We evaluate the framework on 30 labeled blade images covering diverse damage categories. Although the dataset is small due to the difficulty of acquiring verified blade imagery, it covers multiple representative defect types. On this test set, the RAG-grounded VLM correctly classified all samples, whereas the same VLM without retrieval performed worse in both accuracy and precision. We further compare against open-vocabulary baselines and incorporate uncertainty Clopper-Pearson confidence intervals to account for the small-sample setting. Ablation studies indicate that the key advantage of the framework lies in explainability and generalizability: retrieved references ground the reasoning process and enable the detection of previously unseen defects by leveraging domain knowledge rather than relying solely on visual cues. This research contributes a data-efficient solution for industrial inspection that reduces dependence on extensive labeled datasets.

---

### Interpreting and Mitigating Unwanted Uncertainty in LLMs

Authors: Tiasa Singha Roy, Ayush Rajesh Jhaveri, Ilias Triantafyllopoulos
Published: 2025-10-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.22866v1

Despite their impressive capabilities, Large Language Models (LLMs) exhibit unwanted uncertainty, a phenomenon where a model changes a previously correct answer into an incorrect one when re-prompted. This behavior undermines trust and poses serious risks in high-stakes domains. In this work, we investigate the mechanisms that drive this phenomenon. We adapt the Needle-in-a-Haystack retrieval framework and integrate a Flip-style re-evaluation prompt to simulate realistic answer-flipping scenarios. We find that retrieval heads are not primarily responsible for avoiding uncertainty. Instead, we identify a small set of non-retrieval attention heads that disproportionately attend to misleading tokens in uncertain contexts. Masking these heads yields significant improvements, reducing flip behavior by up to 15% without introducing incoherence or overcorrection. However, when tested for downstream tasks, we observe trade-offs with flip behavior. Our findings contribute to the growing field of mechanistic interpretability and present a simple yet effective technique for mitigating uncertainty-driven failure modes in LLMs.

---

### Long-Term PM2.5 Forecasting Using a DTW-Enhanced CNN-GRU Model

Authors: Amirali Ataee Naeini, Arshia Ataee Naeini, Fatemeh Karami Mohammadi, Omid Ghaffarpasand
Published: 2025-10-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.22863v2

Reliable long-term forecasting of PM2.5 concentrations is critical for public health early-warning systems, yet existing deep learning approaches struggle to maintain prediction stability beyond 48 hours, especially in cities with sparse monitoring networks. This paper presents a deep learning framework that combines Dynamic Time Warping (DTW) for intelligent station similarity selection with a CNN-GRU architecture to enable extended-horizon PM2.5 forecasting in Isfahan, Iran, a city characterized by complex pollution dynamics and limited monitoring coverage. Unlike existing approaches that rely on computationally intensive transformer models or external simulation tools, our method integrates three key innovations: (i) DTW-based historical sampling to identify similar pollution patterns across peer stations, (ii) a lightweight CNN-GRU architecture augmented with meteorological features, and (iii) a scalable design optimized for sparse networks. Experimental validation using multi-year hourly data from eight monitoring stations demonstrates superior performance compared to state-of-the-art deep learning methods, achieving R2 = 0.91 for 24-hour forecasts. Notably, this is the first study to demonstrate stable 10-day PM2.5 forecasting (R2 = 0.73 at 240 hours) without performance degradation, addressing critical early-warning system requirements. The framework's computational efficiency and independence from external tools make it particularly suitable for deployment in resource-constrained urban environments.

---

### Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement

Authors: Linyang He, Tianjun Zhong, Richard Antonello, Gavin Mischler, Micah Goldblum, Nima Mesgarani
Published: 2025-10-26
Categories: cs.CL, q-bio.NC
arXiv: https://arxiv.org/abs/2510.22860v3

Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model neural responses to language, their internal representations are highly "entangled," mixing information about lexicon, syntax, meaning, and reasoning. This entanglement biases conventional brain encoding analyses toward linguistically shallow features (e.g., lexicon and syntax), making it difficult to isolate the neural substrates of cognitively deeper processes. Here, we introduce a residual disentanglement method that computationally isolates these components. By first probing an LM to identify feature-specific layers, our method iteratively regresses out lower-level representations to produce four nearly orthogonal embeddings for lexicon, syntax, meaning, and, critically, reasoning. We used these disentangled embeddings to model intracranial (ECoG) brain recordings from neurosurgical patients listening to natural speech. We show that: 1) This isolated reasoning embedding exhibits unique predictive power, accounting for variance in neural activity not explained by other linguistic features and even extending to the recruitment of visual regions beyond classical language areas. 2) The neural signature for reasoning is temporally distinct, peaking later (~350-400ms) than signals related to lexicon, syntax, and meaning, consistent with its position atop a processing hierarchy. 3) Standard, non-disentangled LLM embeddings can be misleading, as their predictive success is primarily attributable to linguistically shallow features, masking the more subtle contributions of deeper cognitive processing.

---

### Guardian: Decoupling Exploration from Safety in Reinforcement Learning

Authors: Kaitong Cai, Jusheng Zhang, Jing Yang, Keze Wang
Published: 2025-10-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.22859v1

Hybrid offline--online reinforcement learning (O2O RL) promises both sample efficiency and robust exploration, but suffers from instability due to distribution shift between offline and online data. We introduce RLPD-GX, a framework that decouples policy optimization from safety enforcement: a reward-seeking learner explores freely, while a projection-based guardian guarantees rule-consistent execution and safe value backups. This design preserves the exploratory value of online interactions without collapsing to conservative policies. To further stabilize training, we propose dynamic curricula that gradually extend temporal horizons and anneal offline--online data mixing. We prove convergence via a contraction property of the guarded Bellman operator, and empirically show state-of-the-art performance on Atari-100k, achieving a normalized mean score of 3.02 (+45\% over prior hybrid methods) with stronger safety and stability. Beyond Atari, ablations demonstrate consistent gains across safety-critical and long-horizon tasks, underscoring the generality of our design. Extensive and comprehensive results highlight decoupled safety enforcement as a simple yet principled route to robust O2O RL, suggesting a broader paradigm for reconciling exploration and safety in reinforcement learning.

---

### A Review of Neural Networks in Precipitation Prediction

Authors: Yugong Zeng, Jiayuan Wang, Jonathan Wu
Published: 2025-10-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.22855v2

Precipitation prediction has undergone a profound transformation. A notable limitation of traditional NWP is the need for extensive statistical post-processing. To address this challenge, neural network-based approaches were developed. These approaches offer a framework that directly learns the mapping from atmospheric predictors to precipitation targets. Based on the technological development, this article first reviews the traditional precipitation forecasting methods and summarizes the development trends of precipitation forecasting based on neural networks. We then outline the training process, loss functions, and some datasets for precipitation prediction. In the main body of the article, we detail the basic artificial neural networks (ANNs), spatial feature extraction models, time feature extraction models, generative models, Transformer models, graph neural networks (GNNs), and emerging hybrid models. Finally, in the appendix, we supplement the commonly used evaluation metrics. This paper focuses on the advantages and disadvantages of various neural network models in precipitation forecasting applications, and also pays attention to the latest progress of neural network-based methods. Overall, neural networks have significantly improved the accuracy of short-term and medium-term precipitation forecasting, but still face challenges in representing extreme rainfall, handling imbalanced data, and ensuring physical consistency. The latest progress shows that future prediction systems will increasingly rely on the integration of multiple sources of data and hybrid physical-data-driven models to enhance their robustness and applicability. By compositing research covering multiple eras and paradigms, we not only depict the history of neural networks in precipitation prediction but also outline future directions in next generation forecasting systems.

---

### Encoder-Decoder Diffusion Language Models for Efficient Training and Inference

Authors: Marianne Arriola, Yair Schiff, Hao Phung, Aaron Gokaslan, Volodymyr Kuleshov
Published: 2025-10-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.22852v1

Discrete diffusion models enable parallel token sampling for faster inference than autoregressive approaches. However, prior diffusion models use a decoder-only architecture, which requires sampling algorithms that invoke the full network at every denoising step and incur high computational cost. Our key insight is that discrete diffusion models perform two types of computation: 1) representing clean tokens and 2) denoising corrupted tokens, which enables us to use separate modules for each task. We propose an encoder-decoder architecture to accelerate discrete diffusion inference, which relies on an encoder to represent clean tokens and a lightweight decoder to iteratively refine a noised sequence. We also show that this architecture enables faster training of block diffusion models, which partition sequences into blocks for better quality and are commonly used in diffusion language model inference. We introduce a framework for Efficient Encoder-Decoder Diffusion (E2D2), consisting of an architecture with specialized training and sampling algorithms, and we show that E2D2 achieves superior trade-offs between generation quality and inference throughput on summarization, translation, and mathematical reasoning tasks. We provide the code, model weights, and blog post on the project page: https://m-arriola.com/e2d2

---

### Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models

Authors: Lexiang Xiong, Chengyu Liu, Jingwen Ye, Yan Liu, Yuecong Xu
Published: 2025-10-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.22851v1

Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery, a novel training-free, zero-shot framework for concept erasure that operates directly on text embeddings before the diffusion process. It dynamically estimates the presence of target concepts in a prompt and performs a calibrated vector subtraction to neutralize their influence at the source, enhancing both erasure completeness and locality. The framework includes a Co-Occurrence Encoding module for robust multi-concept erasure and a visual feedback loop to address latent concept persistence. As a training-free method, Semantic Surgery adapts dynamically to each prompt, ensuring precise interventions. Extensive experiments on object, explicit content, artistic style, and multi-celebrity erasure tasks show our method significantly outperforms state-of-the-art approaches. We achieve superior completeness and robustness while preserving locality and image quality (e.g., 93.58 H-score in object erasure, reducing explicit content to just 1 instance, and 8.09 H_a in style erasure with no quality degradation). This robustness also allows our framework to function as a built-in threat detection system, offering a practical solution for safer text-to-image generation.

---

### Once Upon an Input: Reasoning via Per-Instance Program Synthesis

Authors: Adam Stein, Neelay Velingker, Mayur Naik, Eric Wong
Published: 2025-10-26
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.22849v1

Large language models (LLMs) excel at zero-shot inference but continue to struggle with complex, multi-step reasoning. Recent methods that augment LLMs with intermediate reasoning steps such as Chain of Thought (CoT) and Program of Thought (PoT) improve performance but often produce undesirable solutions, especially in algorithmic domains. We introduce Per-Instance Program Synthesis (PIPS), a method that generates and refines programs at the instance-level using structural feedback without relying on task-specific guidance or explicit test cases. To further improve performance, PIPS incorporates a confidence metric that dynamically chooses between direct inference and program synthesis on a per-instance basis. Experiments across three frontier LLMs and 30 benchmarks including all tasks of Big Bench Extra Hard (BBEH), visual question answering tasks, relational reasoning tasks, and mathematical reasoning tasks show that PIPS improves the absolute harmonic mean accuracy by up to 8.6% and 9.4% compared to PoT and CoT respectively, and reduces undesirable program generations by 65.1% on the algorithmic tasks compared to PoT with Gemini-2.0-Flash.

---

### Self-induced stochastic resonance: A physics-informed machine learning approach

Authors: Divyesh Savaliya, Marius E. Yamakou
Published: 2025-10-26
Categories: cs.LG, nlin.AO, stat.ML
arXiv: https://arxiv.org/abs/2510.22848v2

Self-induced stochastic resonance (SISR) is the emergence of coherent oscillations in slow-fast excitable systems driven solely by noise, without external periodic forcing or proximity to a bifurcation. This work presents a physics-informed machine learning framework for modeling and predicting SISR in the stochastic FitzHugh-Nagumo neuron. We embed the governing stochastic differential equations and SISR-asymptotic timescale-matching constraints directly into a Physics-Informed Neural Network (PINN) based on a Noise-Augmented State Predictor architecture. The composite loss integrates data fidelity, dynamical residuals, and barrier-based physical constraints derived from Kramers' escape theory. The trained PINN accurately predicts the dependence of spike-train coherence on noise intensity, excitability, and timescale separation, matching results from direct stochastic simulations with substantial improvements in accuracy and generalization compared with purely data-driven methods, while requiring significantly less computation. The framework provides a data-efficient and interpretable surrogate model for simulating and analyzing noise-induced coherence in multiscale stochastic systems.

---

### Leveraging Large Language Models to Identify Conversation Threads in Collaborative Learning

Authors: Prerna Ravi, Dong Won Lee, Beatriz Flamia, Jasmine David, Brandon Hanks, Cynthia Breazeal, Emma Anderson, Grace Lin
Published: 2025-10-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.22844v1

Understanding how ideas develop and flow in small-group conversations is critical for analyzing collaborative learning. A key structural feature of these interactions is threading, the way discourse talk naturally organizes into interwoven topical strands that evolve over time. While threading has been widely studied in asynchronous text settings, detecting threads in synchronous spoken dialogue remains challenging due to overlapping turns and implicit cues. At the same time, large language models (LLMs) show promise for automating discourse analysis but often struggle with long-context tasks that depend on tracing these conversational links. In this paper, we investigate whether explicit thread linkages can improve LLM-based coding of relational moves in group talk. We contribute a systematic guidebook for identifying threads in synchronous multi-party transcripts and benchmark different LLM prompting strategies for automated threading. We then test how threading influences performance on downstream coding of conversational analysis frameworks, that capture core collaborative actions such as agreeing, building, and eliciting. Our results show that providing clear conversational thread information improves LLM coding performance and underscores the heavy reliance of downstream analysis on well-structured dialogue. We also discuss practical trade-offs in time and cost, emphasizing where human-AI hybrid approaches can yield the best value. Together, this work advances methods for combining LLMs and robust conversational thread structures to make sense of complex, real-time group interactions.

---

### FastJAM: a Fast Joint Alignment Model for Images

Authors: Omri Hirsch, Ron Shapira Weber, Shira Ifergane, Oren Freifeld
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22842v2

Joint Alignment (JA) of images aims to align a collection of images into a unified coordinate frame, such that semantically-similar features appear at corresponding spatial locations. Most existing approaches often require long training times, large-capacity models, and extensive hyperparameter tuning. We introduce FastJAM, a rapid, graph-based method that drastically reduces the computational complexity of joint alignment tasks. FastJAM leverages pairwise matches computed by an off-the-shelf image matcher, together with a rapid nonparametric clustering, to construct a graph representing intra- and inter-image keypoint relations. A graph neural network propagates and aggregates these correspondences, efficiently predicting per-image homography parameters via image-level pooling. Utilizing an inverse-compositional loss, that eliminates the need for a regularization term over the predicted transformations (and thus also obviates the hyperparameter tuning associated with such terms), FastJAM performs image JA quickly and effectively. Experimental results on several benchmarks demonstrate that FastJAM achieves results better than existing modern JA methods in terms of alignment quality, while reducing computation time from hours or minutes to mere seconds. Our code is available at our project webpage, https://bgu-cs-vil.github.io/FastJAM/

---

### Lyapunov Function-guided Reinforcement Learning for Flight Control

Authors: Yifei Li, Erik-Jan van Kampen
Published: 2025-10-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.22840v1

A cascaded online learning flight control system has been developed and enhanced with respect to action smoothness. In this paper, we investigate the convergence performance of the control system, characterized by the increment of a Lyapunov function candidate. The derivation of this metric accounts for discretization errors and state prediction errors introduced by the incremental model. Comparative results are presented through flight control simulations.

---

### Graph Neural Network Assisted Genetic Algorithm for Structural Dynamic Response and Parameter Optimization

Authors: Sagnik Mukherjee, Indrajit Barua
Published: 2025-10-26
Categories: cs.NE, cs.CE
arXiv: https://arxiv.org/abs/2510.22839v3

The optimization of structural parameters, such as mass(m), stiffness(k), and damping coefficient(c), is critical for designing efficient, resilient, and stable structures. Conventional numerical approaches, including Finite Element Method (FEM) and Computational Fluid Dynamics (CFD) simulations, provide high-fidelity results but are computationally expensive for iterative optimization tasks, as each evaluation requires solving the governing equations for every parameter combination. This study proposes a hybrid data-driven framework that integrates a Graph Neural Network (GNN) surrogate model with a Genetic Algorithm (GA) optimizer to overcome these challenges. The GNN is trained to accurately learn the nonlinear mapping between structural parameters and dynamic displacement responses, enabling rapid predictions without repeatedly solving the system equations. A dataset of single-degree-of-freedom (SDOF) system responses is generated using the Newmark Beta method across diverse mass, stiffness, and damping configurations. The GA then searches for globally optimal parameter sets by minimizing predicted displacements and enhancing dynamic stability. Results demonstrate that the GNN and GA framework achieves strong convergence, robust generalization, and significantly reduced computational cost compared to conventional simulations. This approach highlights the effectiveness of combining machine learning surrogates with evolutionary optimization for automated and intelligent structural design.

---

### Semantic-Preserving Cross-Style Visual Reasoning for Robust Multi-Modal Understanding in Large Vision-Language Models

Authors: Aya Nakayama, Brian Wong, Yuji Nishimura, Kaito Tanaka
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22838v1

The "style trap" poses a significant challenge for Large Vision-Language Models (LVLMs), hindering robust semantic understanding across diverse visual styles, especially in in-context learning (ICL). Existing methods often fail to effectively decouple style from content, hindering generalization. To address this, we propose the Semantic-Preserving Cross-Style Visual Reasoner (SP-CSVR), a novel framework for stable semantic understanding and adaptive cross-style visual reasoning. SP-CSVR integrates a Cross-Style Feature Encoder (CSFE) for style-content disentanglement, a Semantic-Aligned In-Context Decoder (SAICD) for efficient few-shot style adaptation, and an Adaptive Semantic Consistency Module (ASCM) employing multi-task contrastive learning to enforce cross-style semantic invariance. Extensive experiments on a challenging multi-style dataset demonstrate SP-CSVR's state-of-the-art performance across visual captioning, visual question answering, and in-context style adaptation. Comprehensive evaluations, including ablation studies and generalization analysis, confirm SP-CSVR's efficacy in enhancing robustness, generalization, and efficiency across diverse visual styles.

---

### Rethinking the Text-Vision Reasoning Imbalance in MLLMs through the Lens of Training Recipes

Authors: Guanyu Yao, Qiucheng Wu, Yang Zhang, Zhaowen Wang, Handong Zhao, Shiyu Chang
Published: 2025-10-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.22836v2

Multimodal large language models (MLLMs) have demonstrated strong capabilities on vision-and-language tasks. However, recent findings reveal an imbalance in their reasoning capabilities across visual and textual modalities. Specifically, current MLLMs often over-rely on textual cues while under-attending to visual content, resulting in suboptimal performance on tasks that require genuine visual reasoning. We refer to this phenomenon as the \textit{modality gap}, defined as the performance disparity between text-centric and vision-centric inputs. In this paper, we analyze the modality gap through the lens of training recipes. We first show that existing training recipes tend to amplify this gap. Then, we systematically explore strategies to bridge it from two complementary perspectives: data and loss design. Our findings provide insights into developing training recipes that mitigate the modality gap and promote more balanced multimodal reasoning. Our code is publicly available at https://github.com/UCSB-NLP-Chang/Bridging-Modality-Gap.

---

### Clustering by Denoising: Latent plug-and-play diffusion for single-cell data

Authors: Dominik Meier, Shixing Yu, Sagnik Nandy, Promit Ghosal, Kyra Gan
Published: 2025-10-26
Categories: cs.LG, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2510.22835v3

Single-cell RNA sequencing (scRNA-seq) enables the study of cellular heterogeneity. Yet, clustering accuracy, and with it downstream analyses based on cell labels, remain challenging due to measurement noise and biological variability. In standard latent spaces (e.g., obtained through PCA), data from different cell types can be projected close together, making accurate clustering difficult. We introduce a latent plug-and-play diffusion framework that separates the observation and denoising space. This separation is operationalized through a novel Gibbs sampling procedure: the learned diffusion prior is applied in a low-dimensional latent space to perform denoising, while to steer this process, noise is reintroduced into the original high-dimensional observation space. This unique "input-space steering" ensures the denoising trajectory remains faithful to the original data structure. Our approach offers three key advantages: (1) adaptive noise handling via a tunable balance between prior and observed data; (2) uncertainty quantification through principled uncertainty estimates for downstream analysis; and (3) generalizable denoising by leveraging clean reference data to denoise noisier datasets, and via averaging, improve quality beyond the training set. We evaluate robustness on both synthetic and real single-cell genomics data. Our method improves clustering accuracy on synthetic data across varied noise levels and dataset shifts. On real-world single-cell data, our method demonstrates improved biological coherence in the resulting cell clusters, with cluster boundaries that better align with known cell type markers and developmental trajectories.

---

### Toward Agents That Reason About Their Computation

Authors: Adrian Orenstein, Jessica Jiajing Chen, Gwyneth Anne Delos Santos, Bayley Sapara, Michael Bowling
Published: 2025-10-26
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.22833v3

While reinforcement learning agents can achieve superhuman performance in many complex tasks, they typically do not become more computationally efficient as they improve. In contrast, humans gradually require less cognitive effort as they become more proficient at a task. If agents could reason about their compute as they learn, could they similarly reduce their computation footprint? If they could, we could have more energy efficient agents or free up compute cycles for other processes like planning. In this paper, we experiment with showing agents the cost of their computation and giving them the ability to control when they use compute. We conduct our experiments on the Arcade Learning Environment, and our results demonstrate that with the same training compute budget, agents that reason about their compute perform better on 75% of games. Furthermore, these agents use three times less compute on average. We analyze individual games and show where agents gain these efficiencies. An interactive version of this paper is available at https://adrianorenstein.com/paper/toward-compute.

---

### HRM-Agent: Training a recurrent reasoning model in dynamic environments using reinforcement learning

Authors: Long H Dang, David Rawlinson
Published: 2025-10-26
Categories: cs.AI, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.22832v1

The Hierarchical Reasoning Model (HRM) has impressive reasoning abilities given its small size, but has only been applied to supervised, static, fully-observable problems. One of HRM's strengths is its ability to adapt its computational effort to the difficulty of the problem. However, in its current form it cannot integrate and reuse computation from previous time-steps if the problem is dynamic, uncertain or partially observable, or be applied where the correct action is undefined, characteristics of many real-world problems. This paper presents HRM-Agent, a variant of HRM trained using only reinforcement learning. We show that HRM can learn to navigate to goals in dynamic and uncertain maze environments. Recent work suggests that HRM's reasoning abilities stem from its recurrent inference process. We explore the dynamics of the recurrent inference process and find evidence that it is successfully reusing computation from earlier environment time-steps.

---

### Exploration of Summarization by Generative Language Models for Automated Scoring of Long Essays

Authors: Haowei Hua, Hong Jiao, Xinyi Wang
Published: 2025-10-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.22830v4

BERT and its variants are extensively explored for automated scoring. However, a limit of 512 tokens for these encoder-based models showed the deficiency in automated scoring of long essays. Thus, this research explores generative language models for automated scoring of long essays via summarization and prompting. The results revealed great improvement of scoring accuracy with QWK increased from 0.822 to 0.8878 for the Learning Agency Lab Automated Essay Scoring 2.0 dataset.

---

### LLM-based Fusion of Multi-modal Features for Commercial Memorability Prediction

Authors: Aleksandar Pramov
Published: 2025-10-26
Categories: cs.CV, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2510.22829v1

This paper addresses the prediction of commercial (brand) memorability as part of "Subtask 2: Commercial/Ad Memorability" within the "Memorability: Predicting movie and commercial memorability" task at the MediaEval 2025 workshop competition. We propose a multimodal fusion system with a Gemma-3 LLM backbone that integrates pre-computed visual (ViT) and textual (E5) features by multi-modal projections. The model is adapted using Low-Rank Adaptation (LoRA). A heavily-tuned ensemble of gradient boosted trees serves as a baseline. A key contribution is the use of LLM-generated rationale prompts, grounded in expert-derived aspects of memorability, to guide the fusion model. The results demonstrate that the LLM-based system exhibits greater robustness and generalization performance on the final test set, compared to the baseline. The paper's codebase can be found at https://github.com/dsgt-arc/mediaeval-2025-memorability

---

### Efficiently Learning Synthetic Control Models for High-dimensional Disaggregated Data

Authors: Ye Shen, Rui Song, Alberto Abadie
Published: 2025-10-26
Categories: stat.ME, econ.TH, stat.ML
arXiv: https://arxiv.org/abs/2510.22828v1

The Synthetic Control method (SC) has become a valuable tool for estimating causal effects. Originally designed for single-treated unit scenarios, it has recently found applications in high-dimensional disaggregated settings with multiple treated units. However, challenges in practical implementation and computational efficiency arise in such scenarios. To tackle these challenges, we propose a novel approach that integrates the Multivariate Square-root Lasso method into the synthetic control framework. We rigorously establish the estimation error bounds for fitting the Synthetic Control weights using Multivariate Square-root Lasso, accommodating high-dimensionality and time series dependencies. Additionally, we quantify the estimation error for the Average Treatment Effect on the Treated (ATT). Through simulation studies, we demonstrate that our method offers superior computational efficiency without compromising estimation accuracy. We apply our method to assess the causal impact of COVID-19 Stay-at-Home Orders on the monthly unemployment rate in the United States at the county level.

---

### FairJudge: Abstention-Aware Multimodal Judges for Fairness and Alignment Evaluation in Text-to-Image Models

Authors: Zahraa Al Sahili, Maimuna Nowaz, Maryam Fetanat, Ioannis Patras, Matthew Purver
Published: 2025-10-26
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.22827v3

Evaluating text-to-image (T2I) systems requires judging not only whether an image matches a prompt, but also whether socially salient attributes are represented faithfully and without unsupported inference. Existing automated evaluators typically rely on face-centric recognizers or contrastive image--text similarity, which provide limited diagnostic feedback and often force predictions even when visual evidence is ambiguous or absent. For fairness-sensitive attributes such as religion and disability, where cues may be contextual, indirect, or intentionally unspecified, these evaluators can therefore miss failure modes that careful human reviewers would notice. We introduce \textsc{FairJudge}, an abstention-aware evaluation protocol that uses instruction-following multimodal LLMs as structured judges for social-attribute prediction, profession grounding, and prompt--image alignment. The protocol constrains outputs to closed label sets, requires visible-evidence rationales, supports an explicit \textsc{unspecified} decision when cues are insufficient, and maps rubric-based alignment judgments to $(-1,1)$. These constraints turn MLLM judging from open-ended assessment into a parseable, auditable evaluation procedure. Across four attribute-prediction benchmarks and three profession/alignment benchmarks, \textsc{FairJudge} outperforms or complements CLIP, DeepFace, VIEScore, and VQAScore. Ablations show that closed labels, abstention, and evidence reporting are central to reliability. We further introduce \textsc{DIVERSIFY} and \textsc{DIVERSIFY-Professions}, two context-rich resources for evaluating social representation and profession grounding beyond face-visible or iconic cues. We release code, prompts, datasets, parser logs, and per-image judge outputs to support reproducible auditing.

---

### Logical GANs: Adversarial Learning through Ehrenfeucht Fraisse Games

Authors: Mirco A. Mannucci
Published: 2025-10-26
Categories: cs.LG, cs.LO, math.LO
arXiv: https://arxiv.org/abs/2510.22824v1

GANs promise indistinguishability, logic explains it. We put the two on a budget: a discriminator that can only ``see'' up to a logical depth $k$, and a generator that must look correct to that bounded observer. \textbf{LOGAN} (LOGical GANs) casts the discriminator as a depth-$k$ Ehrenfeucht--Fraïssé (EF) \emph{Opponent} that searches for small, legible faults (odd cycles, nonplanar crossings, directed bridges), while the generator plays \emph{Builder}, producing samples that admit a $k$-round matching to a target theory $T$. We ship a minimal toolkit -- an EF-probe simulator and MSO-style graph checkers -- and four experiments including real neural GAN training with PyTorch. Beyond verification, we score samples with a \emph{logical loss} that mixes budgeted EF round-resilience with cheap certificate terms, enabling a practical curriculum on depth. Framework validation demonstrates $92\%$--$98\%$ property satisfaction via simulation (Exp.~3), while real neural GAN training achieves $5\%$--$14\%$ improvements on challenging properties and $98\%$ satisfaction on connectivity (matching simulation) through adversarial learning (Exp.~4). LOGAN is a compact, reproducible path toward logic-bounded generation with interpretable failures, proven effectiveness (both simulated and real training), and dials for control.

---

### Cross-Lingual Stability and Bias in Instruction-Tuned Language Models for Humanitarian NLP

Authors: Poli Nemkova, Amrit Adhikari, Matthew Pearson, Vamsi Krishna Sadu, Mark V. Albert
Published: 2025-10-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.22823v1

Humanitarian organizations face a critical choice: invest in costly commercial APIs or rely on free open-weight models for multilingual human rights monitoring. While commercial systems offer reliability, open-weight alternatives lack empirical validation -- especially for low-resource languages common in conflict zones. This paper presents the first systematic comparison of commercial and open-weight large language models (LLMs) for human-rights-violation detection across seven languages, quantifying the cost-reliability trade-off facing resource-constrained organizations. Across 78,000 multilingual inferences, we evaluate six models -- four instruction-aligned (Claude-Sonnet-4, DeepSeek-V3, Gemini-Flash-2.0, GPT-4.1-mini) and two open-weight (LLaMA-3-8B, Mistral-7B) -- using both standard classification metrics and new measures of cross-lingual reliability: Calibration Deviation (CD), Decision Bias (B), Language Robustness Score (LRS), and Language Stability Score (LSS). Results show that alignment, not scale, determines stability: aligned models maintain near-invariant accuracy and balanced calibration across typologically distant and low-resource languages (e.g., Lingala, Burmese), while open-weight models exhibit significant prompt-language sensitivity and calibration drift. These findings demonstrate that multilingual alignment enables language-agnostic reasoning and provide practical guidance for humanitarian organizations balancing budget constraints with reliability in multilingual deployment.

---

### Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits

Authors: Jingxin Zhan, Yuze Han, Zhihua Zhang
Published: 2025-10-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.22819v3

The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learner's actual decisions and describes the evolution of the learning process over time. However, in multi-armed bandits, most existing algorithmic analyses mainly focus on the order of regret, while the last-iterate (simple regret) convergence rate remains less explored---especially for the widely studied Follow-the-Regularized-Leader (FTRL) algorithms. Recently, FTRL with the $1/2$-Tsallis entropy regularizer $Ψ(p) = -4\sum_{i=1}^d \sqrt{p_i}$ (the $1/2$-Tsallis-INF algorithm, by arXiv:1807.07623) was shown to achieve the desirable Best-of-Both-Worlds (BOBW) guarantees and perform well in both adversarial and stochastic settings. Nevertheless, its last-iterate convergence rate has not yet been fully studied. This paper studies the $1/2$-Tsallis-INF algorithm in stochastic bandits and shows that its sampling simple regret decays at rate $\mathcal{O}(t^{-1})$, without requiring the optimal arm to be unique. Under a unique optimal arm, we further show that the expected Bregman divergence induced by $Ψ$ between the point mass on the optimal arm and the sampling distribution at iteration $t$ decays at rate $\mathcal{O}(t^{-1/2})$. Matching lower bounds under the same uniqueness condition show that both exponents of $t$ are tight.

---

### Air Quality Prediction Using LOESS-ARIMA and Multi-Scale CNN-BiLSTM with Residual-Gated Attention

Authors: Soham Pahari, Sandeep Chand Kumain
Published: 2025-10-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.22818v1

Air pollution remains a critical environmental and public health concern in Indian megacities such as Delhi, Kolkata, and Mumbai, where sudden spikes in pollutant levels challenge timely intervention. Accurate Air Quality Index (AQI) forecasting is difficult due to the coexistence of linear trends, seasonal variations, and volatile nonlinear patterns. This paper proposes a hybrid forecasting framework that integrates LOESS decomposition, ARIMA modeling, and a multi-scale CNN-BiLSTM network with a residual-gated attention mechanism. The LOESS step separates the AQI series into trend, seasonal, and residual components, with ARIMA modeling the smooth components and the proposed deep learning module capturing multi-scale volatility in the residuals. Model hyperparameters are tuned via the Unified Adaptive Multi-Stage Metaheuristic Optimizer (UAMMO), combining multiple optimization strategies for efficient convergence. Experiments on 2021-2023 AQI datasets from the Central Pollution Control Board show that the proposed method consistently outperforms statistical, deep learning, and hybrid baselines across PM2.5, O3, CO, and NOx in three major cities, achieving up to 5-8% lower MSE and higher R^2 scores (>0.94) for all pollutants. These results demonstrate the framework's robustness, sensitivity to sudden pollution events, and applicability to urban air quality management.

---

### Will Humanity Be Rendered Obsolete by AI?

Authors: Mohamed El Louadi, Emna Ben Romdhane
Published: 2025-10-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.22814v3

This article analyzes the existential risks artificial intelligence (AI) poses to humanity, tracing the trajectory from current AI to ultraintelligence. Drawing on Irving J. Good and Nick Bostrom's theoretical work, plus recent publications (AI 2027; If Anyone Builds It, Everyone Dies), it explores AGI and superintelligence. Considering machines' exponentially growing cognitive power and hypothetical IQs, it addresses the ethical and existential implications of an intelligence vastly exceeding humanity's, fundamentally alien. Human extinction may result not from malice, but from uncontrollable, indifferent cognitive superiority.

---

### Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks

Authors: Jingyuan Liu, Hao Qiu, Lin Yang, Mengfan Xu
Published: 2025-10-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.22811v1

We study the distributed multi-agent multi-armed bandit problem with heterogeneous rewards over random communication graphs. Uniquely, at each time step $t$ agents communicate over a time-varying random graph $G_t$ generated by applying the Erdős-Rényi model to a fixed connected base graph $G$ (for classical Erdős-Rényi graphs, $G$ is a complete graph), where each potential edge in $G$ is randomly and independently present with the link probability $p$. Notably, the resulting random graph is not necessarily connected at each time step. Each agent's arm rewards follow time-invariant distributions, and the reward distribution for the same arm may differ across agents. The goal is to minimize the cumulative expected regret relative to the global mean reward of each arm, defined as the average of that arm's mean rewards across all agents. To this end, we propose a fully distributed algorithm that integrates the arm elimination strategy with the random gossip algorithm. We theoretically show that the regret upper bound is of order $\log T$ and is highly interpretable, where $T$ is the time horizon. It includes the optimal centralized regret $O\left(\sum_{k: Δ_k>0} \frac{\log T}{Δ_k}\right)$ and an additional term $O\left(\frac{N^2 \log T}{p λ_{N-1}(Lap(G))} + \frac{KN^2 \log T}{p}\right)$ where $N$ and $K$ denote the total number of agents and arms, respectively. This term reflects the impact of $G$'s algebraic connectivity $λ_{N-1}(Lap(G))$ and the link probability $p$, and thus highlights a fundamental trade-off between communication efficiency and regret. As a by-product, we show a nearly optimal regret lower bound. Finally, our numerical experiments not only show the superiority of our algorithm over existing benchmarks, but also validate the theoretical regret scaling with problem complexity.

---