# Research Papers — 2025-10 · bundle page 161 of 217

> Full-text markdown of papers #8001–8050 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/161
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/160.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/162.md)

### Toward Reliable Clinical Coding with Language Models: Verification and Lightweight Adaptation

Authors: Zhangdie Yuan, Han-Chin Shing, Mitch Strong, Chaitanya Shivade
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07629v1

Accurate clinical coding is essential for healthcare documentation, billing, and decision-making. While prior work shows that off-the-shelf LLMs struggle with this task, evaluations based on exact match metrics often overlook errors where predicted codes are hierarchically close but incorrect. Our analysis reveals that such hierarchical misalignments account for a substantial portion of LLM failures. We show that lightweight interventions, including prompt engineering and small-scale fine-tuning, can improve accuracy without the computational overhead of search-based methods. To address hierarchically near-miss errors, we introduce clinical code verification as both a standalone task and a pipeline component. To mitigate the limitations in existing datasets, such as incomplete evidence and inpatient bias in MIMIC, we release an expert double-annotated benchmark of outpatient clinical notes with ICD-10 codes. Our results highlight verification as an effective and reliable step toward improving LLM-based medical coding.

---

### LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics

Authors: Chongyu Fan, Changsheng Wang, Yancheng Huang, Soumyadeep Pal, Sijia Liu
Published: 2025-10-08
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.07626v1

Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright) while preserving useful model capabilities. Despite rapid progress over the past two years, research in LLM unlearning remains fragmented, with limited clarity on what constitutes effective unlearning and how it should be rigorously evaluated. In this work, we present a principled taxonomy of twelve recent stateful unlearning methods, grouped into three methodological families: divergence-driven optimization, representation misalignment, and rejection-based targeted unlearning. Building on this taxonomy, we revisit the evaluation of unlearning effectiveness (UE), utility retention (UT), and robustness (Rob), focusing on the WMDP benchmark. Our analysis shows that current evaluations, dominated by multiple-choice question (MCQ) accuracy, offer only a narrow perspective, often overstating success while overlooking the model's actual generation behavior. To address this gap, we introduce open question-answering (Open-QA) metrics that better capture generative performance and reveal the inherent UE-UT tradeoff across method families. Furthermore, we demonstrate that robustness requires finer-grained analysis: for example, vulnerabilities differ substantially between in-domain relearning and out-of-domain fine-tuning, even though both fall under model-level attacks. Through this study, we hope to deliver a full-stack revisit of LLM unlearning and actionable guidance for designing and evaluating future methods.

---

### From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation

Authors: Abdelhakim Benechehab, Gabriel Singer, Corentin Léger, Youssef Attia El Hili, Giuseppe Paolo, Albert Thomas, Maurizio Filippone, Balázs Kégl
Published: 2025-10-08
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.07624v3

Generative models form the backbone of modern machine learning, underpinning state-of-the-art systems in text, vision, and multimodal applications. While Maximum Likelihood Estimation has traditionally served as the dominant training paradigm, recent work have highlighted its limitations, particularly in generalization and susceptibility to catastrophic forgetting compared to Reinforcement Learning techniques, such as Policy Gradient methods. However, these approaches depend on explicit reward signals, which are often unavailable in practice, leaving open the fundamental problem of how to align generative models when only high-quality datasets are accessible. In this work, we address this challenge via a Bilevel Optimization framework, where the reward function is treated as the optimization variable of an outer-level problem, while a policy gradient objective defines the inner-level. We then conduct a theoretical analysis of this optimization problem in a tractable setting and extract insights that, as we demonstrate, generalize to applications such as tabular classification and model-based reinforcement learning. We release the code at https://github.com/abenechehab/nll_to_po .

---

### A Case for Leveraging Generative AI to Expand and Enhance Training in the Provision of Mental Health Services

Authors: Hannah R. Lawrence, Shannon Wiltsey Stirman, Samuel Dorison, Taedong Yun, Megan Jones Bell
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07623v1

Generative artificial intelligence (Generative AI) is transforming healthcare. With this evolution comes optimism regarding the impact it will have on mental health, as well as concern regarding the risks that come with generative AI operating in the mental health domain. Much of the investment in, and academic and public discourse about, AI-powered solutions for mental health has focused on therapist chatbots. Despite the common assumption that chatbots will be the most impactful application of GenAI to mental health, we make the case here for a lower-risk, high impact use case: leveraging generative AI to enhance and scale training in mental health service provision. We highlight key benefits of using generative AI to help train people to provide mental health services and present a real-world case study in which generative AI improved the training of veterans to support one another's mental health. With numerous potential applications of generative AI in mental health, we illustrate why we should invest in using generative AI to support training people in mental health service provision.

---

### Retentive Relevance: Capturing Long-Term User Value in Recommendation Systems

Authors: Saeideh Bakhshi, Phuong Mai Nguyen, Robert Schiller, Tiantian Xu, Pawan Kodandapani, Andrew Levine, Cayman Simpson, Qifan Wang
Published: 2025-10-08
Categories: cs.IR, cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2510.07621v1

Recommendation systems have traditionally relied on short-term engagement signals, such as clicks and likes, to personalize content. However, these signals are often noisy, sparse, and insufficient for capturing long-term user satisfaction and retention. We introduce Retentive Relevance, a novel content-level survey-based feedback measure that directly assesses users' intent to return to the platform for similar content. Unlike other survey measures that focus on immediate satisfaction, Retentive Relevance targets forward-looking behavioral intentions, capturing longer term user intentions and providing a stronger predictor of retention. We validate Retentive Relevance using psychometric methods, establishing its convergent, discriminant, and behavioral validity. Through large-scale offline modeling, we show that Retentive Relevance significantly outperforms both engagement signals and other survey measures in predicting next-day retention, especially for users with limited historical engagement. We develop a production-ready proxy model that integrates Retentive Relevance into the final stage of a multi-stage ranking system on a social media platform. Calibrated score adjustments based on this model yield substantial improvements in engagement, and retention, while reducing exposure to low-quality content, as demonstrated by large-scale A/B experiments. This work provides the first empirically validated framework linking content-level user perceptions to retention outcomes in production systems. We offer a scalable, user-centered solution that advances both platform growth and user experience. Our work has broad implications for responsible AI development.

---

### DGTEN: A Robust Deep Gaussian based Graph Neural Network for Dynamic Trust Evaluation with Uncertainty-Quantification Support

Authors: Muhammad Usman, Yugyung Lee
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.07620v2

Dynamic trust evaluation in large, rapidly evolving graphs demands models that capture changing relationships, express calibrated confidence, and resist adversarial manipulation. DGTEN (Deep Gaussian-Based Trust Evaluation Network) introduces a unified graph-based framework that does all three by combining uncertainty-aware message passing, expressive temporal modeling, and built-in defenses against trust-targeted attacks. It represents nodes and edges as Gaussian distributions so that both semantic signals and epistemic uncertainty propagate through the graph neural network, enabling risk-aware trust decisions rather than overconfident guesses. To track how trust evolves, it layers hybrid absolute-Gaussian-hourglass positional encoding with Kolmogorov-Arnold network-based unbiased multi-head attention, then applies an ordinary differential equation-based residual learning module to jointly model abrupt shifts and smooth trends. Robust adaptive ensemble coefficient analysis prunes or down-weights suspicious interactions using complementary cosine and Jaccard similarity, curbing reputation laundering, sabotage, and on-off attacks. On two signed Bitcoin trust networks, DGTEN delivers standout gains where it matters most: in single-timeslot prediction on Bitcoin-OTC, it improves MCC by +12.34% over the best dynamic baseline; in the cold-start scenario on Bitcoin-Alpha, it achieves a +25.00% MCC improvement, the largest across all tasks and datasets; while under adversarial on-off attacks, it surpasses the baseline by up to +10.23% MCC. These results endorse the unified DGTEN framework.

---

### Traceability and Accountability in Role-Specialized Multi-Agent LLM Pipelines

Authors: Amine Barrak
Published: 2025-10-08
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2510.07614v1

Sequential multi-agent systems built with large language models (LLMs) can automate complex software tasks, but they are hard to trust because errors quietly pass from one stage to the next. We study a traceable and accountable pipeline, meaning a system with clear roles, structured handoffs, and saved records that let us trace who did what at each step and assign blame when things go wrong. Our setting is a Planner -> Executor -> Critic pipeline. We evaluate eight configurations of three state-of-the-art LLMs on three benchmarks and analyze where errors start, how they spread, and how they can be fixed. Our results show: (1) adding a structured, accountable handoff between agents markedly improves accuracy and prevents the failures common in simple pipelines; (2) models have clear role-specific strengths and risks (e.g., steady planning vs. high-variance critiquing), which we quantify with repair and harm rates; and (3) accuracy-cost-latency trade-offs are task-dependent, with heterogeneous pipelines often the most efficient. Overall, we provide a practical, data-driven method for designing, tracing, and debugging reliable, predictable, and accountable multi-agent systems.

---

### Vocabulary embeddings organize linguistic structure early in language model training

Authors: Isabel Papadimitriou, Jacob Prince
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.07613v1

Large language models (LLMs) work by manipulating the geometry of input embedding vectors over multiple layers. Here, we ask: how are the input vocabulary representations of language models structured, and how and when does this structure evolve over training? To answer this question, we use representational similarity analysis, running a suite of experiments that correlate the geometric structure of the input embeddings and output embeddings of two open-source models (Pythia 12B and OLMo 7B) with semantic, syntactic, and frequency-based metrics over the course of training. Our key findings are as follows: 1) During training, the vocabulary embedding geometry quickly converges to high correlations with a suite of semantic and syntactic features; 2) Embeddings of high-frequency and function words (e.g., "the," "of") converge to their final vectors faster than lexical and low-frequency words, which retain some alignment with the bias in their random initializations. These findings help map the dynamic trajectory by which input embeddings organize around linguistic structure, revealing distinct roles for word frequency and function. Our findings motivate a deeper study of how the evolution of vocabulary geometry may facilitate specific capability gains during model training.

---

### Inspection Planning Primitives with Implicit Models

Authors: Jingyang You, Hanna Kurniawati, Lashika Medagoda
Published: 2025-10-08
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.07611v1

The aging and increasing complexity of infrastructures make efficient inspection planning more critical in ensuring safety. Thanks to sampling-based motion planning, many inspection planners are fast. However, they often require huge memory. This is particularly true when the structure under inspection is large and complex, consisting of many struts and pillars of various geometry and sizes. Such structures can be represented efficiently using implicit models, such as neural Signed Distance Functions (SDFs). However, most primitive computations used in sampling-based inspection planner have been designed to work efficiently with explicit environment models, which in turn requires the planner to use explicit environment models or performs frequent transformations between implicit and explicit environment models during planning. This paper proposes a set of primitive computations, called Inspection Planning Primitives with Implicit Models (IPIM), that enable sampling-based inspection planners to entirely use neural SDFs representation during planning. Evaluation on three scenarios, including inspection of a complex real-world structure with over 92M triangular mesh faces, indicates that even a rudimentary sampling-based planner with IPIM can generate inspection trajectories of similar quality to those generated by the state-of-the-art planner, while using up to 70x less memory than the state-of-the-art inspection planner.

---

### Transformer-Based Indirect Structural Health Monitoring of Rail Infrastructure with Attention-Driven Detection and Localization of Transient Defects

Authors: Sizhe Ma, Katherine A. Flanigan, Mario Bergés, James D. Brooks
Published: 2025-10-08
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2510.07606v1

Indirect structural health monitoring (iSHM) for broken rail detection using onboard sensors presents a cost-effective paradigm for railway track assessment, yet reliably detecting small, transient anomalies (2-10 cm) remains a significant challenge due to complex vehicle dynamics, signal noise, and the scarcity of labeled data limiting supervised approaches. This study addresses these issues through unsupervised deep learning. We introduce an incremental synthetic data benchmark designed to systematically evaluate model robustness against progressively complex challenges like speed variations, multi-channel inputs, and realistic noise patterns encountered in iSHM. Using this benchmark, we evaluate several established unsupervised models alongside our proposed Attention-Focused Transformer. Our model employs a self-attention mechanism, trained via reconstruction but innovatively deriving anomaly scores primarily from deviations in learned attention weights, aiming for both effectiveness and computational efficiency. Benchmarking results reveal that while transformer-based models generally outperform others, all tested models exhibit significant vulnerability to high-frequency localized noise, identifying this as a critical bottleneck for practical deployment. Notably, our proposed model achieves accuracy comparable to the state-of-the-art solution while demonstrating better inference speed. This highlights the crucial need for enhanced noise robustness in future iSHM models and positions our more efficient attention-based approach as a promising foundation for developing practical onboard anomaly detection systems.

---

### Quick-CapsNet (QCN): A fast alternative to Capsule Networks

Authors: Pouya Shiri, Ramin Sharifi, Amirali Baniasadi
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07600v1

The basic computational unit in Capsule Network (CapsNet) is a capsule (vs. neurons in Convolutional Neural Networks (CNNs)). A capsule is a set of neurons, which form a vector. CapsNet is used for supervised classification of data and has achieved state-of-the-art accuracy on MNIST digit recognition dataset, outperforming conventional CNNs in detecting overlapping digits. Moreover, CapsNet shows higher robustness towards affine transformation when compared to CNNs for MNIST datasets. One of the drawbacks of CapsNet, however, is slow training and testing. This can be a bottleneck for applications that require a fast network, especially during inference. In this work, we introduce Quick-CapsNet (QCN) as a fast alternative to CapsNet, which can be a starting point to develop CapsNet for fast real-time applications. QCN builds on producing a fewer number of capsules, which results in a faster network. QCN achieves this at the cost of marginal loss in accuracy. Inference is 5x faster on MNIST, F-MNIST, SVHN and Cifar-10 datasets. We also further enhanced QCN by employing a more powerful decoder instead of the default decoder to further improve QCN.

---

### Locality-Sensitive Hashing-Based Efficient Point Transformer for Charged Particle Reconstruction

Authors: Shitij Govil, Jack P. Rodgers, Yuan-Tang Chou, Siqi Miao, Amit Saha, Advaith Anand, Kilian Lieret, Gage DeZoort, Mia Liu, Javier Duarte, Pan Li, Shih-Chieh Hsu
Published: 2025-10-08
Categories: hep-ex, cs.LG
arXiv: https://arxiv.org/abs/2510.07594v2

Charged particle track reconstruction is a foundational task in collider experiments and the main computational bottleneck in particle reconstruction. Graph neural networks (GNNs) have shown strong performance for this problem, but costly graph construction, irregular computations, and random memory access patterns substantially limit their throughput. The recently proposed Hashing-based Efficient Point Transformer (HEPT) offers a theoretically guaranteed near-linear complexity for large point cloud processing via locality-sensitive hashing (LSH) in attention computations; however, its evaluations have largely focused on embedding quality, and the object condensation pipeline on which HEPT relies requires a post-hoc clustering step (e.g., DBScan) that can dominate runtime. In this work, we make two contributions. First, we present a unified, fair evaluation of physics tracking performance for HEPT and a representative GNN-based pipeline under the same dataset and metrics. Second, we introduce HEPTv2 by extending HEPT with a lightweight decoder that eliminates the clustering stage and directly predicts track assignments. This modification preserves HEPT's regular, hardware-friendly computations while enabling ultra-fast end-to-end inference. On the TrackML dataset, optimized HEPTv2 achieves approximately 28 ms per event on an A100 while maintaining competitive tracking efficiency. These results position HEPTv2 as a practical, scalable alternative to GNN-based pipelines for fast tracking.

---

### AgentAsk: Multi-Agent Systems Need to Ask

Authors: Bohan Lin, Kuo Yang, Zelin Tan, Yingchuan Lai, Chen Zhang, Guibin Zhang, Xinlei Yu, Miao Yu, Xu Wang, Yudong Zhang, Yang Wang
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07593v2

Multi-agent systems (MAS) built on large language models promise improved problem-solving through collaboration, yet they often fail to consistently outperform strong single-agent baselines due to error propagation at inter-agent message handoffs.In this work, we conduct a systematic empirical analysis of such failures and introduce an edge-level error taxonomy that identifies four dominant error types: Data Gap, Signal Corruption, Referential Drift, and Capability Gap, as primary sources of failure in multi-agent interactions. Building on this taxonomy, we propose AgentAsk, a lightweight clarification module designed to intervene at the edge level in MAS to prevent cascading errors. The module operates by strategically applying minimal clarifications at critical points within the system, improving the accuracy and efficiency of the overall task. AgentAsk is trained to balance the trade-offs between clarification cost, latency, and accuracy, while it is also architecture-agnostic and can be easily integrated into existing systems. Evaluated across five benchmarks, AgentAsk consistently improves accuracy by up to 4.69%, while keeping latency and extra costs below 10% compared to baseline MAS, showcasing its high efficiency and minimal overhead.

---

### Creating ConLangs to Probe the Metalinguistic Grammatical Knowledge of LLMs

Authors: Chihiro Taguchi, Richard Sproat
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07591v3

We present a system that uses LLMs as a tool in the development of Constructed Languages -- ConLangs, which we call IASC (Interactive Agentic System for ConLangs). The system is modular in that it creates each of the components -- phonology, morphology and syntax, lexicon, orthography, and grammatical handbook, using module-specific sets of prompts. The approach is agentic in that various modules allow for refining the output given automatically-generated commentary on a previous step. Our main goals are twofold. First, we aim to provide tools that facilitate an engaging and enjoyable experience in creating artificially constructed languages. Second, the focus of this paper is on using our ConLang framework as a novel way to explore what LLMs 'know' about language -- not what they know about any particular language or encyclopedic facts, but how much they know about and understand language and linguistic concepts. In the experiments, we particularly focus on the morphosyntax module and show that there is a fairly wide gulf in capabilities both among different LLMs and among different linguistic specifications, with it being notably easier for systems to deal with more typologically common patterns than rarer ones. All code is released.

---

### Transferable Generative Models Bridge Femtosecond to Nanosecond Time-Step Molecular Dynamics

Authors: Juan Viguera Diez, Mathias Schreiner, Simon Olsson
Published: 2025-10-08
Categories: physics.chem-ph, stat.ML
arXiv: https://arxiv.org/abs/2510.07589v2

Understanding molecular structure, dynamics, and reactivity requires bridging processes that occur across widely separated time scales. Conventional molecular dynamics simulations provide atomistic resolution, but their femtosecond time steps limit access to the slow conformational changes and relaxation processes that govern chemical function. Here, we introduce a deep generative modeling framework that accelerates sampling of molecular dynamics by four orders of magnitude while retaining physical realism. Applied to small organic molecules and peptides, the approach enables quantitative characterization of equilibrium ensembles and dynamical relaxation processes that were previously only accessible by costly brute-force simulation. Importantly, the method generalizes across chemical composition and system size, extrapolating to peptides larger than those used for training, and captures chemically meaningful transitions on extended time scales. By expanding the accessible range of molecular motions without sacrificing atomistic detail, this approach opens new opportunities for probing conformational landscapes, thermodynamics, and kinetics in systems central to chemistry and biophysics.

---

### TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs

Authors: Jacob Chmura, Shenyang Huang, Tran Gia Bao Ngo, Ali Parviz, Farimah Poursafaei, Jure Leskovec, Michael Bronstein, Guillaume Rabusseau, Matthias Fey, Reihaneh Rabbany
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.07586v1

Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like PyTorch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks comparable infrastructure. Existing TG libraries are often tailored to specific architectures, hindering support for diverse models in this rapidly evolving field. Additionally, the divide between continuous- and discrete-time dynamic graph methods (CTDG and DTDG) limits direct comparisons and idea transfer. To address these gaps, we introduce Temporal Graph Modelling (TGM), a research-oriented library for ML on temporal graphs, the first to unify CTDG and DTDG approaches. TGM offers first-class support for dynamic node features, time-granularity conversions, and native handling of link-, node-, and graph-level tasks. Empirically, TGM achieves an average 7.8x speedup across multiple models, datasets, and tasks compared to the widely used DyGLib, and an average 175x speedup on graph discretization relative to available implementations. Beyond efficiency, we show in our experiments how TGM unlocks entirely new research possibilities by enabling dynamic graph property prediction and time-driven training paradigms, opening the door to questions previously impractical to study. TGM is available at https://github.com/tgm-team/tgm

---

### Expanding the Action Space of LLMs to Reason Beyond Language

Authors: Zhongqi Yue, Weishi Wang, Yundaichuan Zhan, Juncheng Li, Daniel Dahlmeier, Fredrik D. Johansson
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07581v2

Large Language Models (LLMs) are powerful reasoners in natural language, but their actions are typically confined to outputting vocabulary tokens. As a result, interactions with external environments -- such as symbolic operators or simulators -- must be expressed through text in predefined formats, parsed, and routed to external interfaces. This overloads the model's language with both reasoning and control duties, and requires a hand-crafted parser, external to the LLM. To address this, we decouple environment interactions from language by internalizing them in an Expanded Action space (ExpA), beyond the vocabulary. The model starts reasoning in the default language environment, but may trigger routing actions and switch to an external environment at any time. From there, the model can only invoke environment-specific actions, receive feedback from the environment, and potentially route back to language as a result. To promote effective exploration of the expanded action space and new environments, we introduce ExpA Reinforcement Learning (EARL) with counterfactual policy optimization. On tasks requiring multi-turn interactions and contingent planning, EARL outperforms strong baselines with vocabulary-constrained actions. It performs robustly across calculator-based multi-task learning and, in the partially observed sorting problem, achieves perfect Sort-4 accuracy while self-discovering an efficient algorithm competitive with classical designs.

---

### MaizeStandCounting (MaSC): Automated and Accurate Maize Stand Counting from UAV Imagery Using Image Processing and Deep Learning

Authors: Dewi Endah Kharismawati, Toni Kazic
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07580v1

Accurate maize stand counts are essential for crop management and research, informing yield prediction, planting density optimization, and early detection of germination issues. Manual counting is labor-intensive, slow, and error-prone, especially across large or variable fields. We present MaizeStandCounting (MaSC), a robust algorithm for automated maize seedling stand counting from RGB imagery captured by low-cost UAVs and processed on affordable hardware. MaSC operates in two modes: (1) mosaic images divided into patches, and (2) raw video frames aligned using homography matrices. Both modes use a lightweight YOLOv9 model trained to detect maize seedlings from V2-V10 growth stages. MaSC distinguishes maize from weeds and other vegetation, then performs row and range segmentation based on the spatial distribution of detections to produce precise row-wise stand counts. Evaluation against in-field manual counts from our 2024 summer nursery showed strong agreement with ground truth (R^2= 0.616 for mosaics, R^2 = 0.906 for raw frames). MaSC processed 83 full-resolution frames in 60.63 s, including inference and post-processing, highlighting its potential for real-time operation. These results demonstrate MaSC's effectiveness as a scalable, low-cost, and accurate tool for automated maize stand counting in both research and production environments.

---

### Linguistic Patterns in Pandemic-Related Content: A Comparative Analysis of COVID-19, Constraint, and Monkeypox Datasets

Authors: Mkululi Sikosana, Sean Maudsley-Barton, Oluwaseun Ajao
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.07579v1

This study conducts a computational linguistic analysis of pandemic-related online discourse to examine how language distinguishes health misinformation from factual communication. Drawing on three corpora: COVID-19 false narratives (n = 7588), general COVID-19 content (n = 10700), and Monkeypox-related posts (n = 5787), we identify significant differences in readability, rhetorical markers, and persuasive language use. COVID-19 misinformation exhibited markedly lower readability scores and contained over twice the frequency of fear-related or persuasive terms compared to the other datasets. It also showed minimal use of exclamation marks, contrasting with the more emotive style of Monkeypox content. These patterns suggest that misinformation employs a deliberately complex rhetorical style embedded with emotional cues, a combination that may enhance its perceived credibility. Our findings contribute to the growing body of work on digital health misinformation by highlighting linguistic indicators that may aid detection efforts. They also inform public health messaging strategies and theoretical models of crisis communication in networked media environments. At the same time, the study acknowledges limitations, including reliance on traditional readability indices, use of a deliberately narrow persuasive lexicon, and reliance on static aggregate analysis. Future research should therefore incorporate longitudinal designs, broader emotion lexicons, and platform-sensitive approaches to strengthen robustness.

---

### Accuracy, Memory Efficiency and Generalization: A Comparative Study on Liquid Neural Networks and Recurrent Neural Networks

Authors: Shilong Zong, Alex Bierly, Almuatazbellah Boker, Hoda Eldardiry
Published: 2025-10-08
Categories: cs.LG, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2510.07578v1

This review aims to conduct a comparative analysis of liquid neural networks (LNNs) and traditional recurrent neural networks (RNNs) and their variants, such as long short-term memory networks (LSTMs) and gated recurrent units (GRUs). The core dimensions of the analysis include model accuracy, memory efficiency, and generalization ability. By systematically reviewing existing research, this paper explores the basic principles, mathematical models, key characteristics, and inherent challenges of these neural network architectures in processing sequential data. Research findings reveal that LNN, as an emerging, biologically inspired, continuous-time dynamic neural network, demonstrates significant potential in handling noisy, non-stationary data, and achieving out-of-distribution (OOD) generalization. Additionally, some LNN variants outperform traditional RNN in terms of parameter efficiency and computational speed. However, RNN remains a cornerstone in sequence modeling due to its mature ecosystem and successful applications across various tasks. This review identifies the commonalities and differences between LNNs and RNNs, summarizes their respective shortcomings and challenges, and points out valuable directions for future research, particularly emphasizing the importance of improving the scalability of LNNs to promote their application in broader and more complex scenarios.

---

### Benchmarking is Broken -- Don't Let AI be its Own Judge

Authors: Zerui Cheng, Stella Wohnig, Ruchika Gupta, Samiul Alam, Tassallah Abdullahi, João Alves Ribeiro, Christian Nielsen-Garcia, Saif Mir, Siran Li, Jason Orender, Seyed Ali Bahrainian, Daniel Kirste et al.
Published: 2025-10-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.07575v2

The meteoric rise of AI, with its rapidly expanding market capitalization, presents both transformative opportunities and critical challenges. Chief among these is the urgent need for a new, unified paradigm for trustworthy evaluation, as current benchmarks increasingly reveal critical vulnerabilities. Issues like data contamination and selective reporting by model developers fuel hype, while inadequate data quality control can lead to biased evaluations that, even if unintentionally, may favor specific approaches. As a flood of participants enters the AI space, this "Wild West" of assessment makes distinguishing genuine progress from exaggerated claims exceptionally difficult. Such ambiguity blurs scientific signals and erodes public confidence, much as unchecked claims would destabilize financial markets reliant on credible oversight from agencies like Moody's. In high-stakes human examinations (e.g., SAT, GRE), substantial effort is devoted to ensuring fairness and credibility; why settle for less in evaluating AI, especially given its profound societal impact? This position paper argues that the current laissez-faire approach is unsustainable. We contend that true, sustainable AI advancement demands a paradigm shift: a unified, live, and quality-controlled benchmarking framework robust by construction, not by mere courtesy and goodwill. To this end, we dissect the systemic flaws undermining today's AI evaluation, distill the essential requirements for a new generation of assessments, and introduce PeerBench (with its prototype implementation at https://www.peerbench.ai/), a community-governed, proctored evaluation blueprint that embodies this paradigm through sealed execution, item banking with rolling renewal, and delayed transparency. Our goal is to pave the way for evaluations that can restore integrity and deliver genuinely trustworthy measures of AI progress.

---

### Symbolic-Diffusion: Deep Learning Based Symbolic Regression with D3PM Discrete Token Diffusion

Authors: Ryan T. Tymkow, Benjamin D. Schnapp, Mojtaba Valipour, Ali Ghodshi
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07570v1

Symbolic regression refers to the task of finding a closed-form mathematical expression to fit a set of data points. Genetic programming based techniques are the most common algorithms used to tackle this problem, but recently, neural-network based approaches have gained popularity. Most of the leading neural-network based models used for symbolic regression utilize transformer-based autoregressive models to generate an equation conditioned on encoded input points. However, autoregressive generation is limited to generating tokens left-to-right, and future generated tokens are conditioned only on previously generated tokens. Motivated by the desire to generate all tokens simultaneously to produce improved closed-form equations, we propose Symbolic Diffusion, a D3PM based discrete state-space diffusion model which simultaneously generates all tokens of the equation at once using discrete token diffusion. Using the bivariate dataset developed for SymbolicGPT, we compared our diffusion-based generation approach to an autoregressive model based on SymbolicGPT, using equivalent encoder and transformer architectures. We demonstrate that our novel approach of using diffusion-based generation for symbolic regression can offer comparable and, by some metrics, improved performance over autoregressive generation in models using similar underlying architectures, opening new research opportunities in neural-network based symbolic regression.

---

### Automated Machine Learning for Unsupervised Tabular Tasks

Authors: Prabhant Singh, Pieter Gijsbers, Elif Ceren Gok Yildirim, Murat Onur Yildirim, Joaquin Vanschoren
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07569v2

In this work, we present LOTUS (Learning to Learn with Optimal Transport for Unsupervised Scenarios), a simple yet effective method to perform model selection for multiple unsupervised machine learning(ML) tasks such as outlier detection and clustering. Our intuition behind this work is that a machine learning pipeline will perform well in a new dataset if it previously worked well on datasets with a similar underlying data distribution. We use Optimal Transport distances to find this similarity between unlabeled tabular datasets and recommend machine learning pipelines with one unified single method on two downstream unsupervised tasks: outlier detection and clustering. We present the effectiveness of our approach with experiments against strong baselines and show that LOTUS is a very promising first step toward model selection for multiple unsupervised ML tasks.

---

### Cross-Modal Attention Guided Unlearning in Vision-Language Models

Authors: Karuna Bhaila, Aneesh Komanduri, Minh-Hao Van, Xintao Wu
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07567v1

Vision-Language Models (VLMs) have demonstrated immense capabilities in multi-modal understanding and inference tasks such as Visual Question Answering (VQA), which requires models to infer outputs based on visual and textual context simultaneously. Such inference abilities of large-scale pretrained models are often attributed to the massive scale of pre-training data collected across several domains. However, the models may memorize private and/or sensitive information during training and regurgitate it in inference. Recently, machine unlearning has been leveraged to address the leakage of private data in LLMs. VLMs add a layer of complexity to this process, as the visual context in the query may also contain sensitive information in addition to the text. To address this issue, we explore unlearning for vision-language models, specifically for the VQA task. We explore the role of visual tokens for output generation in VLMs using cross-modal attention and utilize it to formulate Cross-Modal Attention Guided Unlearning (CAGUL), a lightweight and efficient VLM unlearning framework. In contrast to computationally expensive model finetuning methods, CAGUL utilizes external modules to encode unlearning information in visual tokens of low importance for relevant queries. We find that the transformed visual tokens not only prevent leakage but also retain reference model behavior. Experimental results show that our method performs better or on par with finetuning-based baselines without altering the pre-trained model parameters or incurring retraining costs, making it a practical and effective unlearning solution for VLMs.

---

### Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER

Authors: Junyi Zhu, Savas Ozkan, Andrea Maracani, Sinan Mutlu, Cho Jung Min, Mete Ozay
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.07566v1

Deploying natural language processing (NLP) models on mobile platforms requires models that can adapt across diverse applications while remaining efficient in memory and computation. We investigate pre-finetuning strategies to enhance the adaptability of lightweight BERT-like encoders for two fundamental NLP task families: named entity recognition (NER) and text classification. While pre-finetuning improves downstream performance for each task family individually, we find that naïve multi-task pre-finetuning introduces conflicting optimization signals that degrade overall performance. To address this, we propose a simple yet effective multi-task pre-finetuning framework based on task-primary LoRA modules, which enables a single shared encoder backbone with modular adapters. Our approach achieves performance comparable to individual pre-finetuning while meeting practical deployment constraint. Experiments on 21 downstream tasks show average improvements of +0.8% for NER and +8.8% for text classification, demonstrating the effectiveness of our method for versatile mobile NLP applications.

---

### EBGAN-MDN: An Energy-Based Adversarial Framework for Multi-Modal Behavior Cloning

Authors: Yixiao Li, Julia Barth, Thomas Kiefer, Ahmad Fraij
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07562v1

Multi-modal behavior cloning faces significant challenges due to mode averaging and mode collapse, where traditional models fail to capture diverse input-output mappings. This problem is critical in applications like robotics, where modeling multiple valid actions ensures both performance and safety. We propose EBGAN-MDN, a framework that integrates energy-based models, Mixture Density Networks (MDNs), and adversarial training. By leveraging a modified InfoNCE loss and an energy-enforced MDN loss, EBGAN-MDN effectively addresses these challenges. Experiments on synthetic and robotic benchmarks demonstrate superior performance, establishing EBGAN-MDN as a effective and efficient solution for multi-modal learning tasks.

---

### Investigating Thematic Patterns and User Preferences in LLM Interactions using BERTopic

Authors: Abhay Bhandarkar, Gaurav Mishra, Khushi Juchani, Harsh Singhal
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.CY, cs.HC
arXiv: https://arxiv.org/abs/2510.07557v1

This study applies BERTopic, a transformer-based topic modeling technique, to the lmsys-chat-1m dataset, a multilingual conversational corpus built from head-to-head evaluations of large language models (LLMs). Each user prompt is paired with two anonymized LLM responses and a human preference label, used to assess user evaluation of competing model outputs. The main objective is uncovering thematic patterns in these conversations and examining their relation to user preferences, particularly if certain LLMs are consistently preferred within specific topics. A robust preprocessing pipeline was designed for multilingual variation, balancing dialogue turns, and cleaning noisy or redacted data. BERTopic extracted over 29 coherent topics including artificial intelligence, programming, ethics, and cloud infrastructure. We analysed relationships between topics and model preferences to identify trends in model-topic alignment. Visualization techniques included inter-topic distance maps, topic probability distributions, and model-versus-topic matrices. Our findings inform domain-specific fine-tuning and optimization strategies for improving real-world LLM performance and user satisfaction.

---

### Label Semantics for Robust Hyperspectral Image Classification

Authors: Rafin Hassan, Zarin Tasnim Roshni, Rafiqul Bari, Alimul Islam, Nabeel Mohammed, Moshiur Farazi, Shafin Rahman
Published: 2025-10-08
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.07556v1

Hyperspectral imaging (HSI) classification is a critical tool with widespread applications across diverse fields such as agriculture, environmental monitoring, medicine, and materials science. Due to the limited availability of high-quality training samples and the high dimensionality of spectral data, HSI classification models are prone to overfitting and often face challenges in balancing accuracy and computational complexity. Furthermore, most of HSI classification models are monomodal, where it solely relies on spectral-spatial data to learn decision boundaries in the high dimensional embedding space. To address this, we propose a general-purpose Semantic Spectral-Spatial Fusion Network (S3FN) that uses contextual, class specific textual descriptions to complement the training of an HSI classification model. Specifically, S3FN leverages LLMs to generate comprehensive textual descriptions for each class label that captures their unique characteristics and spectral behaviors. These descriptions are then embedded into a vector space using a pre-trained text encoder such as BERT or RoBERTa to extract meaningful label semantics which in turn leads to a better feature-label alignment for improved classification performance. To demonstrate the effectiveness of our approach, we evaluate our model on three diverse HSI benchmark datasets - Hyperspectral Wood, HyperspectralBlueberries, and DeepHS-Fruit and report significant performance boost. Our results highlight the synergy between textual semantics and spectral-spatial data, paving the way for further advancements in semantically augmented HSI classification models. Codes are be available in: https://github.com/milab-nsu/S3FN

---

### Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime

Authors: Lénaïc Chizat, Pierre Marion, Yerkin Yesbay
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07554v1

Dropout is a standard training technique for neural networks that consists of randomly deactivating units at each step of their gradient-based training. It is known to improve performance in many settings, including in the large-scale training of language or vision models. As a first step towards understanding the role of dropout in large neural networks, we study the large-width asymptotics of gradient descent with dropout on two-layer neural networks with the mean-field initialization scale. We obtain a rich asymptotic phase diagram that exhibits five distinct nondegenerate phases depending on the relative magnitudes of the dropout rate, the learning rate, and the width. Notably, we find that the well-studied "penalty" effect of dropout only persists in the limit with impractically small learning rates of order $O(1/\text{width})$. For larger learning rates, this effect disappears and in the limit, dropout is equivalent to a "random geometry" technique, where the gradients are thinned randomly after the forward and backward pass have been computed. In this asymptotic regime, the limit is described by a mean-field jump process where the neurons' update times follow independent Poisson or Bernoulli clocks (depending on whether the learning rate vanishes or not). For some of the phases, we obtain a description of the limit dynamics both in path-space and in distribution-space. The convergence proofs involve a mix of tools from mean-field particle systems and stochastic processes. Together, our results lay the groundwork for a renewed theoretical understanding of dropout in large-scale neural networks.

---

### An Evaluation Study of Hybrid Methods for Multilingual PII Detection

Authors: Harshit Rajgarhia, Suryam Gupta, Asif Shaik, Gulipalli Praveen Kumar, Y Santhoshraj, Sanka Nithya Tanvy Nishitha, Abhishek Mukherji
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07551v1

The detection of Personally Identifiable Information (PII) is critical for privacy compliance but remains challenging in low-resource languages due to linguistic diversity and limited annotated data. We present RECAP, a hybrid framework that combines deterministic regular expressions with context-aware large language models (LLMs) for scalable PII detection across 13 low-resource locales. RECAP's modular design supports over 300 entity types without retraining, using a three-phase refinement pipeline for disambiguation and filtering. Benchmarked with nervaluate, our system outperforms fine-tuned NER models by 82% and zero-shot LLMs by 17% in weighted F1-score. This work offers a scalable and adaptable solution for efficient PII detection in compliance-focused applications.

---

### TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility

Authors: Saman Motamed, Minghao Chen, Luc Van Gool, Iro Laina
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.07550v1

Despite impressive visual fidelity, modern video generative models frequently produce sequences that violate intuitive physical laws, such as objects floating, teleporting, or morphing in ways that defy causality. While humans can easily detect such implausibilities, there remains no robust method for quantitatively assessing physical realism in video. In this work, we explore whether Video-Language Models (VLMs) can be trained to serve as reliable judges of physical plausibility. We find that existing VLMs struggle to identify physics violations, exposing fundamental limitations in their temporal and causal reasoning. To address this, we introduce TRAVL, a fine-tuning recipe that combines a balanced training dataset with a trajectory-aware attention module to improve motion encoding and discrimination in VLMs. To evaluate physical reasoning more rigorously, we propose ImplausiBench, a benchmark of 300 videos (150 real, 150 generated) that removes linguistic biases and isolates visual-temporal understanding. Performance is reported both with gold-standard human judgments and stricter LLM-as-judge metrics. Together, TRAVL and ImplausiBench offer a unified framework for probing and improving physical plausibility in multimodal models, shedding light on a challenging and underexplored aspect of visual-temporal understanding.

---

### Targeted Digital Twin via Flow Map Learning and Its Application to Fluid Dynamics

Authors: Qifan Chen, Zhongshu Xu, Jinjin Zhang, Dongbin Xiu
Published: 2025-10-08
Categories: cs.LG, math.NA, physics.flu-dyn
arXiv: https://arxiv.org/abs/2510.07549v1

We present a numerical framework for constructing a targeted digital twin (tDT) that directly models the dynamics of quantities of interest (QoIs) in a full digital twin (DT). The proposed approach employs memory-based flow map learning (FML) to develop a data-driven model of the QoIs using short bursts of trajectory data generated through repeated executions of the full DT. This renders the construction of the FML-based tDT an entirely offline computational process. During online simulation, the learned tDT can efficiently predict and analyze the long-term dynamics of the QoIs without requiring simulations of the full DT system, thereby achieving substantial computational savings. After introducing the general numerical procedure, we demonstrate the construction and predictive capability of the tDT in a computational fluid dynamics (CFD) example: two-dimensional incompressible flow past a cylinder. The QoIs in this problem are the hydrodynamic forces exerted on the cylinder. The resulting tDTs are compact dynamical systems that evolve these forces without explicit knowledge of the underlying flow field. Numerical results show that the tDTs yield accurate long-term predictions of the forces while entirely bypassing full flow simulations.

---

### PickStyle: Video-to-Video Style Transfer with Context-Style Adapters

Authors: Soroush Mehraban, Vida Adeli, Jacob Rommann, Kyryl Truskovskyi, Harrison Sanborn, Babak Taati, Cole Clifford
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07546v2

We address the task of video style transfer with diffusion models, where the goal is to preserve the context of an input video while rendering it in a target style specified by a text prompt. A major challenge is the lack of paired video data for supervision. We propose PickStyle, a video-to-video style transfer framework that augments pretrained video diffusion backbones with style adapters and benefits from paired still image data with source-style correspondences for training. PickStyle inserts low-rank adapters into the self-attention layers of conditioning modules, enabling efficient specialization for motion-style transfer while maintaining strong alignment between video content and style. To bridge the gap between static image supervision and dynamic video, we construct synthetic training clips from paired images by applying shared augmentations that simulate camera motion, ensuring temporal priors are preserved. In addition, we introduce Context-Style Classifier-Free Guidance (CS-CFG), a novel factorization of classifier-free guidance into independent text (style) and video (context) directions. CS-CFG ensures that context is preserved in generated video while the style is effectively transferred. Experiments across benchmarks show that our approach achieves temporally coherent, style-faithful, and content-preserving video translations, outperforming existing baselines both qualitatively and quantitatively.

---

### Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices

Authors: Md Tahmid Rahman Laskar, Mohammed Saidul Islam, Ridwan Mahbub, Mizanur Rahman, Amran Bhuiyan, Israt Jahan, Mir Tafseer Nayeem, Shafiq Joty, Enamul Hoque, Jimmy Huang
Published: 2025-10-08
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.07545v2

Large Vision-Language Models (LVLMs) with only 7B parameters have shown promise as automated judges in chart comprehension tasks. However, tiny models (<=2B parameters) still perform poorly as judges, limiting their real-world use in resource-constrained settings. To address this, we propose two approaches to ensure cost-efficient evaluation: (i) multi-criteria prompting, which combines separate evaluation criteria into a single query, and (ii) domain-adaptive transfer learning, in which we fine-tune a 2B-parameter LVLM on synthetic judgments in a chart dataset to create the ChartJudge. Experiments show that multi-criteria prompting exposes robustness gaps, which led to a huge drop in performance for 7B models, including specialized LVLM judges like LLaVA-Critic. In addition, we find that our tiny LVLM (ChartJudge) can effectively transfer knowledge from one dataset to another to make it a more specialized model. Our fine-grained analysis across chart types and query complexities offers actionable insights into trade-offs between model size, prompt design, and transferability, enabling scalable, low-cost evaluation for chart reasoning tasks.

---

### Low-Compute Watermark Removal via Dual-Domain Natural Projection

Authors: Pragati Shuddhodhan Meshram, Varun Chandrasekaran
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07538v2

Effective removal of semantic watermarks requires balancing three competing objectives: \emph{high removal success}, \emph{low perceptual distortion}, and \emph{low computational cost}. However, existing single-image attacks typically optimize only for the first two, achieving strong watermark suppression but relying on expensive, multi-step optimization that limits practical deployment. In this work, we show that this trade-off is fundamental: no current approach achieves all three properties simultaneously. We introduce \textsc{DAWN}, a lightweight, training-free attack that explicitly targets the low-cost regime while maintaining competitive removal performance. \textsc{DAWN} works by projecting a watermarked image onto natural-image priors in complementary frequency and semantic spaces, suppressing watermark signals that deviate from natural statistics, and then applying a decoupled perceptual-alignment step to restore visual consistency with minimal artifact. Across diverse pixel-, frequency-, and latent-space watermarking schemes, \textsc{DAWN} consistently reduces detectability while preserving structural and semantic fidelity, demonstrating that efficient, low-resource watermark removal is feasible with only modest perceptual degradation. Our code is available at https://github.com/Pragati-Meshram/DAWN.

---

### Estimating Fair Graphs from Graph-Stationary Data

Authors: Madeline Navarro, Andrei Buciulea, Samuel Rey, Antonio G. Marques, Santiago Segarra
Published: 2025-10-08
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2510.07536v1

We estimate fair graphs from graph-stationary nodal observations such that connections are not biased with respect to sensitive attributes. Edges in real-world graphs often exhibit preferences for connecting certain pairs of groups. Biased connections can not only exacerbate but even induce unfair treatment for downstream graph-based tasks. We therefore consider group and individual fairness for graphs corresponding to group- and node-level definitions, respectively. To evaluate the fairness of a given graph, we provide multiple bias metrics, including novel measurements in the spectral domain. Furthermore, we propose Fair Spectral Templates (FairSpecTemp), an optimization-based method with two variants for estimating fair graphs from stationary graph signals, a general model for graph data subsuming many existing ones. One variant of FairSpecTemp exploits commutativity properties of graph stationarity while directly constraining bias, while the other implicitly encourages fair estimates by restricting bias in the graph spectrum and is thus more flexible. Our methods enjoy high probability performance bounds, yielding a conditional tradeoff between fairness and accuracy. In particular, our analysis reveals that accuracy need not be sacrificed to recover fair graphs. We evaluate FairSpecTemp on synthetic and real-world data sets to illustrate its effectiveness and highlight the advantages of both variants of FairSpecTemp.

---

### OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs

Authors: Jaeseong Lee, seung-won hwang, Aurick Qiao, Gabriele Oliaro, Ye Wang, Samyam Rajbhandari
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.07535v1

Speculative decoding promises faster inference for large language models (LLMs), yet existing methods fail to generalize to real-world settings. Benchmarks typically assume short contexts (e.g., 2K tokens), whereas practical workloads involve long contexts. We find current approaches degrade severely with long contexts; for instance, EAGLE3 even slows down the generation speed by 0.81x. We address these limitations by releasing a new long-context benchmark (LongSpecBench) and introducing a novel model (OWL). OWL achieves about 5x higher acceptance length than EAGLE3 on long-context inputs through three innovations: (1) an LSTM-based drafter conditioned only on the last-token state, making it generalize to various lengths, (2) a special token (SPEC) in the verifier that produces richer representation for drafter, and (3) a hybrid algorithm combining both tree and non-tree decoding methods. We release all code and datasets to advance future research.

---

### Beyond independent component analysis: identifiability and algorithms

Authors: Alvaro Ribot, Anna Seigal, Piotr Zwiernik
Published: 2025-10-08
Categories: math.ST, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.07525v1

Independent Component Analysis (ICA) is a classical method for recovering latent variables with useful identifiability properties. For independent variables, cumulant tensors are diagonal; relaxing independence yields tensors whose zero structure generalizes diagonality. These models have been the subject of recent work in non-independent component analysis. We show that pairwise mean independence answers the question of how much one can relax independence: it is identifiable, any weaker notion is non-identifiable, and it contains the models previously studied as special cases. Our results apply to distributions with the required zero pattern at any cumulant tensor. We propose an algebraic recovery algorithm based on least-squares optimization over the orthogonal group. Simulations highlight robustness: enforcing full independence can harm estimation, while pairwise mean independence enables more stable recovery. These findings extend the classical ICA framework and provide a rigorous basis for blind source separation beyond independence.

---

### EEG Sleep Stage Classification with Continuous Wavelet Transform and Deep Learning

Authors: Mehdi Zekriyapanah Gashti, Ghasem Farjamnia
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.07524v1

Accurate classification of sleep stages is crucial for the diagnosis and management of sleep disorders. Conventional approaches for sleep scoring rely on manual annotation or features extracted from EEG signals in the time or frequency domain. This study proposes a novel framework for automated sleep stage scoring using time-frequency analysis based on the wavelet transform. The Sleep-EDF Expanded Database (sleep-cassette recordings) was used for evaluation. The continuous wavelet transform (CWT) generated time-frequency maps that capture both transient and oscillatory patterns across frequency bands relevant to sleep staging. Experimental results demonstrate that the proposed wavelet-based representation, combined with ensemble learning, achieves an overall accuracy of 88.37 percent and a macro-averaged F1 score of 73.15, outperforming conventional machine learning methods and exhibiting comparable or superior performance to recent deep learning approaches. These findings highlight the potential of wavelet analysis for robust, interpretable, and clinically applicable sleep stage classification.

---

### ParsTranslit: Truly Versatile Tajik-Farsi Transliteration

Authors: Rayyan Merchant, Kevin Tang
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07520v1

As a digraphic language, the Persian language utilizes two written standards: Perso-Arabic in Afghanistan and Iran, and Tajik-Cyrillic in Tajikistan. Despite the significant similarity between the dialects of each country, script differences prevent simple one-to-one mapping, hindering written communication and interaction between Tajikistan and its Persian-speaking ``siblings''. To overcome this, previously-published efforts have investigated machine transliteration models to convert between the two scripts. Unfortunately, most efforts did not use datasets other than those they created, limiting these models to certain domains of text such as archaic poetry or word lists. A truly usable transliteration system must be capable of handling varied domains, meaning that suck models lack the versatility required for real-world usage. The contrast in domain between data also obscures the task's true difficulty. We present a new state-of-the-art sequence-to-sequence model for Tajik-Farsi transliteration trained across all available datasets, and present two datasets of our own. Our results across domains provide clearer understanding of the task, and set comprehensive comparable leading benchmarks. Overall, our model achieves chrF++ and Normalized CER scores of 87.91 and 0.05 from Farsi to Tajik and 92.28 and 0.04 from Tajik to Farsi. Our model, data, and code are available at https://anonymous.4open.science/r/ParsTranslit-FB30/.

---

### When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning

Authors: Hyeong Kyu Choi, Xiaojin Zhu, Sharon Li
Published: 2025-10-08
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.07517v5

Multi-agent debate (MAD) aims to improve large language model (LLM) reasoning by letting multiple agents exchange answers and then aggregate their opinions. Yet recent studies reveal that agents are not neutral: they are prone to identity-driven sycophancy and self-bias, uncritically adopting a peer's view or stubbornly adhering to their own prior output, undermining the reliability of debate. In this work, we present the first principled framework that joins sycophancy and self-bias to mitigate and quantify identity bias in MAD. First, we formalize the debate dynamics as an identity-weighted Bayesian update process. Second, we propose response anonymization: by removing identity markers from prompts, agents cannot distinguish "self" from "peer", which forces equal weights on agent identity, thereby reducing bias and improving trustworthiness. Third, we define the Identity Bias Coefficient (IBC), a principled bias metric that measures an agent's tendency to follow its peer versus itself. Empirical studies across multiple models and benchmarks confirm that identity bias is widespread, with sycophancy far more common than self-bias. Our findings highlight the need to ensure that MAD systems reason based on content rather than identity. Code is released in https://github.com/deeplearning-wisc/MAD-identity-bias.

---

### CompassLLM: A Multi-Agent Approach toward Geo-Spatial Reasoning for Popular Path Query

Authors: Md. Nazmul Islam Ananto, Shamit Fatin, Mohammed Eunus Ali, Md Rizwan Parvez
Published: 2025-10-08
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.07516v2

The popular path query - identifying the most frequented routes between locations from historical trajectory data - has important applications in urban planning, navigation optimization, and travel recommendations. While traditional algorithms and machine learning approaches have achieved success in this domain, they typically require model training, parameter tuning, and retraining when accommodating data updates. As Large Language Models (LLMs) demonstrate increasing capabilities in spatial and graph-based reasoning, there is growing interest in exploring how these models can be applied to geo-spatial problems. We introduce CompassLLM, a novel multi-agent framework that intelligently leverages the reasoning capabilities of LLMs into the geo-spatial domain to solve the popular path query. CompassLLM employs its agents in a two-stage pipeline: the SEARCH stage that identifies popular paths, and a GENERATE stage that synthesizes novel paths in the absence of an existing one in the historical trajectory data. Experiments on real and synthetic datasets show that CompassLLM demonstrates superior accuracy in SEARCH and competitive performance in GENERATE while being cost-effective.

---

### MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysis

Authors: Qinghua Liu, Sam Heshmati, Zheda Mai, Zubin Abraham, John Paparrizos, Liu Ren
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.CV, cs.DB
arXiv: https://arxiv.org/abs/2510.07513v1

Effective analysis of time series data presents significant challenges due to the complex temporal dependencies and cross-channel interactions in multivariate data. Inspired by the way human analysts visually inspect time series to uncover hidden patterns, we ask: can incorporating visual representations enhance automated time-series analysis? Recent advances in multimodal large language models have demonstrated impressive generalization and visual understanding capability, yet their application to time series remains constrained by the modality gap between continuous numerical data and discrete natural language. To bridge this gap, we introduce MLLM4TS, a novel framework that leverages multimodal large language models for general time-series analysis by integrating a dedicated vision branch. Each time-series channel is rendered as a horizontally stacked color-coded line plot in one composite image to capture spatial dependencies across channels, and a temporal-aware visual patch alignment strategy then aligns visual patches with their corresponding time segments. MLLM4TS fuses fine-grained temporal details from the numerical data with global contextual information derived from the visual representation, providing a unified foundation for multimodal time-series analysis. Extensive experiments on standard benchmarks demonstrate the effectiveness of MLLM4TS across both predictive tasks (e.g., classification) and generative tasks (e.g., anomaly detection and forecasting). These results underscore the potential of integrating visual modalities with pretrained language models to achieve robust and generalizable time-series analysis.

---

### Efficient Generalization via Multimodal Co-Training under Data Scarcity and Distribution Shift

Authors: Tianyu Bell Pan, Damon L. Woodard
Published: 2025-10-08
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2510.07509v1

This paper explores a multimodal co-training framework designed to enhance model generalization in situations where labeled data is limited and distribution shifts occur. We thoroughly examine the theoretical foundations of this framework, deriving conditions under which the use of unlabeled data and the promotion of agreement between classifiers for different modalities lead to significant improvements in generalization. We also present a convergence analysis that confirms the effectiveness of iterative co-training in reducing classification errors. In addition, we establish a novel generalization bound that, for the first time in a multimodal co-training context, decomposes and quantifies the distinct advantages gained from leveraging unlabeled multimodal data, promoting inter-view agreement, and maintaining conditional view independence. Our findings highlight the practical benefits of multimodal co-training as a structured approach to developing data-efficient and robust AI systems that can effectively generalize in dynamic, real-world environments. The theoretical foundations are examined in dialogue with, and in advance of, established co-training principles.

---

### PEAR: Planner-Executor Agent Robustness Benchmark

Authors: Shen Dong, Mingxuan Zhang, Pengfei He, Li Ma, Bhavani Thuraisingham, Hui Liu, Yue Xing
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07505v4

Large Language Model (LLM)-based Multi-Agent Systems (MAS) have emerged as a powerful paradigm for tackling complex, multi-step tasks across diverse domains. However, despite their impressive capabilities, MAS remain susceptible to adversarial manipulation. Existing studies typically examine isolated attack surfaces or specific scenarios, leaving a lack of holistic understanding of MAS vulnerabilities. To bridge this gap, we introduce PEAR, a benchmark for systematically evaluating both the utility and vulnerability of planner-executor MAS. While compatible with various MAS architectures, our benchmark focuses on the planner-executor structure, which is a practical and widely adopted design. Through extensive experiments, we find that (1) a weak planner degrades overall clean task performance more severely than a weak executor; (2) while a memory module is essential for the planner, having a memory module for the executor does not impact the clean task performance; (3) there exists a trade-off between task performance and robustness; and (4) attacks targeting the planner are particularly effective at misleading the system. These findings offer actionable insights for enhancing the robustness of MAS and lay the groundwork for principled defenses in multi-agent settings.

---

### Time-Frequency Filtering Meets Graph Clustering

Authors: Marcelo A. Colominas, Stefan Steinerberger, Hau-Tieng Wu
Published: 2025-10-08
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2510.07503v1

We show that the problem of identifying different signal components from a time-frequency representation can be equivalently phrased as a graph clustering problem: given a graph $G=(V,E)$ one aims to identify `clusters', subgraphs that are strongly connected and have relatively few connections between them. The graph clustering problem is well studied, we show how these ideas can suggest (many) new ways to identify signal components. Numerical experiments illustrate the ideas.

---

### Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death

Authors: Sihyung Park, Wenbin Lu, Shu Yang
Published: 2025-10-08
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2510.07501v1

Truncation by death, a prevalent challenge in critical care, renders traditional dynamic treatment regime (DTR) evaluation inapplicable due to ill-defined potential outcomes. We introduce a principal stratification-based method, focusing on the always-survivor value function. We derive a semiparametrically efficient, multiply robust estimator for multi-stage DTRs, demonstrating its robustness and efficiency. Empirical validation and an application to electronic health records showcase its utility for personalized treatment optimization.

---

### Black-Box Detection of LLM-Generated Text Using Generalized Jensen-Shannon Divergence

Authors: Shuangyi Chen, Ashish Khisti
Published: 2025-10-08
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2510.07500v3

We study black-box detection of machine-generated text under practical constraints: the scoring model (proxy LM) may mismatch the unknown source model, and per-input contrastive generation is costly. We propose SurpMark, a reference-based detector that summarizes a passage by the dynamics of its token surprisals. SurpMark discretizes surprisals into interpretable states, estimates a state-transition matrix for the test text, and scores it via a generalized Jensen-Shannon (GJS) gap between the test transitions and two fixed references (human vs. machine) built once from existing corpora. Theoretically, we derive design guidance for how the discretization bins should scale with data and provide a principled justification for our test statistic. Empirically, across multiple datasets, source models, and scenarios, SurpMark consistently matches or surpasses baselines, demonstrating strong robustness across domains and generators; our experiments on hyperparameter sensitivity exhibit trends that our theoretical results help to explain.

---

### When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs

Authors: Soyeong Jeong, Taehee Jung, Sung Ju Hwang, Joo-Kyung Kim, Dongyeop Kang
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.07499v2

Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge-intensive multi-hop reasoning by integrating large sets of retrieved documents or, in some cases, directly all necessary information. However, simply feeding more documents into the context window fails to capture how evidence should be connected. We address this gap with thought templates, which recast reasoning as reusable thought caches, derived from prior problem solving traces, structuring how evidence is combined and guiding multi-hop inference with factual documents. To keep these templates effective, we propose an update strategy that iteratively refines templates derived from training data through natural-language feedback. Across diverse benchmarks and LCLM families, our approach delivers consistent gains over strong baselines in both retrieval-based and retrieval-free settings. Furthermore, we show that optimized templates can be distilled into smaller open-source models, demonstrating its broad applicability and transparent reasoning reuse. We refer to our framework as Thought Template Augmented LCLMs (ToTAL).

---

### Can Speech LLMs Think while Listening?

Authors: Yi-Jen Shih, Desh Raj, Chunyang Wu, Wei Zhou, SK Bong, Yashesh Gaur, Jay Mahadeokar, Ozlem Kalinli, Mike Seltzer
Published: 2025-10-08
Categories: cs.CL, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.07497v1

Recent advances in speech large language models (speech LLMs) have enabled seamless spoken interactions, but these systems still struggle with complex reasoning tasks. Previously, chain-of-thought (CoT) prompting or fine-tuning has been to shown to significantly improve the reasoning abilities of text-based LLMs. In this work, we investigate the effect of CoT fine-tuning for multi-stream speech LLMs, demonstrating that reasoning in text space improves the accuracy of speech LLMs by 2.4x, on average, over a suite of spoken reasoning tasks. Beyond accuracy, the latency of the spoken response is a crucial factor for interacting with voice-based agents. Inspired by the human behavior of "thinking while listening," we propose methods to reduce the additional latency from reasoning by allowing the model to start reasoning before the user query has ended. To achieve this, we introduce an entropy-based metric, "question completeness," which acts as an indicator to guide the model on the optimal time to start reasoning. This method provides greater control over the accuracy-latency trade-off compared with heuristic-based approaches and, under equivalent latency conditions, yields a 4% accuracy gain on ARC-Easy. Finally, we use Direct Preference Optimization (DPO) on preference data created using rejection sampling to push the accuracy-latency pareto frontier further, resulting in a 70% reduction in latency without loss in accuracy.

---