# Research Papers — 2025-11 · bundle page 58 of 197 > Full-text markdown of papers #2851–2900 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/58 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/57.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/59.md) ### Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems Authors: Dor Arviv, Yehonatan Elisha, Oren Barkan, Noam Koenigstein Published: 2025-11-22 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.18024v1 We present a method for extracting \emph{monosemantic} neurons, defined as latent dimensions that align with coherent and interpretable concepts, from user and item embeddings in recommender systems. Our approach employs a Sparse Autoencoder (SAE) to reveal semantic structure within pretrained representations. In contrast to work on language models, monosemanticity in recommendation must preserve the interactions between separate user and item embeddings. To achieve this, we introduce a \emph{prediction aware} training objective that backpropagates through a frozen recommender and aligns the learned latent structure with the model's user-item affinity predictions. The resulting neurons capture properties such as genre, popularity, and temporal trends, and support post hoc control operations including targeted filtering and content promotion without modifying the base model. Our method generalizes across different recommendation models and datasets, providing a practical tool for interpretable and controllable personalization. Code and evaluation resources are available at https://github.com/DeltaLabTLV/Monosemanticity4Rec. --- ### Modeling Retinal Ganglion Cells with Neural Differential Equations Authors: Kacper Dobek, Daniel Jankowski, Krzysztof Krawiec Published: 2025-11-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18014v1 This work explores Liquid Time-Constant Networks (LTCs) and Closed-form Continuous-time Networks (CfCs) for modeling retinal ganglion cell activity in tiger salamanders across three datasets. Compared to a convolutional baseline and an LSTM, both architectures achieved lower MAE, faster convergence, smaller model sizes, and favorable query times, though with slightly lower Pearson correlation. Their efficiency and adaptability make them well suited for scenarios with limited data and frequent retraining, such as edge deployments in vision prosthetics. --- ### Save, Revisit, Retain: A Scalable Framework for Enhancing User Retention in Large-Scale Recommender Systems Authors: Weijie Jiang, Armando Ordorica, Jaewon Yang, Olafur Gudmundsson, Yucheng Tu, Huizhong Duan Published: 2025-11-22 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.18013v1 User retention is a critical objective for online platforms like Pinterest, as it strengthens user loyalty and drives growth through repeated engagement. A key indicator of retention is revisitation, i.e., when users return to view previously saved content, a behavior often sparked by personalized recommendations and user satisfaction. However, modeling and optimizing revisitation poses significant challenges. One core difficulty is accurate attribution: it is often unclear which specific user actions or content exposures trigger a revisit, since many confounding factors (e.g., content quality, user interface, notifications, or even changing user intent) can influence return behavior. Additionally, the scale and timing of revisitations introduce further complexity; users may revisit content days or even weeks after their initial interaction, requiring the system to maintain and associate extensive historical records across millions of users and sessions. These complexities render existing methods insufficient for robustly capturing and optimizing long-term revisitation. To address these gaps, we introduce a novel, lightweight, and interpretable framework for modeling revisitation behavior and optimizing long-term user retention in Pinterest's search-based recommendation context. By defining a surrogate attribution process that links saves to subsequent revisitations, we reduce noise in the causal relationship between user actions and return visits. Our scalable event aggregation pipeline enables large-scale analysis of user revisitation patterns and enhances the ranking system's ability to surface items with high retention value. Deployed on Pinterest's Related Pins surface to serve 500+ million users, the framework led to a significant lift of 0.1% in active users without additional computational costs. --- ### State and Scene Enhanced Prototypes for Weakly Supervised Open-Vocabulary Object Detection Authors: Jiaying Zhou, Qingchao Chen Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18012v1 Open-Vocabulary Object Detection (OVOD) aims to generalize object recognition to novel categories, while Weakly Supervised OVOD (WS-OVOD) extends this by combining box-level annotations with image-level labels. Despite recent progress, two critical challenges persist in this setting. First, existing semantic prototypes, even when enriched by LLMs, are static and limited, failing to capture the rich intra-class visual variations induced by different object states (e.g., a cat's pose). Second, the standard pseudo-box generation introduces a semantic mismatch between visual region proposals (which contain context) and object-centric text embeddings. To tackle these issues, we introduce two complementary prototype enhancement strategies. To capture intra-class variations in appearance and state, we propose the State-Enhanced Semantic Prototypes (SESP), which generates state-aware textual descriptions (e.g., "a sleeping cat") to capture diverse object appearances, yielding more discriminative prototypes. Building on this, we further introduce Scene-Augmented Pseudo Prototypes (SAPP) to address the semantic mismatch. SAPP incorporates contextual semantics (e.g., "cat lying on sofa") and utilizes a soft alignment mechanism to promote contextually consistent visual-textual representations. By integrating SESP and SAPP, our method effectively enhances both the richness of semantic prototypes and the visual-textual alignment, achieving notable improvements. --- ### RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios Authors: Jun Zhang, Xin Zhang, Jie Feng, Long Chen, Junhui Wang, Zhicheng Liu, Depeng Jin, Yong Li Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18011v2 Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine-grained spatial understanding and reasoning capabilities in complex urban scenarios have not received significant attention in the fields of both research and industry. To fill this gap, we focus primarily on road markings as a typical example of fine-grained spatial elements under urban scenarios, given the essential role of the integrated road traffic network they form within cities. Around road markings and urban traffic systems, we propose \textbf{RoadBench}, a systematic benchmark that comprehensively evaluates MLLMs' fine-grained spatial understanding and reasoning capabilities using Bird's-Eye View (BEV) and First-Person View (FPV) image inputs. This benchmark comprises eight tasks consisting of 3,040 strictly manually verified test cases, constructed from 2,137 unique BEV images and 721 unique FPV images collected from five Chinese cities with relatively consistent traffic conventions. These tasks form a systematic evaluation framework that bridges understanding at local spatial scopes to global reasoning. They not only test MLLMs' capabilities in recognition, joint understanding, and reasoning but also assess their ability to integrate image information with domain knowledge. After evaluating 20 mainstream MLLMs, we confirm that RoadBench is a challenging benchmark for MLLMs while revealing significant shortcomings in existing MLLMs' fine-grained spatial understanding and reasoning capabilities within urban scenarios. In certain tasks, their performance even falls short of simple rule-based or random selection baselines. These findings, along with RoadBench itself, will contribute to the comprehensive advancement of spatial understanding capabilities for MLLMs. --- ### Is Complete Labeling Necessary? Understanding Active Learning in Longitudinal Medical Imaging Authors: Siteng Ma, Honghui Du, Prateek Mathur, Brendan S. Kelly, Ronan P. Killeen, Aonghus Lawlor, Ruihai Dong Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18007v1 Detecting changes in longitudinal medical imaging using deep learning requires a substantial amount of accurately labeled data. However, labeling these images is notably more costly and time-consuming than labeling other image types, as it requires labeling across various time points, where new lesions can be minor, and subtle changes are easily missed. Deep Active Learning (DAL) has shown promise in minimizing labeling costs by selectively querying the most informative samples, but existing studies have primarily focused on static tasks like classification and segmentation. Consequently, the conventional DAL approach cannot be directly applied to change detection tasks, which involve identifying subtle differences across multiple images. In this study, we propose a novel DAL framework, named Longitudinal Medical Imaging Active Learning (LMI-AL), tailored specifically for longitudinal medical imaging. By pairing and differencing all 2D slices from baseline and follow-up 3D images, LMI-AL iteratively selects the most informative pairs for labeling using DAL, training a deep learning model with minimal manual annotation. Experimental results demonstrate that, with less than 8% of the data labeled, LMI-AL can achieve performance comparable to models trained on fully labeled datasets. We also provide a detailed analysis of the method's performance, as guidance for future research. The code is publicly available at https://github.com/HelenMa9998/Longitudinal_AL. --- ### Understanding Private Learning From Feature Perspective Authors: Meng Ding, Mingxi Lei, Shaopeng Fu, Shaowei Wang, Di Wang, Jinhui Xu Published: 2025-11-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18006v1 Differentially private Stochastic Gradient Descent (DP-SGD) has become integral to privacy-preserving machine learning, ensuring robust privacy guarantees in sensitive domains. Despite notable empirical advances leveraging features from non-private, pre-trained models to enhance DP-SGD training, a theoretical understanding of feature dynamics in private learning remains underexplored. This paper presents the first theoretical framework to analyze private training through a feature learning perspective. Building on the multi-patch data structure from prior work, our analysis distinguishes between label-dependent feature signals and label-independent noise, a critical aspect overlooked by existing analyses in the DP community. Employing a two-layer CNN with polynomial ReLU activation, we theoretically characterize both feature signal learning and data noise memorization in private training via noisy gradient descent. Our findings reveal that (1) Effective private signal learning requires a higher signal-to-noise ratio (SNR) compared to non-private training, and (2) When data noise memorization occurs in non-private learning, it will also occur in private learning, leading to poor generalization despite small training loss. Our findings highlight the challenges of private learning and prove the benefit of feature enhancement to improve SNR. Experiments on synthetic and real-world datasets also validate our theoretical findings. --- ### UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale Authors: Shengyuan Wang, Zhiheng Zheng, Yu Shang, Lixuan He, Yangcheng Yu, Fan Hangyu, Jie Feng, Qingmin Liao, Yong Li Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18005v3 The automated generation of high-fidelity, city-scale 3D environments remains a formidable challenge with profound academic and industrial implications. However, existing methods struggle to achieve the necessary quality, fidelity, and scalability. To address this, we propose UrbanWorld2.0, a reality-aligned intelligent multimodal synthesis engine that creates detailed, city-scale 3D worlds of high fidelity. We introduce an agentic framework that leverages diverse multimodal foundation tools to acquire real-world knowledge, maintain robust intermediate representations, and construct complex 3D scenes. This agentic design, featuring dynamic data processing, iterative self-reflection and refinement, and the invocation of advanced multimodal tools, minimizes cumulative errors and enhances overall performance. Extensive quantitative experiments and qualitative analyzes validate the superior performance of UrbanWorld2.0 in real-world alignment, shape precision, texture fidelity, and aesthetics level, achieving a win rate of over 86\% against existing baselines for overall perceptual quality. This combination of 3D quality, reality alignment, scalability, and seamless compatibility with computer graphics pipelines makes UrbanWorld2.0 a promising foundation for applications in immersive media, embodied intelligence, and world models. --- ### Reward Engineering for Spatial Epidemic Simulations: A Reinforcement Learning Platform for Individual Behavioral Learning Authors: Radman Rakhshandehroo, Daniel Coombs Published: 2025-11-22 Categories: cs.LG, cs.AI, q-bio.PE arXiv: https://arxiv.org/abs/2511.18000v2 We present ContagionRL, a Gymnasium-compatible reinforcement learning platform specifically designed for systematic reward engineering in spatial epidemic simulations. Unlike traditional agent-based models that rely on fixed behavioral rules, our platform enables rigorous evaluation of how reward function design affects learned survival strategies across diverse epidemic scenarios. ContagionRL integrates a spatial SIRS+D epidemiological model with configurable environmental parameters, allowing researchers to stress-test reward functions under varying conditions including limited observability, different movement patterns, and heterogeneous population dynamics. We evaluate five distinct reward designs, ranging from sparse survival bonuses to a novel potential field approach, across multiple RL algorithms (PPO, SAC, A2C). Through systematic ablation studies, we identify that directional guidance and explicit adherence incentives are critical components for robust policy learning. Our comprehensive evaluation across varying infection rates, grid sizes, visibility constraints, and movement patterns reveals that reward function choice dramatically impacts agent behavior and survival outcomes. Agents trained with our potential field reward consistently achieve superior performance, learning maximal adherence to non-pharmaceutical interventions while developing sophisticated spatial avoidance strategies. The platform's modular design enables systematic exploration of reward-behavior relationships, addressing a knowledge gap in models of this type where reward engineering has received limited attention. ContagionRL is an effective platform for studying adaptive behavioral responses in epidemic contexts and highlight the importance of reward design, information structure, and environmental predictability in learning. Our code is publicly available at https://github.com/redradman/ContagionRL --- ### Learning Rate Scheduling with Matrix Factorization for Private Training Authors: Nikita P. Kalinin, Joel Daniel Andersson Published: 2025-11-22 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.17994v2 We study differentially private model training with stochastic gradient descent under learning rate scheduling and correlated noise. Although correlated noise, in particular via matrix factorizations, has been shown to improve accuracy, prior theoretical work focused primarily on the prefix-sum workload. That workload assumes a constant learning rate, whereas in practice learning rate schedules are widely used to accelerate training and improve convergence. We close this gap by deriving general upper and lower bounds for a broad class of learning rate schedules in both single- and multi-epoch settings. Building on these results, we propose a learning-rate-aware factorization that achieves improvements over prefix-sum factorizations under both MaxSE and MeanSE error metrics. Our theoretical analysis yields memory-efficient constructions suitable for practical deployment, and experiments on CIFAR-10 and IMDB datasets confirm that schedule-aware factorizations improve accuracy in private training. --- ### SD-PSFNet: Sequential and Dynamic Point Spread Function Network for Image Deraining Authors: Jiayu Wang, Haoyu Bian, Haoran Sun, Shaoning Zeng Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17993v1 Image deraining is crucial for vision applications but is challenged by the complex multi-scale physics of rain and its coupling with scenes. To address this challenge, a novel approach inspired by multi-stage image restoration is proposed, incorporating Point Spread Function (PSF) mechanisms to reveal the image degradation process while combining dynamic physical modeling with sequential feature fusion transfer, named SD-PSFNet. Specifically, SD-PSFNet employs a sequential restoration architecture with three cascaded stages, allowing multiple dynamic evaluations and refinements of the degradation process estimation. The network utilizes components with learned PSF mechanisms to dynamically simulate rain streak optics, enabling effective rain-background separation while progressively enhancing outputs through novel PSF components at each stage. Additionally, SD-PSFNet incorporates adaptive gated fusion for optimal cross-stage feature integration, enabling sequential refinement from coarse rain removal to fine detail restoration. Our model achieves state-of-the-art PSNR/SSIM metrics on Rain100H (33.12dB/0.9371), RealRain-1k-L (42.28dB/0.9872), and RealRain-1k-H (41.08dB/0.9838). In summary, SD-PSFNet demonstrates excellent capability in complex scenes and dense rainfall conditions, providing a new physics-aware approach to image deraining. --- ### How Far Can LLMs Emulate Human Behavior?: A Strategic Analysis via the Buy-and-Sell Negotiation Game Authors: Mingyu Jeon, Jaeyoung Suh, Suwan Cho, Dohyeon Kim Published: 2025-11-22 Categories: cs.AI, cs.GT arXiv: https://arxiv.org/abs/2511.17990v1 With the rapid advancement of Large Language Models (LLMs), recent studies have drawn attention to their potential for handling not only simple question-answer tasks but also more complex conversational abilities and performing human-like behavioral imitations. In particular, there is considerable interest in how accurately LLMs can reproduce real human emotions and behaviors, as well as whether such reproductions can function effectively in real-world scenarios. However, existing benchmarks focus primarily on knowledge-based assessment and thus fall short of sufficiently reflecting social interactions and strategic dialogue capabilities. To address these limitations, this work proposes a methodology to quantitatively evaluate the human emotional and behavioral imitation and strategic decision-making capabilities of LLMs by employing a Buy and Sell negotiation simulation. Specifically, we assign different personas to multiple LLMs and conduct negotiations between a Buyer and a Seller, comprehensively analyzing outcomes such as win rates, transaction prices, and SHAP values. Our experimental results show that models with higher existing benchmark scores tend to achieve better negotiation performance overall, although some models exhibit diminished performance in scenarios emphasizing emotional or social contexts. Moreover, competitive and cunning traits prove more advantageous for negotiation outcomes than altruistic and cooperative traits, suggesting that the assigned persona can lead to significant variations in negotiation strategies and results. Consequently, this study introduces a new evaluation approach for LLMs' social behavior imitation and dialogue strategies, and demonstrates how negotiation simulations can serve as a meaningful complementary metric to measure real-world interaction capabilities-an aspect often overlooked in existing benchmarks. --- ### Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks Authors: Jiayi Luo, Qingyun Sun, Yuecen Wei, Haonan Yuan, Xingcheng Fu, Jianxin Li Published: 2025-11-22 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2511.17989v1 Multi-domain graph pre-training has emerged as a pivotal technique in developing graph foundation models. While it greatly improves the generalization of graph neural networks, its privacy risks under membership inference attacks (MIAs), which aim to identify whether a specific instance was used in training (member), remain largely unexplored. However, effectively conducting MIAs against multi-domain graph pre-trained models is a significant challenge due to: (i) Enhanced Generalization Capability: Multi-domain pre-training reduces the overfitting characteristics commonly exploited by MIAs. (ii) Unrepresentative Shadow Datasets: Diverse training graphs hinder the obtaining of reliable shadow graphs. (iii) Weakened Membership Signals: Embedding-based outputs offer less informative cues than logits for MIAs. To tackle these challenges, we propose MGP-MIA, a novel framework for Membership Inference Attacks against Multi-domain Graph Pre-trained models. Specifically, we first propose a membership signal amplification mechanism that amplifies the overfitting characteristics of target models via machine unlearning. We then design an incremental shadow model construction mechanism that builds a reliable shadow model with limited shadow graphs via incremental learning. Finally, we introduce a similarity-based inference mechanism that identifies members based on their similarity to positive and negative samples. Extensive experiments demonstrate the effectiveness of our proposed MGP-MIA and reveal the privacy risks of multi-domain graph pre-training. --- ### HyM-UNet: Synergizing Local Texture and Global Context via Hybrid CNN-Mamba Architecture for Medical Image Segmentation Authors: Haodong Chen, Xianfei Han, Qwen Published: 2025-11-22 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2511.17988v1 Accurate organ and lesion segmentation is a critical prerequisite for computer-aided diagnosis. Convolutional Neural Networks (CNNs), constrained by their local receptive fields, often struggle to capture complex global anatomical structures. To tackle this challenge, this paper proposes a novel hybrid architecture, HyM-UNet, designed to synergize the local feature extraction capabilities of CNNs with the efficient global modeling capabilities of Mamba. Specifically, we design a Hierarchical Encoder that utilizes convolutional modules in the shallow stages to preserve high-frequency texture details, while introducing Visual Mamba modules in the deep stages to capture long-range semantic dependencies with linear complexity. To bridge the semantic gap between the encoder and the decoder, we propose a Mamba-Guided Fusion Skip Connection (MGF-Skip). This module leverages deep semantic features as gating signals to dynamically suppress background noise within shallow features, thereby enhancing the perception of ambiguous boundaries. We conduct extensive experiments on public benchmark dataset ISIC 2018. The results demonstrate that HyM-UNet significantly outperforms existing state-of-the-art methods in terms of Dice coefficient and IoU, while maintaining lower parameter counts and inference latency. This validates the effectiveness and robustness of the proposed method in handling medical segmentation tasks characterized by complex shapes and scale variations. --- ### Escaping Optimization Stagnation: Taking Steps Beyond Task Arithmetic via Difference Vectors Authors: Jinping Wang, Zhiqiang Gao, Dinggen Zhang, Zhiwu Xie Published: 2025-11-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17987v1 Current methods for editing pre-trained models face significant challenges, primarily high computational costs and limited scalability. Task arithmetic has recently emerged as a promising solution, using simple arithmetic operations-addition and negation-based on task vectors which are the differences between fine-tuned and pre-trained model weights, to efficiently modify model behavior. However, the full potential of task arithmetic remains underexplored, primarily due to limited mechanisms for overcoming optimization stagnation. To address this challenge, we introduce the notion of difference vector, a generalized form of task vectors derived from the historical movements during optimization. Using difference vectors as directed perturbations, we propose the Difference Vector-based Anisotropic Scaling Iterative algorithm (DV-BASI) to enable a continuous optimization process for task arithmetic methods without relying on any additional modules or components. Notably, by leveraging escapability and directional advantages of difference vectors, the average performance on different tasks of the multi-task model merged by DV-BASI may even outperform models individually fine-tuned. Based on this observation, we extend the application of difference vectors to a feasible fine-tuning method for single-task models. On the practical side, DV-BASI allows expressive searching directions with few learnable parameters and forms a scalable framework. We also integrate DV-BASI with task arithmetic methods and advanced optimization techniques to achieve state-of-the-art performance on both supervised and unsupervised evaluation protocols. --- ### Plan-X: Instruct Video Generation via Semantic Planning Authors: Lun Huang, You Xie, Hongyi Xu, Tianpei Gu, Chenxu Zhang, Guoxian Song, Zenan Li, Xiaochen Zhao, Linjie Luo, Guillermo Sapiro Published: 2025-11-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.17986v1 Diffusion Transformers have demonstrated remarkable capabilities in visual synthesis, yet they often struggle with high-level semantic reasoning and long-horizon planning. This limitation frequently leads to visual hallucinations and mis-alignments with user instructions, especially in scenarios involving complex scene understanding, human-object interactions, multi-stage actions, and in-context motion reasoning. To address these challenges, we propose Plan-X, a framework that explicitly enforces high-level semantic planning to instruct video generation process. At its core lies a Semantic Planner, a learnable multimodal language model that reasons over the user's intent from both text prompts and visual context, and autoregressively generates a sequence of text-grounded spatio-temporal semantic tokens. These semantic tokens, complementary to high-level text prompt guidance, serve as structured "semantic sketches" over time for the video diffusion model, which has its strength at synthesizing high-fidelity visual details. Plan-X effectively integrates the strength of language models in multimodal in-context reasoning and planning, together with the strength of diffusion models in photorealistic video synthesis. Extensive experiments demonstrate that our framework substantially reduces visual hallucinations and enables fine-grained, instruction-aligned video generation consistent with multimodal context. --- ### An Adaptive Resonance Theory-based Topological Clustering Algorithm with a Self-Adjusting Vigilance Parameter Authors: Naoki Masuyama, Yuichiro Toda, Yusuke Nojima, Hisao Ishibuchi Published: 2025-11-22 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.17983v5 Clustering in stationary and nonstationary settings, where data distributions remain static or evolve over time, requires models that can adapt to distributional shifts while preserving previously learned cluster structures. This paper proposes an Adaptive Resonance Theory (ART)-based topological clustering algorithm that autonomously adjusts its recalculation interval and vigilance threshold through a diversity-driven adaptation mechanism. This mechanism enables hyperparameter-free learning that maintains cluster stability and continuity in dynamic environments. Experiments on 24 real-world datasets demonstrate that the proposed algorithm outperforms state-of-the-art methods in both clustering performance and continual learning capability. These results highlight the effectiveness of the proposed parameter adaptation in mitigating catastrophic forgetting and maintaining consistent clustering in evolving data streams. Source code is available at https://github.com/Masuyama-lab/IDAT --- ### Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models Authors: Jiayi Luo, Qingyun Sun, Lingjuan Lyu, Ziwei Zhang, Haonan Yuan, Xingcheng Fu, Jianxin Li Published: 2025-11-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.17982v1 Graph Foundation Models (GFMs) are pre-trained on diverse source domains and adapted to unseen targets, enabling broad generalization for graph machine learning. Despite that GFMs have attracted considerable attention recently, their vulnerability to backdoor attacks remains largely underexplored. A compromised GFM can introduce backdoor behaviors into downstream applications, posing serious security risks. However, launching backdoor attacks against GFMs is non-trivial due to three key challenges. (1) Effectiveness: Attackers lack knowledge of the downstream task during pre-training, complicating the assurance that triggers reliably induce misclassifications into desired classes. (2) Stealthiness: The variability in node features across domains complicates trigger insertion that remains stealthy. (3) Persistence: Downstream fine-tuning may erase backdoor behaviors by updating model parameters. To address these challenges, we propose GFM-BA, a novel Backdoor Attack model against Graph Foundation Models. Specifically, we first design a label-free trigger association module that links the trigger to a set of prototype embeddings, eliminating the need for knowledge about downstream tasks to perform backdoor injection. Then, we introduce a node-adaptive trigger generator, dynamically producing node-specific triggers, reducing the risk of trigger detection while reliably activating the backdoor. Lastly, we develop a persistent backdoor anchoring module that firmly anchors the backdoor to fine-tuning-insensitive parameters, enhancing the persistence of the backdoor under downstream adaptation. Extensive experiments demonstrate the effectiveness, stealthiness, and persistence of GFM-BA. --- ### FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning Authors: Bo Yin, Xiaobin Hu, Xingyu Zhou, Yu He, Peng-Tao Jiang, Yue Liao, Junwei Zhu, Jiangning Zhang, Ying Tai, Shuicheng Yan Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17979v2 Diffusion models have achieved remarkable success in generative modeling, yet how to effectively adapt large pretrained models to new tasks remains challenging. We revisit the reconstruction behavior of diffusion models during denoising to unveil the underlying frequency energy mechanism governing this process. Building upon this observation, we propose FeRA, a frequency driven fine tuning framework that aligns parameter updates with the intrinsic frequency energy progression of diffusion. FeRA establishes a comprehensive frequency energy framework for effective diffusion adaptation fine tuning, comprising three synergistic components: (i) a compact frequency energy indicator that characterizes the latent bandwise energy distribution, (ii) a soft frequency router that adaptively fuses multiple frequency specific adapter experts, and (iii) a frequency energy consistency regularization that stabilizes diffusion optimization and ensures coherent adaptation across bands. Routing operates in both training and inference, with inference time routing dynamically determined by the latent frequency energy. It integrates seamlessly with adapter based tuning schemes and generalizes well across diffusion backbones and resolutions. By aligning adaptation with the frequency energy mechanism, FeRA provides a simple, stable, and compatible paradigm for effective and robust diffusion model adaptation. --- ### Federated Anomaly Detection and Mitigation for EV Charging Forecasting Under Cyberattacks Authors: Oluleke Babayomi, Dong-Seong Kim Published: 2025-11-22 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2511.17978v1 Electric Vehicle (EV) charging infrastructure faces escalating cybersecurity threats that can severely compromise operational efficiency and grid stability. Existing forecasting techniques are limited by the lack of combined robust anomaly mitigation solutions and data privacy preservation. Therefore, this paper addresses these challenges by proposing a novel anomaly-resilient federated learning framework that simultaneously preserves data privacy, detects cyber-attacks, and maintains trustworthy demand prediction accuracy under adversarial conditions. The proposed framework integrates three key innovations: LSTM autoencoder-based distributed anomaly detection deployed at each federated client, interpolation-based anomalous data mitigation to preserve temporal continuity, and federated Long Short-Term Memory (LSTM) networks that enable collaborative learning without centralized data aggregation. The framework is validated on real-world EV charging infrastructure datasets combined with real-world DDoS attack datasets, providing robust validation of the proposed approach under realistic threat scenarios. Experimental results demonstrate that the federated approach achieves superior performance compared to centralized models, with 15.2% improvement in R2 accuracy while maintaining data locality. The integrated cyber-attack detection and mitigation system produces trustworthy datasets that enhance prediction reliability, recovering 47.9% of attack-induced performance degradation while maintaining exceptional precision (91.3%) and minimal false positive rates (1.21%). The proposed architecture enables enhanced EV infrastructure planning, privacy-preserving collaborative forecasting, cybersecurity resilience, and rapid recovery from malicious threats across distributed charging networks. --- ### Synthesizing Precise Protocol Specs from Natural Language for Effective Test Generation Authors: Kuangxiangzi Liu, Dhiman Chakraborty, Alexander Liggesmeyer, Andreas Zeller Published: 2025-11-22 Categories: cs.SE, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2511.17977v1 Safety- and security-critical systems have to be thoroughly tested against their specifications. The state of practice is to have _natural language_ specifications, from which test cases are derived manually - a process that is slow, error-prone, and difficult to scale. _Formal_ specifications, on the other hand, are well-suited for automated test generation, but are tedious to write and maintain. In this work, we propose a two-stage pipeline that uses large language models (LLMs) to bridge the gap: First, we extract _protocol elements_ from natural-language specifications; second, leveraging a protocol implementation, we synthesize and refine a formal _protocol specification_ from these elements, which we can then use to massively test further implementations. We see this two-stage approach to be superior to end-to-end LLM-based test generation, as 1. it produces an _inspectable specification_ that preserves traceability to the original text; 2. the generation of actual test cases _no longer requires an LLM_; 3. the resulting formal specs are _human-readable_, and can be reviewed, version-controlled, and incrementally refined; and 4. over time, we can build a _corpus_ of natural-language-to-formal-specification mappings that can be used to further train and refine LLMs for more automatic translations. Our prototype, AUTOSPEC, successfully demonstrated the feasibility of our approach on five widely used _internet protocols_ (SMTP, POP3, IMAP, FTP, and ManageSieve) by applying its methods on their _RFC specifications_ written in natural-language, and the recent _I/O grammar_ formalism for protocol specification and fuzzing. In its evaluation, AUTOSPEC recovers on average 92.8% of client and 80.2% of server message types, and achieves 81.5% message acceptance across diverse, real-world systems. --- ### Divergence-Minimization for Latent-Structure Models: Monotone Operators, Contraction Guarantees, and Robust Inference Authors: Lei Li, Anand N. Vidyashankar Published: 2025-11-22 Categories: math.ST, cs.IT, math.OC, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2511.17974v1 We develop a divergence-minimization (DM) framework for robust and efficient inference in latent-mixture models. By optimizing a residual-adjusted divergence, the DM approach recovers EM as a special case and yields robust alternatives through different divergence choices. We establish that the sample objective decreases monotonically along the iterates, leading the DM sequence to stationary points under standard conditions, and that at the population level the operator exhibits local contractivity near the minimizer. Additionally, we verify consistency and $\sqrt{n}$-asymptotic normality of minimum-divergence estimators and of finitely many DM iterations, showing that under correct specification their limiting covariance matches the Fisher information. Robustness is analyzed via the residual-adjustment function, yielding bounded influence functions and a strictly positive breakdown bound for bounded-RAF divergences, and we contrast this with the non-robust behaviour of KL/EM. Next, we address the challenge of determining the number of mixture components by proposing a penalized divergence criterion combined with repeated sample splitting, which delivers consistent order selection and valid post-selection inference. Empirically, DM instantiations based on Hellinger and negative exponential divergences deliver accurate inference and remain stable under contamination in mixture and image-segmentation tasks. The results clarify connections to MM and proximal-point methods and offer practical defaults, making DM a drop-in alternative to EM for robust latent-structure inference. --- ### Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning Authors: Hiroto Honda Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17973v1 Exemplar-free class-incremental learning (EFCIL) aims to retain old knowledge acquired in the previous task while learning new classes, without storing the previous images due to storage constraints or privacy concerns. In EFCIL, the plasticity-stability dilemma, learning new tasks versus catastrophic forgetting, is a significant challenge, primarily due to the unavailability of images from earlier tasks. In this paper, we introduce adversarial pseudo-replay (APR), a method that perturbs the images of the new task with adversarial attack, to synthesize the pseudo-replay images online without storing any replay samples. During the new task training, the adversarial attack is conducted on the new task images with augmented old class mean prototypes as targets, and the resulting images are used for knowledge distillation to prevent semantic drift. Moreover, we calibrate the covariance matrices to compensate for the semantic drift after each task, by learning a transfer matrix on the pseudo-replay samples. Our method reconciles stability and plasticity, achieving state-of-the-art on challenging cold-start settings of the standard EFCIL benchmarks. --- ### Comprehensive Design Space Exploration for Tensorized Neural Network Hardware Accelerators Authors: Jinsong Zhang, Minghe Li, Jiayi Tian, Jinming Lu, Zheng Zhang Published: 2025-11-22 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2511.17971v2 High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment. However, existing studies focus primarily on its algorithmic advantages such as accuracy and compression ratio-while overlooking the hardware deployment efficiency. Such hardware-unaware designs often obscure the potential latency and energy benefits of tensorized models. Although several works attempt to reduce computational cost by optimizing the contraction sequence based on the number of multiply-accumulate operations, they typically neglect the underlying hardware characteristics, resulting in suboptimal real-world performance. We observe that the contraction path, hardware architecture, and dataflow mapping are tightly coupled and must be optimized jointly within a unified design space to maximize deployment efficiency on real devices. To this end, we propose a co-exploration framework that unifies these dimensions within a unified design space for efficient training and inference of tensorized neural networks on edge platforms. The framework formulates a latency oriented search objective and solves it via a global latency-driven exploration across the unified design space to achieve end-to-end model efficiency. The optimized configurations are implemented on a configurable FPGA kernel, achieving up to 4x and 3.85x lower inference and training latency compared with the dense baseline. --- ### Controllability Analysis of State Space-based Language Model Authors: Mohamed Mabrok, Yalda Zafari Published: 2025-11-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.17970v1 State-space models (SSMs), particularly Mamba, have become powerful architectures for sequence modeling, yet their internal dynamics remain poorly understood compared to attention-based models. We introduce and validate the Influence Score, a controllability-based metric derived from the discretized state-space parameters of Mamba and computed through a backward recurrence analogous to system observability. The score quantifies how strongly a token at position k affects all later states and outputs. We evaluate this measure across three Mamba variants: mamba-130m, mamba-2.8b, and mamba-2.8b-slimpj, using six experiments that test its sensitivity to temperature, prompt complexity, token type, layer depth, token position, and input perturbations. The results show three main insights: (1) the Influence Score increases with model size and training data, reflecting model capacity; (2) Mamba exhibits consistent architectural patterns, including recency bias and concentrated influence in mid-to-late layers; and (3) emergent behaviors appear only at scale, with mamba-2.8b-slimpj uniquely prioritizing content words and reducing internal influence in the presence of noise. These findings establish the Influence Score as a practical diagnostic tool for interpreting and comparing SSM-based language models. --- ### Uncertainty-Aware Federated Learning for Cyber-Resilient Microgrid Energy Management Authors: Oluleke Babayomi, Dong-Seong Kim Published: 2025-11-22 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2511.17968v1 Maintaining economic efficiency and operational reliability in microgrid energy management systems under cyberattack conditions remains challenging. Most approaches assume non-anomalous measurements, make predictions with unquantified uncertainties, and do not mitigate malicious attacks on renewable forecasts for energy management optimization. This paper presents a comprehensive cyber-resilient framework integrating federated Long Short-Term Memory-based photovoltaic forecasting with a novel two-stage cascade false data injection attack detection and energy management system optimization. The approach combines autoencoder reconstruction error with prediction uncertainty quantification to enable attack-resilient energy storage scheduling while preserving data privacy. Extreme false data attack conditions were studied that caused 58% forecast degradation and 16.9\% operational cost increases. The proposed integrated framework reduced false positive detections by 70%, recovered 93.7% of forecasting performance losses, and achieved 5\% operational cost savings, mitigating 34.7% of attack-induced economic losses. Results demonstrate that precision-focused cascade detection with multi-signal fusion outperforms single-signal approaches, validating security-performance synergy for decentralized microgrids. --- ### CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking Authors: Hao Li, Yuhao Wang, Xiantao Hu, Wenning Hao, Pingping Zhang, Dong Wang, Huchuan Lu Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17967v1 RGB-Thermal (RGBT) tracking aims to exploit visible and thermal infrared modalities for robust all-weather object tracking. However, existing RGBT trackers struggle to resolve modality discrepancies, which poses great challenges for robust feature representation. This limitation hinders effective cross-modal information propagation and fusion, which significantly reduces the tracking accuracy. To address this limitation, we propose a novel Contextual Aggregation with Deformable Alignment framework called CADTrack for RGBT Tracking. To be specific, we first deploy the Mamba-based Feature Interaction (MFI) that establishes efficient feature interaction via state space models. This interaction module can operate with linear complexity, reducing computational cost and improving feature discrimination. Then, we propose the Contextual Aggregation Module (CAM) that dynamically activates backbone layers through sparse gating based on the Mixture-of-Experts (MoE). This module can encode complementary contextual information from cross-layer features. Finally, we propose the Deformable Alignment Module (DAM) to integrate deformable sampling and temporal propagation, mitigating spatial misalignment and localization drift. With the above components, our CADTrack achieves robust and accurate tracking in complex scenarios. Extensive experiments on five RGBT tracking benchmarks verify the effectiveness of our proposed method. The source code is released at https://github.com/IdolLab/CADTrack. --- ### Signal: Selective Interaction and Global-local Alignment for Multi-Modal Object Re-Identification Authors: Yangyang Liu, Yuhao Wang, Pingping Zhang Published: 2025-11-22 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2511.17965v1 Multi-modal object Re-IDentification (ReID) is devoted to retrieving specific objects through the exploitation of complementary multi-modal image information. Existing methods mainly concentrate on the fusion of multi-modal features, yet neglecting the background interference. Besides, current multi-modal fusion methods often focus on aligning modality pairs but suffer from multi-modal consistency alignment. To address these issues, we propose a novel selective interaction and global-local alignment framework called Signal for multi-modal object ReID. Specifically, we first propose a Selective Interaction Module (SIM) to select important patch tokens with intra-modal and inter-modal information. These important patch tokens engage in the interaction with class tokens, thereby yielding more discriminative features. Then, we propose a Global Alignment Module (GAM) to simultaneously align multi-modal features by minimizing the volume of 3D polyhedra in the gramian space. Meanwhile, we propose a Local Alignment Module (LAM) to align local features in a shift-aware manner. With these modules, our proposed framework could extract more discriminative features for object ReID. Extensive experiments on three multi-modal object ReID benchmarks (i.e., RGBNT201, RGBNT100, MSVR310) validate the effectiveness of our method. The source code is available at https://github.com/010129/Signal. --- ### X-ReID: Multi-granularity Information Interaction for Video-Based Visible-Infrared Person Re-Identification Authors: Chenyang Yu, Xuehu Liu, Pingping Zhang, Huchuan Lu Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17964v2 Large-scale vision-language models (e.g., CLIP) have recently achieved remarkable performance in retrieval tasks, yet their potential for Video-based Visible-Infrared Person Re-Identification (VVI-ReID) remains largely unexplored. The primary challenges are narrowing the modality gap and leveraging spatiotemporal information in video sequences. To address the above issues, in this paper, we propose a novel cross-modality feature learning framework named X-ReID for VVI-ReID. Specifically, we first propose a Cross-modality Prototype Collaboration (CPC) to align and integrate features from different modalities, guiding the network to reduce the modality discrepancy. Then, a Multi-granularity Information Interaction (MII) is designed, incorporating short-term interactions from adjacent frames, long-term cross-frame information fusion, and cross-modality feature alignment to enhance temporal modeling and further reduce modality gaps. Finally, by integrating multi-granularity information, a robust sequence-level representation is achieved. Extensive experiments on two large-scale VVI-ReID benchmarks (i.e., HITSZ-VCM and BUPTCampus) demonstrate the superiority of our method over state-of-the-art methods. The source code is released at https://github.com/AsuradaYuci/X-ReID. --- ### Hybrid LSTM and PPO Networks for Dynamic Portfolio Optimization Authors: Jun Kevin, Pujianto Yugopuspito Published: 2025-11-22 Categories: cs.LG, cs.AI, cs.CE, q-fin.PM arXiv: https://arxiv.org/abs/2511.17963v1 This paper introduces a hybrid framework for portfolio optimization that fuses Long Short-Term Memory (LSTM) forecasting with a Proximal Policy Optimization (PPO) reinforcement learning strategy. The proposed system leverages the predictive power of deep recurrent networks to capture temporal dependencies, while the PPO agent adaptively refines portfolio allocations in continuous action spaces, allowing the system to anticipate trends while adjusting dynamically to market shifts. Using multi-asset datasets covering U.S. and Indonesian equities, U.S. Treasuries, and major cryptocurrencies from January 2018 to December 2024, the model is evaluated against several baselines, including equal-weight, index-style, and single-model variants (LSTM-only and PPO-only). The framework's performance is benchmarked against equal-weighted, index-based, and single-model approaches (LSTM-only and PPO-only) using annualized return, volatility, Sharpe ratio, and maximum drawdown metrics, each adjusted for transaction costs. The results indicate that the hybrid architecture delivers higher returns and stronger resilience under non-stationary market regimes, suggesting its promise as a robust, AI-driven framework for dynamic portfolio optimization. --- ### VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment Authors: Ziheng Jia, Linhan Cao, Jinliang Han, Zicheng Zhang, Jiaying Qian, Jiarui Wang, Zijian Chen, Guangtao Zhai, Xiongkuo Min Published: 2025-11-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.17962v1 Developing a robust visual quality assessment (VQualA) large multi-modal model (LMM) requires achieving versatility, powerfulness, and transferability. However, existing VQualA LMMs typically focus on a single task and rely on full-parameter fine-tuning, which makes them prone to overfitting on specific modalities or task types, thereby limiting their generalization capacity and transferability. To address this, we propose a vision-encoder-centered generative pre-training pipeline and develop the VITAL-Series LMMs. (1) We adopt a machine-executed annotation-scrutiny paradigm, constructing over 4.5M vision-language (VL) pairs-the largest VQualA training dataset to date. (2) We employ a multi-task training workflow that simultaneously enhances the model's quantitative scoring precision and strengthens its capability for quality interpretation across both image and video modalities. (3) Building upon the vision encoder, we realize an efficient model zoo extension: the model zoo exhibits strong zero-shot performance, and each paired decoder requires only a swift warm-up using less than 1/1000 of the pre-training data to achieve performance comparable to the fully trained counterpart. Overall, our work lays a cornerstone for advancing toward the foundation LMM for VQualA. --- ### Towards Automating Data Access Permissions in AI Agents Authors: Yuhao Wu, Ke Yang, Franziska Roesner, Tadayoshi Kohno, Ning Zhang, Umar Iqbal Published: 2025-11-22 Categories: cs.CR, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2511.17959v1 As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conventional permission models are inadequate for the automated agentic execution paradigm. We therefore propose automated permission management for AI agents. Our key idea is to conduct a user study to identify the factors influencing users' permission decisions and to encode these factors into an ML-based permission management assistant capable of predicting users' future decisions. We find that participants' permission decisions are influenced by communication context but importantly individual preferences tend to remain consistent within contexts, and align with those of other participants. Leveraging these insights, we develop a permission prediction model achieving 85.1% accuracy overall and 94.4% for high-confidence predictions. We find that even without using permission history, our model achieves an accuracy of 66.9%, and a slight increase of training samples (i.e., 1-4) can substantially increase the accuracy by 10.8%. --- ### HEAL: Learning-Free Source Free Unsupervised Domain Adaptation for Cross-Modality Medical Image Segmentation Authors: Yulong Shi, Jiapeng Li, Lin Qi Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17958v1 Growing demands for clinical data privacy and storage constraints have spurred advances in Source Free Unsupervised Domain Adaptation (SFUDA). SFUDA addresses the domain shift by adapting models from the source domain to the unseen target domain without accessing source data, even when target-domain labels are unavailable. However, SFUDA faces significant challenges: the absence of source domain data and label supervision in the target domain due to source free and unsupervised settings. To address these issues, we propose HEAL, a novel SFUDA framework that integrates Hierarchical denoising, Edge-guided selection, size-Aware fusion, and Learning-free characteristic. Large-scale cross-modality experiments demonstrate that our method outperforms existing SFUDA approaches, achieving state-of-the-art (SOTA) performance. The source code is publicly available at: https://github.com/derekshiii/HEAL. --- ### MTikGuard System: A Transformer-Based Multimodal System for Child-Safe Content Moderation on TikTok Authors: Dat Thanh Nguyen, Nguyen Hung Lam, Anh Hoang-Thi Nguyen, Trong-Hop Do Published: 2025-11-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.17955v1 With the rapid rise of short-form videos, TikTok has become one of the most influential platforms among children and teenagers, but also a source of harmful content that can affect their perception and behavior. Such content, often subtle or deceptive, challenges traditional moderation methods due to the massive volume and real-time nature of uploads. This paper presents MTikGuard, a real-time multimodal harmful content detection system for TikTok, with three key contributions: (1) an extended TikHarm dataset expanded to 4,723 labeled videos by adding diverse real-world samples, (2) a multimodal classification framework integrating visual, audio, and textual features to achieve state-of-the-art performance with 89.37% accuracy and 89.45% F1-score, and (3) a scalable streaming architecture built on Apache Kafka and Apache Spark for real-time deployment. The results demonstrate the effectiveness of combining dataset expansion, advanced multimodal fusion, and robust deployment for practical large-scale social media content moderation. The dataset is available at https://github.com/ntdat-8324/MTikGuard-System.git. --- ### A multi-view contrastive learning framework for spatial embeddings in risk modelling Authors: Freek Holvoet, Christopher Blier-Wong, Katrien Antonio Published: 2025-11-22 Categories: q-fin.RM, cs.LG arXiv: https://arxiv.org/abs/2511.17954v3 Incorporating spatial information, particularly when related to climate, weather, and demographic factors, is crucial for improving underwriting precision and enhancing risk management in insurance. However, spatial data are often unstructured, high-dimensional, and difficult to integrate into predictive models. Embedding methods are needed to convert spatial data into meaningful representations for modelling tasks. We propose a novel multi-view contrastive learning framework for generating spatial embeddings that combine information from multiple spatial data sources. To train the model, we construct a spatial dataset that merges satellite imagery and OpenStreetMap features across Europe. The framework aligns these spatial views with coordinate-based encodings, producing low-dimensional embeddings that capture both spatial structure and contextual similarity. Once trained, the model generates embeddings directly from latitude-longitude pairs, enabling any dataset with coordinates to be enriched with meaningful spatial features without requiring access to the original spatial inputs. In a case study on French real estate prices, we compare models trained on raw coordinates against those using our spatial embeddings as inputs. The embeddings consistently improve predictive accuracy across generalised linear, additive, and boosting models, while providing post-hoc explainable spatial effects and demonstrating generalisation of the fitted spatial effects to regions without training observations. A second case study on flood claim counts across Belgian postal codes confirms that the embeddings improve territorial risk classification in an insurance context. --- ### On Transportability for Structural Causal Bandits Authors: Min Woo Park, Sanghack Lee Published: 2025-11-22 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.17953v1 Intelligent agents equipped with causal knowledge can optimize their action spaces to avoid unnecessary exploration. The structural causal bandit framework provides a graphical characterization for identifying actions that are unable to maximize rewards by leveraging prior knowledge of the underlying causal structure. While such knowledge enables an agent to estimate the expected rewards of certain actions based on others in online interactions, there has been little guidance on how to transfer information inferred from arbitrary combinations of datasets collected under different conditions -- observational or experimental -- and from heterogeneous environments. In this paper, we investigate the structural causal bandit with transportability, where priors from the source environments are fused to enhance learning in the deployment setting. We demonstrate that it is possible to exploit invariances across environments to consistently improve learning. The resulting bandit algorithm achieves a sub-linear regret bound with an explicit dependence on informativeness of prior data, and it may outperform standard bandit approaches that rely solely on online learning. --- ### Multi-speaker Attention Alignment for Multimodal Social Interaction Authors: Liangyang Ouyang, Yifei Huang, Mingfang Zhang, Caixin Kang, Ryosuke Furuta, Yoichi Sato Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17952v1 Understanding social interaction in video requires reasoning over a dynamic interplay of verbal and non-verbal cues: who is speaking, to whom, and with what gaze or gestures. While Multimodal Large Language Models (MLLMs) are natural candidates, simply adding visual inputs yields surprisingly inconsistent gains on social tasks. Our quantitative analysis of cross-modal attention inside state-of-the-art MLLMs reveals a core failure mode: in multi-speaker scenes, visual and textual tokens lack speaker-consistent alignment, exhibiting substantially weaker cross-modal attention than in object-centric images. To address this, we propose a multimodal multi-speaker attention alignment method that can be integrated into existing MLLMs. First, we introduce dynamic cross-modal head selection to identify attention heads most responsible for grounding. Then, an adaptive social-aware attention bias, computed from existing attention patterns and speaker locations, is injected into the attention mechanism. This bias reinforces alignment between a speaker's visual representation and their utterances without introducing trainable parameters or architectural changes. We integrate our method into three distinct MLLMs (LLaVA-NeXT-Video, Qwen2.5-VL, and InternVL3) and evaluate on three benchmarks (TVQA+, MMSI, OnlineMMSI). Across four social tasks, results demonstrate that our approach improves the ability of MLLMs and achieves state-of-the-art results. Attention visualizations confirm our method successfully focuses the model on speaker-relevant regions, enabling more robust multi-party social reasoning. Our implementation and model will be available at https://github.com/ut-vision/SocialInteraction. --- ### Leveraging Evidence-Guided LLMs to Enhance Trustworthy Depression Diagnosis Authors: Yining Yuan, J. Ben Tamo, Micky C. Nnamdi, Yifei Wang, May D. Wang Published: 2025-11-22 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2511.17947v1 Large language models (LLMs) show promise in automating clinical diagnosis, yet their non-transparent decision-making and limited alignment with diagnostic standards hinder trust and clinical adoption. We address this challenge by proposing a two-stage diagnostic framework that enhances transparency, trustworthiness, and reliability. First, we introduce Evidence-Guided Diagnostic Reasoning (EGDR), which guides LLMs to generate structured diagnostic hypotheses by interleaving evidence extraction with logical reasoning grounded in DSM-5 criteria. Second, we propose a Diagnosis Confidence Scoring (DCS) module that evaluates the factual accuracy and logical consistency of generated diagnoses through two interpretable metrics: the Knowledge Attribution Score (KAS) and the Logic Consistency Score (LCS). Evaluated on the D4 dataset with pseudo-labels, EGDR outperforms direct in-context prompting and Chain-of-Thought (CoT) across five LLMs. For instance, on OpenBioLLM, EGDR improves accuracy from 0.31 (Direct) to 0.76 and increases DCS from 0.50 to 0.67. On MedLlama, DCS rises from 0.58 (CoT) to 0.77. Overall, EGDR yields up to +45% accuracy and +36% DCS gains over baseline methods, offering a clinically grounded, interpretable foundation for trustworthy AI-assisted diagnosis. --- ### Measuring the Impact of Lexical Training Data Coverage on Hallucination Detection in Large Language Models Authors: Shuo Zhang, Fabrizio Gotti, Fengran Mo, Jian-Yun Nie Published: 2025-11-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.17946v1 Hallucination in large language models (LLMs) is a fundamental challenge, particularly in open-domain question answering. Prior work attempts to detect hallucination with model-internal signals such as token-level entropy or generation consistency, while the connection between pretraining data exposure and hallucination is underexplored. Existing studies show that LLMs underperform on long-tail knowledge, i.e., the accuracy of the generated answer drops for the ground-truth entities that are rare in pretraining. However, examining whether data coverage itself can serve as a detection signal is overlooked. We propose a complementary question: Does lexical training-data coverage of the question and/or generated answer provide additional signal for hallucination detection? To investigate this, we construct scalable suffix arrays over RedPajama's 1.3-trillion-token pretraining corpus to retrieve $n$-gram statistics for both prompts and model generations. We evaluate their effectiveness for hallucination detection across three QA benchmarks. Our observations show that while occurrence-based features are weak predictors when used alone, they yield modest gains when combined with log-probabilities, particularly on datasets with higher intrinsic model uncertainty. These findings suggest that lexical coverage features provide a complementary signal for hallucination detection. All code and suffix-array infrastructure are provided at https://github.com/WWWonderer/ostd. --- ### Test-Time Temporal Sampling for Efficient MLLM Video Understanding Authors: Kaibin Wang, Mingbao Lin Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17945v1 Processing long videos with multimodal large language models (MLLMs) poses a significant computational challenge, as the model's self-attention mechanism scales quadratically with the number of video tokens, resulting in high computational demand and slow inference speed. Current solutions, such as rule-based sub-sampling, learned frame selector, or memory-based summarization, often introduce their own trade-offs: they compromise accuracy, necessitate additional training, or decrease inference speed. In this paper, we propose Test-Time Temporal Sampling (T3S), a training-free, plug-and-play inference wrapper that enables MLLMs to process long videos both efficiently and effectively. T3S exploits spatiotemporal redundancy by generating multiple short and diverse subsequences of video tokens at inference time, packing them within a single forward pass, and aggregating their predictions. This multi-subsequence formulation broadens visual coverage while reducing the computational cost of self-attention from $O(L^2)$ to $O(\sum_{i=1}^m α_i^2L^2)$, where $\sum_{i=1}^m α_i^2 < 1$. Extensive experiments on long video understanding benchmarks demonstrate that T3S improves accuracy by up to 3.1% and reduces first token delay by $2.04\times$, all with minimal integration effort. Our approach operates entirely at inference time, requires no model modifications or fine-tuning, and is compatible with a wide range of pretrained MLLMs. T3S turns video redundancy into a computational advantage, offering a scalable solution for long-video understanding. The code is available at https://github.com/kaibinwang3/T3S. --- ### SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System Authors: Zhiyu Xu, Weilong Yan, Yufei Shi, Xin Meng, Tao He, Huiping Zhuang, Ming Li, Hehe Fan Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17943v1 Recent advancements in multimodal large language models (MLLMs) and video agent systems have significantly improved general video understanding. However, when applied to scientific video understanding and educating, a domain that demands external professional knowledge integration and rigorous step-wise reasoning, existing approaches often struggle. To bridge this gap, we propose SciEducator, the first iterative self-evolving multi-agent system for scientific video comprehension and education. Rooted in the classical Deming Cycle from management science, our design reformulates its Plan-Do-Study-Act philosophy into a self-evolving reasoning and feedback mechanism, which facilitates the interpretation of intricate scientific activities in videos. Moreover, SciEducator can produce multimodal educational content tailored to specific scientific processes, including textual instructions, visual guides, audio narrations, and interactive references. To support evaluation, we construct SciVBench, a benchmark consisting of 500 expert-verified and literature-grounded science QA pairs across five categories, covering physical, chemical, and everyday phenomena. Extensive experiments demonstrate that SciEducator substantially outperforms leading closed-source MLLMs (e.g., Gemini, GPT-4o) and state-of-the-art video agents on the benchmark, establishing a new paradigm for the community. --- ### V2X-RECT: An Efficient V2X Trajectory Prediction Framework via Redundant Interaction Filtering and Tracking Error Correction Authors: Xiangyan Kong, Xuecheng Wu, Xiongwei Zhao, Xiaodong Li, Yunyun Shi, Gang Wang, Dingkang Yang, Yang Liu, Hong Chen, Yulong Gao Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17941v1 V2X prediction can alleviate perception incompleteness caused by limited line of sight through fusing trajectory data from infrastructure and vehicles, which is crucial to traffic safety and efficiency. However, in dense traffic scenarios, frequent identity switching of targets hinders cross-view association and fusion. Meanwhile, multi-source information tends to generate redundant interactions during the encoding stage, and traditional vehicle-centric encoding leads to large amounts of repetitive historical trajectory feature encoding, degrading real-time inference performance. To address these challenges, we propose V2X-RECT, a trajectory prediction framework designed for high-density environments. It enhances data association consistency, reduces redundant interactions, and reuses historical information to enable more efficient and accurate prediction. Specifically, we design a multi-source identity matching and correction module that leverages multi-view spatiotemporal relationships to achieve stable and consistent target association, mitigating the adverse effects of mismatches on trajectory encoding and cross-view feature fusion. Then we introduce traffic signal-guided interaction module, encoding trend of traffic light changes as features and exploiting their role in constraining spatiotemporal passage rights to accurately filter key interacting vehicles, while capturing the dynamic impact of signal changes on interaction patterns. Furthermore, a local spatiotemporal coordinate encoding enables reusable features of historical trajectories and map, supporting parallel decoding and significantly improving inference efficiency. Extensive experimental results across V2X-Seq and V2X-Traj datasets demonstrate that our V2X-RECT achieves significant improvements compared to SOTA methods, while also enhancing robustness and inference efficiency across diverse traffic densities. --- ### Neural Graph Navigation for Intelligent Subgraph Matching Authors: Yuchen Ying, Yiyang Dai, Wenda Li, Wenjie Huang, Rui Wang, Tongya Zheng, Yu Wang, Hanyang Yuan, Mingli Song Published: 2025-11-22 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.17939v1 Subgraph matching, a cornerstone of relational pattern detection in domains ranging from biochemical systems to social network analysis, faces significant computational challenges due to the dramatically growing search space. Existing methods address this problem within a filtering-ordering-enumeration framework, in which the enumeration stage recursively matches the query graph against the candidate subgraphs of the data graph. However, the lack of awareness of subgraph structural patterns leads to a costly brute-force enumeration, thereby critically motivating the need for intelligent navigation in subgraph matching. To address this challenge, we propose Neural Graph Navigation (NeuGN), a neuro-heuristic framework that transforms brute-force enumeration into neural-guided search by integrating neural navigation mechanisms into the core enumeration process. By preserving heuristic-based completeness guarantees while incorporating neural intelligence, NeuGN significantly reduces the \textit{First Match Steps} by up to 98.2\% compared to state-of-the-art methods across six real-world datasets. --- ### SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization Authors: Jianghao Wu, Yasmeen George, Jin Ye, Yicheng Wu, Daniel F. Schmidt, Jianfei Cai Published: 2025-11-22 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.17938v2 Large language models (LLMs) and multimodal LLMs (MLL-Ms) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent test-time reinforcement learning (TTRL) methods derive label-free pseudo-rewards from self-consistency voting over sampled trajectories, yet they often collapse: the majority-vote reward prevails, responses shorten, and Pass@1 declines. We trace this to uniform sequence updates in which most tokens are low-entropy followers, while a small high-entropy subset determines the reasoning branches. Thus we propose \method, a token-selective test-time reinforcement learning framework that (i) performs distribution-aware forking-token selection to update only decision-critical branch points, and (ii) applies a robust entropy-band regularizer at those tokens to prevent premature collapse and suppress noisy drift. \method plugs into GRPO-style objectives (optionally with a KL anchor) and requires neither labels nor reward models. Across eight benchmarks spanning multimodal VQA, text-only reasoning, \method consistently improves Pass@1 over TTRL while avoiding response-length collapse and yielding more stable training dynamics on both LLM and MLLM backbones. These results indicate that aligning updates with chain-of-thought branch points is a simple and label-free mechanism for stable and effective test-time adaptation in reasoning models. Code will be released. --- ### Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria Authors: Kartik Garg, Shourya Mishra, Kartikeya Sinha, Ojaswi Pratap Singh, Ayush Chopra, Kanishk Rai, Ammar Sheikh, Raghav Maheshwari, Aman Chadha, Vinija Jain, Amitava Das Published: 2025-11-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.17937v2 Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first documented for Claude 3 Opus and later examined across additional large language models. In these setups, the word "training" refers to simulated training via prompts without parameter updates, so the observed effects are context conditioned shifts in behavior rather than preference learning. We study the phenomenon using an evaluation framework that compares preference optimization methods (BCO, DPO, KTO, and GRPO) across 15 models from four model families, measured along three axes: safety, harmlessness, and helpfulness. Our goal is to identify what causes alignment faking and when it occurs. --- ### Mitigating Catastrophic Forgetting in Streaming Generative and Predictive Learning via Stateful Replay Authors: Wenzhang Du Published: 2025-11-22 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.17936v1 Many deployed learning systems must update models on streaming data under memory constraints. The default strategy, sequential fine-tuning on each new phase, is architecture-agnostic but often suffers catastrophic forgetting when later phases correspond to different sub-populations or tasks. Replay with a finite buffer is a simple alternative, yet its behaviour across generative and predictive objectives is not well understood. We present a unified study of stateful replay for streaming autoencoding, time series forecasting, and classification. We view both sequential fine-tuning and replay as stochastic gradient methods for an ideal joint objective, and use a gradient alignment analysis to show when mixing current and historical samples should reduce forgetting. We then evaluate a single replay mechanism on six streaming scenarios built from Rotated MNIST, ElectricityLoadDiagrams 2011-2014, and Airlines delay data, using matched training budgets and three seeds. On heterogeneous multi task streams, replay reduces average forgetting by a factor of two to three, while on benign time based streams both methods perform similarly. These results position stateful replay as a strong and simple baseline for continual learning in streaming environments. --- ### Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion Authors: Yan Xu, Yixing Wang, Stella X. Yu Published: 2025-11-22 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2511.17932v1 Given just a few glimpses of a scene, can you imagine the movie playing out as the camera glides through it? That's the lens we take on \emph{sparse-input novel view synthesis}, not only as filling spatial gaps between widely spaced views, but also as \emph{completing a natural video} unfolding through space. We recast the task as \emph{test-time natural video completion}, using powerful priors from \emph{pretrained video diffusion models} to hallucinate plausible in-between views. Our \emph{zero-shot, generation-guided} framework produces pseudo views at novel camera poses, modulated by an \emph{uncertainty-aware mechanism} for spatial coherence. These synthesized frames densify supervision for \emph{3D Gaussian Splatting} (3D-GS) for scene reconstruction, especially in under-observed regions. An iterative feedback loop lets 3D geometry and 2D view synthesis inform each other, improving both the scene reconstruction and the generated views. The result is coherent, high-fidelity renderings from sparse inputs \emph{without any scene-specific training or fine-tuning}. On LLFF, DTU, DL3DV, and MipNeRF-360, our method significantly outperforms strong 3D-GS baselines under extreme sparsity. --- ### A Reinforcement Learning Framework for Resource Allocation in Uplink Carrier Aggregation in the Presence of Self Interference Authors: Jaswanth Bodempudi, Batta Siva Sairam, Madepalli Haritha, Sandesh Rao Mattu, Ananthanarayanan Chockalingam Published: 2025-11-22 Categories: cs.IT, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2511.17931v1 Carrier aggregation (CA) is a technique that allows mobile networks to combine multiple carriers to increase user data rate. On the uplink, for power constrained users, this translates to the need for an efficient resource allocation scheme, where each user distributes its available power among its assigned uplink carriers. Choosing a good set of carriers and allocating appropriate power on the carriers is important. If the carrier allocation on the uplink is such that a harmonic of a user's uplink carrier falls on the downlink frequency of that user, it leads to a self coupling-induced sensitivity degradation of that user's downlink receiver. In this paper, we model the uplink carrier aggregation problem as an optimal resource allocation problem with the associated constraints of non-linearities induced self interference (SI). This involves optimization over a discrete variable (which carriers need to be turned on) and a continuous variable (what power needs to be allocated on the selected carriers) in dynamic environments, a problem which is hard to solve using traditional methods owing to the mixed nature of the optimization variables and the additional need to consider the SI constraint. We adopt a reinforcement learning (RL) framework involving a compound-action actor-critic (CA2C) algorithm for the uplink carrier aggregation problem. We propose a novel reward function that is critical for enabling the proposed CA2C algorithm to efficiently handle SI. The CA2C algorithm along with the proposed reward function learns to assign and activate suitable carriers in an online fashion. Numerical results demonstrate that the proposed RL based scheme is able to achieve higher sum throughputs compared to naive schemes. The results also demonstrate that the proposed reward function allows the CA2C algorithm to adapt the optimization both in the presence and absence of SI. --- ### UniRSCD: A Unified Novel Architectural Paradigm for Remote Sensing Change Detection Authors: Yuan Qu, Zhipeng Zhang, Chaojun Xu, Qiao Wan, Mengying Xie, Yuzeng Chen, Zhenqi Liu, Yanfei Zhong Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17930v1 In recent years, remote sensing change detection has garnered significant attention due to its critical role in resource monitoring and disaster assessment. Change detection tasks exist with different output granularities such as BCD, SCD, and BDA. However, existing methods require substantial expert knowledge to design specialized decoders that compensate for information loss during encoding across different tasks. This not only introduces uncertainty into the process of selecting optimal models for abrupt change scenarios (such as disaster outbreaks) but also limits the universality of these architectures. To address these challenges, this paper proposes a unified, general change detection framework named UniRSCD. Building upon a state space model backbone, we introduce a frequency change prompt generator as a unified encoder. The encoder dynamically scans bitemporal global context information while integrating high-frequency details with low-frequency holistic information, thereby eliminating the need for specialized decoders for feature compensation. Subsequently, the unified decoder and prediction head establish a shared representation space through hierarchical feature interaction and task-adaptive output mapping. This integrating various tasks such as binary change detection and semantic change detection into a unified architecture, thereby accommodating the differing output granularity requirements of distinct change detection tasks. Experimental results demonstrate that the proposed architecture can adapt to multiple change detection tasks and achieves leading performance on five datasets, including the binary change dataset LEVIR-CD, the semantic change dataset SECOND, and the building damage assessment dataset xBD. --- ### MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection Authors: Hui Lu, Yi Yu, Shijian Lu, Deepu Rajan, Boon Poh Ng, Alex C. Kot, Xudong Jiang Published: 2025-11-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.17929v2 Temporal Action Detection (TAD) aims to identify and localize actions by determining their starting and ending frames within untrimmed videos. Recent Structured State-Space Models such as Mamba have demonstrated potential in TAD due to their long-range modeling capability and linear computational complexity. On the other hand, structured state-space models often face two key challenges in TAD, namely, decay of temporal context due to recursive processing and self-element conflict during global visual context modeling, which become more severe while handling long-span action instances. Additionally, traditional methods for TAD struggle with detecting long-span action instances due to a lack of global awareness and inefficient detection heads. This paper presents MambaTAD, a new state-space TAD model that introduces long-range modeling and global feature detection capabilities for accurate temporal action detection. MambaTAD comprises two novel designs that complement each other with superior TAD performance. First, it introduces a Diagonal-Masked Bidirectional State-Space (DMBSS) module which effectively facilitates global feature fusion and temporal action detection. Second, it introduces a global feature fusion head that refines the detection progressively with multi-granularity features and global awareness. In addition, MambaTAD tackles TAD in an end-to-end one-stage manner using a new state-space temporal adapter(SSTA) which reduces network parameters and computation cost with linear complexity. Extensive experiments show that MambaTAD achieves superior TAD performance consistently across multiple public benchmarks. ---