# Research Papers — 2025-10 · bundle page 114 of 217 > Full-text markdown of papers #5651–5700 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/114 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/113.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/115.md) ### The $φ$-PCA Framework: A Unified and Efficiency-Preserving Approach with Robust Variants Authors: Hung Hung, Zhi-Yu Jou, Su-Yun Huang, Shinto Eguchi Published: 2025-10-15 Categories: stat.ME, math.ST, stat.ML arXiv: https://arxiv.org/abs/2510.13159v1 Principal component analysis (PCA) is a fundamental tool in multivariate statistics, yet its sensitivity to outliers and limitations in distributed environments restrict its effectiveness in modern large-scale applications. To address these challenges, we introduce the $φ$-PCA framework which provides a unified formulation of robust and distributed PCA. The class of $φ$-PCA methods retains the asymptotic efficiency of standard PCA, while aggregating multiple local estimates using a proper $φ$ function enhances ordering-robustness, leading to more accurate eigensubspace estimation under contamination. Notably, the harmonic mean PCA (HM-PCA), corresponding to the choice $φ(u)=u^{-1}$, achieves optimal ordering-robustness and is recommended for practical use. Theoretical results further show that robustness increases with the number of partitions, a phenomenon seldom explored in the literature on robust or distributed PCA. Altogether, the partition-aggregation principle underlying $φ$-PCA offers a general strategy for developing robust and efficiency-preserving methodologies applicable to both robust and distributed data analysis. --- ### Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction Authors: Haolin Pan, Jinyuan Dong, Hongbin Zhang, Hongyu Lin, Mingjie Xing, Yanjun Wu Published: 2025-10-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.13158v1 Learning effective numerical representations, or embeddings, of programs is a fundamental prerequisite for applying machine learning to automate and enhance compiler optimization. Prevailing paradigms, however, present a dilemma. Static representations, derived from source code or intermediate representation (IR), are efficient and deterministic but offer limited insight into how a program will behave or evolve under complex code transformations. Conversely, dynamic representations, which rely on runtime profiling, provide profound insights into performance bottlenecks but are often impractical for large-scale tasks due to prohibitive overhead and inherent non-determinism. This paper transcends this trade-off by proposing a novel quasi-dynamic framework for program representation. The core insight is to model a program's optimization sensitivity. We introduce the Program Behavior Spectrum, a new representation generated by probing a program's IR with a diverse set of optimization sequences and quantifying the resulting changes in its static features. To effectively encode this high-dimensional, continuous spectrum, we pioneer a compositional learning approach. Product Quantization is employed to discretize the continuous reaction vectors into structured, compositional sub-words. Subsequently, a multi-task Transformer model, termed PQ-BERT, is pre-trained to learn the deep contextual grammar of these behavioral codes. Comprehensive experiments on two representative compiler optimization tasks -- Best Pass Prediction and -Oz Benefit Prediction -- demonstrate that our method outperforms state-of-the-art static baselines. Our code is publicly available at https://github.com/Panhaolin2001/PREP/. --- ### Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval Authors: Subhendu Khatuya, Shashwat Naidu, Pawan Goyal, Niloy Ganguly Published: 2025-10-15 Categories: cs.CE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.13157v1 Despite continuous advancements in the capabilities of large language models (LLMs), numerical reasoning remains a challenging area. Techniques like chain-of-thought prompting, tree-of-thought prompting, and program-of-thought prompting guide LLMs through intermediate reasoning steps. Although in-context learning with few-shot prompting has improved performance, LLMs still lag behind state-of-the-art models on financial numerical reasoning datasets such as FinQA and ConvFinQA. In this work, we introduce FINDER, a novel two-step framework, to enhance LLMs' capabilities in financial numerical reasoning. The first step utilizes a generative retriever to extract relevant facts from unstructured data, including both text and tables. This is followed by context-aware Program of Thought prompting with dynamic selection of in-context examples. Our model FINDER achieves a new state-of-the-art performance on both the FinQA and ConvFinQA datasets, surpassing previous benchmarks with execution accuracy improvements of 5.98% and 4.05%, respectively. --- ### The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs Authors: Pardis Sadat Zahraei, Gokhan Tur, Dilek Hakkani-Tür, Ehsaneddin Asgari Published: 2025-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.13154v3 What happens inside a language model when alignment training conflicts with a cultural value it encodes? Across 16 MENA countries, 26 models, and 1.53M human survey responses, we show the answer is suppression, not erasure: at the moment of refusal, a model's internal logit distribution correlates with human survey data more strongly than its freely generated answers. We call this the alignment veto. We distinguish suppression failures (accurate internal distributions blocked at output) from representational bias failures (the encoding itself diverges from human values), and show the two require different interventions. The gate is inequitable: the safety tax reaches 37.6%, with a 19.8% alignment-quality gap between best- and worst-served nations, and native-language prompting widens rather than closes it. Sparse autoencoder analysis corroborated by comparisons across alignment stages identifies a candidate DPO-stage feature mediating suppression in Tulu-3-8B. The gate is real, its costs are unequal, and deciding what it should protect is not a technical question. --- ### Foveation Improves Payload Capacity in Steganography Authors: Lifeng Qiu Lin, Henry Kam, Qi Sun, Kaan Akşit Published: 2025-10-15 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2510.13151v2 Steganography finds its use in visual medium such as providing metadata and watermarking. With support of efficient latent representations and foveated rendering, we trained models that improve existing capacity limits from 100 to 500 bits, while achieving better accuracy of up to 1 failure bit out of 2000, at 200K test bits. Finally, we achieve a comparable visual quality of 31.47 dB PSNR and 0.13 LPIPS, showing the effectiveness of novel perceptual design in creating multi-modal latent representations in steganography. --- ### D-com: Accelerating Iterative Processing to Enable Low-rank Decomposition of Activations Authors: Faraz Tahmasebi, Michael Pelluer, Hyoukjun Kwon Published: 2025-10-15 Categories: cs.AR, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2510.13147v1 The computation and memory costs of large language models kept increasing over last decade, which reached over the scale of 1T parameters. To address the challenges from the large scale models, model compression techniques such as low-rank decomposition have been explored. Previous model decomposition works have focused on weight decomposition to avoid costly runtime decomposition, whose latency often significantly exceeds the benefits from decomposition (e.g., 38% more end-to-end latency when running Llama2-7b on A100 with 4K sequence length with activation decomposition compared to no decomposition). In this work, we debunk such observations and report that the input decomposition can be significantly beneficial with a proper choice of decomposition algorithm and hardware support. We adopt progressive decomposition algorithm, Lanczos algorithm, and design a co-accelerator architecture for the decomposition algorithm. To address the memory- boundness of the decomposition operation, we introduce a novel compute replication methodology that moves the op- eration toward compute-bound region, which enables 6.2x speedup in our evaluation. We also develop an output shape- preserving computation scheme that eliminates decomposi- tion costs in consecutive layers. To compensate model quality loss from compression, we introduce a multi-track decom- position approach that separately handles outlier channels for high accuracy and low perplexity with minimal compu- tational costs. Combined together, our accelerator, D-com, provides 22% end-to-end latency improvements compared to A100 GPU at the cost of small model quality degradation (e.g., 3% on AI2 Reasoning Challenge task). --- ### Stable LLM Ensemble: Interaction between Example Representativeness and Diversity Authors: Junichiro Niimi Published: 2025-10-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.13143v1 Large language models (LLMs) have achieved remarkable results in wide range of domains. However, the accuracy and robustness of one-shot LLM predictions remain highly sensitive to the examples and the diversity among ensemble members. This study systematically investigates the effects of example representativeness (one-shot strategy) and output diversity (sampling temperature) on LLM ensemble performance. Two one-shot strategies are compared: centroid-based representative examples (proposed) and randomly sampled examples (baseline) and sampling temperature also is varied. The proposed approach with higher temperature setting significantly outperforms random selection by +7.6% (macro-F1) and -10.5% (RMSE). Furthermore, the proposed model exceeds 5-shot prompting by +21.1% (macro-F1) and -24.0% (RMSE). Our findings demonstrate that combining representative example selection with increased temperature provides the appropriate level of diversity to the ensemble. This work highlights the practical importance of both example selection and controlled diversity in designing effective one-shot LLM ensembles. --- ### Addressing the alignment problem in transportation policy making: an LLM approach Authors: Xiaoyu Yan, Tianxing Dai, Yu Marco Nie Published: 2025-10-15 Categories: cs.CY, cs.CE, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2510.13139v1 A key challenge in transportation planning is that the collective preferences of heterogeneous travelers often diverge from the policies produced by model-driven decision tools. This misalignment frequently results in implementation delays or failures. Here, we investigate whether large language models (LLMs), noted for their capabilities in reasoning and simulating human decision-making, can help inform and address this alignment problem. We develop a multi-agent simulation in which LLMs, acting as agents representing residents from different communities in a city, participate in a referendum on a set of transit policy proposals. Using chain-of-thought reasoning, LLM agents provide ranked-choice or approval-based preferences, which are aggregated using instant-runoff voting (IRV) to model democratic consensus. We implement this simulation framework with both GPT-4o and Claude-3.5, and apply it for Chicago and Houston. Our findings suggest that LLM agents are capable of approximating plausible collective preferences and responding to local context, while also displaying model-specific behavioral biases and modest divergences from optimization-based benchmarks. These capabilities underscore both the promise and limitations of LLMs as tools for solving the alignment problem in transportation decision-making. --- ### Real-Time Sign Language to text Translation using Deep Learning: A Comparative study of LSTM and 3D CNN Authors: Madhumati Pol, Anvay Anturkar, Anushka Khot, Ayush Andure, Aniruddha Ghosh, Anvit Magadum, Anvay Bahadur Published: 2025-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.13137v2 This study investigates the performance of 3D Convolutional Neural Networks (3D CNNs) and Long Short-Term Memory (LSTM) networks for real-time American Sign Language (ASL) recognition. Though 3D CNNs are good at spatiotemporal feature extraction from video sequences, LSTMs are optimized for modeling temporal dependencies in sequential data. We evaluate both architectures on a dataset containing 1,200 ASL signs across 50 classes, comparing their accuracy, computational efficiency, and latency under similar training conditions. Experimental results demonstrate that 3D CNNs achieve 92.4% recognition accuracy but require 3.2% more processing time per frame compared to LSTMs, which maintain 86.7% accuracy with significantly lower resource consumption. The hybrid 3D CNNLSTM model shows decent performance, which suggests that context-dependent architecture selection is crucial for practical implementation.This project provides professional benchmarks for developing assistive technologies, highlighting trade-offs between recognition precision and real-time operational requirements in edge computing environments. --- ### Convergence, design and training of continuous-time dropout as a random batch method Authors: Antonio Álvarez-López, Martín Hernández Published: 2025-10-15 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2510.13134v2 We study continuous-time dropout in controlled differential equations. We introduce a random-batch approximation of additive vector fields. On each time interval of length $h$, a random subset of components is activated and rescaled by its inclusion probabilities, yielding an unbiased approximation of the full field. We prove a uniform-in-time mean-square trajectory error of order $\mathcal O(h)$. At the distribution level, we derive Wasserstein and pointwise density estimates, together with global $L^1$ bounds under moment assumptions. For supervised training, we prove uniform $\mathcal O(\sqrt h)$ root-mean-square fluctuations of the randomized objective and an $\mathcal O(h)$ weak error for its expectation, leading to consistency of optimal values and near-minimizers and, under quadratic growth, convergence in control space. We further characterize how the sampling law affects the error constant through inclusion probabilities and field variance, compare fixed-size sampling, fixed partitions, and Bernoulli dropout, and derive a work--accuracy model for selecting the switching scale. Numerical experiments with neural ODEs illustrate trajectory and transport errors, sampling effects, and objective consistency at a fixed control. --- ### Cluster-Based Client Selection for Dependent Multi-Task Federated Learning in Edge Computing Authors: Jieping Luo, Qiyue Li, Zhizhang Liu, Hang Qi, Jiaying Yin, Jingjin Wu Published: 2025-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.13132v1 We study the client selection problem in Federated Learning (FL) within mobile edge computing (MEC) environments, particularly under the dependent multi-task settings, to reduce the total time required to complete various learning tasks. We propose CoDa-FL, a Cluster-oriented and Dependency-aware framework designed to reduce the total required time via cluster-based client selection and dependent task assignment. Our approach considers Earth Mover's Distance (EMD) for client clustering based on their local data distributions to lower computational cost and improve communication efficiency. We derive a direct and explicit relationship between intra-cluster EMD and the number of training rounds required for convergence, thereby simplifying the otherwise complex process of obtaining the optimal solution. Additionally, we incorporate a directed acyclic graph-based task scheduling mechanism to effectively manage task dependencies. Through numerical experiments, we validate that our proposed CoDa-FL outperforms existing benchmarks by achieving faster convergence, lower communication and computational costs, and higher learning accuracy under heterogeneous MEC settings. --- ### OS-HGAdapter: Open Semantic Hypergraph Adapter for Large Language Models Assisted Entropy-Enhanced Image-Text Alignment Authors: Rongjun Chen, Chengsi Yao, Jinchang Ren, Xianxian Zeng, Peixian Wang, Jun Yuan, Jiawen Li, Huimin Zhao, Xu Lu Published: 2025-10-15 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2510.13131v1 Text-image alignment constitutes a foundational challenge in multimedia content understanding, where effective modeling of cross-modal semantic correspondences critically enhances retrieval system performance through joint embedding space optimization. Given the inherent difference in information entropy between texts and images, conventional approaches often show an imbalance in the mutual retrieval of these two modalities. To address this particular challenge, we propose to use the open semantic knowledge of Large Language Model (LLM) to fill for the entropy gap and reproduce the alignment ability of humans in these tasks. Our entropy-enhancing alignment is achieved through a two-step process: 1) a new prompt template that does not rely on explicit knowledge in the task domain is designed to use LLM to enhance the polysemy description of the text modality. By analogy, the information entropy of the text modality relative to the visual modality is increased; 2) A hypergraph adapter is used to construct multilateral connections between the text and image modalities, which can correct the positive and negative matching errors for synonymous semantics in the same fixed embedding space, whilst reducing the noise caused by open semantic entropy by mapping the reduced dimensions back to the original dimensions. Comprehensive evaluations on the Flickr30K and MS-COCO benchmarks validate the superiority of our Open Semantic Hypergraph Adapter (OS-HGAdapter), showcasing 16.8\% (text-to-image) and 40.1\% (image-to-text) cross-modal retrieval gains over existing methods while establishing new state-of-the-art performance in semantic alignment tasks. --- ### On the Reasoning Abilities of Masked Diffusion Language Models Authors: Anej Svete, Ashish Sabharwal Published: 2025-10-15 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.13117v3 Masked diffusion models (MDMs) for text offer a compelling alternative to traditional autoregressive language models. Parallel generation makes them efficient, but their computational capabilities and the limitations inherent in their parallelism remain largely unexplored. To this end, we characterize what types of reasoning problems MDMs can provably solve and how efficiently. We do this by connecting MDMs to the well-understood reasoning frameworks of chain of thought (CoT) and padded looped transformers (PLTs) in the finite-precision log-width setting: We show that MDMs and polynomially-padded PLTs are, in fact, equivalent in this setting, and that MDMs can solve all problems that CoT-augmented transformers can. Moreover, we showcase classes of problems (including regular languages) for which MDMs are inherently more efficient than CoT transformers, where parallel generation allows for substantially faster reasoning. --- ### Multi-Label Clinical Text Eligibility Classification and Summarization System Authors: Surya Tejaswi Yerramsetty, Almas Fathimah Published: 2025-10-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.13115v1 Clinical trials are central to medical progress because they help improve understanding of human health and the healthcare system. They play a key role in discovering new ways to detect, prevent, or treat diseases, and it is essential that clinical trials include participants with appropriate and diverse medical backgrounds. In this paper, we propose a system that leverages Natural Language Processing (NLP) and Large Language Models (LLMs) to automate multi-label clinical text eligibility classification and summarization. The system combines feature extraction methods such as word embeddings (Word2Vec) and named entity recognition to identify relevant medical concepts, along with traditional vectorization techniques such as count vectorization and TF-IDF (Term Frequency-Inverse Document Frequency). We further explore weighted TF-IDF word embeddings that integrate both count-based and embedding-based strengths to capture term importance effectively. Multi-label classification using Random Forest and SVM models is applied to categorize documents based on eligibility criteria. Summarization techniques including TextRank, Luhn, and GPT-3 are evaluated to concisely summarize eligibility requirements. Evaluation with ROUGE scores demonstrates the effectiveness of the proposed methods. This system shows potential for automating clinical trial eligibility assessment using data-driven approaches, thereby improving research efficiency. --- ### Neural Triangular Transport Maps: A New Approach Towards Sampling in Lattice QCD Authors: Andrey Bryutkin, Youssef Marzouk Published: 2025-10-15 Categories: cs.LG, hep-lat, physics.comp-ph, stat.ML arXiv: https://arxiv.org/abs/2510.13112v1 Lattice field theories are fundamental testbeds for computational physics; yet, sampling their Boltzmann distributions remains challenging due to multimodality and long-range correlations. While normalizing flows offer a promising alternative, their application to large lattices is often constrained by prohibitive memory requirements and the challenge of maintaining sufficient model expressivity. We propose sparse triangular transport maps that explicitly exploit the conditional independence structure of the lattice graph under periodic boundary conditions using monotone rectified neural networks (MRNN). We introduce a comprehensive framework for triangular transport maps that navigates the fundamental trade-off between \emph{exact sparsity} (respecting marginal conditional independence in the target distribution) and \emph{approximate sparsity} (computational tractability without fill-ins). Restricting each triangular map component to a local past enables site-wise parallel evaluation and linear time complexity in lattice size $N$, while preserving the expressive, invertible structure. Using $φ^4$ in two dimensions as a controlled setting, we analyze how node labelings (orderings) affect the sparsity and performance of triangular maps. We compare against Hybrid Monte Carlo (HMC) and established flow approaches (RealNVP). --- ### VPREG: An Optimal Control Formulation for Diffeomorphic Image Registration Based on the Variational Principle Grid Generation Method Authors: Zicong Zhou, Baihan Zhao, Andreas Mang, Guojun Liao Published: 2025-10-15 Categories: cs.CV, math.OC arXiv: https://arxiv.org/abs/2510.13109v1 This paper introduces VPreg, a novel diffeomorphic image registration method. This work provides several improvements to our past work on mesh generation and diffeomorphic image registration. VPreg aims to achieve excellent registration accuracy while controlling the quality of the registration transformations. It ensures a positive Jacobian determinant of the spatial transformation and provides an accurate approximation of the inverse of the registration, a crucial property for many neuroimaging workflows. Unlike conventional methods, VPreg generates this inverse transformation within the group of diffeomorphisms rather than operating on the image space. The core of VPreg is a grid generation approach, referred to as \emph{Variational Principle} (VP), which constructs non-folding grids with prescribed Jacobian determinant and curl. These VP-generated grids guarantee diffeomorphic spatial transformations essential for computational anatomy and morphometry, and provide a more accurate inverse than existing methods. To assess the potential of the proposed approach, we conduct a performance analysis for 150 registrations of brain scans from the OASIS-1 dataset. Performance evaluation based on Dice scores for 35 regions of interest, along with an empirical analysis of the properties of the computed spatial transformations, demonstrates that VPreg outperforms state-of-the-art methods in terms of Dice scores, regularity properties of the computed transformation, and accuracy and consistency of the provided inverse map. We compare our results to ANTs-SyN, Freesurfer-Easyreg, and FSL-Fnirt. --- ### DriveCritic: Towards Context-Aware, Human-Aligned Evaluation for Autonomous Driving with Vision-Language Models Authors: Jingyu Song, Zhenxin Li, Shiyi Lan, Xinglong Sun, Nadine Chang, Maying Shen, Joshua Chen, Katherine A. Skinner, Jose M. Alvarez Published: 2025-10-15 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2510.13108v2 Benchmarking autonomous driving planners to align with human judgment remains a critical challenge, as state-of-the-art metrics like the Extended Predictive Driver Model Score (EPDMS) lack context awareness in nuanced scenarios. To address this, we introduce DriveCritic, a novel framework featuring two key contributions: the DriveCritic dataset, a curated collection of challenging scenarios where context is critical for correct judgment and annotated with pairwise human preferences, and the DriveCritic model, a Vision-Language Model (VLM) based evaluator. Fine-tuned using a two-stage supervised and reinforcement learning pipeline, the DriveCritic model learns to adjudicate between trajectory pairs by integrating visual and symbolic context. Experiments show DriveCritic significantly outperforms existing metrics and baselines in matching human preferences and demonstrates strong context awareness. Overall, our work provides a more reliable, human-aligned foundation to evaluating autonomous driving systems. The project page for DriveCritic is https://song-jingyu.github.io/DriveCritic --- ### TRUSTVIS: A Multi-Dimensional Trustworthiness Evaluation Framework for Large Language Models Authors: Ruoyu Sun, Da Song, Jiayang Song, Yuheng Huang, Lei Ma Published: 2025-10-15 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.13106v1 As Large Language Models (LLMs) continue to revolutionize Natural Language Processing (NLP) applications, critical concerns about their trustworthiness persist, particularly in safety and robustness. To address these challenges, we introduce TRUSTVIS, an automated evaluation framework that provides a comprehensive assessment of LLM trustworthiness. A key feature of our framework is its interactive user interface, designed to offer intuitive visualizations of trustworthiness metrics. By integrating well-known perturbation methods like AutoDAN and employing majority voting across various evaluation methods, TRUSTVIS not only provides reliable results but also makes complex evaluation processes accessible to users. Preliminary case studies on models like Vicuna-7b, Llama2-7b, and GPT-3.5 demonstrate the effectiveness of our framework in identifying safety and robustness vulnerabilities, while the interactive interface allows users to explore results in detail, empowering targeted model improvements. Video Link: https://youtu.be/k1TrBqNVg8g --- ### EgoSocial: Benchmarking Proactive Intervention Ability of Omnimodal LLMs via Egocentric Social Interaction Perception Authors: Xijun Wang, Tanay Sharma, Achin Kulshrestha, Abhimitra Meka, Aveek Purohit, Dinesh Manocha Published: 2025-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.13105v1 As AR/VR technologies become integral to daily life, there's a growing need for AI that understands human social dynamics from an egocentric perspective. However, current LLMs often lack the social awareness to discern when to intervene as AI assistant. This leads to constant, socially unaware responses that may disrupt natural conversation and negatively impact user focus. To address these limitations, we introduce EgoSocial, a large-scale egocentric dataset with 13,500 social video-question pairs, specifically designed to benchmark intervention in social interaction perception. We also present an in-depth analysis of current omnimodal LLMs (OLLMs) to assess their effectiveness in detecting diverse social contextual cues. Experiments show that OLLMs still struggle to detect the intervention timing (14.4% for Gemini 2.5 Pro). We also propose EgoSoD (EgoSocial Detection), an end-to-end method for robustly discerning social dynamics. Informed by our OLLM analysis, EgoSoD integrates multimodal contextual cues (e.g., audio and visual cues) into a social thinking graph, dynamically modeling participants and interactions. Our method proactively detects intervention timing and social interactions, precisely determining when to intervene. Our EgoSoD improves Phi-4 by 45.6% and Gemini 2.5 Pro by 9.9% on Intervention Timing performance, and improves Phi-4 by 20.4% and Gemini 2.5 Pro by 6.9% on overall Social Interaction performance. We will release the dataset and code soon. --- ### ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models Authors: Mingda Li, Xinyu Li, Weinan Zhang, Longxuan Ma Published: 2025-10-15 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.13103v1 Uncertainty Quantification (UQ) is a promising approach to improve model reliability, yet quantifying the uncertainty of Large Language Models (LLMs) is non-trivial. In this work, we establish a connection between the uncertainty of LLMs and their invariance under semantic-preserving intervention from a causal perspective. Building on this foundation, we propose a novel grey-box uncertainty quantification method that measures the variation in model outputs before and after the semantic-preserving intervention. Through theoretical justification, we show that our method provides an effective estimate of epistemic uncertainty. Our extensive experiments, conducted across various LLMs and a variety of question-answering (QA) datasets, demonstrate that our method excels not only in terms of effectiveness but also in computational efficiency. --- ### Gaussian Certified Unlearning in High Dimensions: A Hypothesis Testing Approach Authors: Aaradhya Pandey, Arnab Auddy, Haolin Zou, Arian Maleki, Sanjeev Kulkarni Published: 2025-10-15 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.13094v1 Machine unlearning seeks to efficiently remove the influence of selected data while preserving generalization. Significant progress has been made in low dimensions $(p \ll n)$, but high dimensions pose serious theoretical challenges as standard optimization assumptions of $Ω(1)$ strong convexity and $O(1)$ smoothness of the per-example loss $f$ rarely hold simultaneously in proportional regimes $(p\sim n)$. In this work, we introduce $\varepsilon$-Gaussian certifiability, a canonical and robust notion well-suited to high-dimensional regimes, that optimally captures a broad class of noise adding mechanisms. Then we theoretically analyze the performance of a widely used unlearning algorithm based on one step of the Newton method in the high-dimensional setting described above. Our analysis shows that a single Newton step, followed by a well-calibrated Gaussian noise, is sufficient to achieve both privacy and accuracy in this setting. This result stands in sharp contrast to the only prior work that analyzes machine unlearning in high dimensions \citet{zou2025certified}, which relaxes some of the standard optimization assumptions for high-dimensional applicability, but operates under the notion of $\varepsilon$-certifiability. That work concludes %that a single Newton step is insufficient even for removing a single data point, and that at least two steps are required to ensure both privacy and accuracy. Our result leads us to conclude that the discrepancy in the number of steps arises because of the sub optimality of the notion of $\varepsilon$-certifiability and its incompatibility with noise adding mechanisms, which $\varepsilon$-Gaussian certifiability is able to overcome optimally. --- ### A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection Authors: Ningkang Peng, Yuzhe Mao, Yuhao Zhang, Linjin Qian, Qianfeng Yu, Yanhui Gu, Yi Chen, Li Kong Published: 2025-10-15 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.13093v1 Out-of-Distribution (OOD) detection is a cornerstone for the safe deployment of AI systems in the open world. However, existing methods treat OOD detection as a binary classification problem, a cognitive flattening that fails to distinguish between semantically close (Near-OOD) and distant (Far-OOD) unknown risks. This limitation poses a significant safety bottleneck in applications requiring fine-grained risk stratification. To address this, we propose a paradigm shift from a conventional probabilistic view to a principled information-theoretic framework. We formalize the core task as quantifying the Semantic Surprise of a new sample and introduce a novel ternary classification challenge: In-Distribution (ID) vs. Near-OOD vs. Far-OOD. The theoretical foundation of our work is the concept of Low-Entropy Semantic Manifolds, which are explicitly structured to reflect the data's intrinsic semantic hierarchy. To construct these manifolds, we design a Hierarchical Prototypical Network. We then introduce the Semantic Surprise Vector (SSV), a universal probe that decomposes a sample's total surprise into three complementary and interpretable dimensions: conformity, novelty, and ambiguity. To evaluate performance on this new task, we propose the Normalized Semantic Risk (nSR), a cost-sensitive metric. Experiments demonstrate that our framework not only establishes a new state-of-the-art (sota) on the challenging ternary task, but its robust representations also achieve top results on conventional binary benchmarks, reducing the False Positive Rate by over 60% on datasets like LSUN. --- ### DeepCausalMMM: A Deep Learning Framework for Marketing Mix Modeling with Causal Structure Learning Authors: Aditya Puttaparthi Tirumala Published: 2025-10-15 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2510.13087v3 Marketing Mix Modeling (MMM) estimates the impact of marketing activities on business outcomes such as sales or revenue. Traditional MMM approaches rely on linear regression or Bayesian hierarchical models that assume channel independence and struggle to capture temporal dynamics and non-linear saturation. DeepCausalMMM addresses these limitations by combining deep learning, causal inference, and marketing science. It uses Gated Recurrent Units (GRUs) to learn temporal patterns (adstock, lag) while learning statistical dependencies between channels through Directed Acyclic Graph (DAG) structure with upper triangular constraints. It implements Hill equation saturation curves for diminishing returns and budget optimization. Key features: (1) data-driven hyperparameters learned from data with defaults, (2) linear mean scaling of the dependent variable, (3) configurable attribution priors with dynamic loss scaling, (4) multi-region modeling with shared and region-specific parameters, (5) robust methods including Huber loss, (6) response curve analysis. --- ### Edit-Your-Interest: Efficient Video Editing via Feature Most-Similar Propagation Authors: Yi Zuo, Zitao Wang, Lingling Li, Xu Liu, Fang Liu, Licheng Jiao Published: 2025-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.13084v1 Text-to-image (T2I) diffusion models have recently demonstrated significant progress in video editing. However, existing video editing methods are severely limited by their high computational overhead and memory consumption. Furthermore, these approaches often sacrifice visual fidelity, leading to undesirable temporal inconsistencies and artifacts such as blurring and pronounced mosaic-like patterns. We propose Edit-Your-Interest, a lightweight, text-driven, zero-shot video editing method. Edit-Your-Interest introduces a spatio-temporal feature memory to cache features from previous frames, significantly reducing computational overhead compared to full-sequence spatio-temporal modeling approaches. Specifically, we first introduce a Spatio-Temporal Feature Memory bank (SFM), which is designed to efficiently cache and retain the crucial image tokens processed by spatial attention. Second, we propose the Feature Most-Similar Propagation (FMP) method. FMP propagates the most relevant tokens from previous frames to subsequent ones, preserving temporal consistency. Finally, we introduce an SFM update algorithm that continuously refreshes the cached features, ensuring their long-term relevance and effectiveness throughout the video sequence. Furthermore, we leverage cross-attention maps to automatically extract masks for the instances of interest. These masks are seamlessly integrated into the diffusion denoising process, enabling fine-grained control over target objects and allowing Edit-Your-Interest to perform highly accurate edits while robustly preserving the background integrity. Extensive experiments decisively demonstrate that the proposed Edit-Your-Interest outperforms state-of-the-art methods in both efficiency and visual fidelity, validating its superior effectiveness and practicality. --- ### Agentic Discovery: Closing the Loop with Cooperative Agents Authors: J. Gregory Pauloski, Kyle Chard, Ian T. Foster Published: 2025-10-15 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2510.13081v1 As data-driven methods, artificial intelligence (AI), and automated workflows accelerate scientific tasks, we see the rate of discovery increasingly limited by human decision-making tasks such as setting objectives, generating hypotheses, and designing experiments. We postulate that cooperative agents are needed to augment the role of humans and enable autonomous discovery. Realizing such agents will require progress in both AI and infrastructure. --- ### Counting Hallucinations in Diffusion Models Authors: Shuai Fu, Jian Zhou, Qi Chen, Huang Jing, Huy Anh Nguyen, Xiaohan Liu, Zhixiong Zeng, Lin Ma, Quanshi Zhang, Qi Wu Published: 2025-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.13080v2 Diffusion probabilistic models (DPMs) have demonstrated remarkable progress in generative tasks, such as image and video synthesis. However, they still often produce hallucinated samples (hallucinations) that conflict with real-world knowledge, such as generating an implausible duplicate cup floating beside another cup. Despite their prevalence, the lack of feasible methodologies for systematically quantifying such hallucinations hinders progress in addressing this challenge and obscures potential pathways for designing next-generation generative models under factual constraints. In this work, we bridge this gap by focusing on a specific form of hallucination, which we term counting hallucination, referring to the generation of an incorrect number of instances or structured objects, such as a hand image with six fingers, despite such patterns being absent from the training data. To this end, we construct a dataset suite CountHalluSet, with well-defined counting criteria, comprising ToyShape, SimObject, and RealHand. Using these datasets, we develop a standardized evaluation protocol for quantifying counting hallucinations, and systematically examine how different sampling conditions in DPMs, including solver type, ODE solver order, sampling steps, and initial noise, affect counting hallucination levels. Furthermore, we analyze their correlation with common evaluation metrics such as FID, revealing that this widely used image quality metric fails to capture counting hallucinations consistently. This work aims to take the first step toward systematically quantifying hallucinations in diffusion models and offer new insights into the investigation of hallucination phenomena in image generation. --- ### GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models Authors: Chen Zheng, Yuhang Cai, Deyi Liu, Jin Ma, Yiyuan Ma, Yuan Yang, Jing Liu, Yutao Zeng, Xun Zhou, Siyuan Qiao Published: 2025-10-15 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.13079v1 Modern large language models leverage Mixture-of-Experts (MoE) architectures for efficient scaling, but face a critical challenge: functionally similar experts are often selected simultaneously, creating redundant computation and limiting effective model capacity. Existing auxiliary balance loss methods improve token distribution but fail to address the underlying expert diversity problem. We introduce GatePro, a novel parameter-free method that directly promotes expert selection diversity. GatePro identifies the most similar expert pairs and introduces localized competition mechanisms, preventing redundant expert co-activation while maintaining natural expert specialization. Our comprehensive evaluation demonstrates GatePro's effectiveness across model scales and benchmarks. Analysis demonstrates GatePro's ability to achieve enhanced expert diversity, where experts develop more distinct and complementary capabilities, avoiding functional redundancy. This approach can be deployed hot-swappable during any training phase without additional learnable parameters, offering a practical solution for improving MoE effectiveness. --- ### A Semi-amortized Lifted Learning-to-Optimize Masked (SALLO-M) Transformer Model for Scalable and Generalizable Beamforming Authors: Yubo Zhang, Xiao-Yang Liu, Xiaodong Wang Published: 2025-10-15 Categories: cs.LG, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2510.13077v3 We develop an unsupervised deep learning framework for real-time scalable and generalizable downlink beamforming in multi-user multiple-input single-output (MU-MISO) systems. The proposed semi-amortized lifted learning-to-optimize (SALLO) framework employs a multi-layer Transformer to iteratively refine an auxiliary variable and the beamformer solution, with a few projected gradient ascent steps at each layer. A key feature of our SALLO Transformer model is that it can handle varying numbers of users and antennas, enabled by a user-antenna dual tokenization and a structured sample/attention masking scheme, leading to generalization across different configurations without retraining. To improve convergence and robustness, we introduce three training strategies: (a) sliding-window training to stabilize gradient propagation, (b) curriculum learning with random masking to enable user-antenna configuration generalization and prevent poor early-stage convergence, and (c) sample replay to mitigate catastrophic forgetting during multi-stage training. Ablation studies validate several key architecture designs and show that the enhanced training scheme improves both generalizability and solution quality. Simulation results over both Gaussian and sparse channels show that the proposed scheme consistently outperforms existing deep learning baselines across diverse system configurations and channel conditions. The performance gain becomes more pronounced in overloaded regimes, highlighting improved robustness under challenging scenarios. Furthermore, our scheme surpasses the WMMSE benchmark in underloaded systems and even in overloaded systems when the overloading factor is below certain threshold. These gains are achieved with fast inference and a substantially more lightweight model than wireless foundation models. --- ### Unsupervised Domain Adaptation via Content Alignment for Hippocampus Segmentation Authors: Hoda Kalabizadeh, Ludovica Griffanti, Pak-Hei Yeung, Ana I. L. Namburete, Nicola K. Dinsdale, Konstantinos Kamnitsas Published: 2025-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.13075v1 Deep learning models for medical image segmentation often struggle when deployed across different datasets due to domain shifts - variations in both image appearance, known as style, and population-dependent anatomical characteristics, referred to as content. This paper presents a novel unsupervised domain adaptation framework that directly addresses domain shifts encountered in cross-domain hippocampus segmentation from MRI, with specific emphasis on content variations. Our approach combines efficient style harmonisation through z-normalisation with a bidirectional deformable image registration (DIR) strategy. The DIR network is jointly trained with segmentation and discriminator networks to guide the registration with respect to a region of interest and generate anatomically plausible transformations that align source images to the target domain. We validate our approach through comprehensive evaluations on both a synthetic dataset using Morpho-MNIST (for controlled validation of core principles) and three MRI hippocampus datasets representing populations with varying degrees of atrophy. Across all experiments, our method outperforms existing baselines. For hippocampus segmentation, when transferring from young, healthy populations to clinical dementia patients, our framework achieves up to 15% relative improvement in Dice score compared to standard augmentation methods, with the largest gains observed in scenarios with substantial content shift. These results highlight the efficacy of our approach for accurate hippocampus segmentation across diverse populations. --- ### NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models Authors: Konstantinos Barmpas, Na Lee, Dimitrios Chalatsis, William Raftery, Yannis Panagakis, Dimitrios A. Adamos, Nikolaos Laskaris, Alexandros Koliousis, Dario Farina, Stefanos Zafeiriou Published: 2025-10-15 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2510.13068v4 Biosignals such as electroencephalography (EEG), electrocardiography (ECG), and electromyography (EMG) encode physiological activity across multiple temporal and spectral scales, yielding representations that are rich but challenging for machine learning. Foundation models trained to predict masked signal tokens have shown promise in learning generalizable biosignal representations, yet their performance depends on the tokenizer's ability to preserve high-frequency dynamics and reconstruct signals with high fidelity. We introduce NeuroRVQ, a modality-adaptive biosignal tokenizer family designed for high-fidelity signal reconstruction. To capture the full frequency spectrum, NeuroRVQ decomposes biosignals into frequency-specific representations via multi-scale temporal convolutions, each encoded into hierarchical RVQ codebooks to preserve high-frequency detail, combined with a novel phase-aware training loss that respects the circular topology of Fourier phase. By tuning the temporal resolution, number and size of temporal kernels and RVQ depth, this design adapts to the spectro-temporal characteristics of each biosignal modality. To validate that tokenizer quality drives downstream performance, we train a simple masked-token foundation model for each modality (NeuroRVQ-FM) using the corresponding NeuroRVQ tokenizer. The NeuroRVQ-FM family achieves competitive or superior downstream performance compared to existing modality-specific foundation models, demonstrating that high-fidelity tokenization is a critical factor for effective biosignal modeling. --- ### Direction-aware multi-scale gradient loss for infrared and visible image fusion Authors: Kaixuan Yang, Wei Xiang, Zhenshuai Chen, Tong Jin, Yunpeng Liu Published: 2025-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.13067v1 Infrared and visible image fusion aims to integrate complementary information from co-registered source images to produce a single, informative result. Most learning-based approaches train with a combination of structural similarity loss, intensity reconstruction loss, and a gradient-magnitude term. However, collapsing gradients to their magnitude removes directional information, yielding ambiguous supervision and suboptimal edge fidelity. We introduce a direction-aware, multi-scale gradient loss that supervises horizontal and vertical components separately and preserves their sign across scales. This axis-wise, sign-preserving objective provides clear directional guidance at both fine and coarse resolutions, promoting sharper, better-aligned edges and richer texture preservation without changing model architectures or training protocols. Experiments on open-source model and multiple public benchmarks demonstrate effectiveness of our approach. --- ### Absolute indices for determining compactness, separability and number of clusters Authors: Adil M. Bagirov, Ramiz M. Aliguliyev, Nargiz Sultanova, Sona Taheri Published: 2025-10-15 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.13065v3 Finding "true" clusters in a data set is a challenging problem. Clustering solutions obtained using different models and algorithms do not necessarily provide compact and well-separated clusters or the optimal number of clusters. Cluster validity indices are commonly applied to identify such clusters. Nevertheless, these indices are typically relative, and they are used to compare clustering algorithms or choose the parameters of a clustering algorithm. Moreover, the success of these indices depends on the underlying data structure. This paper introduces novel absolute cluster indices to determine both the compactness and separability of clusters. We define a compactness function for each cluster and a set of neighboring points for cluster pairs. This function is utilized to determine the compactness of each cluster and the whole cluster distribution. The set of neighboring points is used to define the margin between clusters and the overall distribution margin. The proposed compactness and separability indices are applied to identify the true number of clusters. Using a number of synthetic and real-world data sets, we demonstrate the performance of these new indices and compare them with other widely-used cluster validity indices. --- ### True Self-Supervised Novel View Synthesis is Transferable Authors: Thomas W. Mitchel, Hyunwoo Ryu, Vincent Sitzmann Published: 2025-10-15 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.13063v2 In this paper, we identify that the key criterion for determining whether a model is truly capable of novel view synthesis (NVS) is transferability: Whether any pose representation extracted from one video sequence can be used to re-render the same camera trajectory in another. We analyze prior work on self-supervised NVS and find that their predicted poses do not transfer: The same set of poses lead to different camera trajectories in different 3D scenes. Here, we present XFactor, the first geometry-free self-supervised model capable of true NVS. XFactor combines pair-wise pose estimation with a simple augmentation scheme of the inputs and outputs that jointly enables disentangling camera pose from scene content and facilitates geometric reasoning. Remarkably, we show that XFactor achieves transferability with unconstrained latent pose variables, without any 3D inductive biases or concepts from multi-view geometry -- such as an explicit parameterization of poses as elements of SE(3). We introduce a new metric to quantify transferability, and through large-scale experiments, we demonstrate that XFactor significantly outperforms prior pose-free NVS transformers, and show that latent poses are highly correlated with real-world poses through probing experiments. --- ### Towards Human-Centric Intelligent Treatment Planning for Radiation Therapy Authors: Adnan Jafar, Xun Jia Published: 2025-10-15 Categories: physics.med-ph, cs.AI arXiv: https://arxiv.org/abs/2510.13062v1 Current radiation therapy treatment planning is limited by suboptimal plan quality, inefficiency, and high costs. This perspective paper explores the complexity of treatment planning and introduces Human-Centric Intelligent Treatment Planning (HCITP), an AI-driven framework under human oversight, which integrates clinical guidelines, automates plan generation, and enables direct interactions with operators. We expect that HCITP will enhance efficiency, potentially reducing planning time to minutes, and will deliver personalized, high-quality plans. Challenges and potential solutions are discussed. --- ### Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games Authors: Anupam Nayak, Tong Yang, Osman Yagan, Gauri Joshi, Yuejie Chi Published: 2025-10-15 Categories: cs.LG, cs.GT, math.OC, stat.ML arXiv: https://arxiv.org/abs/2510.13060v2 Reverse Kullback-Leibler (KL) divergence-based regularization with respect to a fixed reference policy is widely used in modern reinforcement learning to preserve the desired traits of the reference policy and sometimes to promote exploration (using uniform reference policy, known as entropy regularization). Beyond serving as a mere anchor, the reference policy can also be interpreted as encoding prior knowledge about good actions in the environment. In the context of alignment, recent game-theoretic approaches have leveraged KL regularization with pretrained language models as reference policies, achieving notable empirical success in self-play methods. Despite these advances, the theoretical benefits of KL regularization in game-theoretic settings remain poorly understood. In this work, we develop and analyze algorithms that provably achieve improved sample efficiency under KL regularization. We study both two-player zero-sum matrix games and Markov games: for matrix games, we propose OMG, an algorithm based on best response sampling with optimistic bonuses, and extend this idea to Markov games through the algorithm SOMG, which also uses best response sampling and a novel concept of superoptimistic bonuses. Both algorithms achieve a logarithmic regret in $T$ that scales inversely with the KL regularization strength $β$ in addition to the traditional $\widetilde{\mathcal{O}}(\sqrt{T})$ regret without the $β^{-1}$ dependence. --- ### Reciprocal Space Attention for Learning Long-Range Interactions Authors: Hariharan Ramasubramanian, Alvaro Vazquez-Mayagoitia, Ganesh Sivaraman, Atul C. Thakur Published: 2025-10-15 Categories: cond-mat.mtrl-sci, cs.LG, physics.chem-ph, physics.comp-ph arXiv: https://arxiv.org/abs/2510.13055v1 Machine learning interatomic potentials (MLIPs) have revolutionized the modeling of materials and molecules by directly fitting to ab initio data. However, while these models excel at capturing local and semi-local interactions, they often prove insufficient when an explicit and efficient treatment of long-range interactions is required. To address this limitation, we introduce Reciprocal-Space Attention (RSA), a framework designed to capture long-range interactions in the Fourier domain. RSA can be integrated with any existing local or semi-local MLIP framework. The central contribution of this work is the mapping of a linear-scaling attention mechanism into Fourier space, enabling the explicit modeling of long-range interactions such as electrostatics and dispersion without relying on predefined charges or other empirical assumptions. We demonstrate the effectiveness of our method as a long-range correction to the MACE backbone across diverse benchmarks, including dimer binding curves, dispersion-dominated layered phosphorene exfoliation, and the molecular dipole density of bulk water. Our results show that RSA consistently captures long-range physics across a broad range of chemical and materials systems. The code and datasets for this work is available at https://github.com/rfhari/reciprocal_space_attention --- ### VLA-0: Building State-of-the-Art VLAs with Zero Modification Authors: Ankit Goyal, Hugo Hadfield, Xuning Yang, Valts Blukis, Fabio Ramos Published: 2025-10-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2510.13054v1 Vision-Language-Action models (VLAs) hold immense promise for enabling generalist robot manipulation. However, the best way to build them remains an open question. Current approaches often add complexity, such as modifying the existing vocabulary of a Vision-Language Model (VLM) with action tokens or introducing special action heads. Curiously, the simplest strategy of representing actions directly as text has remained largely unexplored. This work introduces VLA-0 to investigate this idea. We find that VLA-0 is not only effective; it is surprisingly powerful. With the right design, VLA-0 outperforms more involved models. On LIBERO, a popular benchmark for evaluating VLAs, VLA-0 outperforms all existing methods trained on the same robotic data, including $π_0.5$-KI, OpenVLA-OFT and SmolVLA. Furthermore, without large-scale robotics-specific training, it outperforms methods trained on large-scale robotic data, like $π_0.5$-KI, $π_0$, GR00T-N1 and MolmoAct. These findings also translate to the real world, where VLA-0 outperforms SmolVLA, a VLA model pre-trained on large-scale real data. This paper summarizes our unexpected findings and spells out the specific techniques required to unlock the high performance of this simple yet potent VLA design. Visual results, code, and trained models are provided here: https://vla0.github.io/. --- ### Time-Varying Optimization for Streaming Data Via Temporal Weighting Authors: Muhammad Faraz Ul Abrar, Nicolò Michelusi, Erik G. Larsson Published: 2025-10-15 Categories: cs.LG, cs.AI, eess.SP, eess.SY, math.OC arXiv: https://arxiv.org/abs/2510.13052v1 Classical optimization theory deals with fixed, time-invariant objective functions. However, time-varying optimization has emerged as an important subject for decision-making in dynamic environments. In this work, we study the problem of learning from streaming data through a time-varying optimization lens. Unlike prior works that focus on generic formulations, we introduce a structured, \emph{weight-based} formulation that explicitly captures the streaming-data origin of the time-varying objective, where at each time step, an agent aims to minimize a weighted average loss over all the past data samples. We focus on two specific weighting strategies: (1) uniform weights, which treat all samples equally, and (2) discounted weights, which geometrically decay the influence of older data. For both schemes, we derive tight bounds on the ``tracking error'' (TE), defined as the deviation between the model parameter and the time-varying optimum at a given time step, under gradient descent (GD) updates. We show that under uniform weighting, the TE vanishes asymptotically with a $\mathcal{O}(1/t)$ decay rate, whereas discounted weighting incurs a nonzero error floor controlled by the discount factor and the number of gradient updates performed at each time step. Our theoretical findings are validated through numerical simulations. --- ### An Operational Deep Learning System for Satellite-Based High-Resolution Global Nowcasting Authors: Shreya Agrawal, Mohammed Alewi Hassen, Emmanuel Asiedu Brempong, Boris Babenko, Fred Zyda, Olivia Graham, Di Li, Samier Merchant, Santiago Hincapie Potes, Tyler Russell, Danny Cheresnick, Aditya Prakash Kakkirala et al. Published: 2025-10-15 Categories: cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2510.13050v1 Precipitation nowcasting, which predicts rainfall up to a few hours ahead, is a critical tool for vulnerable communities in the Global South frequently exposed to intense, rapidly developing storms. Timely forecasts provide a crucial window to protect lives and livelihoods. Traditional numerical weather prediction (NWP) methods suffer from high latency, low spatial and temporal resolution, and significant gaps in accuracy across the world. Recent machine learning-based nowcasting methods, common in the Global North, cannot be extended to the Global South due to extremely sparse radar coverage. We present Global MetNet, an operational global machine learning nowcasting model. It leverages the Global Precipitation Mission's CORRA dataset, geostationary satellite data, and global NWP data to predict precipitation for the next 12 hours. The model operates at a high resolution of approximately 0.05° (~5km) spatially and 15 minutes temporally. Global MetNet significantly outperforms industry-standard hourly forecasts and achieves significantly higher skill, making forecasts useful over a much larger area of the world than previously available. Our model demonstrates better skill in data-sparse regions than even the best high-resolution NWP models achieve in the US. Validated using ground radar and satellite data, it shows significant improvements across key metrics like the critical success index and fractions skill score for all precipitation rates and lead times. Crucially, our model generates forecasts in under a minute, making it readily deployable for real-time applications. It is already deployed for millions of users on Google Search. This work represents a key step in reducing global disparities in forecast quality and integrating sparse, high-resolution satellite observations into weather forecasting. --- ### AMORE: Adaptive Multi-Output Operator Network for Stiff Chemical Kinetics Authors: Kamaljyoti Nath, Additi Pandey, Bryan T. Susi, Hessam Babaee, George Em Karniadakis Published: 2025-10-15 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.12999v2 Time integration of stiff systems is a primary source of computational cost in combustion, hypersonics, and other reactive transport systems. This stiffness can introduce time scales significantly smaller than those associated with other physical processes, requiring extremely small time steps in explicit schemes or computationally intensive implicit methods. Consequently, strategies to alleviate challenges posed by stiffness are important. While neural operators (DeepONets) can act as surrogates for stiff kinetics, a reliable operator learning strategy is required to appropriately account for differences in error between output variables and samples. Here, we develop AMORE, Adaptive Multi-Output Operator Network, a framework comprising an operator capable of predicting multiple outputs and adaptive loss functions ensuring reliable operator learning. The operator predicts all thermochemical states from given initial conditions. We propose two adaptive loss functions within the framework, considering each state variable's and sample's error to penalize the loss function. We designed the trunk to automatically satisfy Partition of Unity. To enforce unity mass-fraction constraint exactly, we propose an invertible analytical map that transforms the $n$-dimensional species mass-fraction vector into an ($n-1$)-dimensional space. We extend the proposed adaptive loss functions to trunk and branch training in two-step training of DeepONet with multiple outputs. We implemented another unity mass fraction constraint exactly using a softmax function on the predicted mass fraction. We demonstrate efficacy and applicability of our models through two examples: syngas (12 states), GRI-Mech 3.0 (24 active states out of 54). The proposed DeepONet will be a backbone for future CFD studies to accelerate turbulent combustion simulations. AMORE is a general framework, and here, we also demonstrate it for FNO. --- ### Shielded RecRL: Explanation Generation for Recommender Systems without Ranking Degradation Authors: Ansh Tiwari, Ayush Chauhan Published: 2025-10-14 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2601.03608v1 We introduce Shielded RecRL, a reinforcement learning approach to generate personalized explanations for recommender systems without sacrificing the system's original ranking performance. Unlike prior RLHF-based recommender methods that directly optimize item rankings, our two-tower architecture keeps the recommender's ranking model intact while a language model learns to produce helpful explanations. We design a composite reward signal combining explanation length, content relevance, and coherence, and apply proximal policy optimization (PPO) with a KL-divergence constraint to fine-tune a large language model with only 0.4% of its parameters trainable via LoRA adapters. In experiments on an Amazon Books dataset (approximately 50K interactions in the fantasy and romance genres), Shielded RecRL improved the relative click-through rate (CTR) by 22.5% (1.225x over baseline) while keeping the recommender's item-ranking behavior virtually unchanged. An extensive ablation study confirms that our gradient shielding strategy and reward design effectively balance explanation quality and policy drift. Our results demonstrate that Shielded RecRL enhances user-facing aspects of recommendations through rich, personalized explanations without degrading core recommendation accuracy. --- ### Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant Authors: Joseph Matveyenko, James Liu, John David Parsons, Ryan A. Brown, Alina Palimaru, Prateek Puri Published: 2025-10-14 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2512.00009v2 Qualitative research emphasizes constructing meaning through iterative engagement with textual data. Traditionally this human-driven process requires navigating coder fatigue and interpretative drift, thus posing challenges when scaling analysis to larger, more complex datasets. Computational approaches to augment qualitative research have been met with skepticism, partly due to their inability to replicate the nuance, context-awareness, and sophistication of human analysis. Large language models, however, present new opportunities to automate aspects of qualitative analysis while upholding rigor and research quality in important ways. To assess their benefits and limitations - and build trust among qualitative researchers - these approaches must be rigorously benchmarked against human-generated datasets. In this work, we benchmark Muse, an interactive, AI-powered qualitative research system that allows researchers to identify themes and annotate datasets, finding an inter-rater reliability between Muse and humans of Cohen's $κ$ = 0.71 for well-specified codes. We also conduct robust error analysis to identify failure mode, guide future improvements, and demonstrate the capacity to correct for human bias. --- ### MOTION: ML-Assisted On-Device Low-Latency Motion Recognition Authors: Veeramani Pugazhenthi, Wei-Hsiang Chu, Junwei Lu, Jadyn N. Miyahira, Mahdi Eslamimehr, Pratik Satam, Rozhin Yasaei, Soheil Salehi Published: 2025-10-14 Categories: cs.CV, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2512.00008v3 The use of tiny devices capable of low-latency gesture recognition is gaining momentum in everyday human-computer interaction and especially in medical monitoring fields. Embedded solutions such as fall detection, rehabilitation tracking, and patient supervision require fast and efficient tracking of movements while avoiding unwanted false alarms. This study presents an efficient solution on how to build very efficient motion-based models only using triaxial accelerometer sensors. We explore the capability of the AutoML pipelines to extract the most important features from the data segments. This approach also involves training multiple lightweight machine learning algorithms using the extracted features. We use WeBe Band, a multi-sensor wearable device that is equipped with a powerful enough MCU to effectively perform gesture recognition entirely on the device. Of the models explored, we found that the neural network provided the best balance between accuracy, latency, and memory use. Our results also demonstrate that reliable real-time gesture recognition can be achieved in WeBe Band, with great potential for real-time medical monitoring solutions that require a secure and fast response time. --- ### Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning Authors: Guangzhi Wang, Kai Li, Yinghao Jiao, Zhi Liu Published: 2025-10-14 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2511.13726v2 We propose RT (Refine Thought), a method that can enhance the semantic reasoning ability of text embedding models. The method obtains the final semantic representation by running multiple forward passes of the text embedding model. Experiments show that RT achieves significant improvements on semantic reasoning tasks in BRIGHT and the person-job matching benchmark PJBenchmark, while maintaining consistent performance on general-purpose semantic understanding tasks such as C-MTEB. Our results indicate that RT is effective because it further activates the semantic reasoning ability learned during pretraining by decoder-only text embedding models (e.g., Qwen3-Embedding-8B). RT can be seen as a test-time inference method. --- ### StrikeWatch: Wrist-worn Gait Recognition with Compact Time-series Models on Low-power FPGAs Authors: Tianheng Ling, Chao Qian, Peter Zdankin, Torben Weis, Gregor Schiele Published: 2025-10-14 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2510.24738v2 Running offers substantial health benefits, but improper gait patterns can lead to injuries, particularly without expert feedback. While prior gait analysis systems based on cameras, insoles, or body-mounted sensors have demonstrated effectiveness, they are often bulky and limited to offline, post-run analysis. Wrist-worn wearables offer a more practical and non-intrusive alternative, yet enabling real-time gait recognition on such devices remains challenging due to noisy Inertial Measurement Unit (IMU) signals, limited computing resources, and dependence on cloud connectivity. This paper introduces StrikeWatch, a compact wrist-worn system that performs entirely on-device, real-time gait recognition using IMU signals. As a case study, we target the detection of heel versus forefoot strikes to enable runners to self-correct harmful gait patterns through visual and auditory feedback during running. We propose four compact DL architectures (1D-CNN, 1D-SepCNN, LSTM, and Transformer) and optimize them for energy-efficient inference on two representative embedded Field-Programmable Gate Arrays (FPGAs): the AMD Spartan-7 XC7S15 and the Lattice iCE40UP5K. Using our custom-built hardware prototype, we collect a labeled dataset from outdoor running sessions and evaluate all models via a fully automated deployment pipeline. Our results reveal clear trade-offs between model complexity and hardware efficiency. Evaluated across 12 participants, 6-bit quantized 1D-SepCNN achieves the highest average F1 score of 0.847 while consuming just 0.350 microjoule per inference with a latency of 0.140 ms on the iCE40UP5K running at 20 MHz. This configuration supports up to 13.6 days of continuous inference on a 320 mAh battery. All datasets and code are available in the GitHub repository https://github.com/tianheng-ling/StrikeWatch. --- ### Cardi-GPT: An Expert ECG-Record Processing Chatbot Authors: Koustav Mallick, Neel Singh, Mohammedreza Hajiarbabi Published: 2025-10-14 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.24737v1 Interpreting and communicating electrocardiogram (ECG) findings are crucial yet challenging tasks in cardiovascular diagnosis, traditionally requiring significant expertise and precise clinical communication. This paper introduces Cardi-GPT, an advanced expert system designed to streamline ECG interpretation and enhance clinical communication through deep learning and natural language interaction. Cardi-GPT employs a 16-residual-block convolutional neural network (CNN) to process 12-lead ECG data, achieving a weighted accuracy of 0.6194 across 24 cardiac conditions. A novel fuzzification layer converts complex numerical outputs into clinically meaningful linguistic categories, while an integrated chatbot interface facilitates intuitive exploration of diagnostic insights and seamless communication between healthcare providers. The system was evaluated on a diverse dataset spanning six hospitals across four countries, demonstrating superior performance compared to baseline models. Additionally, Cardi-GPT achieved an impressive overall response quality score of 73\%, assessed using a comprehensive evaluation framework that measures coverage, grounding, and coherence. By bridging the gap between intricate ECG data interpretation and actionable clinical insights, Cardi-GPT represents a transformative innovation in cardiovascular healthcare, promising to improve diagnostic accuracy, clinical workflows, and patient outcomes across diverse medical settings. --- ### RNAGenScape: Property-Guided, Optimized Generation of mRNA Sequences with Manifold Langevin Dynamics Authors: Danqi Liao, Chen Liu, Xingzhi Sun, Dié Tang, Haochen Wang, Scott Youlten, Srikar Krishna Gopinath, Haejeong Lee, Ethan C. Strayer, Antonio J. Giraldez, Smita Krishnaswamy Published: 2025-10-14 Categories: q-bio.QM, cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2510.24736v4 Generating property-optimized mRNA sequences is central to applications such as vaccine design and protein replacement therapy, but remains challenging due to limited data, complex sequence-function relationships, and the narrow space of biologically viable sequences. Generative methods that drift away from the data manifold can yield sequences that fail to fold, translate poorly, or are otherwise nonfunctional. We present RNAGenScape, a property-guided manifold Langevin dynamics framework for mRNA sequence generation that operates on a learned manifold of real data. By performing iterative local optimization constrained to this manifold, RNAGenScape preserves favorable computational viability proxies, accesses reliable guidance, and discourages excursions into regions poorly supported by the training data. The framework integrates three components: (1) an autoencoder jointly trained with a property predictor to learn a property-organized latent manifold, (2) a denoising autoencoder that projects updates back onto the manifold, and (3) a property-guided Langevin dynamics procedure that performs optimization along the manifold. Across three real-world mRNA datasets spanning two orders of magnitude in size, RNAGenScape increases median oracle-predicted property gain by up to 267% and success rate by up to 31%, while maintaining good biological viability proxy measures and achieving competitive inference efficiency compared to existing generative approaches. --- ### DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving Scenes Authors: Qirui Hou, Wenzhang Sun, Chang Zeng, Chunfeng Wang, Hao Li, Jianxun Cui Published: 2025-10-14 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2510.24734v1 Real-time, high-fidelity reconstruction of dynamic driving scenes is challenged by complex dynamics and sparse views, with prior methods struggling to balance quality and efficiency. We propose DrivingScene, an online, feed-forward framework that reconstructs 4D dynamic scenes from only two consecutive surround-view images. Our key innovation is a lightweight residual flow network that predicts the non-rigid motion of dynamic objects per camera on top of a learned static scene prior, explicitly modeling dynamics via scene flow. We also introduce a coarse-to-fine training paradigm that circumvents the instabilities common to end-to-end approaches. Experiments on nuScenes dataset show our image-only method simultaneously generates high-quality depth, scene flow, and 3D Gaussian point clouds online, significantly outperforming state-of-the-art methods in both dynamic reconstruction and novel view synthesis. --- ### Emergence of Internal State-Modulated Swarming in Multi-Agent Patch Foraging System Authors: Siddharth Chaturvedi, Ahmed EL-Gazzar, Marcel van Gerven Published: 2025-10-14 Categories: nlin.AO, cs.MA, cs.NE arXiv: https://arxiv.org/abs/2510.18886v2 Active particles are entities that sustain persistent out-of-equilibrium motion by consuming energy. Under certain conditions, they exhibit the tendency to self-organize through coordinated movements, such as swarming via aggregation. While performing non-cooperative foraging tasks, the emergence of such swarming behavior in foragers, exemplifying active particles, has been attributed to the partial observability of the environment, in which the presence of another forager can serve as a proxy signal to indicate the potential presence of a food source or a resource patch. In this paper, we validate this phenomenon by simulating multiple self-propelled foragers as they forage from multiple resource patches in a non-cooperative manner. These foragers operate in a continuous two-dimensional space with stochastic position updates and partial observability. We evolve a shared policy in the form of a continuous-time recurrent neural network that serves as a velocity controller for the foragers. To this end, we use an evolutionary strategy algorithm wherein the different samples of the policy-distribution are evaluated in the same rollout. Then we show that agents are able to learn to adaptively forage in the environment. Next, we show the emergence of swarming in the form of aggregation among the foragers when resource patches are absent. We observe that the strength of this swarming behavior appears to be inversely proportional to the amount of resource stored in the foragers, which supports the risk-sensitive foraging claims. Empirical analysis of the learned controller's hidden states in minimal test runs uncovers their sensitivity to the amount of resource stored in a forager. Clamping these hidden states to represent a lesser amount of resource hastens its learned aggregation behavior. --- ### Deploying Atmospheric and Oceanic AI Models on Chinese Hardware and Framework: Migration Strategies, Performance Optimization and Analysis Authors: Yuze Sun, Wentao Luo, Yanfei Xiang, Jiancheng Pan, Jiahao Li, Quan Zhang, Xiaomeng Huang Published: 2025-10-14 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.17852v1 With the growing role of artificial intelligence in climate and weather research, efficient model training and inference are in high demand. Current models like FourCastNet and AI-GOMS depend heavily on GPUs, limiting hardware independence, especially for Chinese domestic hardware and frameworks. To address this issue, we present a framework for migrating large-scale atmospheric and oceanic models from PyTorch to MindSpore and optimizing for Chinese chips, and evaluating their performance against GPUs. The framework focuses on software-hardware adaptation, memory optimization, and parallelism. Furthermore, the model's performance is evaluated across multiple metrics, including training speed, inference speed, model accuracy, and energy efficiency, with comparisons against GPU-based implementations. Experimental results demonstrate that the migration and optimization process preserves the models' original accuracy while significantly reducing system dependencies and improving operational efficiency by leveraging Chinese chips as a viable alternative for scientific computing. This work provides valuable insights and practical guidance for leveraging Chinese domestic chips and frameworks in atmospheric and oceanic AI model development, offering a pathway toward greater technological independence. ---