# Research Papers — 2025-11 · bundle page 55 of 197 > Full-text markdown of papers #2701–2750 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/55 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/54.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/56.md) ### DiM-TS: Bridge the Gap between Selective State Space Models and Time Series for Generative Modeling Authors: Zihao Yao, Jiankai Zuo, Yaying Zhang Published: 2025-11-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18312v1 Time series data plays a pivotal role in a wide variety of fields but faces challenges related to privacy concerns. Recently, synthesizing data via diffusion models is viewed as a promising solution. However, existing methods still struggle to capture long-range temporal dependencies and complex channel interrelations. In this research, we aim to utilize the sequence modeling capability of a State Space Model called Mamba to extend its applicability to time series data generation. We firstly analyze the core limitations in State Space Model, namely the lack of consideration for correlated temporal lag and channel permutation. Building upon the insight, we propose Lag Fusion Mamba and Permutation Scanning Mamba, which enhance the model's ability to discern significant patterns during the denoising process. Theoretical analysis reveals that both variants exhibit a unified matrix multiplication framework with the original Mamba, offering a deeper understanding of our method. Finally, we integrate two variants and introduce Diffusion Mamba for Time Series (DiM-TS), a high-quality time series generation model that better preserves the temporal periodicity and inter-channel correlations. Comprehensive experiments on public datasets demonstrate the superiority of DiM-TS in generating realistic time series while preserving diverse properties of data. --- ### ScriptViT: Vision Transformer-Based Personalized Handwriting Generation Authors: Sajjan Acharya, Rajendra Baskota Published: 2025-11-23 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.18307v1 Styled handwriting generation aims to synthesize handwritten text that looks both realistic and aligned with a specific writer's style. While recent approaches involving GAN, transformer and diffusion-based models have made progress, they often struggle to capture the full spectrum of writer-specific attributes, particularly global stylistic patterns that span long-range spatial dependencies. As a result, capturing subtle writer-specific traits such as consistent slant, curvature or stroke pressure, while keeping the generated text accurate is still an open problem. In this work, we present a unified framework designed to address these limitations. We introduce a Vision Transformer-based style encoder that learns global stylistic patterns from multiple reference images, allowing the model to better represent long-range structural characteristics of handwriting. We then integrate these style cues with the target text using a cross-attention mechanism, enabling the system to produce handwritten images that more faithfully reflect the intended style. To make the process more interpretable, we utilize Salient Stroke Attention Analysis (SSAA), which reveals the stroke-level features the model focuses on during style transfer. Together, these components lead to handwriting synthesis that is not only more stylistically coherent, but also easier to understand and analyze. --- ### Table Comprehension in Building Codes using Vision Language Models and Domain-Specific Fine-Tuning Authors: Mohammad Aqib, Mohd Hamza, Ying Hei Chui, Qipei Mei Published: 2025-11-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18306v1 Building codes contain critical information for ensuring safety, regulatory compliance, and informed decision-making in construction and engineering. Automated question answering systems over such codes enable quick and accurate access to specific regulatory clauses, improving efficiency and reducing errors. Retrieval-Augmented Generation (RAG) systems are essential for this task as they combine the precision of information retrieval with the generative capabilities of language models. However, tabular data are challenging to extract as they often involve complex layouts, merged cells, multi-row headers, and embedded semantic relationships that are not easily captured by traditional natural language processing techniques and Vision Language Models (VLMs). This paper explores and compares two methods for extracting information from tabular data in building codes using several pre-trained VLMs. First, a direct input method is used, where the image of the page is input directly into the VLMs, which are then tasked with answering questions based on the image. Second, an indirect input method is introduced, which involves converting an image of a page containing tables into the LaTeX code and then answering inquires based on the LaTeX-based input. The experiments find that the direct input method generally resulted in higher accuracy than the indirect input method. To further improve the performance, we fine-tuned each VLM using Low Rank Adaptation (LoRA) on a domain-specific tabular dataset. The fine-tuned models exhibited substantial improvements, with Qwen2.5-VL-3B-Instruct achieving relative accuracy gains exceeding 100%. Our results highlight the potential of parameter-efficient fine-tuning methods to adapt powerful VLMs for understanding complex structured data in specialized fields, such as building code interpretation and regulatory compliance. --- ### DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognition Authors: Raja Kumar, Arka Sadhu, Ram Nevatia Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18305v2 Large Vision Language Models (LVLMs) possess extensive text knowledge but struggles to utilize this knowledge for fine-grained image recognition, often failing to differentiate between visually similar categories. Existing fine-tuning methods using Reinforcement Learning (RL) with exact-match reward signals are often brittle, encourage memorization of training categories, and fail to elicit differential reasoning needed for generalization to unseen classes. To address this, we propose $\textbf{DiVE-k}$, $\textbf{Di}$fferential $\textbf{V}$isual r$\textbf{E}$asoning using top-$\textbf{k}$ generations, framework that leverages model's own top-k predictions as a training signal. For each training image, DiVE-k creates a multiple-choice question from the model's top-k outputs and uses RL to train the model to select the correct answer. This approach requires the model to perform fine-grained differential reasoning among plausible options and provides a simple, verifiable reward signal that mitigates memorization and improves generalization. Experiments on five standard fine-grained datasets show that our method significantly outperforms existing approaches. In the standard base-to-novel generalization setting, DiVE-k surpasses the QWEN2.5-VL-7B and ViRFT by 10.04% and 6.16% on the Harmonic Mean metric, respectively. Further experiments show similar gains in mixed-domain and few-shot scenarios. Our code is available $\href{https://github.com/raja-kumar/DiVE-k}{here}$ --- ### DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognition Authors: Raja Kumar, Arka Sadhu, Ram Nevatia Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18305v1 Large Vision Language Models (LVLMs) possess extensive text knowledge but struggles to utilize this knowledge for fine-grained image recognition, often failing to differentiate between visually similar categories. Existing fine-tuning methods using Reinforcement Learning (RL) with exact-match reward signals are often brittle, encourage memorization of training categories, and fail to elicit differential reasoning needed for generalization to unseen classes. To address this, we propose $\textbf{DiVE-k}$, $\textbf{Di}$fferential $\textbf{V}$isual r$\textbf{E}$asoning using top-$\textbf{k}$ generations, framework that leverages model's own top-k predictions as a training signal. For each training image, DiVE-k creates a multiple-choice question from the model's top-k outputs and uses RL to train the model to select the correct answer. This approach requires the model to perform fine-grained differential reasoning among plausible options and provides a simple, verifiable reward signal that mitigates memorization and improves generalization. Experiments on five standard fine-grained datasets show that our method significantly outperforms existing approaches. In the standard base-to-novel generalization setting, DiVE-k surpasses the QWEN2.5-VL-7B and ViRFT by 10.04% and 6.16% on the Harmonic Mean metric, respectively. Further experiments show similar gains in mixed-domain and few-shot scenarios. --- ### Hierarchical Deep Research with Local-Web RAG: Toward Automated System-Level Materials Discovery Authors: Rui Ding, Rodrigo Pires Ferreira, Yuxin Chen, Junhong Chen Published: 2025-11-23 Categories: cs.LG, cond-mat.mes-hall, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2511.18303v2 We present a long-horizon, hierarchical deep research (DR) agent designed for complex materials and device discovery problems that exceed the scope of existing Machine Learning (ML) surrogates and closed-source commercial agents. Our framework instantiates a locally deployable DR instance that integrates local retrieval-augmented generation with large language model reasoners, enhanced by a Deep Tree of Research (DToR) mechanism that adaptively expands and prunes research branches to maximize coverage, depth, and coherence. We systematically evaluate across 27 nanomaterials/device topics using a large language model (LLM)-as-judge rubric with five web-enabled state-of-the-art models as jurors. In addition, we conduct dry-lab validations on five representative tasks, where human experts use domain simulations (e.g., density functional theory, DFT) to verify whether DR-agent proposals are actionable. Results show that our DR agent produces reports with quality comparable to--and often exceeding--those of commercial systems (ChatGPT-5-thinking/o3/o4-mini-high Deep Research) at a substantially lower cost, while enabling on-prem integration with local data and tools. --- ### Hierarchical Deep Research with Local-Web RAG: Toward Automated System-Level Materials Discovery Authors: Rui Ding, Rodrigo Pires Ferreira, Yuxin Chen, Junhong Chen Published: 2025-11-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18303v1 We present a long-horizon, hierarchical deep research (DR) agent designed for complex materials and device discovery problems that exceed the scope of existing Machine Learning (ML) surrogates and closed-source commercial agents. Our framework instantiates a locally deployable DR instance that integrates local retrieval-augmented generation with large language model reasoners, enhanced by a Deep Tree of Research (DToR) mechanism that adaptively expands and prunes research branches to maximize coverage, depth, and coherence. We systematically evaluate across 27 nanomaterials/device topics using a large language model (LLM)-as-judge rubric with five web-enabled state-of-the-art models as jurors. In addition, we conduct dry-lab validations on five representative tasks, where human experts use domain simulations (e.g., density functional theory, DFT) to verify whether DR-agent proposals are actionable. Results show that our DR agent produces reports with quality comparable to--and often exceeding--those of commercial systems (ChatGPT-5-thinking/o3/o4-mini-high Deep Research) at a substantially lower cost, while enabling on-prem integration with local data and tools. --- ### The Catastrophic Paradox of Human Cognitive Frameworks in Large Language Model Evaluation: A Comprehensive Empirical Analysis of the CHC-LLM Incompatibility Authors: Mohan Reddy Published: 2025-11-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.18302v1 This investigation presents an empirical analysis of the incompatibility between human psychometric frameworks and Large Language Model evaluation. Through systematic assessment of nine frontier models including GPT-5, Claude Opus 4.1, and Gemini 3 Pro Preview using the Cattell-Horn-Carroll theory of intelligence, we identify a paradox that challenges the foundations of cross-substrate cognitive evaluation. Our results show that models achieving above-average human IQ scores ranging from 85.0 to 121.4 simultaneously exhibit binary accuracy rates approaching zero on crystallized knowledge tasks, with an overall judge-binary correlation of r = 0.175 (p = 0.001, n = 1800). This disconnect appears most strongly in the crystallized intelligence domain, where every evaluated model achieved perfect binary accuracy while judge scores ranged from 25 to 62 percent, which cannot occur under valid measurement conditions. Using statistical analyses including Item Response Theory modeling, cross-vendor judge validation, and paradox severity indexing, we argue that this disconnect reflects a category error in applying biological cognitive architectures to transformer-based systems. The implications extend beyond methodology to challenge assumptions about intelligence, measurement, and anthropomorphic biases in AI evaluation. We propose a framework for developing native machine cognition assessments that recognize the non-human nature of artificial intelligence. --- ### "AGI" team at SHROOM-CAP: Data-Centric Approach to Multilingual Hallucination Detection using XLM-RoBERTa Authors: Harsh Rathva, Pruthwik Mishra, Shrikant Malviya Published: 2025-11-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18301v1 The detection of hallucinations in multilingual scientific text generated by Large Language Models (LLMs) presents significant challenges for reliable AI systems. This paper describes our submission to the SHROOM-CAP 2025 shared task on scientific hallucination detection across 9 languages. Unlike most approaches that focus primarily on model architecture, we adopted a data-centric strategy that addressed the critical issue of training data scarcity and imbalance. We unify and balance five existing datasets to create a comprehensive training corpus of 124,821 samples (50% correct, 50% hallucinated), representing a 172x increase over the original SHROOM training data. Our approach fine-tuned XLM-RoBERTa-Large with 560 million parameters on this enhanced dataset, achieves competitive performance across all languages, including \textbf{2nd place in Gujarati} (zero-shot language) with Factuality F1 of 0.5107, and rankings between 4th-6th place across the remaining 8 languages. Our results demonstrate that systematic data curation can significantly outperform architectural innovations alone, particularly for low-resource languages in zero-shot settings. --- ### Cross-Disciplinary Knowledge Retrieval and Synthesis: A Compound AI Architecture for Scientific Discovery Authors: Svitlana Volkova, Peter Bautista, Avinash Hiriyanna, Gabriel Ganberg, Isabel Erickson, Zachary Klinefelter, Nick Abele, Hsien-Te Kao, Grant Engberson Published: 2025-11-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.18298v1 The exponential growth of scientific knowledge has created significant barriers to cross-disciplinary knowledge discovery, synthesis and research collaboration. In response to this challenge, we present BioSage, a novel compound AI architecture that integrates LLMs with RAG, orchestrated specialized agents and tools to enable discoveries across AI, data science, biomedical, and biosecurity domains. Our system features several specialized agents including the retrieval agent with query planning and response synthesis that enable knowledge retrieval across domains with citation-backed responses, cross-disciplinary translation agents that align specialized terminology and methodologies, and reasoning agents that synthesize domain-specific insights with transparency, traceability and usability. We demonstrate the effectiveness of our BioSage system through a rigorous evaluation on scientific benchmarks (LitQA2, GPQA, WMDP, HLE-Bio) and introduce a new cross-modal benchmark for biology and AI, showing that our BioSage agents outperform vanilla and RAG approaches by 13\%-21\% powered by Llama 3.1. 70B and GPT-4o models. We perform causal investigations into compound AI system behavior and report significant performance improvements by adding RAG and agents over the vanilla models. Unlike other systems, our solution is driven by user-centric design principles and orchestrates specialized user-agent interaction workflows supporting scientific activities including but not limited to summarization, research debate and brainstorming. Our ongoing work focuses on multimodal retrieval and reasoning over charts, tables, and structured scientific data, along with developing comprehensive multimodal benchmarks for cross-disciplinary discovery. Our compound AI solution demonstrates significant potential for accelerating scientific advancement by reducing barriers between traditionally siloed domains. --- ### GROOT: Graph Edge Re-growth and Partitioning for the Verification of Large Designs in Logic Synthesis Authors: Kiran Thorat, Hongwu Peng, Yuebo Luo, Xi Xie, Shaoyi Huang, Amit Hasan, Jiahui Zhao, Yingjie Li, Zhijie Shi, Cunxi Yu, Caiwen Ding Published: 2025-11-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18297v1 Traditional verification methods in chip design are highly time-consuming and computationally demanding, especially for large scale circuits. Graph neural networks (GNNs) have gained popularity as a potential solution to improve verification efficiency. However, there lacks a joint framework that considers all chip design domain knowledge, graph theory, and GPU kernel designs. To address this challenge, we introduce GROOT, an algorithm and system co-design framework that contains chip design domain knowledge and redesigned GPU kernels, to improve verification efficiency. More specifically, we create node features utilizing the circuit node types and the polarity of the connections between the input edges to nodes in And-Inverter Graphs (AIGs). We utilize a graph partitioning algorithm to divide the large graphs into smaller sub-graphs for fast GPU processing and develop a graph edge re-growth algorithm to recover verification accuracy. We carefully profile the EDA graph workloads and observe the uniqueness of their polarized distribution of high degree (HD) nodes and low degree (LD) nodes. We redesign two GPU kernels (HD-kernel and LD-kernel), to fit the EDA graph learning workload on a single GPU. We compare the results with state-of-the-art (SOTA) methods: GAMORA, a GNN-based approach, and the traditional ABC framework. Results show that GROOT achieves a significant reduction in memory footprint (59.38 %), with high accuracy (99.96%) for a very large CSA multiplier, i.e. 1,024 bits with a batch size of 16, which consists of 134,103,040 nodes and 268,140,544 edges. We compare GROOT with GPU-based GPU Kernel designs SOTAs such as cuSPARSE, MergePath-SpMM, and GNNAdvisor. We achieve up to 1.104x, 5.796x, and 1.469x improvement in runtime, respectively. --- ### Deep Learning Decision Support System for Open-Pit Mining Optimisation: GPU-Accelerated Planning Under Geological Uncertainty Authors: Iman Rahimi Published: 2025-11-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.18296v1 This study presents Part II of an AI-enhanced Decision Support System (DSS), extending Rahimi (2025, Part I) by introducing a fully uncertainty-aware optimization framework for long-term open-pit mine planning. Geological uncertainty is modelled using a Variational Autoencoder (VAE) trained on 50,000 spatial grade samples, enabling the generation of probabilistic, multi-scenario orebody realizations that preserve geological continuity and spatial correlation. These scenarios are optimized through a hybrid metaheuristic engine integrating Genetic Algorithms (GA), Large Neighborhood Search (LNS), Simulated Annealing (SA), and reinforcement-learning-based adaptive control. An ε-constraint relaxation strategy governs the population exploration phase, allowing near-feasible schedule discovery early in the search and gradual tightening toward strict constraint satisfaction. GPU-parallel evaluation enables the simultaneous assessment of 65,536 geological scenarios, achieving near-real-time feasibility analysis. Results demonstrate up to 1.2 million-fold runtime improvement over IBM CPLEX and significantly higher expected NPV under geological uncertainty, confirming the DSS as a scalable and uncertainty-resilient platform for intelligent mine planning. --- ### MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decoding Authors: Mengchun Zhang, Kateryna Shapovalenko, Yucheng Shao, Eddie Guo, Parusha Pradhan Published: 2025-11-23 Categories: cs.LG, cs.AI, cs.HC, q-bio.NC arXiv: https://arxiv.org/abs/2511.18294v1 Neural decoding from electroencephalography (EEG) remains fundamentally limited by poor generalization to unseen subjects, driven by high inter-subject variability and the lack of large-scale datasets to model it effectively. Existing methods often rely on synthetic subject generation or simplistic data augmentation, but these strategies fail to scale or generalize reliably. We introduce \textit{MultiDiffNet}, a diffusion-based framework that bypasses generative augmentation entirely by learning a compact latent space optimized for multiple objectives. We decode directly from this space and achieve state-of-the-art generalization across various neural decoding tasks using subject and session disjoint evaluation. We also curate and release a unified benchmark suite spanning four EEG decoding tasks of increasing complexity (SSVEP, Motor Imagery, P300, and Imagined Speech) and an evaluation protocol that addresses inconsistent split practices in prior EEG research. Finally, we develop a statistical reporting framework tailored for low-trial EEG settings. Our work provides a reproducible and open-source foundation for subject-agnostic EEG decoding in real-world BCI systems. --- ### ADF-LoRA: Alternating Low-Rank Aggregation for Decentralized Federated Fine-Tuning Authors: Xiaoyu Wang, Xiaotian Li, Zhixiang Zhou, Chen Li, Yong Liu Published: 2025-11-23 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2511.18291v1 This paper revisits alternating low-rank updates for federated fine-tuning and examines their behavior in decentralized federated learning (DFL). While alternating the LoRA matrices has been shown to stabilize aggregation in centralized FL, extending this mechanism to decentralized, peer-to-peer communication introduces new challenges due to phase-state mismatch and block-wise divergence across clients. We introduce ADF-LoRA, which synchronizes the update of only one low-rank matrix per round and mixes both matrices to maintain more consistent parameter states under decentralized propagation. This design preserves the cross-term suppression effect of alternating updates while improving stability in serverless topologies. We provide a convergence analysis under standard smoothness assumptions and evaluate ADF-LoRA on multiple GLUE tasks. Experiments show that ADF-LoRA achieves faster and smoother convergence and delivers the highest average accuracy across tasks, outperforming existing LoRA variants in decentralized FL by a consistent margin. --- ### SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes Authors: Jungho Lee, Minhyeok Lee, Sunghun Yang, Minseok Kang, Sangyoun Lee Published: 2025-11-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18290v1 3D reconstruction in large-scale scenes is a fundamental task in 3D perception, but the inherent trade-off between accuracy and computational efficiency remains a significant challenge. Existing methods either prioritize speed and produce low-quality results, or achieve high-quality reconstruction at the cost of slow inference times. In this paper, we propose SwiftVGGT, a training-free method that significantly reduce inference time while preserving high-quality dense 3D reconstruction. To maintain global consistency in large-scale scenes, SwiftVGGT performs loop closure without relying on the external Visual Place Recognition (VPR) model. This removes redundant computation and enables accurate reconstruction over kilometer-scale environments. Furthermore, we propose a simple yet effective point sampling method to align neighboring chunks using a single Sim(3)-based Singular Value Decomposition (SVD) step. This eliminates the need for the Iteratively Reweighted Least Squares (IRLS) optimization commonly used in prior work, leading to substantial speed-ups. We evaluate SwiftVGGT on multiple datasets and show that it achieves state-of-the-art reconstruction quality while requiring only 33% of the inference time of recent VGGT-based large-scale reconstruction approaches. --- ### TRIDENT: A Trimodal Cascade Generative Framework for Drug and RNA-Conditioned Cellular Morphology Synthesis Authors: Rui Peng, Ziru Liu, Lingyuan Ye, Yuxing Lu, Boxin Shi, Jinzhuo Wang Published: 2025-11-23 Categories: cs.LG, cs.CV, q-bio.QM arXiv: https://arxiv.org/abs/2511.18287v1 Accurately modeling the relationship between perturbations, transcriptional responses, and phenotypic changes is essential for building an AI Virtual Cell (AIVC). However, existing methods typically constrained to modeling direct associations, such as Perturbation $\rightarrow$ RNA or Perturbation $\rightarrow$ Morphology, overlook the crucial causal link from RNA to morphology. To bridge this gap, we propose TRIDENT, a cascade generative framework that synthesizes realistic cellular morphology by conditioning on both the perturbation and the corresponding gene expression profile. To train and evaluate this task, we construct MorphoGene, a new dataset pairing L1000 gene expression with Cell Painting images for 98 compounds. TRIDENT significantly outperforms state-of-the-art approaches, achieving up to 7-fold improvement with strong generalization to unseen compounds. In a case study on docetaxel, we validate that RNA-guided synthesis accurately produces the corresponding phenotype. An ablation study further confirms that this RNA conditioning is essential for the model's high fidelity. By explicitly modeling transcriptome-phenome mapping, TRIDENT provides a powerful in silico tool and moves us closer to a predictive virtual cell. --- ### RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System Authors: Runwei Guan, Rongsheng Hu, Shangshu Chen, Ningyuan Xiao, Xue Xia, Jiayang Liu, Beibei Chen, Ziren Tang, Ningwei Ouyang, Shaofeng Liang, Yuxuan Fan, Wanjie Sun et al. Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18286v2 Current roadside perception systems mainly focus on instance-level perception, which fall short in enabling interaction via natural language and reasoning about traffic behaviors in context. To bridge this gap, we introduce RoadSceneVQA, a large-scale and richly annotated visual question answering (VQA) dataset specifically tailored for roadside scenarios. The dataset comprises 34,736 diverse QA pairs collected under varying weather, illumination, and traffic conditions, targeting not only object attributes but also the intent, legality, and interaction patterns of traffic participants. RoadSceneVQA challenges models to perform both explicit recognition and implicit commonsense reasoning, grounded in real-world traffic rules and contextual dependencies. To fully exploit the reasoning potential of Multi-modal Large Language Models (MLLMs), we further propose CogniAnchor Fusion (CAF), a vision-language fusion module inspired by human-like scene anchoring mechanisms. Moreover, we propose the Assisted Decoupled Chain-of-Thought (AD-CoT) to enhance the reasoned thinking via CoT prompting and multi-task learning. Based on the above, we propose the baseline model RoadMind. Experiments on RoadSceneVQA and CODA-LM benchmark show that the pipeline consistently improves both reasoning accuracy and computational efficiency, allowing the MLLM to achieve state-of-the-art performance in structural traffic perception and reasoning tasks. --- ### RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System Authors: Runwei Guan, Rongsheng Hu, Shangshu Chen, Ningyuan Xiao, Xue Xia, Jiayang Liu, Beibei Chen, Ziren Tang, Ningwei Ouyang, Shaofeng Liang, Yuxuan Fan, Wanjie Sun et al. Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18286v1 Current roadside perception systems mainly focus on instance-level perception, which fall short in enabling interaction via natural language and reasoning about traffic behaviors in context. To bridge this gap, we introduce RoadSceneVQA, a large-scale and richly annotated visual question answering (VQA) dataset specifically tailored for roadside scenarios. The dataset comprises 34,736 diverse QA pairs collected under varying weather, illumination, and traffic conditions, targeting not only object attributes but also the intent, legality, and interaction patterns of traffic participants. RoadSceneVQA challenges models to perform both explicit recognition and implicit commonsense reasoning, grounded in real-world traffic rules and contextual dependencies. To fully exploit the reasoning potential of Multi-modal Large Language Models (MLLMs), we further propose CogniAnchor Fusion (CAF), a vision-language fusion module inspired by human-like scene anchoring mechanisms. Moreover, we propose the Assisted Decoupled Chain-of-Thought (AD-CoT) to enhance the reasoned thinking via CoT prompting and multi-task learning. Based on the above, we propose the baseline model RoadMind. Experiments on RoadSceneVQA and CODA-LM benchmark show that the pipeline consistently improves both reasoning accuracy and computational efficiency, allowing the MLLM to achieve state-of-the-art performance in structural traffic perception and reasoning tasks. --- ### What Can We Actually Steer? A Multi-Behavior Study of Activation Control Authors: Tetiana Bas, Krystian Novak Published: 2025-11-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.18284v2 Large language models (LLMs) require precise behavior control for safe and effective deployment across diverse applications. Activation steering offers a promising approach for LLMs' behavioral control. We focus on the question of how steering effectiveness varies across different behavior types and whether the nature of target behaviors can predict steering success. We address this through empirical analysis of activation steering across 50 behaviors that span persona archetypes, personality traits, misalignment behaviors, style cues, and impersonation of public figures. We present a set of comprehensive experiments on coefficient optimization, vector properties, and data requirements to provide comprehensive guidance for the implementation of activation steering. Our analysis demonstrates that steering effectiveness varies significantly by behavior type, with different behavioral categories exhibiting distinct response patterns to intervention strength. We find that trait expression follows an inverted-U curve with a steering coefficient strength. We also show that vector separation metrics do not predict steering success, but larger training datasets enable more aggressive steering. These findings provide empirically grounded guidance for implementing activation steering and demonstrate that steering effectiveness is heavily influenced by behavior type. --- ### Steering Latent Traits, Not Learned Facts: An Empirical Study of Activation Control Limits Authors: Tetiana Bas, Krystian Novak Published: 2025-11-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.18284v1 Large language models (LLMs) require precise behavior control for safe and effective deployment across diverse applications. Activation steering offers a promising approach for LLMs' behavioral control. We focus on the question of how steering effectiveness varies across different behavior types and whether the nature of target behaviors can predict steering success. We address this through empirical analysis of activation steering across 50 behaviors that span persona archetypes, personality traits, misalignment behaviors, style cues, and impersonation of public figures. We present a set of comprehensive experiments on coefficient optimization, vector properties, and data requirements to provide comprehensive guidance for the implementation of activation steering. Our analysis demonstrates that steering effectiveness varies significantly by behavior type, with different behavioral categories exhibiting distinct response patterns to intervention strength. We find that trait expression follows an inverted-U curve with a steering coefficient strength. We also show that vector separation metrics do not predict steering success, but larger training datasets enable more aggressive steering. These findings provide empirically grounded guidance for implementing activation steering and demonstrate that steering effectiveness is heavily influenced by behavior type. --- ### Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation Authors: Yara Bahram, Mélodie Desbos, Mohammadhadi Shateri, Eric Granger Published: 2025-11-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18281v3 Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within their teacher's domain. Thus, fast and high-quality generation for novel domains relies on two-stage pipelines: Adapt-then-Distill or Distill-then-Adapt. However, both add design complexity and often degrade quality or diversity. We introduce Uni-DAD, a single-stage pipeline that unifies DM distillation and adaptation. It couples two training signals: (i) a dual-domain distribution-matching distillation (DMD) objective that guides the student toward the distributions of the source teacher and a target teacher, and (ii) a multi-head generative adversarial network (GAN) loss that encourages target realism across multiple feature scales. The source domain distillation preserves diverse source knowledge, while the multi-head GAN stabilizes training and reduces overfitting, especially in few-shot regimes. The inclusion of a target teacher facilitates adaptation to more structurally distant domains. We evaluate Uni-DAD on two comprehensive benchmarks for few-shot image generation (FSIG) and subject-driven personalization (SDP) using diffusion backbones. It delivers better or comparable quality to state-of-the-art (SoTA) adaptation methods even with less than 4 sampling steps, and often surpasses two-stage pipelines in quality and diversity. Code: https://github.com/yaramohamadi/uni-DAD. --- ### Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation Authors: Yara Bahram, Melodie Desbos, Mohammadhadi Shateri, Eric Granger Published: 2025-11-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18281v1 Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within their teacher's domain. Thus, fast and high-quality generation for novel domains relies on two-stage training pipelines: Adapt-then-Distill or Distill-then-Adapt. However, both add design complexity and suffer from degraded quality or diversity. We introduce Uni-DAD, a single-stage pipeline that unifies distillation and adaptation of DMs. It couples two signals during training: (i) a dual-domain distribution-matching distillation objective that guides the student toward the distributions of the source teacher and a target teacher, and (ii) a multi-head generative adversarial network (GAN) loss that encourages target realism across multiple feature scales. The source domain distillation preserves diverse source knowledge, while the multi-head GAN stabilizes training and reduces overfitting, especially in few-shot regimes. The inclusion of a target teacher facilitates adaptation to more structurally distant domains. We perform evaluations on a variety of datasets for few-shot image generation (FSIG) and subject-driven personalization (SDP). Uni-DAD delivers higher quality than state-of-the-art (SoTA) adaptation methods even with less than 4 sampling steps, and outperforms two-stage training pipelines in both quality and diversity. --- ### From Tables to Signals: Revealing Spectral Adaptivity in TabPFN Authors: Jianqiao Zheng, Cameron Gordon, Yiping Ji, Hemanth Saratchandran, Simon Lucey Published: 2025-11-23 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.18278v1 Task-agnostic tabular foundation models such as TabPFN have achieved impressive performance on tabular learning tasks, yet the origins of their inductive biases remain poorly understood. In this work, we study TabPFN through the lens of signal reconstruction and provide the first frequency-based analysis of its in-context learning behavior. We show that TabPFN possesses a broader effective frequency capacity than standard ReLU-MLPs, even without hyperparameter tuning. Moreover, unlike MLPs whose spectra evolve primarily over training epochs, we find that TabPFN's spectral capacity adapts directly to the number of samples provided in-context, a phenomenon we term Spectral Adaptivity. We further demonstrate that positional encoding modulates TabPFN's frequency response, mirroring classical results in implicit neural representations. Finally, we show that these properties enable TabPFN to perform training-free and hyperparameter-free image denoising, illustrating its potential as a task-agnostic implicit model. Our analysis provides new insight into the structure and inductive biases of tabular foundation models and highlights their promise for broader signal reconstruction tasks. --- ### Point-to-Point: Sparse Motion Guidance for Controllable Video Editing Authors: Yeji Song, Jaehyun Lee, Mijin Koo, JunHoo Lee, Nojun Kwak Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18277v1 Accurately preserving motion while editing a subject remains a core challenge in video editing tasks. Existing methods often face a trade-off between edit and motion fidelity, as they rely on motion representations that are either overfitted to the layout or only implicitly defined. To overcome this limitation, we revisit point-based motion representation. However, identifying meaningful points remains challenging without human input, especially across diverse video scenarios. To address this, we propose a novel motion representation, anchor tokens, that capture the most essential motion patterns by leveraging the rich prior of a video diffusion model. Anchor tokens encode video dynamics compactly through a small number of informative point trajectories and can be flexibly relocated to align with new subjects. This allows our method, Point-to-Point, to generalize across diverse scenarios. Extensive experiments demonstrate that anchor tokens lead to more controllable and semantically aligned video edits, achieving superior performance in terms of edit and motion fidelity. --- ### Clinician-Directed Large Language Model Software Generation for Therapeutic Interventions in Physical Rehabilitation Authors: Edward Kim, Yuri Cho, Jose Eduardo E. Lima, Julie Muccini, Jenelle Jindal, Alison Scheid, Erik Nelson, Seong Hyun Park, Yuchen Zeng, Alton Sturgis, Caesar Li, Jackie Dai et al. Published: 2025-11-23 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2511.18274v2 Digital health interventions increasingly deliver home exercise programs via sensor-equipped devices such as smartphones, enabling remote monitoring of adherence and performance. However, current software is usually authored before clinical encounters as libraries of modules for broad impairment categories. At the point of care, clinicians can only choose from these modules and adjust a few parameters (for example, duration or repetitions). As a result, individual limitations, goals, and environmental constraints are often not reflected, limiting personalization and benefit. We propose a paradigm in which large language models (LLMs) act as constrained translators that convert clinicians' exercise prescriptions into intervention software. Clinicians remain the decision makers: they design exercises during the encounter, tailored to each patient's impairments, goals, and environment, and the LLM generates matching software. We conducted a prospective single-arm feasibility study with 20 licensed physical and occupational therapists who created 40 individualized upper extremity programs for a standardized patient; 100% of prescriptions were translated into executable software, compared with 55% under a representative template-based digital health intervention (p < 0.01). LLM-generated software correctly delivered 99.7% of instructions and monitored performance with 88.4% accuracy (95% confidence interval, 0.843-0.915). Overall, 90% of therapists judged the system safe for patient interaction and 75% expressed willingness to adopt it in practice. To our knowledge, this is the first prospective evaluation of clinician-directed intervention software generation with an LLM in health care, demonstrating feasibility and motivating larger trials in real patient populations. --- ### Vision Token Masking Alone Cannot Prevent PHI Leakage in Medical Document OCR: A Systematic Evaluation Authors: Richard J. Young Published: 2025-11-23 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2511.18272v1 Large vision-language models (VLMs) are increasingly deployed for optical character recognition (OCR) in healthcare settings, raising critical concerns about protected health information (PHI) exposure during document processing. This work presents the first systematic evaluation of inference-time vision token masking as a privacy-preserving mechanism for medical document OCR using DeepSeek-OCR. We introduce seven masking strategies (V3-V9) targeting different architectural layers (SAM encoder blocks, compression layers, dual vision encoders, projector fusion) and evaluate PHI reduction across HIPAA-defined categories using 100 synthetic medical billing statements (drawn from a corpus of 38,517 annotated documents) with perfect ground-truth annotations. All masking strategies converge to 42.9% PHI reduction, successfully suppressing long-form spatially-distributed identifiers (patient names, dates of birth, physical addresses at 100% effectiveness) while failing to prevent short structured identifiers (medical record numbers, social security numbers, email addresses, account numbers at 0% effectiveness). Ablation studies varying mask expansion radius (r=1,2,3) demonstrate that increased spatial coverage does not improve reduction beyond this ceiling, indicating that language model contextual inference - not insufficient visual masking - drives structured identifier leakage. A simulated hybrid architecture combining vision masking with NLP post-processing achieves 88.6% total PHI reduction (assuming 80% NLP accuracy on remaining identifiers). This negative result establishes boundaries for vision-only privacy interventions in VLMs, provides guidance distinguishing PHI types amenable to vision-level versus language-level redaction, and redirects future research toward decoder-level fine-tuning and hybrid defense-in-depth architectures for HIPAA-compliant medical document processing. --- ### Beyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models Authors: Tianyang Han, Junhao Su, Junjie Hu, Peizhen Yang, Hengyu Shi, Junfeng Luo, Jialin Gao Published: 2025-11-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18271v3 Text-to-image (T2I) models today are capable of producing photorealistic, instruction-following images, yet they still frequently fail on prompts that require implicit world knowledge. Existing evaluation protocols either emphasize compositional alignment or rely on single-round VQA-based scoring, leaving critical dimensions such as knowledge grounding, multi-physics interactions, and auditable evidence-substantially undertested. To address these limitations, we introduce PicWorld, the first comprehensive benchmark that assesses the grasp of implicit world knowledge and physical causal reasoning of T2I models. This benchmark consists of 1,100 prompts across three core categories. To facilitate fine-grained evaluation, we propose PW-Agent, an evidence-grounded multi-agent evaluator to hierarchically assess images on their physical realism and logical consistency by decomposing prompts into verifiable visual evidence. We conduct a thorough analysis of 17 mainstream T2I models on PicWorld, illustrating that they universally exhibit a fundamental limitation in their capacity for implicit world knowledge and physical causal reasoning to varying degrees. The findings highlight the need for reasoning-aware, knowledge-integrative architectures in future T2I systems. --- ### A Fair OR-ML Framework for Resource Substitution in Large-Scale Networks Authors: Ved Mohan, El Mehdi Er Raqabi, Pascal Van Hentenryck Published: 2025-11-23 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2511.18269v1 Ensuring that the right resource is available at the right location and time remains a major challenge for organizations operating large-scale logistics networks. The challenge comes from uneven demand patterns and the resulting asymmetric flow of resources across the arcs, which create persistent imbalances at the network nodes. Resource substitution among multiple, potentially composite and interchangeable, resource types is a cost-effective way to mitigate these imbalances. This leads to the resource substitution problem, which aims at determining the minimum number of resource substitutions from an initial assignment to minimize the overall network imbalance. In decentralized settings, achieving globally coordinated solutions becomes even more difficult. When substitution entails costs, effective prescriptions must also incorporate fairness and account for the individual preferences of schedulers. This paper presents a generic framework that combines operations research (OR) and machine learning (ML) to enable fair resource substitution in large networks. The OR component models and solves the resource substitution problem under a fairness lens. The ML component leverages historical data to learn schedulers' preferences, guide intelligent exploration of the decision space, and enhance computational efficiency by dynamically selecting the top-$κ$ resources for each arc in the network. The framework produces a portfolio of high-quality solutions from which schedulers can select satisfactory trade-offs. The proposed framework is applied to the network of one of the largest package delivery companies in the world, which serves as the primary motivation for this research. Computational results demonstrate substantial improvements over state-of-the-art methods, including an 80% reduction in model size and a 90% decrease in execution time while preserving optimality. --- ### SatSAM2: Motion-Constrained Video Object Tracking in Satellite Imagery using Promptable SAM2 and Kalman Priors Authors: Ruijie Fan, Junyan Ye, Huan Chen, Zilong Huang, Xiaolei Wang, Weijia Li Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18264v3 Existing satellite video tracking methods often struggle with generalization, requiring scenario-specific training to achieve satisfactory performance, and are prone to track loss in the presence of occlusion. To address these challenges, we propose SatSAM2, a zero-shot satellite video tracker built on SAM2, designed to adapt foundation models to the remote sensing domain. SatSAM2 introduces two core modules: a Kalman Filter-based Constrained Motion Module (KFCMM) to exploit temporal motion cues and suppress drift, and a Motion-Constrained State Machine (MCSM) to regulate tracking states based on motion dynamics and reliability. To support large-scale evaluation, we propose MatrixCity Video Object Tracking (MVOT), a synthetic benchmark containing 1,500+ sequences and 157K annotated frames with diverse viewpoints, illumination, and occlusion conditions. Extensive experiments on two satellite tracking benchmarks and MVOT show that SatSAM2 outperforms both traditional and foundation model-based trackers, including SAM2 and its variants. Notably, on the OOTB dataset, SatSAM2 achieves a 5.84% AUC improvement over state-of-the-art methods. Our code and dataset will be publicly released to encourage further research. --- ### MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation Authors: Tao Shen, Xin Wan, Taicai Chen, Rui Zhang, Junwen Pan, Dawei Lu, Fanding Lei, Zhilin Lu, Yunfei Yang, Chen Cheng, Qi She, Chang Liu et al. Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18262v1 Unified multimodal models aim to integrate understanding and generation within a single framework, yet bridging the gap between discrete semantic reasoning and high-fidelity visual synthesis remains challenging. We present MammothModa2 (Mammoth2), a unified autoregressive-diffusion (AR-Diffusion) framework designed to effectively couple autoregressive semantic planning with diffusion-based generation. Mammoth2 adopts a serial design: an AR path equipped with generation experts performs global semantic modeling over discrete tokens, while a single-stream Diffusion Transformer (DiT) decoder handles high-fidelity image synthesis. A carefully designed AR-Diffusion feature alignment module combines multi-layer feature aggregation, unified condition encoding, and in-context conditioning to stably align AR's representations with the diffusion decoder's continuous latents. Mammoth2 is trained end-to-end with joint Next-Token Prediction and Flow Matching objectives, followed by supervised fine-tuning and reinforcement learning over both generation and editing. With roughly 60M supervised generation samples and no reliance on pre-trained generators, Mammoth2 delivers strong text-to-image and instruction-based editing performance on public benchmarks, achieving 0.87 on GenEval, 87.2 on DPGBench, and 4.06 on ImgEdit, while remaining competitive with understanding-only backbones (e.g., Qwen3-VL-8B) on multimodal understanding tasks. These results suggest that a carefully coupled AR-Diffusion architecture can provide high-fidelity generation and editing while maintaining strong multimodal comprehension within a single, parameter- and data-efficient model. --- ### LLM Reasoning for Cold-Start Item Recommendation Authors: Shijun Li, Yu Wang, Jin Wang, Ying Li, Joydeep Ghosh, Anne Cocos Published: 2025-11-23 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2511.18261v3 Large Language Models (LLMs) have shown significant potential for improving recommendation systems through their inherent reasoning capabilities and extensive knowledge base. Yet, existing studies predominantly address warm-start scenarios with abundant user-item interaction data, leaving the more challenging cold-start scenarios, where sparse interactions hinder traditional collaborative filtering methods, underexplored. To address this limitation, we propose novel reasoning strategies designed for cold-start item recommendations within the Netflix domain. Our method utilizes the advanced reasoning capabilities of LLMs to effectively infer user preferences, particularly for newly introduced or rarely interacted items. We systematically evaluate supervised fine-tuning, reinforcement learning-based fine-tuning, and hybrid approaches that combine both methods to optimize recommendation performance. Extensive experiments on real-world data demonstrate significant improvements in both methodological efficacy and practical performance in cold-start recommendation contexts. Remarkably, our reasoning-based fine-tuned models outperform Netflix's production ranking model by up to 8% in certain cases. --- ### Reduced-Basis Deep Operator Learning for Parametric PDEs with Independently Varying Boundary and Source Data Authors: Yueqi Wang, Guang Lin Published: 2025-11-23 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2511.18260v1 Parametric PDEs power modern simulation, design, and digital-twin systems, yet their many-query workloads still hinge on repeatedly solving large finite-element systems. Existing operator-learning approaches accelerate this process but often rely on opaque learned trunks, require extensive labeled data, or break down when boundary and source data vary independently from physical parameters. We introduce RB-DeepONet, a hybrid operator-learning framework that fuses reduced-basis (RB) numerical structure with the branch-trunk architecture of DeepONet. The trunk is fixed to a rigorously constructed RB space generated offline via Greedy selection, granting physical interpretability, stability, and certified error control. The branch network predicts only RB coefficients and is trained label-free using a projected variational residual that targets the RB-Galerkin solution. For problems with independently varying loads or boundary conditions, we develop boundary and source modal encodings that compress exogenous data into low-dimensional coordinates while preserving accuracy. Combined with affine or empirical interpolation decompositions, RB-DeepONet achieves a strict offline-online split: all heavy lifting occurs offline, and online evaluation scales only with the RB dimension rather than the full mesh. We provide convergence guarantees separating RB approximation error from statistical learning error, and numerical experiments show that RB-DeepONet attains accuracy competitive with intrusive RB-Galerkin, POD-DeepONet, and FEONet while using dramatically fewer trainable parameters and achieving significant speedups. This establishes RB-DeepONet as an efficient, stable, and interpretable operator learner for large-scale parametric PDEs. --- ### DiscoVerse: Multi-Agent Pharmaceutical Co-Scientist for Traceable Drug Discovery and Reverse Translation Authors: Xiaochen Zheng, Alvaro Serra, Ilya Schneider Chernov, Maddalena Marchesi, Eunice Musvasva, Tatyana Y. Doktorova Published: 2025-11-23 Categories: cs.CL, cs.MA arXiv: https://arxiv.org/abs/2511.18259v2 Pharmaceutical research and development has accumulated vast and heterogeneous archives of data. Much of this knowledge stems from discontinued programs, and reusing these archives is invaluable for reverse translation. However, in practice, such reuse is often infeasible. In this work, we introduce DiscoVerse, a multi-agent co-scientist designed to support pharmaceutical research and development at Roche. Designed as a human-in-the-loop assistant, DiscoVerse enables domain-specific queries by delivering evidence-based answers: it retrieves relevant data, links across documents, summarises key findings and preserves institutional memory. We assess DiscoVerse through expert evaluation of source-linked outputs. Our evaluation spans a selected subset of 180 molecules from Roche's research and development repositories, encompassing over 0.87 billion BPE tokens and more than four decades of research. To our knowledge, this represents the first agentic framework to be systematically assessed on real pharmaceutical data for reverse translation, enabled by authorized access to confidential archives covering the full lifecycle of drug development. Our contributions include: role-specialized agent designs aligned with scientist workflows; human-in-the-loop support for reverse translation; expert evaluation; and a large-scale demonstration showing promising decision-making insights. In brief, across seven benchmark queries, DiscoVerse achieved near-perfect recall ($\geq 0.99$) with moderate precision ($0.71-0.91$). Qualitative assessments and three real-world pharmaceutical use cases further showed faithful, source-linked synthesis across preclinical and clinical evidence. --- ### Hybrid Agentic AI and Multi-Agent Systems in Smart Manufacturing Authors: Mojtaba A. Farahani, Md Irfan Khan, Thorsten Wuest Published: 2025-11-23 Categories: cs.MA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.18258v1 The convergence of Agentic AI and MAS enables a new paradigm for intelligent decision making in SMS. Traditional MAS architectures emphasize distributed coordination and specialized autonomy, while recent advances in agentic AI driven by LLMs introduce higher order reasoning, planning, and tool orchestration capabilities. This paper presents a hybrid agentic AI and multi agent framework for a Prescriptive Maintenance use case, where LLM based agents provide strategic orchestration and adaptive reasoning, complemented by rule based and SLMs agents performing efficient, domain specific tasks on the edge. The proposed framework adopts a layered architecture that consists of perception, preprocessing, analytics, and optimization layers, coordinated through an LLM Planner Agent that manages workflow decisions and context retention. Specialized agents autonomously handle schema discovery, intelligent feature analysis, model selection, and prescriptive optimization, while a HITL interface ensures transparency and auditability of generated maintenance recommendations. This hybrid design supports dynamic model adaptation, cost efficient maintenance scheduling, and interpretable decision making. An initial proof of concept implementation is validated on two industrial manufacturing datasets. The developed framework is modular and extensible, supporting seamless integration of new agents or domain modules as capabilities evolve. The results demonstrate the system capability to automatically detect schema, adapt preprocessing pipelines, optimize model performance through adaptive intelligence, and generate actionable, prioritized maintenance recommendations. The framework shows promise in achieving improved robustness, scalability, and explainability for RxM in smart manufacturing, bridging the gap between high level agentic reasoning and low level autonomous execution. --- ### Sequence-Adaptive Video Prediction in Continuous Streams using Diffusion Noise Optimization Authors: Sina Mokhtarzadeh Azar, Emad Bahrami, Enrico Pallotta, Gianpiero Francesca, Radu Timofte, Juergen Gall Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18255v2 In this work, we investigate diffusion-based video prediction models, which forecast future video frames, for continuous video streams. In this context, the models observe continuously new training samples, and we aim to leverage this to improve their predictions. We thus propose an approach that continuously adapts a pre-trained diffusion model to a video stream. Since fine-tuning the parameters of a large diffusion model is too expensive, we refine the diffusion noise during inference while keeping the model parameters frozen, allowing the model to adaptively determine suitable sampling noise. We term the approach Sequence Adaptive Video Prediction with Diffusion Noise Optimization (SAVi-DNO). To validate our approach, we introduce a new evaluation setting on the Ego4D dataset, focusing on simultaneous adaptation and evaluation on long continuous videos. Empirical results demonstrate improved performance based on FVD, SSIM, and PSNR metrics on long videos of Ego4D and OpenDV-YouTube, as well as videos of UCF-101 and SkyTimelapse, showcasing SAVi-DNO's effectiveness. --- ### UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehicles Authors: Siyi Li, Qingwen Zhang, Ishan Khatri, Kyle Vedder, Eric Eaton, Deva Ramanan, Neehar Peri Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18254v3 LiDAR scene flow is the task of estimating per-point 3D motion between consecutive point clouds. Recent methods achieve centimeter-level accuracy on popular autonomous vehicle (AV) datasets, but are typically only trained and evaluated on a single sensor. In this paper, we aim to learn general motion priors that transfer to diverse and unseen LiDAR sensors. However, prior work in LiDAR semantic segmentation and 3D object detection demonstrate that naively training on multiple datasets yields worse performance than single dataset models. Interestingly, we find that this conventional wisdom does not hold for motion estimation, and that state-of-the-art scene flow methods greatly benefit from cross-dataset training without architectural modification. We posit that low-level tasks such as motion estimation may be less sensitive to sensor configuration; indeed, our analysis shows that models trained on fast-moving objects (e.g., from highway datasets) perform well on fast-moving objects, even across different datasets. Informed by our analysis, we propose UniFlow, a feedforward model that unifies and trains on multiple large-scale LiDAR scene flow datasets with diverse sensor placements and point cloud densities. Our frustratingly simple solution establishes a new state-of-the-art on Waymo and nuScenes, improving over prior work by 5.1% and 35.2% respectively. Moreover, UniFlow achieves state-of-the-art accuracy on unseen datasets like TruckScenes and AEVAScenes, outperforming prior dataset-specific models by 30.1% and 22.5% respectively. --- ### Coherent Multi-Agent Trajectory Forecasting in Team Sports with CausalTraj Authors: Wei Zhen Teoh Published: 2025-11-23 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.18248v2 Jointly forecasting trajectories of multiple interacting agents is a core challenge in sports analytics and other domains involving complex group dynamics. Accurate prediction enables realistic simulation and strategic understanding of gameplay evolution. Most existing models are evaluated solely on per-agent accuracy metrics (minADE, minFDE), which assess each agent independently on its best-of-k prediction. However these metrics overlook whether the model learns which predicted trajectories can jointly form a plausible multi-agent future. Many state-of-the-art models are designed and optimized primarily based on these metrics. As a result, they may underperform on joint predictions and also fail to generate coherent, interpretable multi-agent scenarios in team sports. We propose CausalTraj, a temporally causal, likelihood-based model that is built to generate jointly probable multi-agent trajectory forecasts. To better assess collective modeling capability, we emphasize joint metrics (minJADE, minJFDE) that measure joint accuracy across agents within the best generated scenario sample. Evaluated on the NBA SportVU, Basketball-U, and Football-U datasets, CausalTraj achieves competitive per-agent accuracy and the best recorded results on joint metrics, while yielding qualitatively coherent and realistic gameplay evolutions. --- ### Tail Distribution of Regret in Optimistic Reinforcement Learning Authors: Sajad Khodadadian, Mehrdad Moharrami Published: 2025-11-23 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2511.18247v3 We derive instance-dependent tail bounds for the regret of optimism-based reinforcement learning in finite-horizon tabular Markov decision processes with unknown transition dynamics. We first study a UCBVI-type (model-based) algorithm and characterize the tail distribution of the cumulative regret $R_K$ over $K$ episodes via explicit bounds on $P(R_K \ge x)$, going beyond analyses limited to $E(R_K)$ or a single high-probability quantile. We analyze two natural exploration-bonus schedules for UCBVI: (i) a $K$-dependent scheme that explicitly incorporates the total number of episodes $K$, and (ii) a $K$-independent (anytime) scheme that depends only on the current episode index. We then complement the model-based results with an analysis of optimistic Q-learning (model-free) under a $K$-dependent bonus schedule. Across both the model-based and model-free settings, we obtain upper bounds on $P(R_K \ge x)$ with a distinctive two-regime structure: a sub-Gaussian tail starting from an instance-dependent scale up to a transition threshold, followed by a sub-Weibull tail beyond that point. We further derive corresponding instance-dependent bounds on the expected regret $E(R_K)$. The proposed algorithms depend on a tuning parameter $α$, which balances the expected regret and the range over which the regret exhibits sub-Gaussian decay. --- ### Developing an AI Course for Synthetic Chemistry Students Authors: Zhiling Zheng Published: 2025-11-23 Categories: cs.AI, cond-mat.mtrl-sci, physics.ed-ph arXiv: https://arxiv.org/abs/2511.18244v1 Artificial intelligence (AI) and data science are transforming chemical research, yet few formal courses are tailored to synthetic and experimental chemists, who often face steep entry barriers due to limited coding experience and lack of chemistry-specific examples. We present the design and implementation of AI4CHEM, an introductory data-driven chem-istry course created for students on the synthetic chemistry track with no prior programming background. The curricu-lum emphasizes chemical context over abstract algorithms, using an accessible web-based platform to ensure zero-install machine learning (ML) workflow development practice and in-class active learning. Assessment combines code-guided homework, literature-based mini-reviews, and collaborative projects in which students build AI-assisted workflows for real experimental problems. Learning gains include increased confidence with Python, molecular property prediction, reaction optimization, and data mining, and improved skills in evaluating AI tools in chemistry. All course materials are openly available, offering a discipline-specific, beginner-accessible framework for integrating AI into synthetic chemistry training. --- ### EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning Authors: Yogesh Kulkarni, Pooyan Fazli Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18242v3 Egocentric video understanding requires procedural reasoning under partial observability and continuously shifting viewpoints. Current multimodal large language models (MLLMs) struggle with this setting, often generating plausible but visually inconsistent or weakly grounded responses. We introduce $\textbf{EgoVITA}$, a framework that decomposes egocentric video reasoning into a structured $\textit{plan-then-verify}$ process. The model first generates an $\textbf{egocentric plan}$: a causal sequence of anticipated actions from a first-person perspective. This plan is then evaluated by an $\textbf{exocentric verification}$ stage that uses third-person reasoning over the same video to verify its spatiotemporal and logical consistency, without exocentric video input. This decomposition enables cross-perspective feedback without requiring paired ego-exo supervision. To train this reasoning process, we adopt Group Relative Policy Optimization (GRPO) with two dense reward signals: one that grounds anticipated actions in subsequent visual observations and another that reinforces consistent third-person verification. $\textbf{EgoVITA}$ achieves state-of-the-art performance on egocentric reasoning benchmarks, outperforming Qwen2.5-VL-7B by $\mathbf{+7.7}$ on EgoBlind and $\mathbf{+4.4}$ on EgoOrient, while maintaining strong generalization on exocentric video tasks with only $52k$ training samples. --- ### Can LLMs Help Allocate Public Health Resources? A Case Study on Childhood Lead Testing Authors: Mohamed Afane, Ying Wang, Juntao Chen Published: 2025-11-23 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.18239v1 Public health agencies face critical challenges in identifying high-risk neighborhoods for childhood lead exposure with limited resources for outreach and intervention programs. To address this, we develop a Priority Score integrating untested children proportions, elevated blood lead prevalence, and public health coverage patterns to support optimized resource allocation decisions across 136 neighborhoods in Chicago, New York City, and Washington, D.C. We leverage these allocation tasks, which require integrating multiple vulnerability indicators and interpreting empirical evidence, to evaluate whether large language models (LLMs) with agentic reasoning and deep research capabilities can effectively allocate public health resources when presented with structured allocation scenarios. LLMs were tasked with distributing 1,000 test kits within each city based on neighborhood vulnerability indicators. Results reveal significant limitations: LLMs frequently overlooked neighborhoods with highest lead prevalence and largest proportions of untested children, such as West Englewood in Chicago, while allocating disproportionate resources to lower-priority areas like Hunts Point in New York City. Overall accuracy averaged 0.46, reaching a maximum of 0.66 with ChatGPT 5 Deep Research. Despite their marketed deep research capabilities, LLMs struggled with fundamental limitations in information retrieval and evidence-based reasoning, frequently citing outdated data and allowing non-empirical narratives about neighborhood conditions to override quantitative vulnerability indicators. --- ### Efficient Covariance Estimation for Sparsified Functional Data Authors: Sijie Zheng, Fandong Meng, Jie Zhou Published: 2025-11-23 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2511.18237v1 Motivated by recent work involving the analysis of leveraging spatial correlations in sparsified mean estimation, we present a novel procedure for constructing covariance estimator. The proposed Random-knots (Random-knots-Spatial) and B-spline (Bspline-Spatial) estimators of the covariance function are computationally efficient. Asymptotic pointwise of the covariance are obtained for sparsified individual trajectories under some regularity conditions. Our proposed nonparametric method well perform the functional principal components analysis for the case of sparsified data, where the number of repeated measurements available per subject is small. In contrast, classical functional data analysis requires a large number of regularly spaced measurements per subject. Model selection techniques, such as the Akaike information criterion, are used to choose the model dimension corresponding to the number of eigenfunctions in the model. Theoretical results are illustrated with Monte Carlo simulation experiments. Finally, we cluster multi-domain data by replacing the covariance function with our proposed covariance estimator during PCA. --- ### Parallel qMRI Reconstruction from 4x Accelerated Acquisitions Authors: Mingi Kang Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18232v1 Magnetic Resonance Imaging (MRI) acquisitions require extensive scan times, limiting patient throughput and increasing susceptibility to motion artifacts. Accelerated parallel MRI techniques reduce acquisition time by undersampling k-space data, but require robust reconstruction methods to recover high-quality images. Traditional approaches like SENSE require both undersampled k-space data and pre-computed coil sensitivity maps. We propose an end-to-end deep learning framework that jointly estimates coil sensitivity maps and reconstructs images from only undersampled k-space measurements at 4x acceleration. Our two-module architecture consists of a Coil Sensitivity Map (CSM) estimation module and a U-Net-based MRI reconstruction module. We evaluate our method on multi-coil brain MRI data from 10 subjects with 8 echoes each, using 2x SENSE reconstructions as ground truth. Our approach produces visually smoother reconstructions compared to conventional SENSE output, achieving comparable visual quality despite lower PSNR/SSIM metrics. We identify key challenges including spatial misalignment between different acceleration factors and propose future directions for improved reconstruction quality. --- ### Adaptive Conformal Prediction for Quantum Machine Learning Authors: Douglas Spencer, Samual Nicholls, Michele Caprio Published: 2025-11-23 Categories: cs.LG, stat.ML, stat.OT arXiv: https://arxiv.org/abs/2511.18225v2 Quantum machine learning seeks to leverage quantum computers to improve upon classical machine learning algorithms. Currently, robust uncertainty quantification methods remain underdeveloped in the quantum domain, despite the critical need for reliable and trustworthy predictions. Recent work has introduced quantum conformal prediction, a framework that produces prediction sets that are guaranteed to contain the true outcome with a user-specified probability. In this work, we formalise how the time-varying noise inherent in quantum processors can undermine conformal guarantees, even when calibration and test data are exchangeable. To address this challenge, we draw on Adaptive Conformal Inference, a method which maintains validity over time via repeated recalibration. We introduce Adaptive Quantum Conformal Prediction (AQCP), an algorithm which provides asymptotic average coverage guarantees under arbitrary hardware noise conditions. Empirical studies on an IBM quantum processor demonstrate that AQCP achieves the target coverage level and exhibits greater stability than quantum conformal prediction. --- ### PPoGA: Predictive Plan-on-Graph with Action for Knowledge Graph Question Answering Authors: MinGyu Jeon, SuWan Cho, JaeYoung Shu Published: 2025-11-22 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2602.00007v1 Large Language Models (LLMs) augmented with Knowledge Graphs (KGs) have advanced complex question answering, yet they often remain susceptible to failure when their initial high-level reasoning plan is flawed. This limitation, analogous to cognitive functional fixedness, prevents agents from restructuring their approach, leading them to pursue unworkable solutions. To address this, we propose PPoGA (Predictive Plan-on-Graph with Action), a novel KGQA framework inspired by human cognitive control and problem-solving. PPoGA incorporates a Planner-Executor architecture to separate high-level strategy from low-level execution and leverages a Predictive Processing mechanism to anticipate outcomes. The core innovation of our work is a self-correction mechanism that empowers the agent to perform not only Path Correction for local execution errors but also Plan Correction by identifying, discarding, and reformulating the entire plan when it proves ineffective. We conduct extensive experiments on three challenging multi-hop KGQA benchmarks: GrailQA, CWQ, and WebQSP. The results demonstrate that PPoGA achieves state-of-the-art performance, significantly outperforming existing methods. Our work highlights the critical importance of metacognitive abilities like problem restructuring for building more robust and flexible AI reasoning systems. --- ### Augmented Assembly: Object Recognition and Hand Tracking for Adaptive Assembly Instructions in Augmented Reality Authors: Alexander Htet Kyaw, Haotian Ma, Sasa Zivkovic, Jenny Sabin Published: 2025-11-22 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.11535v1 Recent advances in augmented reality (AR) have enabled interactive systems that assist users in physical assembly tasks. In this paper, we present an AR-assisted assembly workflow that leverages object recognition and hand tracking to (1) identify custom components, (2) display step-by-step instructions, (3) detect assembly deviations, and (4) dynamically update the instructions based on users' hands-on interactions with physical parts. Using object recognition, the system detects and localizes components in real time to create a digital twin of the workspace. For each assembly step, it overlays bounding boxes in AR to indicate both the current position and the target placement of relevant components, while hand-tracking data verifies whether the user interacts with the correct part. Rather than enforcing a fixed sequence, the system highlights potential assembly errors and interprets user deviations as opportunities for iteration and creative exploration. A case study with LEGO blocks and custom 3D-printed components demonstrates how the system links digital instructions to physical assembly, eliminating the need for manual searching, sorting, or labeling of parts. --- ### WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering Authors: Yifei He, Pranit Chawla, Yaser Souri, Subhojit Som, Xia Song Published: 2025-11-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.10962v3 Computer use agents (CUAs) can operate real-world digital interfaces but remain difficult to train due to the high cost of graphical user interface (GUI) interaction and the scarcity of high-quality trajectory data. Existing datasets rely on human demonstrations, limiting scalability. A natural alternative is to synthesize data from strong CUAs, yet their rollouts are highly noisy, with incorrect or suboptimal actions consisting a large proportion of the steps, making naive imitation ineffective. To tackle this challenge, we introduce a scalable data synthesis pipeline that transforms noisy rollouts into reliable supervision without human annotation. The core idea is step-level filtering, which evaluates actions individually to retain only correct steps, complemented by reasoning augmentation for improved planning. Using this pipeline, we construct WebSTAR, a dataset of 13.3K trajectories and 267K graded, reasoning-rich steps synthesized from OpenAI's computer-use-preview model. We train Qwen-2.5-VL-Instruct models (7B and 32B) on WebSTAR. On WebVoyager, our 7B model surpasses SoTA open-source CUA model UI-TARS-1.5-7B by more than 15% with only supervised finetuning. Building on step-level grading, we further create WebSCORE, a dataset of graded step-level actions, and train StepRM, a 7B multimodal process reward model distilled from o4-mini, which matches its grading quality while being far more efficient to deploy at scale. Our results establish step-level filtering as a key principle for scalable CUA training and construct two new datasets (WebSTAR, WebSCORE) and a lightweight process reward model (StepRM) as practical tools to advance robust and efficient CUAs. --- ### Impact of Data-Oriented and Object-Oriented Design on Performance and Cache Utilization with Artificial Intelligence Algorithms in Multi-Threaded CPUs Authors: Gabriel M. Arantes, Giancarlo Lucca, Eduardo N. Borges, Richard F. Pinto, Bruno L. Dalmazo, Rafael A. Berri Published: 2025-11-22 Categories: cs.AI, cs.PF arXiv: https://arxiv.org/abs/2512.07841v2 The growing performance gap between multi-core CPUs and main memory necessitates hardware-aware software design paradigms. This study provides a comprehensive performance analysis of Data Oriented Design (DOD) versus the traditional Object-Oriented Design (OOD), focusing on cache utilization and efficiency in multi-threaded environments. We developed and compared four distinct versions of the A* search algorithm: single-threaded OOD (ST-OOD), single-threaded DOD (ST-DOD), multi-threaded OOD (MT-OOD), and multi-threaded DOD (MT-DOD). The evaluation was based on metrics including execution time, memory usage, and CPU cache misses. In multi-threaded tests, the DOD implementation demonstrated considerable performance gains, with faster execution times and a lower number of raw system calls and cache misses. While OOD occasionally showed marginal advantages in memory usage or percentage-based cache miss rates, DOD's efficiency in data-intensive operations was more evident. Furthermore, our findings reveal that for a fine-grained task like the A* algorithm, the overhead associated with thread management led to single-threaded versions significantly outperforming their multi-threaded counterparts in both paradigms. We conclude that even when performance differences appear subtle in simple algorithms, the consistent advantages of DOD in critical metrics highlight its foundational architectural superiority, suggesting it is a more effective approach for maximizing hardware efficiency in complex, large-scale AI and parallel computing tasks. --- ### ReVeal-MT: A Physics-Informed Neural Network for Multi-Transmitter Radio Environment Mapping Authors: Mukaram Shahid, Kunal Das, Hadia Ushaq, Hongwei Zhang, Jiming Song, Daji Qiao, Sarath Babu, Yong Guan, Zhengyuan Zhu, Arsalan Ahmad Published: 2025-11-22 Categories: eess.SP, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2512.04100v1 Accurately mapping the radio environment (e.g., identifying wireless signal strength at specific frequency bands and geographic locations) is crucial for efficient spectrum sharing, enabling Secondary Users~(SUs) to access underutilized spectrum bands while protecting Primary Users~(PUs). While existing models have made progress, they often degrade in performance when multiple transmitters coexist, due to the compounded effects of shadowing, interference from adjacent transmitters. To address this challenge, we extend our prior work on Physics-Informed Neural Networks~(PINNs) for single-transmitter mapping to derive a new multi-transmitter Partial Differential Equation~(PDE) formulation of the Received Signal Strength Indicator~(RSSI). We then propose \emph{ReVeal-MT} (Re-constructor and Visualizer of Spectrum Landscape for Multiple Transmitters), a novel PINN which integrates the multi-source PDE residual into a neural network loss function, enabling accurate spectrum landscape reconstruction from sparse RF sensor measurements. ReVeal-MT is validated using real-world measurements from the ARA wireless living lab across rural and suburban environments, and benchmarked against 3GPP and ITU-R channel models and a baseline PINN model for a single transmitter use-case. Results show that ReVeal-MT achieves substantial accuracy gains in multi-transmitter scenarios, e.g., achieving an RMSE of only 2.66\,dB with as few as 45 samples over a 370-square-kilometer region, while maintaining low computational complexity. These findings demonstrate that ReVeal-MT significantly advances radio environment mapping under realistic multi-transmitter conditions, with strong potential for enabling fine-grained spectrum management and precise coexistence between PUs and SUs. --- ### Partial multivariate transformer as a tool for cryptocurrencies time series prediction Authors: Andrzej Tokajuk, Jarosław A. Chudziak Published: 2025-11-22 Categories: q-fin.ST, cs.AI, cs.CE, q-fin.TR arXiv: https://arxiv.org/abs/2512.04099v1 Forecasting cryptocurrency prices is hindered by extreme volatility and a methodological dilemma between information-scarce univariate models and noise-prone full-multivariate models. This paper investigates a partial-multivariate approach to balance this trade-off, hypothesizing that a strategic subset of features offers superior predictive power. We apply the Partial-Multivariate Transformer (PMformer) to forecast daily returns for BTCUSDT and ETHUSDT, benchmarking it against eleven classical and deep learning models. Our empirical results yield two primary contributions. First, we demonstrate that the partial-multivariate strategy achieves significant statistical accuracy, effectively balancing informative signals with noise. Second, we experiment and discuss an observable disconnect between this statistical performance and practical trading utility; lower prediction error did not consistently translate to higher financial returns in simulations. This finding challenges the reliance on traditional error metrics and highlights the need to develop evaluation criteria more aligned with real-world financial objectives. ---