# Research Papers — 2025-11 · bundle page 88 of 197 > Full-text markdown of papers #4351–4400 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/88 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/87.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/89.md) ### AdaFair-MARL: Enforcing Adaptive Fairness Constraints in Multi-Agent Reinforcement Learning Authors: Promise Ekpo, Saesha Agarwal, Felix Grimm, Lekan Molu, Angelique Taylor Published: 2025-11-18 Categories: cs.LG, cs.AI, cs.GT, cs.MA arXiv: https://arxiv.org/abs/2511.14135v2 Fair workload enforcement in heterogeneous multi-agent systems that pursue shared objectives remains challenging. Fixed fairness penalties often introduce inefficiencies, training instability, and conflicting agent incentives. Reward-shaping approaches in fair Multi-Agent Reinforcement Learning (MARL) typically incorporate fairness through heuristic penalties or scalar reward modifications and often rely on post-hoc evaluation. However, these methods do not guarantee that a desired fairness level will be satisfied. To address this limitation, we propose the Adaptive Fairness Multi-Agent Reinforcement Learning (AdaFair-MARL) framework, which formulates workload fairness as an explicit constraint so that agents maintain balanced contributions while optimizing team performance. We present AdaFair-MARL, a constrained cooperative MARL framework whose core algorithmic component is a primal-dual update that enforces workload fairness via adaptive Lagrange multiplier updates. Grounding the framework in a cooperative Markov game, we derive the fairness constraint from Jain's Fairness Index (JFI) geometry and show that the resulting feasible set admits a second-order cone representation, enabling principled Lagrangian dual-ascent updates without manual penalty tuning. Experiments in a simulated hospital coordination environment (MARLHospital) demonstrate the effectiveness of AdaFair-MARL compared to reward-shaping and fixed-penalty fairness methods, improving workload balance while maintaining team performance. We found that AdaFair-MARL achieves nearly perfect constraint satisfaction (0.99-1.00) while significantly improving workload fairness compared to fixed-penalty baselines. --- ### Synthetic Survival Control: Extending Synthetic Controls for "When-If" Decision Authors: Jessy Xinyi Han, Devavrat Shah Published: 2025-11-18 Categories: cs.LG, econ.EM, stat.ML arXiv: https://arxiv.org/abs/2511.14133v1 Estimating causal effects on time-to-event outcomes from observational data is particularly challenging due to censoring, limited sample sizes, and non-random treatment assignment. The need for answering such "when-if" questions--how the timing of an event would change under a specified intervention--commonly arises in real-world settings with heterogeneous treatment adoption and confounding. To address these challenges, we propose Synthetic Survival Control (SSC) to estimate counterfactual hazard trajectories in a panel data setting where multiple units experience potentially different treatments over multiple periods. In such a setting, SSC estimates the counterfactual hazard trajectory for a unit of interest as a weighted combination of the observed trajectories from other units. To provide formal justification, we introduce a panel framework with a low-rank structure for causal survival analysis. Indeed, such a structure naturally arises under classical parametric survival models. Within this framework, for the causal estimand of interest, we establish identification and finite sample guarantees for SSC. We validate our approach using a multi-country clinical dataset of cancer treatment outcomes, where the staggered introduction of new therapies creates a quasi-experimental setting. Empirically, we find that access to novel treatments is associated with improved survival, as reflected by lower post-intervention hazard trajectories relative to their synthetic counterparts. Given the broad relevance of survival analysis across medicine, economics, and public policy, our framework offers a general and interpretable tool for counterfactual survival inference using observational data. --- ### Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation Authors: Yu Zhong, Zihao Zhang, Rui Zhang, Lingdong Huang, Haihan Gao, Shuo Wang, Da Li, Ruijian Han, Jiaming Guo, Shaohui Peng, Di Huang, Yunji Chen Published: 2025-11-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.14131v1 Vision-and-Language Navigation (VLN) requires an agent to dynamically explore complex 3D environments following human instructions. Recent research underscores the potential of harnessing large language models (LLMs) for VLN, given their commonsense knowledge and general reasoning capabilities. Despite their strengths, a substantial gap in task completion performance persists between LLM-based approaches and domain experts, as LLMs inherently struggle to comprehend real-world spatial correlations precisely. Additionally, introducing LLMs is accompanied with substantial computational cost and inference latency. To address these issues, we propose a novel dual-process thinking framework dubbed R3, integrating LLMs' generalization capabilities with VLN-specific expertise in a zero-shot manner. The framework comprises three core modules: Runner, Ruminator, and Regulator. The Runner is a lightweight transformer-based expert model that ensures efficient and accurate navigation under regular circumstances. The Ruminator employs a powerful multimodal LLM as the backbone and adopts chain-of-thought (CoT) prompting to elicit structured reasoning. The Regulator monitors the navigation progress and controls the appropriate thinking mode according to three criteria, integrating Runner and Ruminator harmoniously. Experimental results illustrate that R3 significantly outperforms other state-of-the-art methods, exceeding 3.28% and 3.30% in SPL and RGSPL respectively on the REVERIE benchmark. This pronounced enhancement highlights the effectiveness of our method in handling challenging VLN tasks. --- ### PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval Authors: Chun Chet Ng, Jia Yu Lim, Wei Zeng Low Published: 2025-11-18 Categories: cs.AI, cs.CE, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2511.14130v2 With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application. Extracting task-relevant information from lengthy financial filings is essential for both operational and analytical decision-making. We present PRISM, a training-free framework that integrates refined system prompting, in-context learning (ICL), and lightweight multi-agent coordination for document and chunk ranking tasks. Our primary contribution is a systematic empirical study of when each component provides value: prompt engineering delivers consistent performance with minimal overhead, ICL enhances reasoning for complex queries when applied selectively, and multi-agent systems show potential primarily with larger models and careful architectural design. Extensive ablation studies across FinAgentBench, FiQA-2018, and FinanceBench reveal that simpler configurations often outperform complex multi-agent pipelines, providing practical guidance for practitioners. Our best configuration achieves an NDCG@5 of 0.71818 on FinAgentBench, ranking third while being the only training-free approach in the top three. We provide comprehensive feasibility analyses covering latency, token usage, and cost trade-offs to support deployment decisions. The source code is released at https://bit.ly/prism-ailens. --- ### MalRAG: A Retrieval-Augmented LLM Framework for Open-set Malicious Traffic Identification Authors: Xiang Luo, Chang Liu, Gang Xiong, Chen Yang, Gaopeng Gou, Yaochen Ren, Zhen Li Published: 2025-11-18 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2511.14129v1 Fine-grained identification of IDS-flagged suspicious traffic is crucial in cybersecurity. In practice, cyber threats evolve continuously, making the discovery of novel malicious traffic a critical necessity as well as the identification of known classes. Recent studies have advanced this goal with deep models, but they often rely on task-specific architectures that limit transferability and require per-dataset tuning. In this paper we introduce MalRAG, the first LLM driven retrieval-augmented framework for open-set malicious traffic identification. MalRAG freezes the LLM and operates via comprehensive traffic knowledge construction, adaptive retrieval, and prompt engineering. Concretely, we construct a multi-view traffic database by mining prior malicious traffic from content, structural, and temporal perspectives. Furthermore, we introduce a Coverage-Enhanced Retrieval Algorithm that queries across these views to assemble the most probable candidates, thereby improving the inclusion of correct evidence. We then employ Traffic-Aware Adaptive Pruning to select a variable subset of these candidates based on traffic-aware similarity scores, suppressing incorrect matches and yielding reliable retrieved evidence. Moreover, we develop a suite of guidance prompts where task instruction, evidence referencing, and decision guidance are integrated with the retrieved evidence to improve LLM performance. Across diverse real-world datasets and settings, MalRAG delivers state-of-the-art results in both fine-grained identification of known classes and novel malicious traffic discovery. Ablation and deep-dive analyses further show that MalRAG effective leverages LLM capabilities yet achieves open-set malicious traffic identification without relying on a specific LLM. --- ### 10Cache: Heterogeneous Resource-Aware Tensor Caching and Migration for LLM Training Authors: Sabiha Afroz, Redwan Ibne Seraj Khan, Hadeel Albahar, Jingoo Han, Ali R. Butt Published: 2025-11-18 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2511.14124v1 Training large language models (LLMs) in the cloud faces growing memory bottlenecks due to the limited capacity and high cost of GPUs. While GPU memory offloading to CPU and NVMe has made large-scale training more feasible, existing approaches suffer from high tensor migration latency and suboptimal device memory utilization, ultimately increasing training time and cloud costs. To address these challenges, we present 10Cache, a resource-aware tensor caching and migration system that accelerates LLM training by intelligently coordinating memory usage across GPU, CPU, and NVMe tiers. 10Cache profiles tensor execution order to construct prefetch policies, allocates memory buffers in pinned memory based on tensor size distributions, and reuses memory buffers to minimize allocation overhead. Designed for cloud-scale deployments, 10Cache improves memory efficiency and reduces reliance on high-end GPUs. Across diverse LLM workloads, it achieves up to 2x speedup in training time, improves GPU cache hit rate by up to 86.6x, and increases CPU/GPU memory utilization by up to 2.15x and 1.33x, respectively, compared to state-of-the-art offloading methods. These results demonstrate that 10Cache is a practical and scalable solution for optimizing LLM training throughput and resource efficiency in cloud environments. --- ### Multi-view Phase-aware Pedestrian-Vehicle Incident Reasoning Framework with Vision-Language Models Authors: Hao Zhen, Yunxiang Yang, Jidong J. Yang Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.14120v1 Pedestrian-vehicle incidents remain a critical urban safety challenge, with pedestrians accounting for over 20% of global traffic fatalities. Although existing video-based systems can detect when incidents occur, they provide little insight into how these events unfold across the distinct cognitive phases of pedestrian behavior. Recent vision-language models (VLMs) have shown strong potential for video understanding, but they remain limited in that they typically process videos in isolation, without explicit temporal structuring or multi-view integration. This paper introduces Multi-view Phase-aware Pedestrian-Vehicle Incident Reasoning (MP-PVIR), a unified framework that systematically processes multi-view video streams into structured diagnostic reports through four stages: (1) event-triggered multi-view video acquisition, (2) pedestrian behavior phase segmentation, (3) phase-specific multi-view reasoning, and (4) hierarchical synthesis and diagnostic reasoning. The framework operationalizes behavioral theory by automatically segmenting incidents into cognitive phases, performing synchronized multi-view analysis within each phase, and synthesizing results into causal chains with targeted prevention strategies. Particularly, two specialized VLMs underpin the MP-PVIR pipeline: TG-VLM for behavioral phase segmentation (mIoU = 0.4881) and PhaVR-VLM for phase-aware multi-view analysis, achieving a captioning score of 33.063 and up to 64.70% accuracy on question answering. Finally, a designated large language model is used to generate comprehensive reports detailing scene understanding, behavior interpretation, causal reasoning, and prevention recommendations. Evaluation on the Woven Traffic Safety dataset shows that MP-PVIR effectively translates multi-view video data into actionable insights, advancing AI-driven traffic safety analytics for vehicle-infrastructure cooperative systems. --- ### Real-Time Mobile Video Analytics for Pre-arrival Emergency Medical Services Authors: Liuyi Jin, Amran Haroon, Radu Stoleru, Pasan Gunawardena, Michael Middleton, Jeeeun Kim Published: 2025-11-18 Categories: cs.MM, cs.AI arXiv: https://arxiv.org/abs/2511.14119v1 Timely and accurate pre-arrival video streaming and analytics are critical for emergency medical services (EMS) to deliver life-saving interventions. Yet, current-generation EMS infrastructure remains constrained by one-to-one video streaming and limited analytics capabilities, leaving dispatchers and EMTs to manually interpret overwhelming, often noisy or redundant information in high-stress environments. We present TeleEMS, a mobile live video analytics system that enables pre-arrival multimodal inference by fusing audio and video into a unified decision-making pipeline before EMTs arrive on scene. TeleEMS comprises two key components: TeleEMS Client and TeleEMS Server. The TeleEMS Client runs across phones, smart glasses, and desktops to support bystanders, EMTs en route, and 911 dispatchers. The TeleEMS Server, deployed at the edge, integrates EMS-Stream, a communication backbone that enables smooth multi-party video streaming. On top of EMSStream, the server hosts three real-time analytics modules: (1) audio-to-symptom analytics via EMSLlama, a domain-specialized LLM for robust symptom extraction and normalization; (2) video-to-vital analytics using state-of-the-art rPPG methods for heart rate estimation; and (3) joint text-vital analytics via PreNet, a multimodal multitask model predicting EMS protocols, medication types, medication quantities, and procedures. Evaluation shows that EMSLlama outperforms GPT-4o (exact-match 0.89 vs. 0.57) and that text-vital fusion improves inference robustness, enabling reliable pre-arrival intervention recommendations. TeleEMS demonstrates the potential of mobile live video analytics to transform EMS operations, bridging the gap between bystanders, dispatchers, and EMTs, and paving the way for next-generation intelligent EMS infrastructure. --- ### Distributions In, Distributions Out: The Case for Soft-Label Training Authors: Agamdeep Singh, Ashish Tiwari, Hosein Hasanbeig, Priyanshu Gupta Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.14117v2 Supervised classifiers output a distribution over classes but are typically trained against a single label obtained by collapsing multiple annotators into a majority vote. On tasks where annotator disagreement reflects genuine ambiguity -- natural language inference, politeness, visually ambiguous categorization -- this collapse discards information and forces models to express uniform confidence on inputs where humans systematically disagree. We compare soft-label training, which uses the full annotation distribution as the target, against hard-label training across three datasets spanning vision and NLP (ChaosNLI, POPQUORN, CIFAR-10H). Soft-label training matches or exceeds hard-label accuracy on every dataset, reduces KL divergence to the annotator distribution by 32% on average (p < 10^-4), and produces predictions whose per-sample entropy correlates 61% more strongly with annotator entropy -- models trained on distributions are uncertain precisely where humans are. We argue these benefits follow from a basic observation: when annotators legitimately disagree, the annotation distribution is the correct learning target, not a noisy estimate of it. --- ### Coffee: Controllable Diffusion Fine-tuning Authors: Ziyao Zeng, Jingcheng Ni, Ruyi Liu, Alex Wong Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14113v1 Text-to-image diffusion models can generate diverse content with flexible prompts, which makes them well-suited for customization through fine-tuning with a small amount of user-provided data. However, controllable fine-tuning that prevents models from learning undesired concepts present in the fine-tuning data, and from entangling those concepts with user prompts, remains an open challenge. It is crucial for downstream tasks like bias mitigation, preventing malicious adaptation, attribute disentanglement, and generalizable fine-tuning of diffusion policy. We propose Coffee that allows using language to specify undesired concepts to regularize the adaptation process. The crux of our method lies in keeping the embeddings of the user prompt from aligning with undesired concepts. Crucially, Coffee requires no additional training and enables flexible modification of undesired concepts by modifying textual descriptions. We evaluate Coffee by fine-tuning on images associated with user prompts paired with undesired concepts. Experimental results demonstrate that Coffee can prevent text-to-image models from learning specified undesired concepts during fine-tuning and outperforms existing methods. Code will be released upon acceptance. --- ### Synthetic Clinical Notes for Rare ICD Codes: A Data-Centric Framework for Long-Tail Medical Coding Authors: Truong Vo, Weiyi Wu, Kaize Ding Published: 2025-11-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.14112v1 Automatic ICD coding from clinical text is a critical task in medical NLP but remains hindered by the extreme long-tail distribution of diagnostic codes. Thousands of rare and zero-shot ICD codes are severely underrepresented in datasets like MIMIC-III, leading to low macro-F1 scores. In this work, we propose a data-centric framework that generates high-quality synthetic discharge summaries to mitigate this imbalance. Our method constructs realistic multi-label code sets anchored on rare codes by leveraging real-world co-occurrence patterns, ICD descriptions, synonyms, taxonomy, and similar clinical notes. Using these structured prompts, we generate 90,000 synthetic notes covering 7,902 ICD codes, significantly expanding the training distribution. We fine-tune two state-of-the-art transformer-based models, PLM-ICD and GKI-ICD, on both the original and extended datasets. Experiments show that our approach modestly improves macro-F1 while maintaining strong micro-F1, outperforming prior SOTA. While the gain may seem marginal relative to the computational cost, our results demonstrate that carefully crafted synthetic data can enhance equity in long-tail ICD code prediction. --- ### CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer Authors: Srivathsan Sivakumar, Faisal Z. Qureshi Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.14111v2 Vision Transformers (ViTs) have demonstrated remarkable performance across a range of computer vision tasks; however, their high computational, memory, and energy demands hinder deployment on resource-constrained platforms. In this paper, we propose \emph{Cascaded-ViT (CViT)}, a lightweight and compute-efficient vision transformer architecture featuring a novel feedforward network design called \emph{Cascaded-Chunk Feed Forward Network (CCFFN)}. By splitting input features, CCFFN improves parameter and FLOP efficiency without sacrificing accuracy. Experiments on ImageNet-1K show that our \emph{CViT-XL} model achieves 75.5\% Top-1 accuracy while reducing FLOPs by 15\% and energy consumption by 3.3\% compared to EfficientViT-M5. Across various model sizes, the CViT family consistently exhibits the lowest energy consumption, making it suitable for deployment on battery-constrained devices such as mobile phones and drones. Furthermore, when evaluated using a new metric called \emph{Accuracy-Per-FLOP (APF)}, which quantifies compute efficiency relative to accuracy, CViT models consistently achieve top-ranking efficiency. Particularly, CViT-L is 2.2\% more accurate than EfficientViT-M2 while having comparable APF scores. --- ### Interpretable Multimodal EEG-ECG Framework for Neonatal Seizure Prediction and Patient-Adaptive Transfer Learning Authors: Sithmini Ranasingha, Agasthi Haputhanthri, Hansa Marasinghe, Kithmin Wickremasinghe, Nima Wickramasinghe, Jithangi Wanigasinghe, Chamira U. S. Edussooriya, Joshua P. Kulasingham Published: 2025-11-18 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2511.14110v2 Neonatal seizures carry substantial risks of acute brain injury and long-term neurodevelopmental impairment, motivating the need for timely identification of impending seizure activity. While continuous electroencephalogram (EEG) monitoring remains the clinical gold standard, reliable patient-independent seizure prediction in neonates remains largely under-explored. We propose an interpretable multimodal framework that combines EEG and electrocardiogram (ECG) signals for neonatal seizure prediction. Our method uses mel-frequency cepstral coefficient (MFCC) representations processed by a lightweight (approx. 70k-parameter) convolutional neural network with squeeze-and-excitation attention. The framework was evaluated on the Helsinki neonatal EEG-ECG dataset and the Siena scalp EEG-ECG dataset. Under strict leave-one-patient-out (LOPO) evaluation, patient-independent prediction proved challenging (mean accuracy 58.5%, F1-score 60.3%), highlighting substantial inter-subject variability in neonatal EEG. However, fine-tuning the pretrained model with only five minutes of patient-specific data per class improved performance to 95.87% accuracy and 95.85% F1-score, demonstrating the feasibility of rapid patient-adaptive transfer learning. SHapley Additive exPlanations (SHAP) identified informative EEG channels that showed partial spatial agreement with clinically reported seizure origins. These findings suggest that fully patient-independent neonatal seizure prediction remains challenging, but that patient-adaptive fine-tuning with a small amount of data may provide a practical pathway toward personalized neonatal seizure prediction systems. --- ### A2GC: Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors Authors: Zhenyu Li, Tianyi Shang Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14109v2 Visual Place Recognition (VPR) aims to match query images against a database using visual cues. State-of-the-art methods aggregate features from deep backbones to form global descriptors. Optimal transport-based aggregation methods reformulate feature-to-cluster assignment as a transport problem, but the standard Sinkhorn algorithm symmetrically treats source and target marginals, limiting effectiveness when image features and cluster centers exhibit substantially different distributions. We propose an asymmetric aggregation VPR method with geometric constraints for locally aggregated descriptors, called $A^2$GC-VPR. Our method employs row-column normalization averaging with separate marginal calibration, enabling asymmetric matching that adapts to distributional discrepancies in visual place recognition. Geometric constraints are incorporated through learnable coordinate embeddings, computing compatibility scores fused with feature similarities, thereby promoting spatially proximal features to the same cluster and enhancing spatial awareness. Experimental results on MSLS, NordLand, and Pittsburgh datasets demonstrate superior performance, validating the effectiveness of our approach in improving matching accuracy and robustness. --- ### RTS-Mono: A Real-Time Self-Supervised Monocular Depth Estimation Method for Real-World Deployment Authors: Zeyu Cheng, Tongfei Liu, Tao Lei, Xiang Hua, Yi Zhang, Chengkai Tang Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14107v1 Depth information is crucial for autonomous driving and intelligent robot navigation. The simplicity and flexibility of self-supervised monocular depth estimation are conducive to its role in these fields. However, most existing monocular depth estimation models consume many computing resources. Although some methods have reduced the model's size and improved computing efficiency, the performance deteriorates, seriously hindering the real-world deployment of self-supervised monocular depth estimation models in the real world. To address this problem, we proposed a real-time self-supervised monocular depth estimation method and implemented it in the real world. It is called RTS-Mono, which is a lightweight and efficient encoder-decoder architecture. The encoder is based on Lite-Encoder, and the decoder is designed with a multi-scale sparse fusion framework to minimize redundancy, ensure performance, and improve inference speed. RTS-Mono achieved state-of-the-art (SoTA) performance in high and low resolutions with extremely low parameter counts (3 M) in experiments based on the KITTI dataset. Compared with lightweight methods, RTS-Mono improved Abs Rel and Sq Rel by 5.6% and 9.8% at low resolution and improved Sq Rel and RMSE by 6.1% and 1.9% at high resolution. In real-world deployment experiments, RTS-Mono has extremely high accuracy and can perform real-time inference on Nvidia Jetson Orin at a speed of 49 FPS. Source code is available at https://github.com/ZYCheng777/RTS-Mono. --- ### Stealth Fine-Tuning: Efficiently Breaking Alignment in RVLMs Using Self-Generated CoT Authors: Le Yu, Zhengyue Zhao, Yawen Zheng, Yunhao Liu Published: 2025-11-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.14106v2 Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfaces. In this work, we find that the safety alignment of RVLMs can be easily broken through a novel attack method termed \textbf{Stealth Fine-Tuning}. Our method elicits harmful reasoning traces through \textbf{segment-level interference} and reuses the self-generated outputs as supervised fine-tuning data. To facilitate this, we introduce a \textbf{turn-based weighted} loss that minimizes distribution shift. In our experiment, with only 499 samples and under 3 hours on a single A100 (QLoRA), Stealth Fine-Tuning outperforms IDEATOR by 38.66\% ASR while preserving general reasoning ability, as the tuned model retains the original representation distribution. Experiments on AdvBench and several general benchmarks demonstrate that Stealth Fine-Tuning is a low-cost and highly effective way to bypass alignment defenses. \textcolor{red}{\textbf{Disclaimer: This paper contains content that may be disturbing or offensive.}} --- ### MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts Authors: Wenfeng Wang, Jiacheng Liu, Xiaofeng Hou, Xinfeng Xia, Peng Tang, Mingxuan Zhang, Chao Li, Minyi Guo Published: 2025-11-18 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2511.14102v1 The immense memory requirements of state-of-the-art Mixture-of-Experts (MoE) models present a significant challenge for inference, often exceeding the capacity of a single accelerator. While offloading experts to host memory is a common solution, it introduces a severe I/O bottleneck over the PCIe bus, as the data-dependent nature of expert selection places these synchronous transfers directly on the critical path of execution, crippling performance. This paper argues that the I/O bottleneck can be overcome by trading a small amount of cheap, on-device computation to hide the immense cost of data movement. We present MoE-SpeQ, a new inference system built on a novel co-design of speculative execution and expert offloading. MoE-SpeQ employs a small, on-device draft model to predict the sequence of required experts for future tokens. This foresight enables a runtime orchestrator to prefetch these experts from host memory, effectively overlapping the expensive I/O with useful computation and hiding the latency from the critical path. To maximize performance, an adaptive governor, guided by an Amortization Roofline Model, dynamically tunes the speculation strategy to the underlying hardware. Our evaluation on memory-constrained devices shows that for the Phi-MoE model, MoE-SpeQ achieves at most 2.34x speedup over the state-of-the-art offloading framework. Our work establishes a new, principled approach for managing data-dependent memory access in resource-limited environments, making MoE inference more accessible on commodity hardware. --- ### APD-Agents: A Large Language Model-Driven Multi-Agents Collaborative Framework for Automated Page Design Authors: Xinpeng Chen, Xiaofeng Han, Kaihao Zhang, Guochao Ren, Yujie Wang, Wenhao Cao, Yang Zhou, Jianfeng Lu, Zhenbo Song Published: 2025-11-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.14101v1 Layout design is a crucial step in developing mobile app pages. However, crafting satisfactory designs is time-intensive for designers: they need to consider which controls and content to present on the page, and then repeatedly adjust their size, position, and style for better aesthetics and structure. Although many design software can now help to perform these repetitive tasks, extensive training is needed to use them effectively. Moreover, collaborative design across app pages demands extra time to align standards and ensure consistent styling. In this work, we propose APD-agents, a large language model (LLM) driven multi-agent framework for automated page design in mobile applications. Our framework contains OrchestratorAgent, SemanticParserAgent, PrimaryLayoutAgent, TemplateRetrievalAgent, and RecursiveComponentAgent. Upon receiving the user's description of the page, the OrchestratorAgent can dynamically can direct other agents to accomplish users' design task. To be specific, the SemanticParserAgent is responsible for converting users' descriptions of page content into structured data. The PrimaryLayoutAgent can generate an initial coarse-grained layout of this page. The TemplateRetrievalAgent can fetch semantically relevant few-shot examples and enhance the quality of layout generation. Besides, a RecursiveComponentAgent can be used to decide how to recursively generate all the fine-grained sub-elements it contains for each element in the layout. Our work fully leverages the automatic collaboration capabilities of large-model-driven multi-agent systems. Experimental results on the RICO dataset show that our APD-agents achieve state-of-the-art performance. --- ### Text-Driven Reasoning Video Editing via Reinforcement Learning on Digital Twin Representations Authors: Yiqing Shen, Chenjia Li, Mathias Unberath Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14100v1 Text-driven video editing enables users to modify video content only using text queries. While existing methods can modify video content if explicit descriptions of editing targets with precise spatial locations and temporal boundaries are provided, these requirements become impractical when users attempt to conceptualize edits through implicit queries referencing semantic properties or object relationships. We introduce reasoning video editing, a task where video editing models must interpret implicit queries through multi-hop reasoning to infer editing targets before executing modifications, and a first model attempting to solve this complex task, RIVER (Reasoning-based Implicit Video Editor). RIVER decouples reasoning from generation through digital twin representations of video content that preserve spatial relationships, temporal trajectories, and semantic attributes. A large language model then processes this representation jointly with the implicit query, performing multi-hop reasoning to determine modifications, then outputs structured instructions that guide a diffusion-based editor to execute pixel-level changes. RIVER training uses reinforcement learning with rewards that evaluate reasoning accuracy and generation quality. Finally, we introduce RVEBenchmark, a benchmark of 100 videos with 519 implicit queries spanning three levels and categories of reasoning complexity specifically for reasoning video editing. RIVER demonstrates best performance on the proposed RVEBenchmark and also achieves state-of-the-art performance on two additional video editing benchmarks (VegGIE and FiVE), where it surpasses six baseline methods. --- ### FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration Authors: Jingren Liu, Shuning Xu, Qirui Yang, Yun Wang, Xiangyu Chen, Zhong Ji Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.14099v3 All-in-One Image Restoration (AIO-IR) aims to develop a unified model that can handle multiple degradations under complex conditions. However, existing methods often rely on task-specific designs or latent routing strategies, making it hard to adapt to real-world scenarios with various degradations. We propose FAPE-IR, a Frequency-Aware Planning and Execution framework for image restoration. It uses a frozen Multimodal Large Language Model (MLLM) as a planner to analyze degraded images and generate concise, frequency-aware restoration plans. These plans guide a LoRA-based Mixture-of-Experts (LoRA-MoE) module within a diffusion-based executor, which dynamically selects high- or low-frequency experts, complemented by frequency features of the input image. To further improve restoration quality and reduce artifacts, we introduce adversarial training and a frequency regularization loss. By coupling semantic planning with frequency-based restoration, FAPE-IR offers a unified and interpretable solution for all-in-one image restoration. Extensive experiments show that FAPE-IR achieves state-of-the-art performance across seven restoration tasks and exhibits strong zero-shot generalization under mixed degradations. --- ### Collaborative QA using Interacting LLMs. Impact of Network Structure, Node Capability and Distributed Data Authors: Adit Jain, Vikram Krishnamurthy, Yiming Zhang Published: 2025-11-18 Categories: cs.AI, cs.MA, cs.SI, eess.SY arXiv: https://arxiv.org/abs/2511.14098v1 In this paper, we model and analyze how a network of interacting LLMs performs collaborative question-answering (CQA) in order to estimate a ground truth given a distributed set of documents. This problem is interesting because LLMs often hallucinate when direct evidence to answer a question is lacking, and these effects become more pronounced in a network of interacting LLMs. The hallucination spreads, causing previously accurate LLMs to hallucinate. We study interacting LLMs and their hallucination by combining novel ideas of mean-field dynamics (MFD) from network science and the randomized utility model from economics to construct a useful generative model. We model the LLM with a latent state that indicates if it is truthful or not with respect to the ground truth, and extend a tractable analytical model considering an MFD to model the diffusion of information in a directed network of LLMs. To specify the probabilities that govern the dynamics of the MFD, we propose a randomized utility model. For a network of LLMs, where each LLM has two possible latent states, we posit sufficient conditions for the existence and uniqueness of a fixed point and analyze the behavior of the fixed point in terms of the incentive (e.g., test-time compute) given to individual LLMs. We experimentally study and analyze the behavior of a network of $100$ open-source LLMs with respect to data heterogeneity, node capability, network structure, and sensitivity to framing on multiple semi-synthetic datasets. --- ### BCE3S: Binary Cross-Entropy Based Tripartite Synergistic Learning for Long-tailed Recognition Authors: Weijia Fan, Qiufu Li, Jiajun Wen, Xiaoyang Peng Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14097v1 For long-tailed recognition (LTR) tasks, high intra-class compactness and inter-class separability in both head and tail classes, as well as balanced separability among all the classifier vectors, are preferred. The existing LTR methods based on cross-entropy (CE) loss not only struggle to learn features with desirable properties but also couple imbalanced classifier vectors in the denominator of its Softmax, amplifying the imbalance effects in LTR. In this paper, for the LTR, we propose a binary cross-entropy (BCE)-based tripartite synergistic learning, termed BCE3S, which consists of three components: (1) BCE-based joint learning optimizes both the classifier and sample features, which achieves better compactness and separability among features than the CE-based joint learning, by decoupling the metrics between feature and the imbalanced classifier vectors in multiple Sigmoid; (2) BCE-based contrastive learning further improves the intra-class compactness of features; (3) BCE-based uniform learning balances the separability among classifier vectors and interactively enhances the feature properties by combining with the joint learning. The extensive experiments show that the LTR model trained by BCE3S not only achieves higher compactness and separability among sample features, but also balances the classifier's separability, achieving SOTA performance on various long-tailed datasets such as CIFAR10-LT, CIFAR100-LT, ImageNet-LT, and iNaturalist2018. --- ### NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval Authors: Junchen Li, Rongzheng Wang, Yihong Huang, Qizhi Chen, Jiasheng Zhang, Shuang Liang Published: 2025-11-18 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2511.14096v1 Retrieval-augmented generation (RAG) greatly enhances large language models (LLMs) performance in knowledge-intensive tasks. However, naive RAG methods struggle with multi-hop question answering due to their limited capacity to capture complex dependencies across documents. Recent studies employ graph-based RAG to capture document connections. However, these approaches often result in a loss of semantic coherence and introduce irrelevant noise during node matching and subgraph construction. To address these limitations, we propose NeuroPath, an LLM-driven semantic path tracking RAG framework inspired by the path navigational planning of place cells in neurobiology. It consists of two steps: Dynamic Path Tracking and Post-retrieval Completion. Dynamic Path Tracking performs goal-directed semantic path tracking and pruning over the constructed knowledge graph (KG), improving noise reduction and semantic coherence. Post-retrieval Completion further reinforces these benefits by conducting second-stage retrieval using intermediate reasoning and the original query to refine the query goal and complete missing information in the reasoning path. NeuroPath surpasses current state-of-the-art baselines on three multi-hop QA datasets, achieving average improvements of 16.3% on recall@2 and 13.5% on recall@5 over advanced graph-based RAG methods. Moreover, compared to existing iter-based RAG methods, NeuroPath achieves higher accuracy and reduces token consumption by 22.8%. Finally, we demonstrate the robustness of NeuroPath across four smaller LLMs (Llama3.1, GLM4, Mistral0.3, and Gemma3), and further validate its scalability across tasks of varying complexity. Code is available at https://github.com/KennyCaty/NeuroPath. --- ### SMGeo: Cross-View Object Geo-Localization with Grid-Level Mixture-of-Experts Authors: Fan Zhang, Haoyuan Ren, Fei Ma, Qiang Yin, Yongsheng Zhou Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14093v1 Cross-view object Geo-localization aims to precisely pinpoint the same object across large-scale satellite imagery based on drone images. Due to significant differences in viewpoint and scale, coupled with complex background interference, traditional multi-stage "retrieval-matching" pipelines are prone to cumulative errors. To address this, we present SMGeo, a promptable end-to-end transformer-based model for object Geo-localization. This model supports click prompting and can output object Geo-localization in real time when prompted to allow for interactive use. The model employs a fully transformer-based architecture, utilizing a Swin-Transformer for joint feature encoding of both drone and satellite imagery and an anchor-free transformer detection head for coordinate regression. In order to better capture both inter-modal and intra-view dependencies, we introduce a grid-level sparse Mixture-of-Experts (GMoE) into the cross-view encoder, allowing it to adaptively activate specialized experts according to the content, scale and source of each grid. We also employ an anchor-free detection head for coordinate regression, directly predicting object locations via heat-map supervision in the reference images. This approach avoids scale bias and matching complexity introduced by predefined anchor boxes. On the drone-to-satellite task, SMGeo achieves leading performance in accuracy at IoU=0.25 and mIoU metrics (e.g., 87.51%, 62.50%, and 61.45% in the test set, respectively), significantly outperforming representative methods such as DetGeo (61.97%, 57.66%, and 54.05%, respectively). Ablation studies demonstrate complementary gains from shared encoding, query-guided fusion, and grid-level sparse mixture-of-experts. --- ### GCA-ResUNet:Image segmentation in medical images using grouped coordinate attention Authors: Jun Ding, Shang Gao Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.14087v1 Medical image segmentation underpins computer-aided diagnosis and therapy by supporting clinical diagnosis, preoperative planning, and disease monitoring. While U-Net style convolutional neural networks perform well due to their encoder-decoder structures with skip connections, they struggle to capture long-range dependencies. Transformer-based variants address global context but often require heavy computation and large training datasets. This paper proposes GCA-ResUNet, an efficient segmentation network that integrates Grouped Coordinate Attention (GCA) into ResNet-50 residual blocks. GCA uses grouped coordinate modeling to jointly encode global dependencies across channels and spatial locations, strengthening feature representation and boundary delineation while adding minimal parameter and FLOP overhead compared with self-attention. On the Synapse dataset, GCA-ResUNet achieves a Dice score of 86.11%, and on the ACDC dataset, it reaches 92.64%, surpassing several state-of-the-art baselines while maintaining fast inference and favorable computational efficiency. These results indicate that GCA offers a practical way to enhance convolutional architectures with global modeling capability, enabling high-accuracy and resource-efficient medical image segmentation. --- ### Error-Driven Scene Editing for 3D Grounding in Large Language Models Authors: Yue Zhang, Zun Wang, Han Lin, Jialu Li, Jianing Yang, Yonatan Bitton, Idan Szpektor, Mohit Bansal Published: 2025-11-18 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.14086v2 Despite recent progress in 3D-LLMs, they remain limited in accurately grounding language to visual and spatial elements in 3D environments. This limitation stems in part from training data that focuses on language reasoning rather than spatial understanding due to scarce 3D resources, leaving inherent grounding biases unresolved. To address this, we propose 3D scene editing as a key mechanism to generate visual counterfactuals that mitigate these biases through fine-grained spatial manipulation, without requiring costly scene reconstruction or large-scale 3D data collection. Furthermore, to make these edits targeted and directly address the specific weaknesses of the model, we introduce DEER-3D, an error-driven framework that diagnoses grounding failures and generates targeted counterfactual training supervision via a structured "Decompose, Diagnose, Edit, and Retrain" loop. Specifically, given a grounding failure, DEER-3D first identifies the predicate-level error (e.g., attribute or spatial relation). It then performs minimal predicate-aligned scene edits, such as recoloring or repositioning, and constructs aligned question-answer pairs that explicitly target the failed predicate, forming targeted counterfactual training examples. We evaluate our editing pipeline across multiple benchmarks for 3D grounding and scene understanding tasks, consistently demonstrating improvements across all grounding datasets through iterative refinement (4-6% gains). DEER-3D underscores the effectiveness of targeted, error-driven scene editing in bridging linguistic reasoning with spatial grounding in 3D LLMs. --- ### Observational Auditing of Label Privacy Authors: Iden Kalemaj, Luca Melis, Maxime Boucher, Ilya Mironov, Saeed Mahloujifar Published: 2025-11-18 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2511.14084v3 Differential privacy (DP) auditing is essential for evaluating privacy guarantees in machine learning systems. Existing auditing methods, however, pose a significant challenge for large-scale systems since they require modifying the training dataset -- for instance, by injecting out-of-distribution canaries or removing samples from training. Such interventions on the training data pipeline are resource-intensive and involve considerable engineering overhead. We introduce a novel observational auditing framework that leverages the inherent randomness of data distributions, enabling privacy evaluation without altering the original dataset. Our approach extends privacy auditing beyond traditional membership inference to protected attributes, with labels as a special case, addressing a key gap in existing techniques. We provide theoretical foundations for our method and perform experiments on Criteo and CIFAR-10 datasets that demonstrate its effectiveness in auditing label privacy guarantees. This work opens new avenues for practical privacy auditing in large-scale production environments. --- ### Fully Automated Deep Learning Based Glenoid Bone Loss Measurement and Severity Stratification on 3D CT in Shoulder Instability Authors: Zhonghao Liu, Hanxue Gu, Qihang Li, Michael Fox, Jay M. Levin, Maciej A. Mazurowski, Brian C. Lau Published: 2025-11-18 Categories: cs.CV, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2511.14083v2 To develop and validate a fully automated, deep-learning pipeline for measuring glenoid bone loss on 3D CT scans using linear-based, en-face view, and best-circle method. Shoulder CT scans of 81 patients were retrospectively collected between January 2013 and March 2023. Our algorithm consists of three main stages: (1) Segmentation, where we developed a U-Net to automatically segment the glenoid and humerus; (2) anatomical landmark detection, where a second network predicts glenoid rim points; and (3) geometric fitting, where we applied a principal component analysis (PCA), projection, and circle fitting to compute the percentage of bone loss. The performance of the pipeline was evaluated using DSC for segmentation and MAE and ICC for bone-loss measurement; intermediate outputs (rim point sets and en-face view) were also assessed. Automated measurements showed strong agreement with consensus readings, exceeding surgeon-to-surgeon consistency (ICC 0.84 vs 0.78 for all patients; ICC 0.71 vs 0.63 for low bone loss; ICC 0.83 vs 0.21 for high bone loss; P < 0.001). For the classification task of assigning each patient to different bone loss severity subgroups, the pipeline's sensitivity was 71.4% for the low-severity group and 85.7% for the high-severity group, with no instances of misclassifying low as high or vice versa. A fully automated, deep learning-based pipeline for glenoid bone-loss measurement on CT scans can be a clinically reliable tool to assist clinicians with preoperative planning for shoulder instability. We are releasing our model and dataset at https://github.com/Edenliu1/Auto-Glenoid-Measurement-DL-Pipeline . --- ### Zero-Training Task-Specific Model Synthesis for Few-Shot Medical Image Classification Authors: Yao Qin, Yangyang Yan, YuanChao Yang, Jinhua Pang, Huanyong Bi, Yuan Liu, HaiHua Wang Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.14082v1 Deep learning models have achieved remarkable success in medical image analysis but are fundamentally constrained by the requirement for large-scale, meticulously annotated datasets. This dependency on "big data" is a critical bottleneck in the medical domain, where patient data is inherently difficult to acquire and expert annotation is expensive, particularly for rare diseases where samples are scarce by definition. To overcome this fundamental challenge, we propose a novel paradigm: Zero-Training Task-Specific Model Synthesis (ZS-TMS). Instead of adapting a pre-existing model or training a new one, our approach leverages a large-scale, pre-trained generative engine to directly synthesize the entire set of parameters for a task-specific classifier. Our framework, the Semantic-Guided Parameter Synthesizer (SGPS), takes as input minimal, multi-modal task information as little as a single example image (1-shot) and a corresponding clinical text description to directly synthesize the entire set of parameters for a task-specific classifier. The generative engine interprets these inputs to generate the weights for a lightweight, efficient classifier (e.g., an EfficientNet-V2), which can be deployed for inference immediately without any task-specific training or fine-tuning. We conduct extensive evaluations on challenging few-shot classification benchmarks derived from the ISIC 2018 skin lesion dataset and a custom rare disease dataset. Our results demonstrate that SGPS establishes a new state-of-the-art, significantly outperforming advanced few-shot and zero-shot learning methods, especially in the ultra-low data regimes of 1-shot and 5-shot classification. This work paves the way for the rapid development and deployment of AI-powered diagnostic tools, particularly for the long tail of rare diseases where data is critically limited. --- ### Meta-SimGNN: Adaptive and Robust WiFi Localization Across Dynamic Configurations and Diverse Scenarios Authors: Qiqi Xiao, Ziqi Ye, Yinghui He, Jianwei Liu, Guanding Yu Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.14076v1 To promote the practicality of deep learning-based localization, existing studies aim to address the issue of scenario dependence through meta-learning. However, these studies primarily focus on variations in environmental layouts while overlooking the impact of changes in device configurations, such as bandwidth, the number of access points (APs), and the number of antennas used. Unlike environmental changes, variations in device configurations affect the dimensionality of channel state information (CSI), thereby compromising neural network usability. To address this issue, we propose Meta-SimGNN, a novel WiFi localization system that integrates graph neural networks with meta-learning to improve localization generalization and robustness. First, we introduce a fine-grained CSI graph construction scheme, where each AP is treated as a graph node, allowing for adaptability to changes in the number of APs. To structure the features of each node, we propose an amplitude-phase fusion method and a feature extraction method. The former utilizes both amplitude and phase to construct CSI images, enhancing data reliability, while the latter extracts dimension-consistent features to address variations in bandwidth and the number of antennas. Second, a similarity-guided meta-learning strategy is developed to enhance adaptability in diverse scenarios. The initial model parameters for the fine-tuning stage are determined by comparing the similarity between the new scenario and historical scenarios, facilitating rapid adaptation of the model to the new localization scenario. Extensive experimental results over commodity WiFi devices in different scenarios show that Meta-SimGNN outperforms the baseline methods in terms of localization generalization and accuracy. --- ### CFG-OEC: Classifier Free Guidance with Orthogonal Error Correction Authors: Nakgyu Yang, Yechan Lee, SooJean Han Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.14075v2 Classifier free guidance is a standard method for conditional sampling in diffusion models, but its sampling rule is not aligned with the objective used in training. This mismatch induces a structural sampling error through the interaction of conditional and unconditional prediction errors. We analyze this issue by decomposing the sampling error into a base term and a cross term determined by the alignment of the two errors. Based on this analysis we propose CFG with orthogonal error correction (CFG-OEC), a structural modification that reduces the interaction term. For practical settings where ground truth noise is not observable, we introduce a proxy computed from model predictions and a dynamic method that stabilizes correction across diffusion timesteps. Experiments in a controlled environment validate our theoretical error decomposition and proxy construction. Image generation on Stable Diffusion v1.5 and Stable Diffusion XL show that CFG-OEC improves FID and CLIP scores over CFG and CFG++ across multiple samplers and guidance regimes. --- ### Dynamic Black-box Backdoor Attacks on IoT Sensory Data Authors: Ajesh Koyatan Chathoth, Stephen Lee Published: 2025-11-18 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2511.14074v1 Sensor data-based recognition systems are widely used in various applications, such as gait-based authentication and human activity recognition (HAR). Modern wearable and smart devices feature various built-in Inertial Measurement Unit (IMU) sensors, and such sensor-based measurements can be fed to a machine learning-based model to train and classify human activities. While deep learning-based models have proven successful in classifying human activity and gestures, they pose various security risks. In our paper, we discuss a novel dynamic trigger-generation technique for performing black-box adversarial attacks on sensor data-based IoT systems. Our empirical analysis shows that the attack is successful on various datasets and classifier models with minimal perturbation on the input data. We also provide a detailed comparative analysis of performance and stealthiness to various other poisoning techniques found in backdoor attacks. We also discuss some adversarial defense mechanisms and their impact on the effectiveness of our trigger-generation technique. --- ### Based on Data Balancing and Model Improvement for Multi-Label Sentiment Classification Performance Enhancement Authors: Zijin Su, Huanzhu Lyu, Yuren Niu, Yiming Liu Published: 2025-11-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.14073v3 Multi-label sentiment classification plays a vital role in natural language processing by detecting multiple emotions within a single text. However, existing datasets like GoEmotions often suffer from severe class imbalance, which hampers model performance, especially for underrepresented emotions. To address this, we constructed a balanced multi-label sentiment dataset by integrating the original GoEmotions data, emotion-labeled samples from Sentiment140 using a RoBERTa-base-GoEmotions model, and manually annotated texts generated by GPT-4 mini. Our data balancing strategy ensured an even distribution across 28 emotion categories. Based on this dataset, we developed an enhanced multi-label classification model that combines pre-trained FastText embeddings, convolutional layers for local feature extraction, bidirectional LSTM for contextual learning, and an attention mechanism to highlight sentiment-relevant words. A sigmoid-activated output layer enables multi-label prediction, and mixed precision training improves computational efficiency. Experimental results demonstrate significant improvements in accuracy, precision, recall, F1-score, and AUC compared to models trained on imbalanced data, highlighting the effectiveness of our approach. --- ### CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMs Authors: Jingyu Lei, Gaoang Wang, Der-Horng Lee Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14072v1 Large Vision-Language Models (LVLMs) usually suffer from prohibitive computational and memory costs due to the quadratic growth of visual tokens with image resolution. Existing token compression methods, while varied, often lack a high-level semantic understanding, leading to suboptimal merges, information redundancy, or context loss. To address these limitations, we introduce CORE (Compact Object-centric REpresentations), a new paradigm for visual token compression. CORE leverages an efficient segmentation decoder to generate object masks, which serve as a high-level semantic prior to guide the merging of visual tokens into a compact set of object-centric representations. Furthermore, a novel centroid-guided sorting mechanism restores a coherent spatial order to the merged tokens, preserving vital positional information. Extensive experiments show that CORE not only establishes a new state-of-the-art on six authoritative benchmarks for fixed-rate compression, but also achieves dramatic efficiency gains in adaptive-rate settings. Even under extreme compression, after aggressively retaining with only 2.2% of all visual tokens, CORE still maintains 97.4% of baseline performance. Our work demonstrates the superiority of object-centric representations for efficient and effective LVLM processing. --- ### ELiC: Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and Bag-of-Encoders Authors: Junsik Kim, Gun Bang, Soowoong Kim Published: 2025-11-18 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2511.14070v3 Hierarchical LiDAR geometry compression encodes voxel occupancies from low to high bit-depths, yet prior methods treat each depth independently and re-estimate local context from coordinates at every level, limiting compression efficiency. We present ELiC, a real-time framework that combines cross-bit-depth feature propagation, a Bag-of-Encoders (BoE) selection scheme, and a Morton-order-preserving hierarchy. Cross-bit-depth propagation reuses features extracted at denser, lower depths to support prediction at sparser, higher depths. BoE selects, per depth, the most suitable coding network from a small pool, adapting capacity to observed occupancy statistics without training a separate model for each level. The Morton hierarchy maintains global Z-order across depth transitions, eliminating per-level sorting and reducing latency. Together these components improve entropy modeling and computation efficiency, yielding state-of-the-art compression at real-time throughput on Ford and SemanticKITTI. Code and pretrained models are available at https://github.com/moolgom/ELiCv1. --- ### CafeMed: Causal Attention Fusion Enhanced Medication Recommendation Authors: Kelin Ren, Chan-Yang Ju, Dong-Ho Lee Published: 2025-11-18 Categories: cs.LG, cs.AI, stat.ME arXiv: https://arxiv.org/abs/2511.14064v1 Medication recommendation systems play a crucial role in assisting clinicians with personalized treatment decisions. While existing approaches have made significant progress in learning medication representations, they suffer from two fundamental limitations: (i) treating medical entities as independent features without modeling their synergistic effects on medication selection; (ii) employing static causal relationships that fail to adapt to patient-specific contexts and health states. To address these challenges, we propose CafeMed, a framework that integrates dynamic causal reasoning with cross-modal attention for safe and accurate medication recommendation. CafeMed introduces two key components: the Causal Weight Generator (CWG) that transforms static causal effects into dynamic modulation weights based on individual patient states, and the Channel Harmonized Attention Refinement Module (CHARM) that captures complex interdependencies between diagnoses and procedures. This design enables CafeMed to model how different medical conditions jointly influence treatment decisions while maintaining medication safety constraints. Extensive experiments on MIMIC-III and MIMIC-IV datasets demonstrate that CafeMed significantly outperforms state-of-the-art baselines, achieving superior accuracy in medication prediction while maintaining the lower drug--drug interaction rates. Our results indicate that incorporating dynamic causal relationships and cross-modal synergies leads to more clinically-aligned and personalized medication recommendations. Our code is released publicly at https://github.com/rkl71/CafeMed. --- ### Semantic Context Matters: Improving Conditioning for Autoregressive Models Authors: Dongyang Jin, Ryan Xu, Jianhao Zeng, Rui Lan, Yancheng Bai, Lei Sun, Xiangxiang Chu Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14063v2 Recently, autoregressive (AR) models have shown strong potential in image generation, offering better scalability and easier integration with unified multi-modal systems compared to diffusion-based methods. However, extending AR models to general image editing remains challenging due to weak and inefficient conditioning, often leading to poor instruction adherence and visual artifacts. To address this, we propose SCAR, a Semantic-Context-driven method for Autoregressive models. SCAR introduces two key components: Compressed Semantic Prefilling, which encodes high-level semantics into a compact and efficient prefix, and Semantic Alignment Guidance, which aligns the last visual hidden states with target semantics during autoregressive decoding to enhance instruction fidelity. Unlike decoding-stage injection methods, SCAR builds upon the flexibility and generality of vector-quantized-based prefilling while overcoming its semantic limitations and high cost. It generalizes across both next-token and next-set AR paradigms with minimal architectural changes. SCAR achieves superior visual fidelity and semantic alignment on both instruction editing and controllable generation benchmarks, outperforming prior AR-based methods while maintaining controllability. Code will be released at https://github.com/AMAP-ML/SCAR. --- ### LogPurge: Log Data Purification for Anomaly Detection via Rule-Enhanced Filtering Authors: Shenglin Zhang, Ziang Chen, Zijing Que, Yilun Liu, Yongqian Sun, Sicheng Wei, Dan Pei, Hailin Li Published: 2025-11-18 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2511.14062v1 Log anomaly detection, which is critical for identifying system failures and preempting security breaches, detects irregular patterns within large volumes of log data, and impacts domains such as service reliability, performance optimization, and database log analysis. Modern log anomaly detection methods rely on training deep learning models on clean, anomaly-free log sequences. However, obtaining such clean log data requires costly and tedious human labeling, and existing automatic cleaning methods fail to fully integrate the specific characteristics and actual semantics of logs in their purification process. In this paper, we propose a cost-aware, rule-enhanced purification framework, LogPurge, that automatically selects a sufficient subset of normal log sequences from contamination log sequences to train a anomaly detection model. Our approach involves a two-stage filtering algorithm: In the first stage, we use a large language model (LLM) to remove clustered anomalous patterns and enhance system rules to improve LLM's understanding of system logs; in the second stage, we utilize a divide-and-conquer strategy that decomposes the remaining contaminated regions into smaller subproblems, allowing each to be effectively purified through the first stage procedure. Our experiments, conducted on two public datasets and one industrial dataset, show that our method significantly removes an average of 98.74% of anomalies while retaining 82.39% of normal samples. Compared to the latest unsupervised log sample selection algorithms, our method achieves F-1 score improvements of 35.7% and 84.11% on the public datasets, and an impressive 149.72% F-1 improvement on the private dataset, demonstrating the effectiveness of our approach. --- ### A Machine Learning-Based Multimodal Framework for Wearable Sensor-Based Archery Action Recognition and Stress Estimation Authors: Xianghe Liu, Jiajia Liu, Chuxian Xu, Minghan Wang, Hongbo Peng, Tao Sun, Jiaqi Xu Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.14057v1 In precision sports such as archery, athletes' performance depends on both biomechanical stability and psychological resilience. Traditional motion analysis systems are often expensive and intrusive, limiting their use in natural training environments. To address this limitation, we propose a machine learning-based multimodal framework that integrates wearable sensor data for simultaneous action recognition and stress estimation. Using a self-developed wrist-worn device equipped with an accelerometer and photoplethysmography (PPG) sensor, we collected synchronized motion and physiological data during real archery sessions. For motion recognition, we introduce a novel feature--Smoothed Differential Acceleration (SmoothDiff)--and employ a Long Short-Term Memory (LSTM) model to identify motion phases, achieving 96.8% accuracy and 95.9% F1-score. For stress estimation, we extract heart rate variability (HRV) features from PPG signals and apply a Multi-Layer Perceptron (MLP) classifier, achieving 80% accuracy in distinguishing high- and low-stress levels. The proposed framework demonstrates that integrating motion and physiological sensing can provide meaningful insights into athletes' technical and mental states. This approach offers a foundation for developing intelligent, real-time feedback systems for training optimization in archery and other precision sports. --- ### Radial Compensation: The Inverse Base-Distribution Problem for Chart-Based Generative Models on Riemannian Manifolds Authors: Marios Papamichalis, Regina Ruane Published: 2025-11-18 Categories: cs.LG, cs.AI, cs.IT, math.DG, stat.ML arXiv: https://arxiv.org/abs/2511.14056v3 Latent-variable models on spheres and hyperbolic spaces usually draw a Gaussian in the tangent space at a base point and push it onto the manifold. On these spaces the distance from the base point is the coordinate that carries meaning: depth in a hierarchy, the angle of a rotation, the deviation of a protein frame from a reference. We show that the standard construction silently replaces whatever distance distribution the modeler intended with a fixed one, a scaled chi law whose shape no setting of the scale can change. We then solve the reverse problem. Given the intended distance distribution, we derive in closed form the tangent density that realizes it, prove it is the only isotropic choice with chart-independent likelihoods for a broad class of charts, and prove a lower bound with explicit constants on what ignoring the problem costs a variational autoencoder. Experiments backed by an exact per-run normalization audit confirm that the compensated prior is invariant to the chart and stable across scales, every wrapped baseline we train collapses to the boundary of its chart, curvature becomes recoverable where the wrapped prior fails and protein-orientation likelihood improves from 2.58 to 0.87 nats at identical accuracy. --- ### Making Evidence Actionable in Adaptive Learning Authors: Amirreza Mehrabi, Jason W. Morphew, Breejha Quezada, N. Sanjay Rebello Published: 2025-11-18 Categories: cs.AI, cs.CE, stat.AP, stat.OT arXiv: https://arxiv.org/abs/2511.14052v1 Adaptive learning often diagnoses precisely yet intervenes weakly, yielding help that is mistimed or misaligned. This study presents evidence supporting an instructor-governed feedback loop that converts concept-level assessment evidence into vetted micro-interventions. The adaptive learning algorithm contains three safeguards: adequacy as a hard guarantee of gap closure, attention as a budgeted constraint for time and redundancy, and diversity as protection against overfitting to a single resource. We formalize intervention assignment as a binary integer program with constraints for coverage, time, difficulty windows informed by ability estimates, prerequisites encoded by a concept matrix, and anti-redundancy enforced through diversity. Greedy selection serves low-richness and tight-latency regimes, gradient-based relaxation serves rich repositories, and a hybrid method transitions along a richness-latency frontier. In simulation and in an introductory physics deployment with one thousand two hundred four students, both solvers achieved full skill coverage for essentially all learners within bounded watch time. The gradient-based method reduced redundant coverage by approximately twelve percentage points relative to greedy and harmonized difficulty across slates, while greedy delivered comparable adequacy with lower computational cost in scarce settings. Slack variables localized missing content and supported targeted curation, sustaining sufficiency across subgroups. The result is a tractable and auditable controller that closes the diagnostic-pedagogical loop and delivers equitable, load-aware personalization at classroom scale. --- ### SmallML: Bayesian Transfer Learning for Small-Data Predictive Analytics Authors: Semen Leontev Published: 2025-11-18 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.14049v1 Small and medium-sized enterprises (SMEs) represent 99.9% of U.S. businesses yet remain systematically excluded from AI due to a mismatch between their operational scale and modern machine learning's data requirements. This paper introduces SmallML, a Bayesian transfer learning framework achieving enterprise-level prediction accuracy with datasets as small as 50-200 observations. We develop a three-layer architecture integrating transfer learning, hierarchical Bayesian modeling, and conformal prediction. Layer 1 extracts informative priors from 22,673 public records using a SHAP-based procedure transferring knowledge from gradient boosting to logistic regression. Layer 2 implements hierarchical pooling across J=5-50 SMEs with adaptive shrinkage, balancing population patterns with entity-specific characteristics. Layer 3 provides conformal sets with finite-sample coverage guarantees P(y in C(x)) >= 1-alpha for distribution-free uncertainty quantification. Validation on customer churn data demonstrates 96.7% +/- 4.2% AUC with 100 observations per business -- a +24.2 point improvement over independent logistic regression (72.5% +/- 8.1%), with p < 0.000001. Conformal prediction achieves 92% empirical coverage at 90% target. Training completes in 33 minutes on standard CPU hardware. By enabling enterprise-grade predictions for 33 million U.S. SMEs previously excluded from machine learning, SmallML addresses a critical gap in AI democratization. Keywords: Bayesian transfer learning, hierarchical models, conformal prediction, small-data analytics, SME machine learning --- ### Wasserstein Distributionally Robust Nash Equilibrium Seeking with Heterogeneous Data: A Lagrangian Approach Authors: Zifan Wang, Georgios Pantazis, Sergio Grammatico, Michael M. Zavlanos, Karl H. Johansson Published: 2025-11-18 Categories: math.OC, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2511.14048v2 We study a class of distributionally robust games where agents are allowed to heterogeneously choose their risk aversion with respect to distributional shifts of the uncertainty. In our formulation, heterogeneous Wasserstein ball constraints on each distribution are enforced through a penalty function leveraging a Lagrangian formulation. We then formulate the distributionally robust Nash equilibrium problem and show that under certain assumptions it is equivalent to a finite-dimensional variational inequality problem with a strongly monotone mapping. We then design an approximate Nash equilibrium seeking algorithm and prove convergence of the average regret to a quantity that diminishes with the number of iterations, thus learning the desired equilibrium up to an a priori specified accuracy. Numerical simulations corroborate our theoretical findings. --- ### Auditing Data Membership in Reinforcement Learning With Verifiable Rewards Authors: Yule Liu, Heyi Zhang, Jinyi Zheng, Zhen Sun, Zifan Peng, Jiaheng Wei, Tianshuo Cong, Yilong Yang, Xinlei He Published: 2025-11-18 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.14045v2 Reinforcement Learning with Verifiable Rewards (RLVR) has become a core training stage in recent large language models (LLMs). Its reliance on non-public, high-value prompt sets raises concerns about unauthorized data use, creating a need for exposure auditing. A natural tool is membership inference attacks (MIAs), but existing methods detect fitting to a fixed target string. This does not apply to RLVR, which generates responses from the model itself and reinforces successful ones, thus hindering the auditing of data exposure. We show that it remains detectable: RLVR reshapes the model's response distribution on training prompts, producing behavioral traces that can be surfaced through targeted auditing. We propose Divergence-in-Behavior Auditing (DIBA), a white-box query-level auditing framework for RLVR. DIBA compares a fine-tuned model against its pre-RLVR checkpoint along two axes: reward-side evidence capturing changes in verifiable task success, and policy-side evidence capturing prompt-conditioned behavioral drift. By aggregating over multiple stochastic rollouts, DIBA produces a stable query-level auditing signal. Under a white-box setting, DIBA consistently outperforms strong transferred likelihood-based baselines, including calibrated and self-generated variants, achieving around 0.8 AUC and an order-of-magnitude stronger TPR@0.1%FPR. We further show that RLVR auditing is stronger when training leaves non-trivial prompt-specific traces and weaker when the base model already performs well on the prompt. Under a practical grey-box setting, transfer is often robust across model sizes under the same RLVR algorithm, but more varied across algorithms, and can remain useful under distribution shift with carefully chosen shadow data. --- ### The CHASM-SWPC Dataset for Coronal Hole Detection & Analysis Authors: Cutter Beck, Evan Smith, Khagendra Katuwal, Rudra Kafle, Jacob Whitehill Published: 2025-11-18 Categories: astro-ph.IM, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.14044v1 Coronal holes (CHs) are low-activity, low-density solar coronal regions with open magnetic field lines (Cranmer 2009). In the extreme ultraviolet (EUV) spectrum, CHs appear as dark patches. Using daily hand-drawn maps from the Space Weather Prediction Center (SWPC), we developed a semi-automated pipeline to digitize the SWPC maps into binary segmentation masks. The resulting masks constitute the CHASM-SWPC dataset, a high-quality dataset to train and test automated CH detection models, which is released with this paper. We developed CHASM (Coronal Hole Annotation using Semi-automatic Methods), a software tool for semi-automatic annotation that enables users to rapidly and accurately annotate SWPC maps. The CHASM tool enabled us to annotate 1,111 CH masks, comprising the CHASM-SWPC-1111 dataset. We then trained multiple CHRONNOS (Coronal Hole RecOgnition Neural Network Over multi-Spectral-data) architecture (Jarolim et al. 2021) neural networks using the CHASM-SWPC dataset and compared their performance. Training the CHRONNOS neural network on these data achieved an accuracy of 0.9805, a True Skill Statistic (TSS) of 0.6807, and an intersection-over-union (IoU) of 0.5668, which is higher than the original pretrained CHRONNOS model Jarolim et al. (2021) achieved an accuracy of 0.9708, a TSS of 0.6749, and an IoU of 0.4805, when evaluated on the CHASM-SWPC-1111 test set. --- ### AISAC: An Integrated multi-agent System for Transparent, Retrieval-Grounded Scientific Assistance Authors: Chandrachur Bhattacharya, Sibendu Som Published: 2025-11-18 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2511.14043v3 AI Scientific Assistant Core (AISAC) is a transparent, modular multi-agent runtime developed at Argonne National Laboratory to support long-horizon, evidence-grounded scientific reasoning. Rather than proposing new agent algorithms or claiming autonomous scientific discovery, AISAC contributes a governed execution substrate that operationalizes key requirements for deploying agentic AI in scientific practice, including explicit role semantics, budgeted context management, traceable execution, and reproducible interaction with tools and knowledge. AISAC enforces four structural guarantees for scientific reasoning: (1) declarative agent registration with runtime-enforced role semantics and automatic system prompt generation; (2) budgeted orchestration via explicit per-turn context and delegation depth limits; (3) role-aligned memory access across episodic, dialogue, and evidence layers; and (4) trace-driven transparency through persistent execution records and a live event-stream interface. These guarantees are implemented through hybrid persistent memory (SQLite and dual FAISS indices), governed retrieval with agent-scoped RAG, structured tool execution with schema validation, and a configuration-driven bootstrap mechanism that enables project specific extension without modifying the shared core. AISAC is currently deployed across multiple scientific workflows at Argonne, including combustion science, materials research, and energy process safety, demonstrating its use as a reusable substrate for domain-specialized AI scientific assistants. --- ### Splat Regression Models Authors: Mara Daniels, Philippe Rigollet Published: 2025-11-18 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2511.14042v1 We introduce a highly expressive class of function approximators called Splat Regression Models. Model outputs are mixtures of heterogeneous and anisotropic bump functions, termed splats, each weighted by an output vector. The power of splat modeling lies in its ability to locally adjust the scale and direction of each splat, achieving both high interpretability and accuracy. Fitting splat models reduces to optimization over the space of mixing measures, which can be implemented using Wasserstein-Fisher-Rao gradient flows. As a byproduct, we recover the popular Gaussian Splatting methodology as a special case, providing a unified theoretical framework for this state-of-the-art technique that clearly disambiguates the inverse problem, the model, and the optimization algorithm. Through numerical experiments, we demonstrate that the resulting models and algorithms constitute a flexible and promising approach for solving diverse approximation, estimation, and inverse problems involving low-dimensional data. --- ### Saliency-Guided Deep Learning for Bridge Defect Detection in Drone Imagery Authors: Loucif Hebbache, Dariush Amirkhani, Mohand Saïd Allili, Jean-François Lapointe Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14040v1 Anomaly object detection and classification are one of the main challenging tasks in computer vision and pattern recognition. In this paper, we propose a new method to automatically detect, localize and classify defects in concrete bridge structures using drone imagery. This framework is constituted of two main stages. The first stage uses saliency for defect region proposals where defects often exhibit local discontinuities in the normal surface patterns with regard to their surrounding. The second stage employs a YOLOX-based deep learning detector that operates on saliency-enhanced images obtained by applying bounding-box level brightness augmentation to salient defect regions. Experimental results on standard datasets confirm the performance of our framework and its suitability in terms of accuracy and computational efficiency, which give a huge potential to be implemented in a self-powered inspection system. --- ### Flood-LDM: Generalizable Latent Diffusion Models for rapid and accurate zero-shot High-Resolution Flood Mapping Authors: Sun Han Neo, Sachith Seneviratne, Herath Mudiyanselage Viraj Vidura Herath, Abhishek Saha, Sanka Rasnayaka, Lucy Amanda Marshall Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14033v1 Flood prediction is critical for emergency planning and response to mitigate human and economic losses. Traditional physics-based hydrodynamic models generate high-resolution flood maps using numerical methods requiring fine-grid discretization; which are computationally intensive and impractical for real-time large-scale applications. While recent studies have applied convolutional neural networks for flood map super-resolution with good accuracy and speed, they suffer from limited generalizability to unseen areas. In this paper, we propose a novel approach that leverages latent diffusion models to perform super-resolution on coarse-grid flood maps, with the objective of achieving the accuracy of fine-grid flood maps while significantly reducing inference time. Experimental results demonstrate that latent diffusion models substantially decrease the computational time required to produce high-fidelity flood maps without compromising on accuracy, enabling their use in real-time flood risk management. Moreover, diffusion models exhibit superior generalizability across different physical locations, with transfer learning further accelerating adaptation to new geographic regions. Our approach also incorporates physics-informed inputs, addressing the common limitation of black-box behavior in machine learning, thereby enhancing interpretability. Code is available at https://github.com/neosunhan/flood-diff. --- ### FashionMAC: Deformation-Free Fashion Image Generation with Fine-Grained Model Appearance Customization Authors: Rong Zhang, Jinxiao Li, Jingnan Wang, Zhiwen Zuo, Jianfeng Dong, Wei Li, Chi Wang, Weiwei Xu, Xun Wang Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14031v2 Garment-centric fashion image generation aims to synthesize realistic and controllable human models dressing a given garment, which has attracted growing interest due to its practical applications in e-commerce. The key challenges of the task lie in two aspects: (1) faithfully preserving the garment details, and (2) gaining fine-grained controllability over the model's appearance. Existing methods typically require performing garment deformation in the generation process, which often leads to garment texture distortions. Also, they fail to control the fine-grained attributes of the generated models, due to the lack of specifically designed mechanisms. To address these issues, we propose FashionMAC, a novel diffusion-based deformation-free framework that achieves high-quality and controllable fashion showcase image generation. The core idea of our framework is to eliminate the need for performing garment deformation and directly outpaint the garment segmented from a dressed person, which enables faithful preservation of the intricate garment details. Moreover, we propose a novel region-adaptive decoupled attention (RADA) mechanism along with a chained mask injection strategy to achieve fine-grained appearance controllability over the synthesized human models. Specifically, RADA adaptively predicts the generated regions for each fine-grained text attribute and enforces the text attribute to focus on the predicted regions by a chained mask injection strategy, significantly enhancing the visual fidelity and the controllability. Extensive experiments validate the superior performance of our framework compared to existing state-of-the-art methods. ---