# Research Papers — 2025-11 · bundle page 157 of 197 > Full-text markdown of papers #7801–7850 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/157 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/156.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/158.md) ### Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs Authors: Renfei Zhang, Manasa Kaniselvan, Rylan Schaeffer, Niloofar Mireshghallah Published: 2025-11-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.05933v3 Reinforcement learning (RL) is often credited with improving reasoning at the expense of factual knowledge. We instead find that reasoning models outperform their instruction-tuned versions on factual recall by accessing existing parametric knowledge more effectively. Across five model families, structured prompting, which explicitly guides models through hierarchical traversal, recovers most of this gap, suggesting that much of the missing knowledge is latent rather than absent. Controlled RL experiments further support this: training on unseen, non-extractable facts improves recall of held-out, frequent but previously inaccessible facts, ruling out simple data exposure. Decomposing the training objective further attributes this gain to iterated on-policy exploration. The same mechanism appears behaviorally and internally: the reasoning advantage grows with retrieval depth, while layerwise analysis finds similar factual representations but divergent query representations. Distilled models, in contrast, often imitate self-correction without acquiring the exploration needed for navigation. Together, these findings suggest that improving factual recall in LLMs depends not only on expanding what models know but also on teaching them to navigate it, motivating future post-training methods that optimize traversal. --- ### The Future of AI in the GCC Post-NPM Landscape: A Comparative Analysis of Kuwait and the UAE Authors: Mohammad Rashed Albous, Bedour Alboloushi, Arnaud Lacheret Published: 2025-11-08 Categories: cs.CY, cs.AI, econ.TH arXiv: https://arxiv.org/abs/2511.05932v1 Comparative evidence on how Gulf Cooperation Council (GCC) states turn artificial intelligence (AI) ambitions into post--New Public Management (post-NPM) outcomes is scarce because most studies examine Western democracies. We analyze constitutional, collective-choice, and operational rules shaping AI uptake in two contrasting GCC members, the United Arab Emirates (UAE) and Kuwait, and whether they foster citizen centricity, collaborative governance, and public value creation. Anchored in Ostrom's Institutional Analysis and Development framework, the study combines a most similar/most different systems design with multiple sources: 62 public documents from 2018--2025, embedded UAE cases (Smart Dubai and MBZUAI), and 39 interviews with officials conducted Aug 2024--May 2025. Dual coding and process tracing connect rule configurations to AI performance. Cross-case analysis identifies four reinforcing mechanisms behind divergent trajectories. In the UAE, concentrated authority, credible sanctions, pro-innovation narratives, and flexible reinvestment rules scale pilots into hundreds of services and sizable recycled savings. In Kuwait, dispersed veto points, exhortative sanctions, cautious discourse, and lapsed AI budgets confine initiatives to pilot mode despite equivalent fiscal resources. The findings refine institutional theory by showing that vertical rule coherence, not wealth, determines AI's public-value yield, and temper post-NPM optimism by revealing that efficiency metrics serve societal goals only when backed by enforceable safeguards. To curb ethics washing and test transferability beyond the GCC, future work should track rule diffusion over time, develop blended legitimacy--efficiency scorecards, and examine how narrative framing shapes citizen consent for data sharing. --- ### Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement Authors: Hiroaki Hayashi, Bo Pang, Wenting Zhao, Ye Liu, Akash Gokul, Srijan Bansal, Caiming Xiong, Semih Yavuz, Yingbo Zhou Published: 2025-11-08 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2511.05931v1 Large language model (LLM) based agents are increasingly used to tackle software engineering tasks that require multi-step reasoning and code modification, demonstrating promising yet limited performance. However, most existing LLM agents typically operate within static execution frameworks, lacking a principled mechanism to learn and self-improve from their own experience and past rollouts. As a result, their performance remains bounded by the initial framework design and the underlying LLM's capabilities. We propose Self-Abstraction from Grounded Experience (SAGE), a framework that enables agents to learn from their own task executions and refine their behavior through self-abstraction. After an initial rollout, the agent induces a concise plan abstraction from its grounded experience, distilling key steps, dependencies, and constraints. This learned abstraction is then fed back as contextual guidance, refining the agent's policy and supporting more structured, informed subsequent executions. Empirically, SAGE delivers consistent performance gains across diverse LLM backbones and agent architectures. Notably, it yields a 7.2% relative performance improvement over the strong Mini-SWE-Agent baseline when paired with the GPT-5 (high) backbone. SAGE further achieves strong overall performance on SWE-Bench Verified benchmark, reaching 73.2% and 74% Pass@1 resolve rates with the Mini-SWE-Agent and OpenHands CodeAct agent framework, respectively. --- ### CoMA: Complementary Masking and Hierarchical Dynamic Multi-Window Self-Attention in a Unified Pre-training Framework Authors: Jiaxuan Li, Qing Xu, Xiangjian He, Ziyu Liu, Chang Xing, Zhen Chen, Daokun Zhang, Rong Qu, Chang Wen Chen Published: 2025-11-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.05929v1 Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing pretraining efficiency and yielding excellent adaptability across downstream tasks. However, MAE and other MAE-style paradigms that adopt random masking generally require more pre-training epochs to maintain adaptability. Meanwhile, ViT in MAE suffers from inefficient parameter use due to fixed spatial resolution across layers. To overcome these limitations, we propose the Complementary Masked Autoencoders (CoMA), which employ a complementary masking strategy to ensure uniform sampling across all pixels, thereby improving effective learning of all features and enhancing the model's adaptability. Furthermore, we introduce DyViT, a hierarchical vision transformer that employs a Dynamic Multi-Window Self-Attention (DM-MSA), significantly reducing the parameters and FLOPs while improving fine-grained feature learning. Pre-trained on ImageNet-1K with CoMA, DyViT matches the downstream performance of MAE using only 12% of the pre-training epochs, demonstrating more effective learning. It also attains a 10% reduction in pre-training time per epoch, further underscoring its superior pre-training efficiency. --- ### Artificial intelligence and the Gulf Cooperation Council workforce adapting to the future of work Authors: Mohammad Rashed Albous, Melodena Stephens, Odeh Rashed Al-Jayyousi Published: 2025-11-08 Categories: cs.CY, cs.AI, econ.GN arXiv: https://arxiv.org/abs/2511.05927v1 The rapid expansion of artificial intelligence (AI) in the Gulf Cooperation Council (GCC) raises a central question: are investments in compute infrastructure matched by an equally robust build-out of skills, incentives, and governance? Grounded in socio-technical systems (STS) theory, this mixed-methods study audits workforce preparedness across Kingdom of Saudi Arabia (KSA), the United Arab Emirates (UAE), Qatar, Kuwait, Bahrain, and Oman. We combine term frequency--inverse document frequency (TF--IDF) analysis of six national AI strategies (NASs), an inventory of 47 publicly disclosed AI initiatives (January 2017--April 2025), paired case studies, the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) and the Saudi Data & Artificial Intelligence Authority (SDAIA) Academy, and a scenario matrix linking oil-revenue slack (technical capacity) to regulatory coherence (social alignment). Across the corpus, 34/47 initiatives (0.72; 95% Wilson CI 0.58--0.83) exhibit joint social--technical design; country-level indices span 0.57--0.90 (small n; intervals overlap). Scenario results suggest that, under our modeled conditions, regulatory convergence plausibly binds outcomes more than fiscal capacity: fragmented rules can offset high oil revenues, while harmonized standards help preserve progress under austerity. We also identify an emerging two-track talent system, research elites versus rapidly trained practitioners, that risks labor-market bifurcation without bridging mechanisms. By extending STS inquiry to oil-rich, state-led economies, the study refines theory and sets a research agenda focused on longitudinal coupling metrics, ethnographies of coordination, and outcome-based performance indicators. --- ### DiScoFormer: Plug-In Density and Score Estimation with Transformers Authors: Vasily Ilin, Peter Sushko, Ranjay Krishna Published: 2025-11-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.05924v4 Estimating probability density and its score from samples remains a core problem in generative modeling, Bayesian inference, and kinetic theory. Existing methods are bifurcated: classical kernel density estimators (KDE) generalize across distributions but suffer from the curse of dimensionality, while modern neural score models achieve high precision but require retraining for every target distribution. We introduce DiScoFormer (Density and Score Transformer), a ``train-once, infer-anywhere" equivariant Transformer that maps i.i.d. samples to both density values and score vectors, generalizing across distributions and sample sizes. Analytically, we prove that self-attention can recover normalized KDE, establishing it as a functional generalization of kernel methods; empirically, individual attention heads learn multi-scale, kernel-like behaviors. The model converges faster and achieves higher precision than KDE for density estimation, and provides a high-fidelity plug-in score oracle for score-debiased KDE, Fisher information computation, and Fokker-Planck-type PDEs. --- ### Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation Authors: Qiming Li, Zekai Ye, Xiaocheng Feng, Weihong Zhong, Weitao Ma, Xiachong Feng Published: 2025-11-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05923v3 Despite the remarkable advancements of Large Vision-Language Models (LVLMs), the mechanistic interpretability remains underexplored. Existing analyses are insufficiently comprehensive and lack examination covering visual and textual tokens, model components, and the full range of layers. This limitation restricts actionable insights to improve the faithfulness of model output and the development of downstream tasks, such as hallucination mitigation. To address this limitation, we introduce Fine-grained Cross-modal Causal Tracing (FCCT) framework, which systematically quantifies the causal effects on visual object perception. FCCT conducts fine-grained analysis covering the full range of visual and textual tokens, three core model components including multi-head self-attention (MHSA), feed-forward networks (FFNs), and hidden states, across all decoder layers. Our analysis is the first to demonstrate that MHSAs of the last token in middle layers play a critical role in aggregating cross-modal information, while FFNs exhibit a three-stage hierarchical progression for the storage and transfer of visual object representations. Building on these insights, we propose Intermediate Representation Injection (IRI), a training-free inference-time technique that reinforces visual object information flow by precisely intervening on cross-modal representations at specific components and layers, thereby enhancing perception and mitigating hallucination. Consistent improvements across five widely used benchmarks and LVLMs demonstrate IRI achieves state-of-the-art performance, while preserving inference speed and other foundational performance. --- ### IDALC: A Semi-Supervised Framework for Intent Detection and Active Learning based Correction Authors: Ankan Mullick, Sukannya Purkayastha, Saransh Sharma, Pawan Goyal, Niloy Ganguly Published: 2025-11-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.05921v3 Voice-controlled dialog systems have become immensely popular due to their ability to perform a wide range of actions in response to diverse user queries. These agents possess a predefined set of skills or intents to fulfill specific user tasks. But every system has its own limitations. There are instances where, even for known intents, if any model exhibits low confidence, it results in rejection of utterances that necessitate manual annotation. Additionally, as time progresses, there may be a need to retrain these agents with new intents from the system-rejected queries to carry out additional tasks. Labeling all these emerging intents and rejected utterances over time is impractical, thus calling for an efficient mechanism to reduce annotation costs. In this paper, we introduce IDALC (Intent Detection and Active Learning based Correction), a semi-supervised framework designed to detect user intents and rectify system-rejected utterances while minimizing the need for human annotation. Empirical findings on various benchmark datasets demonstrate that our system surpasses baseline methods, achieving a 5-10% higher accuracy and a 4-8% improvement in macro-F1. Remarkably, we maintain the overall annotation cost at just 6-10% of the unlabelled data available to the system. The overall framework of IDALC is shown in Fig. 1 --- ### IoT-based Fresh Produce Supply Chain Under Uncertainty: An Adaptive Optimization Framework Authors: Chirag Seth, Mehrdad Pirnia, James H Bookbinder Published: 2025-11-08 Categories: math.OC, cs.AI arXiv: https://arxiv.org/abs/2511.05920v1 Fruits and vegetables form a vital component of the global economy; however, their distribution poses complex logistical challenges due to high perishability, supply fluctuations, strict quality and safety standards, and environmental sensitivity. In this paper, we propose an adaptive optimization model that accounts for delays, travel time, and associated temperature changes impacting produce shelf life, and compare it against traditional approaches such as Robust Optimization, Distributionally Robust Optimization, and Stochastic Programming. Additionally, we conduct a series of computational experiments using Internet of Things (IoT) sensor data to evaluate the performance of our proposed model. Our study demonstrates that the proposed adaptive model achieves a higher shelf life, extending it by over 18\% compared to traditional optimization models, by dynamically mitigating temperature deviations through a temperature feedback mechanism. The promising results demonstrate the potential of this approach to improve both the freshness and efficiency of logistics systems an aspect often neglected in previous works. --- ### Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs Authors: Alina Fastowski, Bardh Prenkaj, Yuxiao Li, Gjergji Kasneci Published: 2025-11-08 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.05919v3 LLMs are now an integral part of information retrieval. As such, their role as question answering chatbots raises significant concerns due to their shown vulnerability to adversarial man-in-the-middle (MitM) attacks. Here, we propose the first principled attack evaluation on LLM factual memory under prompt injection via Xmera, our novel, theory-grounded MitM framework. By perturbing the input given to "victim" LLMs in three closed-book and fact-based QA settings, we undermine the correctness of the responses and assess the uncertainty of their generation process. Surprisingly, trivial instruction-based attacks report the highest success rate (up to ~85.3%) while simultaneously having a high uncertainty for incorrectly answered questions. To provide a simple defense mechanism against Xmera, we train Random Forest classifiers on the response uncertainty levels to distinguish between attacked and unattacked queries (average AUC of up to ~94.8%). We believe that signaling users to be cautious about the answers they receive from black-box and potentially corrupt LLMs is a first checkpoint toward user cyberspace safety. --- ### NILC: Discovering New Intents with LLM-assisted Clustering Authors: Hongtao Wang, Renchi Yang, Wenqing Lin Published: 2025-11-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.05913v2 New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user utterances, which finds prevalent use in practical dialogue systems. Existing works towards NID mainly adopt a cascaded architecture, wherein the first stage focuses on encoding the utterances into informative text embeddings beforehand, while the latter is to group similar embeddings into clusters (i.e., intents), typically by K-Means. However, such a cascaded pipeline fails to leverage the feedback from both steps for mutual refinement, and, meanwhile, the embedding-only clustering overlooks nuanced textual semantics, leading to suboptimal performance. To bridge this gap, this paper proposes NILC, a novel clustering framework specially catered for effective NID. Particularly, NILC follows an iterative workflow, in which clustering assignments are judiciously updated by carefully refining cluster centroids and text embeddings of uncertain utterances with the aid of large language models (LLMs). Specifically, NILC first taps into LLMs to create additional semantic centroids for clusters, thereby enriching the contextual semantics of the Euclidean centroids of embeddings. Moreover, LLMs are then harnessed to augment hard samples (ambiguous or terse utterances) identified from clusters via rewriting for subsequent cluster correction. Further, we inject supervision signals through non-trivial techniques seeding and soft must links for more accurate NID in the semi-supervised setting. Extensive experiments comparing NILC against multiple recent baselines under both unsupervised and semi-supervised settings showcase that NILC can achieve significant performance improvements over six benchmark datasets of diverse domains consistently. --- ### The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation Authors: Zhengyuan Liu, Stella Xin Yin, Bryan Chen Zhengyu Tan, Roy Ka-Wei Lee, Guimei Liu, Dion Hoe-Lian Goh, Wenya Wang, Nancy F. Chen Published: 2025-11-08 Categories: cs.CY, cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2511.05903v2 User simulation is important for developing and evaluating human-centered AI, yet current student simulation in educational applications has significant limitations. Existing approaches focus on single learning experiences and do not account for students' gradual knowledge construction and evolving skill sets. Moreover, large language models are optimized to produce direct and accurate responses, making it challenging to represent the incomplete understanding and developmental constraints that characterize real learners. In this paper, we introduce a novel framework for memory-based student simulation that incorporates developmental trajectories through a hierarchical memory mechanism with structured knowledge representation. The framework also integrates metacognitive processes and personality traits to enrich the individual learner profiling, through dynamical consolidation of both cognitive development and personal learning characteristics. In practice, we implement a curriculum-aligned simulator grounded on the Next Generation Science Standards. Experimental results show that our approach can effectively reflect the gradual nature of knowledge development and the characteristic difficulties students face, providing a more accurate representation of learning processes. --- ### Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations Authors: Rui Yang, Matthew Yu Heng Wong, Huitao Li, Xin Li, Wentao Zhu, Jingchi Liao, Kunyu Yu, Jonathan Chong Kai Liew, Weihao Xuan, Yingjian Chen, Yuhe Ke, Jasmine Chiat Ling Ong et al. Published: 2025-11-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.05901v2 The rapid growth of medical knowledge and increasing complexity of clinical practice pose challenges. In this context, large language models (LLMs) have demonstrated value; however, inherent limitations remain. Retrieval-augmented generation (RAG) technologies show potential to enhance their clinical applicability. This study reviewed RAG applications in medicine. We found that research primarily relied on publicly available data, with limited application in private data. For retrieval, approaches commonly relied on English-centric embedding models, while LLMs were mostly generic, with limited use of medical-specific LLMs. For evaluation, automated metrics evaluated generation quality and task performance, whereas human evaluation focused on accuracy, completeness, relevance, and fluency, with insufficient attention to bias and safety. RAG applications were concentrated on question answering, report generation, text summarization, and information extraction. Overall, medical RAG remains at an early stage, requiring advances in clinical validation, cross-linguistic adaptation, and support for low-resource settings to enable trustworthy and responsible global use. --- ### Q$^2$: Quantization-Aware Gradient Balancing and Attention Alignment for Low-Bit Quantization Authors: Zhaoyang Wang, Dong Wang Published: 2025-11-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.05898v2 Quantization-aware training (QAT) has achieved remarkable success in low-bit ($\leq$4-bit) quantization for classification networks. However, when applied to more complex visual tasks such as object detection and image segmentation, performance still suffers significant degradation. A key cause of this limitation has been largely overlooked in the literature. In this work, we revisit this phenomenon from a new perspective and identify a major failure factor: gradient imbalance at feature fusion stages, induced by accumulated quantization errors. This imbalance biases the optimization trajectory and impedes convergence under low-bit quantization. Based on this diagnosis, we propose Q$^2$, a two-pronged framework comprising: (1) Quantization-aware Gradient Balancing Fusion (Q-GBFusion), a closed-loop mechanism that dynamically rebalances gradient contributions during feature fusion; and (2) Quantization-aware Attention Distribution Alignment (Q-ADA), a parameter-free supervision strategy that reconstructs the supervision distribution using semantic relevance and quantization sensitivity, yielding more stable and reliable supervision to stabilize training and accelerate convergence. Extensive experiments show that our method, as a plug-and-play and general strategy, can be integrated into various state-of-the-art QAT pipelines, achieving an average +2.5\% mAP gain on object detection and a +3.7\% mDICE improvement on image segmentation. Notably, it is applied only during training and introduces no inference-time overhead, making it highly practical for real-world deployment. --- ### Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning Authors: Fei Yu, Quan Deng, Shengeng Tang, Yuehua Li, Lechao Cheng Published: 2025-11-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05894v1 Understanding 3D scenes in open-world settings poses fundamental challenges for vision and robotics, particularly due to the limitations of closed-vocabulary supervision and static annotations. To address this, we propose a unified framework for Open-World 3D Scene Graph Generation with Retrieval-Augmented Reasoning, which enables generalizable and interactive 3D scene understanding. Our method integrates Vision-Language Models (VLMs) with retrieval-based reasoning to support multimodal exploration and language-guided interaction. The framework comprises two key components: (1) a dynamic scene graph generation module that detects objects and infers semantic relationships without fixed label sets, and (2) a retrieval-augmented reasoning pipeline that encodes scene graphs into a vector database to support text/image-conditioned queries. We evaluate our method on 3DSSG and Replica benchmarks across four tasks-scene question answering, visual grounding, instance retrieval, and task planning-demonstrating robust generalization and superior performance in diverse environments. Our results highlight the effectiveness of combining open-vocabulary perception with retrieval-based reasoning for scalable 3D scene understanding. --- ### Hybrid second-order gradient histogram based global low-rank sparse regression for robust face recognition Authors: Hongxia Li, Ying Ji, Yongxin Dong, Yuehua Feng Published: 2025-11-08 Categories: cs.CV, math.OC arXiv: https://arxiv.org/abs/2511.05893v2 Low-rank sparse regression models have been widely adopted in face recognition due to their robustness against occlusion and illumination variations. However, existing methods often suffer from insufficient feature representation and limited modeling of structured corruption across samples. To address these issues, this paper proposes a Hybrid second-order gradient Histogram based Global Low-Rank Sparse Regression (H2H-GLRSR) model. First, we propose the Histogram of Oriented Hessian (HOH) to capture second-order geometric characteristics such as curvature and ridge patterns. By fusing HOH and first-order gradient histograms, we construct a unified local descriptor, termed the Hybrid second-order gradient Histogram (H2H), which enhances structural discriminability under challenging conditions. Subsequently, the H2H features are incorporated into an extended version of the Sparse Regularized Nuclear Norm based Matrix Regression (SR\_NMR) model, where a global low-rank constraint is imposed on the residual matrix to exploit cross-sample correlations in structured noise. The resulting H2H-GLRSR model achieves superior discrimination and robustness. Experimental results on benchmark datasets demonstrate that the proposed method significantly outperforms state-of-the-art regression-based classifiers in both recognition accuracy and computational efficiency. --- ### SAR-FAH: A Frequency-Adaptive Hybrid Network based on Neural ODEs for Structural-Preserving SAR Despeckling Authors: Ziqing Ma, Chang Yang, Zhichang Guo, Yao Li Published: 2025-11-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05890v2 Synthetic Aperture Radar (SAR) images are inherently degraded by speckle noise that severely limits their reliability in high-precision applications. As a signal-dependent multiplicative noise, speckle noise exhibits distinct statistical properties in homogeneous and heterogeneous regions of SAR images, which are spatially coupled. Nevertheless, existing deep learning despeckling methods operate directly in the spatial domain overlooking this statistical difference. It imposes a suboptimal trade-off between noise suppression and structure preservation, inevitably leading to artifacts, edge blurring, and texture distortion. To address these limitations, we propose a Frequency-Adaptive Hybrid model based on Neural Ordinary Differential Equations (NODEs) for SAR despeckling, termed SAR-FAH. It is a novel divide-and-conquer architecture that performs despeckling in the frequency domain to achieve improved structural preservation. We first fully decouple homogeneous and heterogeneous regions in the frequency domain via wavelet transform according to their local spatial characteristics and then revisit the statistical characteristics of speckle noise. Guided by the distinct properties of each sub-band, we design specialized sub-networks for frequency-specific restoration. Specifically, based on the smoothness of the low-frequency sub-band, the low-frequency denoising process is controlled by the module based on NODEs to ensure sufficient smoothness without artifacts, while the high-frequency sub-bands are processed by enhanced U-Net by incorporating deformable convolutions to better suppress noise and preserve edges and textures. Extensive experiments on both synthetic and real SAR images demonstrate that the proposed SAR-FAH outperforms the state-of-the-art methods both quantitatively and qualitatively. --- ### An item is worth one token in Multimodal Large Language Models-based Sequential Recommendation Authors: Qiyong Zhong, Jiajie Su, Ming Yang, Yunshan Ma, Xiaolin Zheng, Chaochao Chen Published: 2025-11-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2511.05885v3 Sequential recommendations (SR) predict users' future interactions based on their historical behavior. The rise of Large Language Models (LLMs) has brought powerful generative and reasoning capabilities, significantly enhancing SR performance, while Multimodal LLMs (MLLMs) further extend this by introducing data like images and interactive relationships. However, critical issues remain, i.e., (a) Suboptimal item representations caused by lengthy and redundant descriptions, leading to inefficiencies in both training and inference; (b) Modality-related cognitive bias, as LLMs are predominantly pretrained on textual data, limiting their ability to effectively integrate and utilize non-textual modalities; (c) Weakening sequential perception in long interaction sequences, where attention mechanisms struggle to capture earlier interactions, hindering the modeling of long-range dependencies. To address these issues, we propose Speeder, an efficient MLLM-based paradigm for SR featuring three key innovations: 1) Multimodal Representation Compression (MRC), which condenses item attributes into concise yet informative tokens, reducing redundancy and computational cost; 2) Modality-aware Progressive Optimization (MPO), enabling gradual learning of multimodal representations; 3) Sequential Position Awareness Enhancement (SPAE), improving the LLM's capability to capture both relative and absolute sequential dependencies in long interaction sequences. Extensive experiments on real-world datasets demonstrate the effectiveness and efficiency of Speeder. Speeder increases training speed to 250% of the original while reducing inference time to 25% on the Amazon dataset. --- ### Unveiling Modality Bias: Automated Sample-Specific Analysis for Multimodal Misinformation Benchmarks Authors: Hehai Lin, Hui Liu, Shilei Cao, Jing Li, Haoliang Li, Wenya Wang Published: 2025-11-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.05883v1 Numerous multimodal misinformation benchmarks exhibit bias toward specific modalities, allowing detectors to make predictions based solely on one modality. While previous research has quantified bias at the dataset level or manually identified spurious correlations between modalities and labels, these approaches lack meaningful insights at the sample level and struggle to scale to the vast amount of online information. In this paper, we investigate the design for automated recognition of modality bias at the sample level. Specifically, we propose three bias quantification methods based on theories/views of different levels of granularity: 1) a coarse-grained evaluation of modality benefit; 2) a medium-grained quantification of information flow; and 3) a fine-grained causality analysis. To verify the effectiveness, we conduct a human evaluation on two popular benchmarks. Experimental results reveal three interesting findings that provide potential direction toward future research: 1)~Ensembling multiple views is crucial for reliable automated analysis; 2)~Automated analysis is prone to detector-induced fluctuations; and 3)~Different views produce a higher agreement on modality-balanced samples but diverge on biased ones. --- ### Hard-constraint physics-residual networks for hydrogen crossover prediction and high-pressure extrapolation in PEM water electrolysis Authors: Yong-Woon Kim, Jihyeok Lee, Chulung Kang, Yung-Cheol Byun Published: 2025-11-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.05879v5 Hydrogen crossover is a critical safety and efficiency constraint in high-pressure polymer electrolyte membrane water electrolysis (PEMWE), but accurate prediction remains difficult because data are limited, transport physics are strongly coupled, and industrial operation requires reliable extrapolation beyond observed conditions. This study develops a hard-constraint physics-residual network (PR-Net) for hydrogen crossover prediction in PEMWE and compares it with a purely data-driven neural network (NN) and a soft-constraint physics-informed neural network (PINN). PR-Net embeds Henry's, Fick's, and Faraday's laws as a deterministic backbone and learns only a residual correction for unmodelled nonlinear effects. The benchmark includes 184 observations from eight peer-reviewed sources across six membrane types, covering 1-200 bar, $25-85°C$, and $0.05-5.0 A cm^{-2}$. PR-Net achieves $R^2 = 99.57 \pm 0.16%$, with 9-fold lower prediction variability than NN and PINN. In pressure-axis extrapolation, PR-Net attains $R^2 = 94.02 \pm 0.92%$ at 200 bar, 2.5 times beyond the training pressure range, compared with $68.06 \pm 5.52%$ for PINN and $58.00 \pm 8.60%$ for NN (p < 0.001). Residual analysis indicates that the learned correction captures part of the high-pressure gas-phase non-ideality and recovers a transport-regime transition near $0.23 A cm^{-2}$ between Fickian diffusion-dominated and Faradaic production-dominated transport. With a computation time of $1.08 \pm 0.34 ms$ on low-power embedded hardware, PR-Net provides a practical framework for real-time crossover monitoring, adaptive process control, and safer high-pressure green-hydrogen operation. --- ### FusionLog: Cross-System Log-based Anomaly Detection via Fusion of General and Proprietary Knowledge Authors: Xinlong Zhao, Tong Jia, Minghua He, Xixuan Yang, Ying Li Published: 2025-11-08 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2511.05878v3 Log-based anomaly detection is critical for ensuring the stability and reliability of web systems. One of the key problems in this task is the lack of sufficient labeled logs, which limits the rapid deployment in new systems. Existing works usually leverage large-scale labeled logs from a mature web system and a small amount of labeled logs from a new system, using transfer learning to extract and generalize general knowledge across both domains. However, these methods focus solely on the transfer of general knowledge and neglect the disparity and potential mismatch between such knowledge and the proprietary knowledge of target system, thus constraining performance. To address this limitation, we propose FusionLog, a novel zero-label cross-system log-based anomaly detection method that effectively achieves the fusion of general and proprietary knowledge, enabling cross-system generalization without any labeled target logs. Specifically, we first design a training-free router based on semantic similarity that dynamically partitions unlabeled target logs into 'general logs' and 'proprietary logs.' For general logs, FusionLog employs a small model based on system-agnostic representation meta-learning for direct training and inference, inheriting the general anomaly patterns shared between the source and target systems. For proprietary logs, we iteratively generate pseudo-labels and fine-tune the small model using multi-round collaborative knowledge distillation and fusion based on large language model (LLM) and small model (SM) to enhance its capability to recognize anomaly patterns specific to the target system. Experimental results on three public log datasets from different systems show that FusionLog achieves over 90% F1-score under a fully zero-label setting, significantly outperforming state-of-the-art cross-system log-based anomaly detection methods. --- ### MoEGCL: Mixture of Ego-Graphs Contrastive Representation Learning for Multi-View Clustering Authors: Jian Zhu, Xin Zou, Jun Sun, Cheng Luo, Lei Liu, Lingfang Zeng, Ning Zhang, Bian Wu, Chang Tang, Lirong Dai Published: 2025-11-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.05876v5 In recent years, the advancement of Graph Neural Networks (GNNs) has significantly propelled progress in Multi-View Clustering (MVC). However, existing methods face the problem of coarse-grained graph fusion. Specifically, current approaches typically generate a separate graph structure for each view and then perform weighted fusion of graph structures at the view level, which is a relatively rough strategy. To address this limitation, we present a novel Mixture of Ego-Graphs Contrastive Representation Learning (MoEGCL). It mainly consists of two modules. In particular, we propose an innovative Mixture of Ego-Graphs Fusion (MoEGF), which constructs ego graphs and utilizes a Mixture-of-Experts network to implement fine-grained fusion of ego graphs at the sample level, rather than the conventional view-level fusion. Additionally, we present the Ego Graph Contrastive Learning (EGCL) module to align the fused representation with the view-specific representation. The EGCL module enhances the representation similarity of samples from the same cluster, not merely from the same sample, further boosting fine-grained graph representation. Extensive experiments demonstrate that MoEGCL achieves state-of-the-art results in deep multi-view clustering tasks. The source code is publicly available at https://github.com/HackerHyper/MoEGCL. --- ### Towards a Humanized Social-Media Ecosystem: AI-Augmented HCI Design Patterns for Safety, Agency & Well-Being Authors: Mohd Ruhul Ameen, Akif Islam Published: 2025-11-08 Categories: cs.HC, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.05875v1 Social platforms connect billions of people, yet their engagement-first algorithms often work on users rather than with them, amplifying stress, misinformation, and a loss of control. We propose Human-Layer AI (HL-AI)--user-owned, explainable intermediaries that sit in the browser between platform logic and the interface. HL-AI gives people practical, moment-to-moment control without requiring platform cooperation. We contribute a working Chrome/Edge prototype implementing five representative pattern frameworks--Context-Aware Post Rewriter, Post Integrity Meter, Granular Feed Curator, Micro-Withdrawal Agent, and Recovery Mode--alongside a unifying mathematical formulation balancing user utility, autonomy costs, and risk thresholds. Evaluation spans technical accuracy, usability, and behavioral outcomes. The result is a suite of humane controls that help users rewrite before harm, read with integrity cues, tune feeds with intention, pause compulsive loops, and seek shelter during harassment, all while preserving agency through explanations and override options. This prototype offers a practical path to retrofit today's feeds with safety, agency, and well-being, inviting rigorous cross-cultural user evaluation. --- ### An Empirical Study of Reasoning Steps in Thinking Code LLMs Authors: Haoran Xue, Gias Uddin, Song Wang Published: 2025-11-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.05874v1 Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accuracy for code generation. However, the quality of these reasoning chains remains underexplored. We present a comprehensive empirical study examining the reasoning process and quality of thinking LLMs for code generation. We evaluate six state-of-the-art reasoning LLMs (DeepSeek-R1, OpenAI-o3-mini, Claude-3.7-Sonnet-Thinking, Gemini-2.0-Flash-Thinking, Gemini-2.5-Flash, and Qwen-QwQ) across 100 code generation tasks of varying difficulty from BigCodeBench. We quantify reasoning-chain structure through step counts and verbosity, conduct controlled step-budget adjustments, and perform a 21-participant human evaluation across three dimensions: efficiency, logical correctness, and completeness. Our step-count interventions reveal that targeted step increases can improve resolution rates for certain models/tasks, while modest reductions often preserve success on standard tasks, rarely on hard ones. Through systematic analysis, we develop a reasoning-problematic taxonomy, identifying completeness as the dominant failure mode. Task complexity significantly impacts reasoning quality; hard problems are substantially more prone to incompleteness than standard tasks. Our stability analysis demonstrates that thinking LLMs maintain consistent logical structures across computational effort levels and can self-correct previous errors. This study provides new insights into the strengths and limitations of current thinking LLMs in software engineering. --- ### EndoIR: Degradation-Agnostic All-in-One Endoscopic Image Restoration via Noise-Aware Routing Diffusion Authors: Tong Chen, Xinyu Ma, Long Bai, Wenyang Wang, Yue Sun, Luping Zhou Published: 2025-11-08 Categories: eess.IV, cs.AI, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.05873v2 Endoscopic images often suffer from diverse and co-occurring degradations such as low lighting, smoke, and bleeding, which obscure critical clinical details. Existing restoration methods are typically task-specific and often require prior knowledge of the degradation type, limiting their robustness in real-world clinical use. We propose EndoIR, an all-in-one, degradation-agnostic diffusion-based framework that restores multiple degradation types using a single model. EndoIR introduces a Dual-Domain Prompter that extracts joint spatial-frequency features, coupled with an adaptive embedding that encodes both shared and task-specific cues as conditioning for denoising. To mitigate feature confusion in conventional concatenation-based conditioning, we design a Dual-Stream Diffusion architecture that processes clean and degraded inputs separately, with a Rectified Fusion Block integrating them in a structured, degradation-aware manner. Furthermore, Noise-Aware Routing Block improves efficiency by dynamically selecting only noise-relevant features during denoising. Experiments on SegSTRONG-C and CEC datasets demonstrate that EndoIR achieves state-of-the-art performance across multiple degradation scenarios while using fewer parameters than strong baselines, and downstream segmentation experiments confirm its clinical utility. --- ### Adaptation and Fine-tuning with TabPFN for Travelling Salesman Problem Authors: Nguyen Gia Hien Vu, Yifan Tang, Rey Lim, Yifan Yang, Hang Ma, Ke Wang, G. Gary Wang Published: 2025-11-08 Categories: cs.LG, cs.AI, math.CO arXiv: https://arxiv.org/abs/2511.05872v1 Tabular Prior-Data Fitted Network (TabPFN) is a foundation model designed for small to medium-sized tabular data, which has attracted much attention recently. This paper investigates the application of TabPFN in Combinatorial Optimization (CO) problems. The aim is to lessen challenges in time and data-intensive training requirements often observed in using traditional methods including exact and heuristic algorithms, Machine Learning (ML)-based models, to solve CO problems. Proposing possibly the first ever application of TabPFN for such a purpose, we adapt and fine-tune the TabPFN model to solve the Travelling Salesman Problem (TSP), one of the most well-known CO problems. Specifically, we adopt the node-based approach and the node-predicting adaptation strategy to construct the entire TSP route. Our evaluation with varying instance sizes confirms that TabPFN requires minimal training, adapts to TSP using a single sample, performs better generalization across varying TSP instance sizes, and reduces performance degradation. Furthermore, the training process with adaptation and fine-tuning is completed within minutes. The methodology leads to strong solution quality even without post-processing and achieves performance comparable to other models with post-processing refinement. Our findings suggest that the TabPFN model is a promising approach to solve structured and CO problems efficiently under training resource constraints and rapid deployment requirements. --- ### HarmoQ: Harmonized Post-Training Quantization for High-Fidelity Image Authors: Hongjun Wang, Jiyuan Chen, Xuan Song, Yinqiang Zheng Published: 2025-11-08 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2511.05868v2 Post-training quantization offers an efficient pathway to deploy super-resolution models, yet existing methods treat weight and activation quantization independently, missing their critical interplay. Through controlled experiments on SwinIR, we uncover a striking asymmetry: weight quantization primarily degrades structural similarity, while activation quantization disproportionately affects pixel-level accuracy. This stems from their distinct roles--weights encode learned restoration priors for textures and edges, whereas activations carry input-specific intensity information. Building on this insight, we propose HarmoQ, a unified framework that harmonizes quantization across components through three synergistic steps: structural residual calibration proactively adjusts weights to compensate for activation-induced detail loss, harmonized scale optimization analytically balances quantization difficulty via closed-form solutions, and adaptive boundary refinement iteratively maintains this balance during optimization. Experiments show HarmoQ achieves substantial gains under aggressive compression, outperforming prior art by 0.46 dB on Set5 at 2-bit while delivering 3.2x speedup and 4x memory reduction on A100 GPUs. This work provides the first systematic analysis of weight-activation coupling in super-resolution quantization and establishes a principled solution for efficient high-quality image restoration. --- ### Can LLM Infer Risk Information From MCP Server System Logs? Authors: Jiayi Fu, Yuansen Zhang, Yinggui Wang Published: 2025-11-08 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2511.05867v3 Large Language Models (LLMs) demonstrate strong capabilities in solving complex tasks when integrated with external tools. The Model Context Protocol (MCP) has become a standard interface for enabling such tool-based interactions. However, these interactions introduce substantial security concerns, particularly when the MCP server is compromised or untrustworthy. While prior benchmarks primarily focus on prompt injection attacks or analyze the vulnerabilities of LLM-MCP interaction trajectories, limited attention has been given to the underlying system logs associated with malicious MCP servers. To address this gap, we present the first synthetic benchmark for evaluating LLMs' ability to identify security risks from system logs. We define nine categories of MCP server risks and generate 1,800 synthetic system logs using ten state-of-the-art LLMs. These logs are embedded in the return values of 243 curated MCP servers, yielding a dataset of 2,421 chat histories for training and 471 queries for evaluation. Our pilot experiments reveal that smaller models often fail to detect risky system logs, leading to high false negatives. While models trained with supervised fine-tuning (SFT) tend to over-flag benign logs, resulting in elevated false positives, Reinforcement Learning with Verifiable Reward (RLVR) offers a better precision-recall balance. In particular, after training with Group Relative Policy Optimization (GRPO), Llama3.1-8B-Instruct achieves 83 percent accuracy, surpassing the best-performing large remote model by 9 percentage points. Fine-grained, per-category analysis further underscores the effectiveness of reinforcement learning in enhancing LLM safety within the MCP framework. Code and data are available at https://github.com/PorUna-byte/MCP-RiskCue. --- ### Light-Field Dataset for Disparity Based Depth Estimation Authors: Suresh Nehra, Aupendu Kar, Jayanta Mukhopadhyay, Prabir Kumar Biswas Published: 2025-11-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05866v1 A Light Field (LF) camera consists of an additional two-dimensional array of micro-lenses placed between the main lens and sensor, compared to a conventional camera. The sensor pixels under each micro-lens receive light from a sub-aperture of the main lens. This enables the image sensor to capture both spatial information and the angular resolution of a scene point. This additional angular information is used to estimate the depth of a 3-D scene. The continuum of virtual viewpoints in light field data enables efficient depth estimation using Epipolar Line Images (EPIs) with robust occlusion handling. However, the trade-off between angular information and spatial information is very critical and depends on the focal position of the camera. To design, develop, implement, and test novel disparity-based light field depth estimation algorithms, the availability of suitable light field image datasets is essential. In this paper, a publicly available light field image dataset is introduced and thoroughly described. We have also demonstrated the effect of focal position on the disparity of a 3-D point as well as the shortcomings of the currently available light field dataset. The proposed dataset contains 285 light field images captured using a Lytro Illum LF camera and 13 synthetic LF images. The proposed dataset also comprises a synthetic dataset with similar disparity characteristics to those of a real light field camera. A real and synthetic stereo light field dataset is also created by using a mechanical gantry system and Blender. The dataset is available at https://github.com/aupendu/light-field-dataset. --- ### CGCE: Classifier-Guided Concept Erasure in Generative Models Authors: Viet Nguyen, Vishal M. Patel Published: 2025-11-08 Categories: cs.CV, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2511.05865v3 Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content. To mitigate this, concept erasure methods have been developed to remove undesirable concepts from pre-trained models. However, existing methods remain vulnerable to adversarial attacks that can regenerate the erased content. Moreover, achieving robust erasure often degrades the model's generative quality for safe, unrelated concepts, creating a difficult trade-off between safety and performance. To address this challenge, we introduce Classifier-Guided Concept Erasure (CGCE), an efficient plug-and-play framework that provides robust concept erasure for diverse generative models without altering their original weights. CGCE uses a lightweight classifier operating on text embeddings to first detect and then refine prompts containing undesired concepts. By modifying only unsafe embeddings at inference time, our method prevents harmful content generation while preserving the model's original quality on benign prompts. Extensive experiments show that CGCE achieves state-of-the-art robustness against a wide range of red-teaming attacks. Our approach also maintains high generative utility, demonstrating a superior balance between safety and performance. We showcase the versatility of CGCE through its successful application to various modern T2I and T2V models, establishing it as a practical and effective solution for safe generative AI. --- ### EMOD: A Unified EEG Emotion Representation Framework Leveraging V-A Guided Contrastive Learning Authors: Yuning Chen, Sha Zhao, Shijian Li, Gang Pan Published: 2025-11-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.05863v2 Emotion recognition from EEG signals is essential for affective computing and has been widely explored using deep learning. While recent deep learning approaches have achieved strong performance on single EEG emotion datasets, their generalization across datasets remains limited due to the heterogeneity in annotation schemes and data formats. Existing models typically require dataset-specific architectures tailored to input structure and lack semantic alignment across diverse emotion labels. To address these challenges, we propose EMOD: A Unified EEG Emotion Representation Framework Leveraging Valence-Arousal (V-A) Guided Contrastive Learning. EMOD learns transferable and emotion-aware representations from heterogeneous datasets by bridging both semantic and structural gaps. Specifically, we project discrete and continuous emotion labels into a unified V-A space and formulate a soft-weighted supervised contrastive loss that encourages emotionally similar samples to cluster in the latent space. To accommodate variable EEG formats, EMOD employs a flexible backbone comprising a Triple-Domain Encoder followed by a Spatial-Temporal Transformer, enabling robust extraction and integration of temporal, spectral, and spatial features. We pretrain EMOD on 8 public EEG datasets and evaluate its performance on three benchmark datasets. Experimental results show that EMOD achieves the state-of-the-art performance, demonstrating strong adaptability and generalization across diverse EEG-based emotion recognition scenarios. --- ### Predicting the Future by Retrieving the Past Authors: Dazhao Du, Tao Han, Song Guo Published: 2025-11-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.05859v1 Deep learning models such as MLP, Transformer, and TCN have achieved remarkable success in univariate time series forecasting, typically relying on sliding window samples from historical data for training. However, while these models implicitly compress historical information into their parameters during training, they are unable to explicitly and dynamically access this global knowledge during inference, relying only on the local context within the lookback window. This results in an underutilization of rich patterns from the global history. To bridge this gap, we propose Predicting the Future by Retrieving the Past (PFRP), a novel approach that explicitly integrates global historical data to enhance forecasting accuracy. Specifically, we construct a Global Memory Bank (GMB) to effectively store and manage global historical patterns. A retrieval mechanism is then employed to extract similar patterns from the GMB, enabling the generation of global predictions. By adaptively combining these global predictions with the outputs of any local prediction model, PFRP produces more accurate and interpretable forecasts. Extensive experiments conducted on seven real-world datasets demonstrate that PFRP significantly enhances the average performance of advanced univariate forecasting models by 8.4\%. Codes can be found in https://github.com/ddz16/PFRP. --- ### Can a Small Model Learn to Look Before It Leaps? Dynamic Learning and Proactive Correction for Hallucination Detection Authors: Zepeng Bao, Shen Zhou, Qiankun Pi, Jianhao Chen, Mayi Xu, Ming Zhong, Yuanyuan Zhu, Tieyun Qian Published: 2025-11-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.05854v2 Hallucination in large language models (LLMs) remains a critical barrier to their safe deployment. For hallucination detection to be practical in real-world scenarios, the use of efficient small models is essential to ensure low latency and minimal resource consumption. However, existing methods rely on fixed verification strategies, where simply tuning small models to mimic fixed verification trajectories fails to capture the adaptability required for diverse hallucination patterns, thereby inducing planning instability. To address this limitation, we propose a ``Learning to Evaluate and Adaptively Plan'' (LEAP) framework, which shifts hallucination detection from fixed execution to dynamic strategy learning. Specifically, LEAP first employs a powerful teacher model to iteratively explore and refine verification strategies through a failure-driven loop. This dynamic planning capability is then distilled into an efficient student model, augmented by a novel proactive correction mechanism that enables the model to evaluate and optimize its verification strategy before execution. Experiments on three benchmarks demonstrate that LEAP outperforms state-of-the-art methods, offering an effective and scalable solution for reliable hallucination detection. --- ### Point Cloud Segmentation of Integrated Circuits Package Substrates Surface Defects Using Causal Inference: Dataset Construction and Methodology Authors: Bingyang Guo, Qiang Zuo, Ruiyun Yu Published: 2025-11-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05853v1 The effective segmentation of 3D data is crucial for a wide range of industrial applications, especially for detecting subtle defects in the field of integrated circuits (IC). Ceramic package substrates (CPS), as an important electronic material, are essential in IC packaging owing to their superior physical and chemical properties. However, the complex structure and minor defects of CPS, along with the absence of a publically available dataset, significantly hinder the development of CPS surface defect detection. In this study, we construct a high-quality point cloud dataset for 3D segmentation of surface defects in CPS, i.e., CPS3D-Seg, which has the best point resolution and precision compared to existing 3D industrial datasets. CPS3D-Seg consists of 1300 point cloud samples under 20 product categories, and each sample provides accurate point-level annotations. Meanwhile, we conduct a comprehensive benchmark based on SOTA point cloud segmentation algorithms to validate the effectiveness of CPS3D-Seg. Additionally, we propose a novel 3D segmentation method based on causal inference (CINet), which quantifies potential confounders in point clouds through Structural Refine (SR) and Quality Assessment (QA) Modules. Extensive experiments demonstrate that CINet significantly outperforms existing algorithms in both mIoU and accuracy. --- ### Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation Authors: Yinjie Cheng, Paul Youssef, Christin Seifert, Jörg Schlötterer, Zhixue Zhao Published: 2025-11-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.05852v4 Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting LLMs to new domains and tasks. Despite their widespread adoption, these two post-training interventions have been studied in isolation, leaving open a crucial question: if we fine-tune an edited model, do the edits survive? This question is motivated by practical objectives: removing covert or malicious edits, and preserving beneficial edits. If fine-tuning impairs edits (Fig.1), current KE methods become less efficient, as a newly fine-tuned model requires re-editing; if edits persist, fine-tuned models risk propagating hidden malicious edits, raising serious safety concerns. To this end, we systematically quantify edit decay after fine-tuning across 254 experimental configurations. Our results show that in general, edits decay substantially after subsequent fine-tuning. AlphaEdit exhibits the greatest decay on the zsRE benchmark when applied to GPT-J, where 25.27% of previously successful edits become unsuccessful after fine-tuning. We further find that fine-tuning only the edited layers is sufficient to effectively remove edits, while incurring only modest degradation in downstream performance. Surprisingly, fine-tuning non-edited layers leads to greater edit decay than all-layer fine-tuning. Besides, our activation space analysis reveals that fine-tuning produces a larger and more coherent representational shift, both in magnitude and direction, than KE. Overall, our study underscores the necessity of evaluating KE within the broader LLM application pipeline. --- ### Retrieval Quality at Context Limit Authors: Max McKinnon Published: 2025-11-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2511.05850v1 The ability of large language models (LLMs) to recall and retrieve information from long contexts is critical for many real-world applications. Prior work (Liu et al., 2023) reported that LLMs suffer significant drops in retrieval accuracy for facts placed in the middle of large contexts, an effect known as "Lost in the Middle" (LITM). We find the model Gemini 2.5 Flash can answer needle-in-a-haystack questions with great accuracy regardless of document position including when the document is nearly at the input context limit. Our results suggest that the "Lost in the Middle" effect is not present for simple factoid Q\&A in Gemini 2.5 Flash, indicating substantial improvements in long-context retrieval. --- ### EGG-SR: Embedding Symbolic Equivalence into Symbolic Regression via Equality Graph Authors: Nan Jiang, Ziyi Wang, Yexiang Xue Published: 2025-11-08 Categories: cs.SC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.05849v2 Symbolic regression seeks to uncover physical laws from experimental data by searching for closed-form expressions, which is an important task in AI-driven scientific discovery. Yet the exponential growth of the search space of expression renders the task computationally challenging. A promising yet underexplored direction for reducing the search space and accelerating training lies in *symbolic equivalence*: many expressions, although syntactically different, define the same function -- for example, $\log(x_1^2x_2^3)$, $\log(x_1^2)+\log(x_2^3)$, and $2\log(x_1)+3\log(x_2)$. Existing algorithms treat such variants as distinct outputs, leading to redundant exploration and slow learning. We introduce EGG-SR, a unified framework that integrates symbolic equivalence into a class of modern symbolic regression methods, including Monte Carlo Tree Search (MCTS), Deep Reinforcement Learning (DRL), and Large Language Models (LLMs). EGG-SR compactly represents equivalent expressions through the proposed EGG module (via equality graphs), accelerating learning by: (1) pruning redundant subtree exploration in EGG-MCTS, (2) aggregating rewards across equivalent generated sequences in EGG-DRL, and (3) enriching feedback prompts in EGG-LLM. Theoretically, we show the benefit of embedding EGG into learning: it tightens the regret bound of MCTS and reduces the variance of the DRL gradient estimator. Empirically, EGG-SR consistently enhances a class of symbolic regression models across several benchmarks, discovering more accurate expressions within the same time limit. Project page is at: https://nan-jiang-group.github.io/egg-sr. --- ### Enhancing Diffusion Model Guidance through Calibration and Regularization Authors: Seyed Alireza Javid, Amirhossein Bagheri, Nuria González-Prelcic Published: 2025-11-08 Categories: cs.CV, cs.AI, cs.IT, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2511.05844v3 Classifier-guided diffusion models have emerged as a powerful approach for conditional image generation, but they suffer from overconfident predictions during early denoising steps, causing the guidance gradient to vanish. This paper introduces two complementary contributions to address this issue. First, we propose a differentiable calibration objective based on the Smooth Expected Calibration Error (Smooth ECE), which improves classifier calibration with minimal fine-tuning and yields measurable improvements in Frechet Inception Distance (FID). Second, we develop enhanced sampling guidance methods that operate on off-the-shelf classifiers without requiring retraining. These include tilted sampling with batch-level reweighting, adaptive entropy-regularized sampling to preserve diversity, and a novel f-divergence-based sampling strategy that strengthens class-consistent guidance while maintaining mode coverage. Experiments on ImageNet 128x128 demonstrate that our divergence-regularized guidance achieves an FID of 2.13 using a ResNet-101 classifier, improving upon existing classifier-guided diffusion methods while requiring no diffusion model retraining. The results show that principled calibration and divergence-aware sampling provide practical and effective improvements for classifier-guided diffusion. --- ### Cross-Task Generalization in Handwriting-Based Alzheimer's Screening via Vision Language Adaptation Authors: Changqing Gong, Huafeng Qin, Mounim A. El-Yacoubi Published: 2025-11-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.05841v2 Alzheimer's disease (AD) is a prevalent neurodegenerative disorder for which early detection is critical. Handwriting, which can be disrupted by subtle motor and cognitive decline, provides a non-invasive and cost-effective window for AD screening. Existing handwriting-based AD studies mostly rely on online trajectories and hand-crafted features, while the influence of handwriting task type on diagnostic performance and cross-task generalization remains underexplored. Meanwhile, large-scale vision--language models have demonstrated strong transfer and adaptation ability in natural-image anomaly detection and several medical modalities, such as chest X-ray and brain MRI. However, handwriting-based disease detection remains unexplored within this paradigm. To address this gap, we introduce a lightweight Cross-Layer Fusion Adapter (CLFA) framework that repurposes Contrastive Language--Image Pre-training (CLIP) for handwriting-based AD screening. CLFA inserts multi-level adapters into a frozen visual encoder, combining cross-layer feature fusion with depthwise 2D convolution on patch grids to capture both local stroke irregularities and higher-level handwriting structure. This design progressively aligns pretrained vision--language representations with AD-related handwriting cues and supports transfer from supervised source tasks to task-disjoint unseen target tasks. On the Darwin dataset, under the subject-disjoint cross-task protocol, averaged over all 600 task-disjoint source-target pairs, CLFA achieves 74.63\% AUC, 74.85\% accuracy, and 73.72\% F1 score, outperforming the best competing model by 2.15, 1.79, and 1.87 percentage points, respectively. --- ### Training-Free Adaptive Quantization for Variable Rate Image Coding for Machines Authors: Yui Tatsumi, Ziyue Zeng, Hiroshi Watanabe Published: 2025-11-08 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2511.05836v3 Image Coding for Machines (ICM) has become increasingly important with the rapid integration of computer vision technology into real-world applications. However, most neural network-based ICM frameworks operate at a fixed rate, thus requiring individual training for each target bitrate. This limitation may restrict their practical usage. Existing variable rate image compression approaches mitigate this issue but often rely on additional training, which increases computational costs and complicates deployment. Moreover, variable rate control has not been thoroughly explored for ICM. To address these challenges, we propose a training-free framework for quantization strength control which enables flexible bitrate adjustment. By exploiting the scale parameter predicted by the hyperprior network, the proposed method adaptively modulates quantization step sizes across both channel and spatial dimensions. This allows the model to preserve semantically important regions while coarsely quantizing less critical areas. Our architectural design further enables continuous bitrate control through a single parameter. Experimental results demonstrate the effectiveness of our proposed method, achieving up to 11.07% BD-rate savings over the non-adaptive variable rate baseline. The code is available at https://github.com/qwert-top/AQVR-ICM. --- ### TYrPPG: Uncomplicated and Enhanced Learning Capability rPPG for Remote Heart Rate Estimation Authors: Taixi Chen, Yiu-ming Cheung Published: 2025-11-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05833v1 Remote photoplethysmography (rPPG) can remotely extract physiological signals from RGB video, which has many advantages in detecting heart rate, such as low cost and no invasion to patients. The existing rPPG model is usually based on the transformer module, which has low computation efficiency. Recently, the Mamba model has garnered increasing attention due to its efficient performance in natural language processing tasks, demonstrating potential as a substitute for transformer-based algorithms. However, the Mambaout model and its variants prove that the SSM module, which is the core component of the Mamba model, is unnecessary for the vision task. Therefore, we hope to prove the feasibility of using the Mambaout-based module to remotely learn the heart rate. Specifically, we propose a novel rPPG algorithm called uncomplicated and enhanced learning capability rPPG (TYrPPG). This paper introduces an innovative gated video understanding block (GVB) designed for efficient analysis of RGB videos. Based on the Mambaout structure, this block integrates 2D-CNN and 3D-CNN to enhance video understanding for analysis. In addition, we propose a comprehensive supervised loss function (CSL) to improve the model's learning capability, along with its weakly supervised variants. The experiments show that our TYrPPG can achieve state-of-the-art performance in commonly used datasets, indicating its prospects and superiority in remote heart rate estimation. The source code is available at https://github.com/Taixi-CHEN/TYrPPG. --- ### Hilbert-Guided Sparse Local Attention Authors: Yunge Li, Lanyu Xu Published: 2025-11-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.05832v2 The quadratic compute and memory costs of global self-attention severely limit its use in high-resolution images. Local attention reduces complexity by restricting attention to neighborhoods. Block-sparse kernels can further improve the efficiency of local attention, but conventional local attention patterns often fail to deliver significant speedups because tokens within a window are not contiguous in the 1D sequence. This work proposes a novel method for constructing windows and neighborhoods based on the Hilbert curve. Image tokens are first reordered along a Hilbert curve, and windows and neighborhoods are then formed on the reordered 1D sequence. From a block-sparse perspective, this strategy significantly increases block sparsity and can be combined with existing block-sparse kernels to improve the efficiency of 2D local attention. Experiments show that the proposed Hilbert Window Attention and Hilbert Slide Attention can accelerate window attention and slide attention by about $4\times$ and $18\times$, respectively. To assess practicality, the strategy is instantiated as the Hilbert Window Transformer and the Hilbert Neighborhood Transformer, both of which achieve end-to-end speedups with minimal accuracy loss. Overall, combining Hilbert-guided local attention with block-sparse kernels offers a general and practical approach to enhancing the efficiency of 2D local attention for images. --- ### CADM: Cluster-customized Adaptive Distance Metric for Categorical Data Clustering Authors: Taixi Chen, Yiu-ming Cheung, Yiqun Zhang Published: 2025-11-08 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.05826v2 An appropriate distance metric is crucial for categorical data clustering, as the distance between categorical data cannot be directly calculated. However, the distances between attribute values usually vary in different clusters induced by their different distributions, which has not been taken into account, thus leading to unreasonable distance measurement. Therefore, we propose a cluster-customized distance metric for categorical data clustering, which can competitively update distances based on different distributions of attributes in each cluster. In addition, we extend the proposed distance metric to the mixed data that contains both numerical and categorical attributes. Experiments demonstrate the efficacy of the proposed method, i.e., achieving an average ranking of around first in fourteen datasets. The source code is available at https://anonymous.4open.science/r/CADM-47D8 --- ### AiEDA: An Open-Source AI-Aided Design Library for Design-to-Vector Authors: Yihang Qiu, Zengrong Huang, Simin Tao, Hongda Zhang, Weiguo Li, Xinhua Lai, Rui Wang, Weiqiang Wang, Xingquan Li Published: 2025-11-08 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2511.05823v1 Recent research has demonstrated that artificial intelligence (AI) can assist electronic design automation (EDA) in improving both the quality and efficiency of chip design. But current AI for EDA (AI-EDA) infrastructures remain fragmented, lacking comprehensive solutions for the entire data pipeline from design execution to AI integration. Key challenges include fragmented flow engines that generate raw data, heterogeneous file formats for data exchange, non-standardized data extraction methods, and poorly organized data storage. This work introduces a unified open-source library for EDA (AiEDA) that addresses these issues. AiEDA integrates multiple design-to-vector data representation techniques that transform diverse chip design data into universal multi-level vector representations, establishing an AI-aided design (AAD) paradigm optimized for AI-EDA workflows. AiEDA provides complete physical design flows with programmatic data extraction and standardized Python interfaces bridging EDA datasets and AI frameworks. Leveraging the AiEDA library, we generate iDATA, a 600GB dataset of structured data derived from 50 real chip designs (28nm), and validate its effectiveness through seven representative AAD tasks spanning prediction, generation, optimization and analysis. The code is publicly available at https://github.com/OSCC-Project/AiEDA, while the full iDATA dataset is being prepared for public release, providing a foundation for future AI-EDA research. --- ### Policy Gradient-Based EMT-in-the-Loop Learning to Mitigate Sub-Synchronous Control Interactions Authors: Sayak Mukherjee, Ramij R. Hossain, Kaustav Chatterjee, Sameer Nekkalapu, Marcelo Elizondo Published: 2025-11-08 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2511.05822v1 This paper explores the development of learning-based tunable control gains using EMT-in-the-loop simulation framework (e.g., PSCAD interfaced with Python-based learning modules) to address critical sub-synchronous oscillations. Since sub-synchronous control interactions (SSCI) arise from the mis-tuning of control gains under specific grid configurations, effective mitigation strategies require adaptive re-tuning of these gains. Such adaptiveness can be achieved by employing a closed-loop, learning-based framework that considers the grid conditions responsible for such sub-synchronous oscillations. This paper addresses this need by adopting methodologies inspired by Markov decision process (MDP) based reinforcement learning (RL), with a particular emphasis on simpler deep policy gradient methods with additional SSCI-specific signal processing modules such as down-sampling, bandpass filtering, and oscillation energy dependent reward computations. Our experimentation in a real-world event setting demonstrates that the deep policy gradient based trained policy can adaptively compute gain settings in response to varying grid conditions and optimally suppress control interaction-induced oscillations. --- ### From Ranking to Reasoning: Explainable Web API Recommendation via Semantic Reasoning Authors: Zishuo Xu, Dezhong Yao, Yao Wan Published: 2025-11-08 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.05820v2 The rapid growth of Web APIs has made automated Web API recommendation essential for efficient mashup development. However, existing approaches suffer from two major limitations: 1) they rely on fixed top-N recommendation strategies that cannot adapt to mashup complexity, and 2) they provide little or no explanation for recommended APIs, limiting transparency and user trust. To address these challenges, we propose WAR-R1, an explainable Web API recommendation framework that integrates semantic reasoning with adaptive, variable-cardinality recommendation. Built on a lightweight large language model (LLM), WAR-R1 generates both a set of relevant APIs and a natural-language justification for each recommendation. To support adaptive recommendation size, we introduce special start and stop tokens that allow the model to learn when to begin and terminate API generation. WAR-R1 is trained in two stages: supervised fine-tuning on an annotated mashup-API corpus, followed by reinforcement learning using Group Relative Policy Optimization (GRPO) with low-rank adaptation to jointly optimize recommendation accuracy and reasoning quality. Experiments on the ProgrammableWeb dataset show that WAR-R1 outperforms state-of-the-art baselines by up to 10.89% in recommendation accuracy while consistently producing high-quality, semantically grounded explanations. Extensive ablation studies validate the effectiveness of reinforcement learning, special token design, and integrated reasoning. --- ### LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting Authors: Yuchen Su, Zhineng Chen, Yongkun Du, Zuxuan Wu, Hongtao Xie, Yu-Gang Jiang Published: 2025-11-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05818v2 End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped text remains challenging. We identify the primary bottleneck as the lack of a reliable and efficient text detection method. To address this, we propose a novel parameterized text shape representation based on low-rank approximation for precise detection and a triple assignment detection head for fast inference. Specifically, unlike current data-irrelevant shape representation methods, we exploit shape correlations among labeled text boundaries to construct a robust low-rank subspace. By minimizing an $\ell_1$-norm objective, we extract orthogonal vectors that capture the intrinsic text shape from noisy annotations, enabling precise reconstruction via the linear combination of only a few basis vectors. Next, the triple assignment scheme decouples training complexity from inference speed. It utilizes a deep sparse branch to guide an ultra-lightweight inference branch, while a dense branch provides rich parallel supervision. Building upon these advancements, we integrate the enhanced detection module with a lightweight recognition branch to form an end-to-end text spotting framework, termed LRANet++, capable of accurately and efficiently spotting arbitrary-shaped text. Extensive experiments on challenging benchmarks demonstrate the superiority of LRANet++ compared to state-of-the-art methods. Code is available at: https://github.com/ychensu/LRANet-PP. --- ### Parametric Pareto Set Learning for Expensive Multi-Objective Optimization Authors: Ji Cheng, Bo Xue, Qingfu Zhang Published: 2025-11-08 Categories: cs.NE arXiv: https://arxiv.org/abs/2511.05815v1 Parametric multi-objective optimization (PMO) addresses the challenge of solving an infinite family of multi-objective optimization problems, where optimal solutions must adapt to varying parameters. Traditional methods require re-execution for each parameter configuration, leading to prohibitive costs when objective evaluations are computationally expensive. To address this issue, we propose Parametric Pareto Set Learning with multi-objective Bayesian Optimization (PPSL-MOBO), a novel framework that learns a unified mapping from both preferences and parameters to Pareto-optimal solutions. PPSL-MOBO leverages a hypernetwork with Low-Rank Adaptation (LoRA) to efficiently capture parametric variations, while integrating Gaussian process surrogates and hypervolume-based acquisition to minimize expensive function evaluations. We demonstrate PPSL-MOBO's effectiveness on two challenging applications: multi-objective optimization with shared components, where certain design variables must be identical across solution families due to modular constraints, and dynamic multi-objective optimization, where objectives evolve over time. Unlike existing methods that cannot directly solve PMO problems in a unified manner, PPSL-MOBO learns a single model that generalizes across the entire parameter space. By enabling instant inference of Pareto sets for new parameter values without retraining, PPSL-MOBO provides an efficient solution for expensive PMO problems. --- ### In-depth Analysis on Caching and Pre-fetching in Mixture of Experts Offloading Authors: Shuning Lin, Yifan He, Yitong Chen Published: 2025-11-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.05814v1 In today's landscape, Mixture of Experts (MoE) is a crucial architecture that has been used by many of the most advanced models. One of the major challenges of MoE models is that they usually require much more memory than their dense counterparts due to their unique architecture, and hence are harder to deploy in environments with limited GPU memory, such as edge devices. MoE offloading is a promising technique proposed to overcome this challenge, especially if it is enhanced with caching and pre-fetching, but prior work stopped at suboptimal caching algorithm and offered limited insights. In this work, we study MoE offloading in depth and make the following contributions: 1. We analyze the expert activation and LRU caching behavior in detail and provide traces. 2. We propose LFU caching optimization based on our analysis and obtain strong improvements from LRU. 3. We implement and experiment speculative expert pre-fetching, providing detailed trace showing its huge potential . 4. In addition, our study extensively covers the behavior of the MoE architecture itself, offering information on the characteristic of the gating network and experts. This can inspire future work on the interpretation of MoE models and the development of pruning techniques for MoE architecture with minimal performance loss. --- ### MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling Authors: Yu Zhang, Hui-Ling Zhen, Mingxuan Yuan, Bei Yu Published: 2025-11-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.05811v2 Training large language models with FP8 formats offers significant efficiency gains. However, the reduced numerical precision of FP8 poses challenges for stable and accurate training. Current frameworks preserve training performance using mixed-granularity quantization, i.e., applying per-group quantization for activations and per-tensor/block quantization for weights. While effective, per-group quantization requires scaling along the inner dimension of matrix multiplication, introducing additional dequantization overhead. Moreover, these frameworks often rely on just-in-time scaling to dynamically adjust scaling factors based on the current data distribution. However, this online quantization is inefficient for FP8 training, as it involves multiple memory reads and writes that negate the performance benefits of FP8. To overcome these limitations, we propose MOSS, a novel FP8 training framework that ensures both efficiency and numerical stability. MOSS introduces two key innovations: (1) a two-level microscaling strategy for quantizing sensitive activations, which balances precision and dequantization cost by combining a high-precision global scale with compact, power-of-two local scales; and (2) automatic scaling for weights in linear layers, which eliminates the need for costly max-reduction operations by predicting and adjusting scaling factors during training. Leveraging these techniques, MOSS enables efficient FP8 training of a 7B parameter model, achieving performance comparable to the BF16 baseline while achieving up to 34% higher training throughput. ---