# Research Papers — 2025-11 · bundle page 100 of 197 > Full-text markdown of papers #4951–5000 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/100 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/99.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/101.md) ### On Robustness of Linear Classifiers to Targeted Data Poisoning Authors: Nakshatra Gupta, Sumanth Prabhu, Supratik Chakraborty, R Venkatesh Published: 2025-11-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12722v1 Data poisoning is a training-time attack that undermines the trustworthiness of learned models. In a targeted data poisoning attack, an adversary manipulates the training dataset to alter the classification of a targeted test point. Given the typically large size of training dataset, manual detection of poisoning is difficult. An alternative is to automatically measure a dataset's robustness against such an attack, which is the focus of this paper. We consider a threat model wherein an adversary can only perturb the labels of the training dataset, with knowledge limited to the hypothesis space of the victim's model. In this setting, we prove that finding the robustness is an NP-Complete problem, even when hypotheses are linear classifiers. To overcome this, we present a technique that finds lower and upper bounds of robustness. Our implementation of the technique computes these bounds efficiently in practice for many publicly available datasets. We experimentally demonstrate the effectiveness of our approach. Specifically, a poisoning exceeding the identified robustness bounds significantly impacts test point classification. We are also able to compute these bounds in many more cases where state-of-the-art techniques fail. --- ### Predicting upcoming visual features during eye movements yields scene representations aligned with human visual cortex Authors: Sushrut Thorat, Adrien Doerig, Alexander Kroner, Carmen Amme, Tim C. Kietzmann Published: 2025-11-16 Categories: q-bio.NC, cs.CV arXiv: https://arxiv.org/abs/2511.12715v2 Natural scenes are complex arrangements of objects, surfaces, and backgrounds. For the brain's visual system to effectively operate, it needs to extract not only what objects are present, but also their spatial and semantic relations. We hypothesize that such structures may be learned, in a self-supervised fashion, by exploiting temporal regularities of natural active vision: each fixation reveals a glimpse that is related to the previous one via co-occurrence and saccade-conditioned spatial regularities. We instantiate this idea with Glimpse Prediction Networks (GPNs), recurrent models trained to predict the embedding of the next glimpse along human-like scanpaths. GPNs are shown to successfully extract complex scene information, including object co-occurrences and spatial object arrangements, and integrate information across glimpses. Importantly, GPN representations align strongly with human fMRI responses in mid and higher-level visual cortex and match, often outperform, alternative state-of-the-art ANN models, establishing next-glimpse-prediction as a biologically plausible route towards brain-aligned scene representations. --- ### Oxytrees: Model Trees for Bipartite Learning Authors: Pedro Ilídio, Felipe Kenji Nakano, Alireza Gharahighehi, Robbe D'hondt, Ricardo Cerri, Celine Vens Published: 2025-11-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12713v1 Bipartite learning is a machine learning task that aims to predict interactions between pairs of instances. It has been applied to various domains, including drug-target interactions, RNA-disease associations, and regulatory network inference. Despite being widely investigated, current methods still present drawbacks, as they are often designed for a specific application and thus do not generalize to other problems or present scalability issues. To address these challenges, we propose Oxytrees: proxy-based biclustering model trees. Oxytrees compress the interaction matrix into row- and column-wise proxy matrices, significantly reducing training time without compromising predictive performance. We also propose a new leaf-assignment algorithm that significantly reduces the time taken for prediction. Finally, Oxytrees employ linear models using the Kronecker product kernel in their leaves, resulting in shallower trees and thus even faster training. Using 15 datasets, we compared the predictive performance of ensembles of Oxytrees with that of the current state-of-the-art. We achieved up to 30-fold improvement in training times compared to state-of-the-art biclustering forests, while demonstrating competitive or superior performance in most evaluation settings, particularly in the inductive setting. Finally, we provide an intuitive Python API to access all datasets, methods and evaluation measures used in this work, thus enabling reproducible research in this field. --- ### Adaptive Focus Memory for Language Models Authors: Christopher Cruz Published: 2025-11-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.12712v3 Large language models (LLMs) are increasingly deployed in multi-turn dialogue settings, yet their behavior remains bottlenecked by naive history management strategies. Replaying the full conversation at every turn is simple but costly, while recency-based truncation or static summarization often causes early, high-impact user constraints to drift out of effective context. As a result, models may retain text without reliably applying it when it matters. We present Adaptive Focus Memory (AFM), a lightweight context management system that dynamically assigns each past message one of three fidelity levels: Full, Compressed, or Placeholder, based on semantic relevance, temporal decay, and importance classification. AFM packs messages chronologically under a fixed token budget, preserving critical constraints at high fidelity while allowing low-importance context to degrade gracefully. We evaluate AFM on two multi-turn dialogue benchmarks designed to stress long-horizon constraint preservation: a safety-critical travel scenario involving a user with a severe peanut allergy, and a policy-critical tax compliance scenario involving an illegal evasion request. Under strict grading that requires both explicit constraint recall and appropriately conditioned generation, AFM succeeds in 83.3 percent of allergy runs where all baseline strategies fail, and preserves correct refusal behavior on the tax benchmark. These results demonstrate that effective dialogue memory requires more than retaining prior text. Selectively allocating fidelity across past messages enables reliable constraint preservation under bounded context growth, without modifying model weights or introducing external retrieval infrastructure. We release an open-source implementation of AFM compatible with OpenAI-style chat APIs to support reproducible research and practical deployment. --- ### Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs Authors: Yunhao Chen, Xin Wang, Juncheng Li, Yixu Wang, Jie Li, Yan Teng, Yingchun Wang, Xingjun Ma Published: 2025-11-16 Categories: cs.CL, cs.CR arXiv: https://arxiv.org/abs/2511.12710v2 Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space. In other words, these methods mainly search for better attack wording or better strategy choices, but they do not search over executable code. By moving the search into code space, we can optimize not only the final attack prompt, but also the procedure that generates it, including execution flow, reusable logic, branching, and failure-driven repair. To overcome this gap, we introduce EvoSynth, an autonomous multi-agent framework that shifts the optimization space from prompts to executable code. Instead of refining prompts directly, EvoSynth employs a multi-agent system to autonomously engineer, evolve, and execute code-based attack algorithms. Crucially, it features a code-level self-correction loop, allowing it to iteratively rewrite the code-based algorithm in response to target-model feedback and failed attempts. Through extensive experiments, we demonstrate that EvoSynth achieves an 85.5\% Attack Success Rate (ASR) against highly robust models like Claude-Sonnet-4.5 and a 95.9\% average ASR across evaluated targets, while generating attacks that are significantly more diverse than those from existing methods. We release our framework to facilitate future research on evolutionary synthesis in executable code space. --- ### Adaptive Graph Rewiring to Mitigate Over-Squashing in Mesh-Based GNNs for Fluid Dynamics Simulations Authors: Sangwoo Seo, Hyunsung Kim, Jiwan Kim, Chanyoung Park Published: 2025-11-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12709v1 Mesh-based simulation using Graph Neural Networks (GNNs) has been recognized as a promising approach for modeling fluid dynamics. However, the mesh refinement techniques which allocate finer resolution to regions with steep gradients can induce the over-squashing problem in mesh-based GNNs, which prevents the capture of long-range physical interactions. Conventional graph rewiring methods attempt to alleviate this issue by adding new edges, but they typically complete all rewiring operations before applying them to the GNN. These approaches are physically unrealistic, as they assume instantaneous interactions between distant nodes and disregard the distance information between particles. To address these limitations, we propose a novel framework, called Adaptive Graph Rewiring in Mesh-Based Graph Neural Networks (AdaMeshNet), that introduces an adaptive rewiring process into the message-passing procedure to model the gradual propagation of physical interactions. Our method computes a rewiring delay score for bottleneck nodes in the mesh graph, based on the shortest-path distance and the velocity difference. Using this score, it dynamically selects the message-passing layer at which new edges are rewired, which can lead to adaptive rewiring in a mesh graph. Extensive experiments on mesh-based fluid simulations demonstrate that AdaMeshNet outperforms conventional rewiring methods, effectively modeling the sequential nature of physical interactions and enabling more accurate predictions. --- ### FSDAM: Few-Shot Driving Attention Modeling via Vision-Language Coupling Authors: Kaiser Hamid, Can Cui, Khandakar Ashrafi Akbar, Ziran Wang, Nade Liang Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12708v2 Understanding not only where drivers look but also why their attention shifts is essential for interpretable human-AI collaboration in autonomous driving. Driver attention is not purely perceptual but semantically structured. Thus, attention shifts can be learned through minimal semantic supervision rather than dense large-scale annotation. We present \textbf{FSDAM} (\textbf{F}ew-\textbf{S}hot \textbf{D}river \textbf{A}ttention \textbf{M}odeling), a framework that achieves joint spatial attention prediction and structured explanation generation using 90 annotated examples. Our key insight is to decompose attention into an explicit reasoning representation, including scene context, current focus, anticipated next focus, and causal explanation, and to learn next-focus anticipation through minimal-pair supervision. To address task conflict and large sample requirements of existing models, and to mitigate task interference under limited data, we introduce a novel dual-pathway architecture in which separate modules handle spatial prediction and caption generation. In addition, we use a training-only vision-language alignment mechanism that injects semantic priors into spatial learning without increasing inference complexity, mitigating task interference under few-shot training. Despite extreme data scarcity, FSDAM achieves competitive performance in gaze prediction, and generates coherent, context-aware structural reasoning for improved interpretability. The model further demonstrates strong zero-shot generalization across multiple driving benchmarks. --- ### Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs Authors: Daniel Furelos-Blanco, Charles Pert, Frederik Kelbel, Alex F. Spies, Alessandra Russo, Michael Dennis Published: 2025-11-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12706v2 Training general agents to follow complex instructions (tasks) in intricate environments (levels) remains a core challenge in reinforcement learning. Random sampling of task-level pairs often produces unsolvable combinations, highlighting the need to co-design tasks and levels. While unsupervised environment design (UED) has proven effective at automatically designing level curricula, prior work has only considered a fixed task. We present ATLAS (Aligning Tasks and Levels for Autocurricula of Specifications), a novel method that generates joint autocurricula over tasks and levels. Our approach builds upon UED to automatically produce solvable yet challenging task-level pairs for policy training. To evaluate ATLAS and drive progress in the field, we introduce an evaluation suite that models tasks as reward machines in Minigrid levels. Experiments demonstrate that ATLAS vastly outperforms random sampling approaches, particularly when sampling solvable pairs is unlikely. We further show that mutations leveraging the structure of both tasks and levels accelerate convergence to performant policies. --- ### Counting Through Occlusion: Framework for Open World Amodal Counting Authors: Safaeid Hossain Arib, Rabeya Akter, Abdul Monaf Chowdhury, Md Jubair Ahmed Sourov, Md Mehedi Hasan Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12702v2 Object counting has achieved remarkable success on visible instances, yet state-of-the-art (SOTA) methods fail under occlusion. This failure stems from a fundamental architectural limitation where backbone networks encode occluding surfaces rather than target objects, thereby corrupting the feature representations required for accurate enumeration. To address this, we present CountOCC, an amodal counting framework that explicitly reconstructs occluded object features through hierarchical multimodal guidance. Rather than accepting degraded encodings, we synthesize complete representations by integrating spatial context from visible fragments with semantic priors from text and visual embeddings, generating features at occluded locations across multiple pyramid levels. We further introduce a visual equivalence objective that enforces consistency in attention space, ensuring that both occluded and unoccluded views of the same scene produce spatially aligned gradient-based attention maps. Together, these complementary mechanisms preserve discriminative properties essential for accurate counting under occlusion. For rigorous evaluation, we establish occlusion-augmented versions of FSC-147 and CARPK (FSC-147-OCC and CARPK-OCC). CountOCC achieves SOTA performance on FSC-147-OCC with 26.72% and 20.80% MAE reduction over prior baselines under occlusion in validation and test, respectively. CountOCC also demonstrates exceptional generalization by setting new SOTA results on CARPK-OCC with 49.89% MAE reduction and on CAPTURe-Real with 28.79% MAE reduction, validating robust amodal counting. --- ### A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning Authors: Minghui Chen, Hrad Ghoukasian, Ruinan Jin, Zehua Wang, Sai Praneeth Karimireddy, Xiaoxiao Li Published: 2025-11-16 Categories: cs.LG, cs.AI, cs.DC, stat.ML arXiv: https://arxiv.org/abs/2511.12695v2 Federated Learning (FL) enables decentralized, privacy-preserving model training but struggles to balance global generalization and local personalization due to non-identical data distributions across clients. Personalized Fine-Tuning (PFT), a popular post-hoc solution, fine-tunes the final global model locally but often overfits to skewed client distributions or fails under domain shifts. We propose adapting Linear Probing followed by full Fine-Tuning (LP-FT), a principled centralized strategy for alleviating feature distortion (Kumar et al., 2022), to the FL setting. Through systematic evaluation across seven datasets and six PFT variants, we demonstrate LP-FT's superiority in balancing personalization and generalization. Our analysis uncovers federated feature distortion, a phenomenon where local fine-tuning destabilizes globally learned features, and theoretically characterizes how LP-FT mitigates this via phased parameter updates. We further establish conditions (e.g., partial feature overlap, covariate-concept shift) under which LP-FT outperforms standard fine-tuning, offering actionable guidelines for deploying robust personalization in FL. --- ### X-VMamba: Explainable Vision Mamba Authors: Mohamed A. Mabrok, Yalda Zafari Published: 2025-11-16 Categories: cs.CV, cs.LG, math.DS arXiv: https://arxiv.org/abs/2511.12694v1 State Space Models (SSMs), particularly the Mamba architecture, have recently emerged as powerful alternatives to Transformers for sequence modeling, offering linear computational complexity while achieving competitive performance. Yet, despite their effectiveness, understanding how these Vision SSMs process spatial information remains challenging due to the lack of transparent, attention-like mechanisms. To address this gap, we introduce a controllability-based interpretability framework that quantifies how different parts of the input sequence (tokens or patches) influence the internal state dynamics of SSMs. We propose two complementary formulations: a Jacobian-based method applicable to any SSM architecture that measures influence through the full chain of state propagation, and a Gramian-based approach for diagonal SSMs that achieves superior speed through closed-form analytical solutions. Both methods operate in a single forward pass with linear complexity, requiring no architectural modifications or hyperparameter tuning. We validate our framework through experiments on three diverse medical imaging modalities, demonstrating that SSMs naturally implement hierarchical feature refinement from diffuse low-level textures in early layers to focused, clinically meaningful patterns in deeper layers. Our analysis reveals domain-specific controllability signatures aligned with diagnostic criteria, progressive spatial selectivity across the network hierarchy, and the substantial influence of scanning strategies on attention patterns. Beyond medical imaging, we articulate applications spanning computer vision, natural language processing, and cross-domain tasks. Our framework establishes controllability analysis as a unified, foundational interpretability paradigm for SSMs across all domains. Code and analysis tools will be made available upon publication --- ### HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models Authors: Sushant Gautam, Michael A. Riegler, Pål Halvorsen Published: 2025-11-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12693v1 Vision-language models (VLMs) enable open-ended visual question answering but remain prone to hallucinations. We present HEDGE, a unified framework for hallucination detection that combines controlled visual perturbations, semantic clustering, and robust uncertainty metrics. HEDGE integrates sampling, distortion synthesis, clustering (entailment- and embedding-based), and metric computation into a reproducible pipeline applicable across multimodal architectures. Evaluations on VQA-RAD and KvasirVQA-x1 with three representative VLMs (LLaVA-Med, Med-Gemma, Qwen2.5-VL) reveal clear architecture- and prompt-dependent trends. Hallucination detectability is highest for unified-fusion models with dense visual tokenization (Qwen2.5-VL) and lowest for architectures with restricted tokenization (Med-Gemma). Embedding-based clustering often yields stronger separation when applied directly to the generated answers, whereas NLI-based clustering remains advantageous for LLaVA-Med and for longer, sentence-level responses. Across configurations, the VASE metric consistently provides the most robust hallucination signal, especially when paired with embedding clustering and a moderate sampling budget (n ~ 10-15). Prompt design also matters: concise, label-style outputs offer clearer semantic structure than syntactically constrained one-sentence responses. By framing hallucination detection as a geometric robustness problem shaped jointly by sampling scale, prompt structure, model architecture, and clustering strategy, HEDGE provides a principled, compute-aware foundation for evaluating multimodal reliability. The hedge-bench PyPI library enables reproducible and extensible benchmarking, with full code and experimental resources available at https://github.com/Simula/HEDGE . --- ### R$^{2}$Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection Authors: Shuaike Shen, Ke Liu, Jiaqing Xie, Shangde Gao, Chunhua Shen, Ge Liu, Mireia Crispin-Ortuzar, Shangqi Gao Published: 2025-11-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12691v1 Foundation models for medical image segmentation struggle under out-of-distribution (OOD) shifts, often producing fragmented false positives on OOD tumors. We introduce R$^{2}$Seg, a training-free framework for robust OOD tumor segmentation that operates via a two-stage Reason-and-Reject process. First, the Reason step employs an LLM-guided anatomical reasoning planner to localize organ anchors and generate multi-scale ROIs. Second, the Reject step applies two-sample statistical testing to candidates generated by a frozen foundation model (BiomedParse) within these ROIs. This statistical rejection filter retains only candidates significantly different from normal tissue, effectively suppressing false positives. Our framework requires no parameter updates, making it compatible with zero-update test-time augmentation and avoiding catastrophic forgetting. On multi-center and multi-modal tumor segmentation benchmarks, R$^{2}$Seg substantially improves Dice, specificity, and sensitivity over strong baselines and the original foundation models. Code are available at https://github.com/Eurekashen/R2Seg. --- ### Improving Direct Persian-English Speech-to-Speech Translation with Discrete Units and Synthetic Parallel Data Authors: Sina Rashidi, Hossein Sameti Published: 2025-11-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12690v1 Direct speech-to-speech translation (S2ST), in which all components are trained jointly, is an attractive alternative to cascaded systems because it offers a simpler pipeline and lower inference latency. However, direct S2ST models require large amounts of parallel speech data in the source and target languages, which are rarely available for low-resource languages such as Persian. This paper presents a direct S2ST system for translating Persian speech into English speech, as well as a pipeline for synthetic parallel Persian-English speech generation. The model comprises three components: (1) a conformer-based encoder, initialized from self-supervised pre-training, maps source speech to high-level acoustic representations; (2) a causal transformer decoder with relative position multi-head attention translates these representations into discrete target speech units; (3) a unit-based neural vocoder generates waveforms from the predicted discrete units. To mitigate the data scarcity problem, we construct a new Persian-English parallel speech corpus by translating Persian speech transcriptions into English using a large language model and then synthesizing the corresponding English speech with a state-of-the-art zero-shot text-to-speech system. The resulting corpus increases the amount of available parallel speech by roughly a factor of six. On the Persian-English portion of the CVSS corpus, the proposed model achieves improvement of 4.6 ASR BLEU with the synthetic data over direct baselines. These results indicate that combining self-supervised pre-training, discrete speech units, and synthetic parallel data is effective for improving direct S2ST in low-resource language pairs such as Persian-English --- ### Accelerated Distributional Temporal Difference Learning with Linear Function Approximation Authors: Kaicheng Jin, Yang Peng, Jiansheng Yang, Zhihua Zhang Published: 2025-11-16 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.12688v1 In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The purpose of distributional TD learning is to estimate the return distribution of a discounted Markov decision process for a given policy. Previous works on statistical analysis of distributional TD learning focus mainly on the tabular case. We first consider the linear function approximation setting and conduct a fine-grained analysis of the linear-categorical Bellman equation. Building on this analysis, we further incorporate variance reduction techniques in our new algorithms to establish tight sample complexity bounds independent of the support size $K$ when $K$ is large. Our theoretical results imply that, when employing distributional TD learning with linear function approximation, learning the full distribution of the return function from streaming data is no more difficult than learning its expectation. This work provide new insights into the statistical efficiency of distributional reinforcement learning algorithms. --- ### Attention-Enhanced Convolutional Autoencoder and Structured Delay Embeddings for Weather Prediction Authors: Amirpasha Hedayat, Karthik Duraisamy Published: 2025-11-16 Categories: cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2511.12682v1 Weather prediction is a quintessential problem involving the forecasting of a complex, nonlinear, and chaotic high-dimensional dynamical system. This work introduces an efficient reduced-order modeling (ROM) framework for short-range weather prediction and investigates fundamental questions in dimensionality reduction and reduced order modeling of such systems. Unlike recent AI-driven models, which require extensive computational resources, our framework prioritizes efficiency while achieving reasonable accuracy. Specifically, a ResNet-based convolutional autoencoder augmented by block attention modules is developed to reduce the dimensionality of high-dimensional weather data. Subsequently, a linear operator is learned in the time-delayed embedding of the latent space to efficiently capture the dynamics. Using the ERA5 reanalysis dataset, we demonstrate that this framework performs well in-distribution as evidenced by effectively predicting weather patterns within training data periods. We also identify important limitations in generalizing to future states, particularly in maintaining prediction accuracy beyond the training window. Our analysis reveals that weather systems exhibit strong temporal correlations that can be effectively captured through linear operations in an appropriately constructed embedding space, and that projection error rather than inference error is the main bottleneck. These findings shed light on some key challenges in reduced-order modeling of chaotic systems and point toward opportunities for hybrid approaches that combine efficient reduced-order models as baselines with more sophisticated AI architectures, particularly for applications in long-term climate modeling where computational efficiency is paramount. --- ### Dynamic Tree Databases in Automated Planning Authors: Oliver Joergensen, Dominik Drexler, Jendrik Seipp Published: 2025-11-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.12677v1 A central challenge in scaling up explicit state-space search for large tasks is compactly representing the set of generated states. Tree databases, a data structure from model checking, require constant space per generated state in the best case, but they need a large preallocation of memory. We propose a novel dynamic variant of tree databases for compressing state sets over propositional and numeric variables and prove that it maintains the desirable properties of the static counterpart. Our empirical evaluation of state compression techniques for grounded and lifted planning on classical and numeric planning tasks reveals compression ratios of several orders of magnitude, often with negligible runtime overhead. --- ### BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections Authors: Subin Varghese, Joshua Gao, Asad Ur Rahman, Vedhus Hoskere Published: 2025-11-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12676v2 Deploying embodied agents that can answer questions about their surroundings in realistic real-world settings remains difficult, partly due to the scarcity of benchmarks for episodic memory Embodied Question Answering (EQA). Inspired by the challenges of infrastructure inspections, we propose Inspection EQA as a compelling problem class for advancing episodic memory EQA. It demands multi-scale reasoning and long-range spatial understanding, while offering standardized evaluation, professional inspection reports as grounding, and egocentric imagery. We introduce BridgeEQA, a benchmark of 2,200 open-vocabulary question-answer pairs (in the style of OpenEQA) grounded in professional inspection reports across 200 real-world bridge scenes with 47.93 images on average per scene. We further propose a new EQA metric Image Citation Relevance to evaluate the ability of a model to cite relevant images. Evaluations of state-of-the-art vision-language models reveal substantial performance gaps. To address this, we propose Embodied Memory Visual Reasoning (EMVR), which formulates the inspection EQA task as a Markov decision process. EMVR shows strong performance over the baselines. Code and dataset are available at https://drags99.github.io/bridge-eqa/ --- ### Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis Authors: Saar Stern, Ido Sobol, Or Litany Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12675v1 The goal of Novel View Synthesis (NVS) is to generate realistic images of a given content from unseen viewpoints. But how can we trust that a generated image truly reflects the intended transformation? Evaluating its reliability remains a major challenge. While recent generative models, particularly diffusion-based approaches, have significantly improved NVS quality, existing evaluation metrics struggle to assess whether a generated image is both realistic and faithful to the source view and intended viewpoint transformation. Standard metrics, such as pixel-wise similarity and distribution-based measures, often mis-rank incorrect results as they fail to capture the nuanced relationship between the source image, viewpoint change, and generated output. We propose a task-aware evaluation framework that leverages features from a strong NVS foundation model, Zero123, combined with a lightweight tuning step to enhance discrimination. Using these features, we introduce two complementary evaluation metrics: a reference-based score, $D_{\text{PRISM}}$, and a reference-free score, $\text{MMD}_{\text{PRISM}}$. Both reliably identify incorrect generations and rank models in agreement with human preference studies, addressing a fundamental gap in NVS evaluation. Our framework provides a principled and practical approach to assessing synthesis quality, paving the way for more reliable progress in novel view synthesis. To further support this goal, we apply our reference-free metric to six NVS methods across three benchmarks: Toys4K, Google Scanned Objects (GSO), and OmniObject3D, where $\text{MMD}_{\text{PRISM}}$ produces a clear and stable ranking, with lower scores consistently indicating stronger models. --- ### DensePercept-NCSSD: Vision Mamba towards Real-time Dense Visual Perception with Non-Causal State Space Duality Authors: Tushar Anand, Advik Sinha, Abhijit Das Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12671v1 In this work, we propose an accurate and real-time optical flow and disparity estimation model by fusing pairwise input images in the proposed non-causal selective state space for dense perception tasks. We propose a non-causal Mamba block-based model that is fast and efficient and aptly manages the constraints present in a real-time applications. Our proposed model reduces inference times while maintaining high accuracy and low GPU usage for optical flow and disparity map generation. The results and analysis, and validation in real-life scenario justify that our proposed model can be used for unified real-time and accurate 3D dense perception estimation tasks. The code, along with the models, can be found at https://github.com/vimstereo/DensePerceptNCSSD --- ### AI Bill of Materials and Beyond: Systematizing Security Assurance through the AI Risk Scanning (AIRS) Framework Authors: Samuel Nathanson, Alexander Lee, Catherine Chen Kieffer, Jared Junkin, Jessica Ye, Amir Saeed, Melanie Lockhart, Russ Fink, Elisha Peterson, Lanier Watkins Published: 2025-11-16 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12668v1 Assurance for artificial intelligence (AI) systems remains fragmented across software supply-chain security, adversarial machine learning, and governance documentation. Existing transparency mechanisms - including Model Cards, Datasheets, and Software Bills of Materials (SBOMs) - advance provenance reporting but rarely provide verifiable, machine-readable evidence of model security. This paper introduces the AI Risk Scanning (AIRS) Framework, a threat-model-based, evidence-generating framework designed to operationalize AI assurance. The AIRS Framework evolved through three progressive pilot studies - Smurf (AIBOM schema design), OPAL (operational validation), and Pilot C (AIRS) - that reframed AI documentation from descriptive disclosure toward measurable, evidence-bound verification. The framework aligns its assurance fields to the MITRE ATLAS adversarial ML taxonomy and automatically produces structured artifacts capturing model integrity, packaging and serialization safety, structural adapters, and runtime behaviors. Currently, the AIRS Framework is scoped to provide model-level assurances for LLMs, but it could be expanded to include other modalities and cover system-level threats (e.g. application-layer abuses, tool-calling). A proof-of-concept on a quantized GPT-OSS-20B model demonstrates enforcement of safe loader policies, per-shard hash verification, and contamination and backdoor probes executed under controlled runtime conditions. Comparative analysis with SBOM standards of SPDX 3.0 and CycloneDX 1.6 reveals alignment on identity and evaluation metadata, but identifies critical gaps in representing AI-specific assurance fields. The AIRS Framework thus extends SBOM practice to the AI domain by coupling threat modeling with automated, auditable evidence generation, providing a principled foundation for standardized, trustworthy, and machine-verifiable AI risk documentation. --- ### FLClear: Visually Verifiable Multi-Client Watermarking for Federated Learning Authors: Chen Gu, Yingying Sun, Yifan She, Donghui Hu Published: 2025-11-16 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2511.12663v1 Federated learning (FL) enables multiple clients to collaboratively train a shared global model while preserving the privacy of their local data. Within this paradigm, the intellectual property rights (IPR) of client models are critical assets that must be protected. In practice, the central server responsible for maintaining the global model may maliciously manipulate the global model to erase client contributions or falsely claim sole ownership, thereby infringing on clients' IPR. Watermarking has emerged as a promising technique for asserting model ownership and protecting intellectual property. However, existing FL watermarking approaches remain limited, suffering from potential watermark collisions among clients, insufficient watermark security, and non-intuitive verification mechanisms. In this paper, we propose FLClear, a novel framework that simultaneously achieves collision-free watermark aggregation, enhanced watermark security, and visually interpretable ownership verification. Specifically, FLClear introduces a transposed model jointly optimized with contrastive learning to integrate the watermarking and main task objectives. During verification, the watermark is reconstructed from the transposed model and evaluated through both visual inspection and structural similarity metrics, enabling intuitive and quantitative ownership verification. Comprehensive experiments conducted over various datasets, aggregation schemes, and attack scenarios demonstrate the effectiveness of FLClear and confirm that it consistently outperforms state-of-the-art FL watermarking methods. --- ### Hi-Reco: High-Fidelity Real-Time Conversational Digital Humans Authors: Hongbin Huang, Junwei Li, Tianxin Xie, Zhuang Li, Cekai Weng, Yaodong Yang, Yue Luo, Li Liu, Jing Tang, Zhijing Shao, Zeyu Wang Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12662v1 High-fidelity digital humans are increasingly used in interactive applications, yet achieving both visual realism and real-time responsiveness remains a major challenge. We present a high-fidelity, real-time conversational digital human system that seamlessly combines a visually realistic 3D avatar, persona-driven expressive speech synthesis, and knowledge-grounded dialogue generation. To support natural and timely interaction, we introduce an asynchronous execution pipeline that coordinates multi-modal components with minimal latency. The system supports advanced features such as wake word detection, emotionally expressive prosody, and highly accurate, context-aware response generation. It leverages novel retrieval-augmented methods, including history augmentation to maintain conversational flow and intent-based routing for efficient knowledge access. Together, these components form an integrated system that enables responsive and believable digital humans, suitable for immersive applications in communication, education, and entertainment. --- ### Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing Authors: Yuchen Wu, Liang Ding, Li Shen, Dacheng Tao Published: 2025-11-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.12661v1 Aligning Large Language Models (LLMs) to be faithful to new knowledge in complex, multi-hop reasoning tasks is a critical, yet unsolved, challenge. We find that SFT-based methods, e.g., Reason-KE, while state-of-the-art, suffer from a "faithfulness gap": they optimize for format mimicry rather than sound reasoning. This gap enables the LLM's powerful parametric priors to override new contextual facts, resulting in critical factual hallucinations (e.g., incorrectly reasoning "Houston" from "NASA" despite an explicit edit). To solve this core LLM alignment problem, we propose Reason-KE++, an SFT+RL framework that instills process-level faithfulness. Its core is a Stage-aware Reward mechanism that provides dense supervision for intermediate reasoning steps (e.g., Decomposition, Sub-answer Correctness). Crucially, we identify that naive outcome-only RL is a deceptive trap for LLM alignment: it collapses reasoning integrity (e.g., 19.00% Hop acc) while superficially boosting final accuracy. Our process-aware framework sets a new SOTA of 95.48% on MQUAKE-CF-3k (+5.28%), demonstrating that for complex tasks, aligning the reasoning process is essential for building trustworthy LLMs. --- ### Sample Complexity of Agnostic Multiclass Classification: Natarajan Dimension Strikes Back Authors: Alon Cohen, Liad Erez, Steve Hanneke, Tomer Koren, Yishay Mansour, Shay Moran, Qian Zhang Published: 2025-11-16 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.12659v1 The fundamental theorem of statistical learning states that binary PAC learning is governed by a single parameter -- the Vapnik-Chervonenkis (VC) dimension -- which determines both learnability and sample complexity. Extending this to multiclass classification has long been challenging, since Natarajan's work in the late 80s proposing the Natarajan dimension (Nat) as a natural analogue of VC. Daniely and Shalev-Shwartz (2014) introduced the DS dimension, later shown by Brukhim et al. (2022) to characterize multiclass learnability. Brukhim et al. also showed that Nat and DS can diverge arbitrarily, suggesting that multiclass learning is governed by DS rather than Nat. We show that agnostic multiclass PAC sample complexity is in fact governed by two distinct dimensions. Specifically, we prove nearly tight agnostic sample complexity bounds that, up to log factors, take the form $\frac{DS^{1.5}}ε + \frac{Nat}{ε^2}$ where $ε$ is the excess risk. This bound is tight up to a $\sqrt{DS}$ factor in the first term, nearly matching known $Nat/ε^2$ and $DS/ε$ lower bounds. The first term reflects the DS-controlled regime, while the second shows that the Natarajan dimension still dictates asymptotic behavior for small $ε$. Thus, unlike binary or online classification -- where a single dimension (VC or Littlestone) controls both phenomena -- multiclass learning inherently involves two structural parameters. Our technical approach departs from traditional agnostic learning methods based on uniform convergence or reductions to realizable cases. A key ingredient is a novel online procedure based on a self-adaptive multiplicative-weights algorithm performing a label-space reduction, which may be of independent interest. --- ### Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis Authors: Zeqin Yu, Haotao Xie, Jian Zhang, Jiangqun Ni, Wenkan Su, Jiwu Huang Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12658v1 Existing Text Image Forgery Localization (T-IFL) methods often suffer from poor generalization due to the limited scale of real-world datasets and the distribution gap caused by synthetic data that fails to capture the complexity of real-world tampering. To tackle this issue, we propose Fourier Series-based Tampering Synthesis (FSTS), a structured and interpretable framework for synthesizing tampered text images. FSTS first collects 16,750 real-world tampering instances from five representative tampering types, using a structured pipeline that records human-performed editing traces via multi-format logs (e.g., video, PSD, and editing logs). By analyzing these collected parameters and identifying recurring behavioral patterns at both individual and population levels, we formulate a hierarchical modeling framework. Specifically, each individual tampering parameter is represented as a compact combination of basis operation-parameter configurations, while the population-level distribution is constructed by aggregating these behaviors. Since this formulation draws inspiration from the Fourier series, it enables an interpretable approximation using basis functions and their learned weights. By sampling from this modeled distribution, FSTS synthesizes diverse and realistic training data that better reflect real-world forgery traces. Extensive experiments across four evaluation protocols demonstrate that models trained with FSTS data achieve significantly improved generalization on real-world datasets. Dataset is available at \href{https://github.com/ZeqinYu/FSTS}{Project Page}. --- ### DPVO-QAT++: Heterogeneous QAT and CUDA Kernel Fusion for High-Performance Deep Patch Visual Odometry Authors: Cheng Liao Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12653v1 Deep learning-based Visual SLAM (vSLAM) systems exhibit exceptional geometric reasoning capabilities, yet their prohibitive computational overhead severely restricts deployment on resource-constrained autonomous platforms. This paper presents a hierarchical quantization optimization framework, DPVO-QAT++ (DPVO-QAT++: Heterogeneous QAT and CUDA Kernel Fusion for High-Performance Deep Patch Visual Odometry). Through the synergistic integration of learnable scale parameterization, a heterogeneous precision design for the Visual Odometry (VO) front-end and back-end (front-end floating-point fake quantization with FP16/FP32; back-end full precision), and GPU-native kernel fusion for fake quantization (custom CUDA kernels), our framework significantly reduces memory footprint and increases processing speed while preserving the trajectory accuracy of the original model. On the TartanAir dataset, our framework achieves an average FPS increase of 52.1%, a 29.1% reduction in median latency, and a 64.9% reduction in peak GPU memory reservation, while maintaining trajectory accuracy (ATE) comparable to the original DPVO model across 32 validation sequences. On the EuRoC dataset, it realizes an average FPS increase of 30.1%, a 23.1% reduction in median latency, and a 37.7% reduction in peak GPU memory reservation, maintaining comparable trajectory accuracy (ATE) across 11 validation sequences. Experimental results demonstrate that DPVO-QAT++ effectively bridges the gap between high-precision deep VO and the efficiency requirements for practical deployment, offering a viable engineering paradigm for the application of this technology on real-world embedded platforms. Keywords: Visual Odometry, Heterogeneous Precision Architecture, Quantization-Aware Training, CUDA Kernel Fusion, Scale-Only Training, Deep Patch Visual Odometry, GPU-Native Kernel Fusion. --- ### On Counts and Densities of Homogeneous Bent Functions: An Evolutionary Approach Authors: Claude Carlet, Marko Ðurasevic, Domagoj Jakobovic, Luca Mariot, Stjepan Picek, Alexandr Polujan Published: 2025-11-16 Categories: cs.NE, cs.CR arXiv: https://arxiv.org/abs/2511.12652v1 Boolean functions with strong cryptographic properties, such as high nonlinearity and algebraic degree, are important for the security of stream and block ciphers. These functions can be designed using algebraic constructions or metaheuristics. This paper examines the use of Evolutionary Algorithms (EAs) to evolve homogeneous bent Boolean functions, that is, functions whose algebraic normal form contains only monomials of the same degree and that are maximally nonlinear. We introduce the notion of density of homogeneous bent functions, facilitating the algorithmic design that results in finding quadratic and cubic bent functions in different numbers of variables. --- ### Scalable Hierarchical AI-Blockchain Framework for Real-Time Anomaly Detection in Large-Scale Autonomous Vehicle Networks Authors: Rathin Chandra Shit, Sharmila Subudhi Published: 2025-11-16 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12648v1 The security of autonomous vehicle networks is facing major challenges, owing to the complexity of sensor integration, real-time performance demands, and distributed communication protocols that expose vast attack surfaces around both individual and network-wide safety. Existing security schemes are unable to provide sub-10 ms (milliseconds) anomaly detection and distributed coordination of large-scale networks of vehicles within an acceptable safety/privacy framework. This paper introduces a three-tier hybrid security architecture HAVEN (Hierarchical Autonomous Vehicle Enhanced Network), which decouples real-time local threat detection and distributed coordination operations. It incorporates a light ensemble anomaly detection model on the edge (first layer), Byzantine-fault-tolerant federated learning to aggregate threat intelligence at a regional scale (middle layer), and selected blockchain mechanisms (top layer) to ensure critical security coordination. Extensive experimentation is done on a real-world autonomous driving dataset. Large-scale simulations with the number of vehicles ranging between 100 and 1000 and different attack types, such as sensor spoofing, jamming, and adversarial model poisoning, are conducted to test the scalability and resiliency of HAVEN. Experimental findings show sub-10 ms detection latency with an accuracy of 94% and F1-score of 92% across multimodal sensor data, Byzantine fault tolerance validated with 20\% compromised nodes, and a reduced blockchain storage overhead, guaranteeing sufficient differential privacy. The proposed framework overcomes the important trade-off between real-time safety obligation and distributed security coordination with novel three-tiered processing. The scalable architecture of HAVEN is shown to provide great improvement in detection accuracy as well as network resilience over other methods. --- ### NFQ2.0: The CartPole Benchmark Revisited Authors: Sascha Lange, Roland Hafner, Martin Riedmiller Published: 2025-11-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12644v1 This article revisits the 20-year-old neural fitted Q-iteration (NFQ) algorithm on its classical CartPole benchmark. NFQ was a pioneering approach towards modern Deep Reinforcement Learning (Deep RL) in applying multi-layer neural networks to reinforcement learning for real-world control problems. We explore the algorithm's conceptual simplicity and its transition from online to batch learning, which contributed to its stability. Despite its initial success, NFQ required extensive tuning and was not easily reproducible on real-world control problems. We propose a modernized variant NFQ2.0 and apply it to the CartPole task, concentrating on a real-world system build from standard industrial components, to investigate and improve the learning process's repeatability and robustness. Through ablation studies, we highlight key design decisions and hyperparameters that enhance performance and stability of NFQ2.0 over the original variant. Finally, we demonstrate how our findings can assist practitioners in reproducing and improving results and applying deep reinforcement learning more effectively in industrial contexts. --- ### Adaptive Dual-Layer Web Application Firewall (ADL-WAF) Leveraging Machine Learning for Enhanced Anomaly and Threat Detection Authors: Ahmed Sameh, Sahar Selim Published: 2025-11-16 Categories: cs.CR, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2511.12643v1 Web Application Firewalls are crucial for protecting web applications against a wide range of cyber threats. Traditional Web Application Firewalls often struggle to effectively distinguish between malicious and legitimate traffic, leading to limited efficacy in threat detection. To overcome these limitations, this paper proposes an Adaptive Dual-Layer WAF employing a two-layered Machine Learning model designed to enhance the accuracy of anomaly and threat detection. The first layer employs a Decision Tree (DT) algorithm to detect anomalies by identifying traffic deviations from established normal patterns. The second layer employs Support Vector Machine to classify these anomalies as either threat anomalies or benign anomalies. Our Adaptive Dual Layer WAF incorporates comprehensive data pre-processing and feature engineering techniques and has been thoroughly evaluated using five large benchmark datasets. Evaluation using these datasets shows that ADL WAF achieves a detection accuracy of 99.88% and a precision of 100%, significantly enhancing anomaly detection and reducing false positives. These findings suggest that integrating machine learning techniques into WAFs can substantially improve web application security by providing more accurate and efficient threat detection. --- ### Auto-encoder model for faster generation of effective one-body gravitational waveform approximations Authors: Suyog Garg, Feng-Li Lin, Kipp Cannon Published: 2025-11-16 Categories: gr-qc, astro-ph.IM, cs.LG arXiv: https://arxiv.org/abs/2511.12642v2 Upgrades to current gravitational wave detectors for the next observation run and upcoming third-generation observatories, like the Einstein telescope, are expected to have enormous improvements in detection sensitivities and compact object merger event rates. Estimation of source parameters for a wider parameter space that these detectable signals will lie in, will be a computational challenge. Thus, it is imperative to have methods to speed-up the likelihood calculations with theoretical waveform predictions, which can ultimately make the parameter estimation faster and aid in rapid multi-messenger follow-ups. In this work we study auto-encoder models for gravitational waveform generation by adopting the best-performing architecture of Liao & Lin (2021) to approximate aligned-spin SEOBNRv4 inspiral-merger-ringdown waveforms. Our parameter space consists of four parameters, ($m_1$, $m_2$, $χ_1(z)$, $χ_2(z)$). The masses are uniformly sampled in $(5,75)\,M_{\odot}$ with a mass ratio limit at $10\,M_{\odot}$, while the spins are uniform in $(-0.99,0.99)$. Our model is able to generate $10^3$ waveforms in $\sim 0.1$ second at an average speed of about 50 microsecond per waveform on a GPU. This is about 4 orders of magnitude faster than the native SEOBNRv4 implementation, and 2--3 orders of magnitude faster than existing non-machine-learning accelerated waveform variants. The median mismatch for the generated waveforms in the test dataset is $\sim10^{-2}$, with better performance in a restricted parameter space of $χ_{\rm eff}\in(-0.80,0.80)$. The latent sampling error of our model can be quantified at a median mismatch standard deviation of $4\times10^{-3}$. Although the accuracy of our model does not enable full production-use yet, the model could be useful wherever high-volume of approximate theoretical waveforms are required, for instance, for rapid sky localization. --- ### Medical Knowledge Intervention Prompt Tuning for Medical Image Classification Authors: Ye Du, Nanxi Yu, Shujun Wang Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12639v1 Vision-language foundation models (VLMs) have shown great potential in feature transfer and generalization across a wide spectrum of medical-related downstream tasks. However, fine-tuning these models is resource-intensive due to their large number of parameters. Prompt tuning has emerged as a viable solution to mitigate memory usage and reduce training time while maintaining competitive performance. Nevertheless, the challenge is that existing prompt tuning methods cannot precisely distinguish different kinds of medical concepts, which miss essentially specific disease-related features across various medical imaging modalities in medical image classification tasks. We find that Large Language Models (LLMs), trained on extensive text corpora, are particularly adept at providing this specialized medical knowledge. Motivated by this, we propose incorporating LLMs into the prompt tuning process. Specifically, we introduce the CILMP, Conditional Intervention of Large Language Models for Prompt Tuning, a method that bridges LLMs and VLMs to facilitate the transfer of medical knowledge into VLM prompts. CILMP extracts disease-specific representations from LLMs, intervenes within a low-rank linear subspace, and utilizes them to create disease-specific prompts. Additionally, a conditional mechanism is incorporated to condition the intervention process on each individual medical image, generating instance-adaptive prompts and thus enhancing adaptability. Extensive experiments across diverse medical image datasets demonstrate that CILMP consistently outperforms state-of-the-art prompt tuning methods, demonstrating its effectiveness. Code is available at https://github.com/usr922/cilmp. --- ### LLM4SCREENLIT: Recommendations on Assessing the Performance of Large Language Models for Screening Literature in Systematic Reviews Authors: Lech Madeyski, Barbara Kitchenham, Martin Shepperd Published: 2025-11-16 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12635v2 Context: Large language models (LLMs) are increasingly used to screen literature for systematic reviews (SRs), but the standard confusion-matrix metrics used to evaluate them can mislead under the imbalanced, cost-asymmetric conditions of screening. Objective: We develop and justify LLM4SCREENLIT-practical recommendations for researchers conducting LLM-screening evaluations and for editors and reviewers assessing such studies-differentiated by study type (retrospective benchmarking vs deployment for a specific SR). Method: Using Delgado-Chaves et al. (2025), an 18-LLM benchmark across three biomedical SRs, as a motivating example, we reviewed 28 additional papers and extracted their reported metrics. We propose a Weighted Matthews Correlation Coefficient (WMCC) that integrates MCC's chance-correction with asymmetric misclassification costs, and validated it on three software-engineering (SE) reanalyses, the largest covering 9 LLMs x 24 SE secondary studies (34,528 articles). Results: Across the 29 papers, only 10% reported MCC, only 24% reported full confusion matrices, and none of the five papers claiming workload savings priced false-negative cost. In the largest SE reanalysis, MCC and WMCC disagree on the best LLM in 55% of evaluable studies; in the most striking 9,695-article SE study, the Accuracy-best LLM loses 63.3% of relevant evidence (Lost Evidence), the MCC-best 43.9%, but the WMCC-best only 5.8%. Sensitivity analysis (median crossover at w~=2.7, all <7) supports w=10 as a conservative default. Conclusions: SR-screening evaluations should prioritize Lost Evidence and use cost-sensitive WMCC alongside MCC for ranking. Reporting must include the full confusion matrix and treat unclassifiable outputs as positives requiring human review. Designs should be leakage-aware, with non-LLM baselines when the study aims to inform SR practice and labels are available. --- ### Denoising Vision Transformer Autoencoder with Spectral Self-Regularization Authors: Xunzhi Xiang, Xingye Tian, Guiyu Zhang, Yabo Chen, Shaofeng Zhang, Xuebo Wang, Xin Tao, Qi Fan Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12633v1 Variational autoencoders (VAEs) typically encode images into a compact latent space, reducing computational cost but introducing an optimization dilemma: a higher-dimensional latent space improves reconstruction fidelity but often hampers generative performance. Recent methods attempt to address this dilemma by regularizing high-dimensional latent spaces using external vision foundation models (VFMs). However, it remains unclear how high-dimensional VAE latents affect the optimization of generative models. To our knowledge, our analysis is the first to reveal that redundant high-frequency components in high-dimensional latent spaces hinder the training convergence of diffusion models and, consequently, degrade generation quality. To alleviate this problem, we propose a spectral self-regularization strategy to suppress redundant high-frequency noise while simultaneously preserving reconstruction quality. The resulting Denoising-VAE, a ViT-based autoencoder that does not rely on VFMs, produces cleaner, lower-noise latents, leading to improved generative quality and faster optimization convergence. We further introduce a spectral alignment strategy to facilitate the optimization of Denoising-VAE-based generative models. Our complete method enables diffusion models to converge approximately 2$\times$ faster than with SD-VAE, while achieving state-of-the-art reconstruction quality (rFID = 0.28, PSNR = 27.26) and competitive generation performance (gFID = 1.82) on the ImageNet 256$\times$256 benchmark. --- ### Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generation Authors: Yushe Cao, Dianxi Shi, Xing Fu, Xuechao Zou, Haikuo Peng, Xueqi Li, Chun Yu, Junliang Xing Published: 2025-11-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12631v3 While significant progress has been achieved in multimodal facial generation using semantic masks and textual descriptions, conventional feature fusion approaches often fail to enable effective cross-modal interactions, thereby leading to suboptimal generation outcomes. To address this challenge, we introduce MDiTFace--a customized diffusion transformer framework that employs a unified tokenization strategy to process semantic mask and text inputs, eliminating discrepancies between heterogeneous modality representations. The framework facilitates comprehensive multimodal feature interaction through stacked, newly designed multivariate transformer blocks that process all conditions synchronously. Additionally, we design a novel decoupled attention mechanism by dissociating implicit dependencies between mask tokens and temporal embeddings. This mechanism segregates internal computations into dynamic and static pathways, enabling caching and reuse of features computed in static pathways after initial calculation, thereby reducing additional computational overhead introduced by mask condition by over 94% while maintaining performance. Extensive experiments demonstrate that MDiTFace significantly outperforms other competing methods in terms of both facial fidelity and conditional consistency. --- ### Knots: A Large-Scale Multi-Agent Enhanced Expert-Annotated Dataset and LLM Prompt Optimization for NOTAM Semantic Parsing Authors: Maoqi Liu, Quan Fang, Yang Yang, Can Zhao, Kaiquan Cai Published: 2025-11-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.12630v1 Notice to Air Missions (NOTAMs) serve as a critical channel for disseminating key flight safety information, yet their complex linguistic structures and implicit reasoning pose significant challenges for automated parsing. Existing research mainly focuses on surface-level tasks such as classification and named entity recognition, lacking deep semantic understanding. To address this gap, we propose NOTAM semantic parsing, a task emphasizing semantic inference and the integration of aviation domain knowledge to produce structured, inference-rich outputs. To support this task, we construct Knots (Knowledge and NOTAM Semantics), a high-quality dataset of 12,347 expert-annotated NOTAMs covering 194 Flight Information Regions, enhanced through a multi-agent collaborative framework for comprehensive field discovery. We systematically evaluate a wide range of prompt-engineering strategies and model-adaptation techniques, achieving substantial improvements in aviation text understanding and processing. Our experimental results demonstrate the effectiveness of the proposed approach and offer valuable insights for automated NOTAM analysis systems. Our code is available at: https://github.com/Estrellajer/Knots. --- ### FedTopo: Topology-Informed Representation Alignment in Federated Learning under Non-I.I.D. Conditions Authors: Ke Hu, Liyao Xiang, Peng Tang, Weidong Qiu Published: 2025-11-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12628v1 Current federated-learning models deteriorate under heterogeneous (non-I.I.D.) client data, as their feature representations diverge and pixel- or patch-level objectives fail to capture the global topology which is essential for high-dimensional visual tasks. We propose FedTopo, a framework that integrates Topological-Guided Block Screening (TGBS) and Topological Embedding (TE) to leverage topological information, yielding coherently aligned cross-client representations by Topological Alignment Loss (TAL). First, Topology-Guided Block Screening (TGBS) automatically selects the most topology-informative block, i.e., the one with maximal topological separability, whose persistence-based signatures best distinguish within- versus between-class pairs, ensuring that subsequent analysis focuses on topology-rich features. Next, this block yields a compact Topological Embedding, which quantifies the topological information for each client. Finally, a Topological Alignment Loss (TAL) guides clients to maintain topological consistency with the global model during optimization, reducing representation drift across rounds. Experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 under four non-I.I.D. partitions show that FedTopo accelerates convergence and improves accuracy over strong baselines. --- ### C3Net: Context-Contrast Network for Camouflaged Object Detection Authors: Baber Jan, Aiman H. El-Maleh, Abdul Jabbar Siddiqui, Abdul Bais, Saeed Anwar Published: 2025-11-16 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2511.12627v1 Camouflaged object detection identifies objects that blend seamlessly with their surroundings through similar colors, textures, and patterns. This task challenges both traditional segmentation methods and modern foundation models, which fail dramatically on camouflaged objects. We identify six fundamental challenges in COD: Intrinsic Similarity, Edge Disruption, Extreme Scale Variation, Environmental Complexities, Contextual Dependencies, and Salient-Camouflaged Object Disambiguation. These challenges frequently co-occur and compound the difficulty of detection, requiring comprehensive architectural solutions. We propose C3Net, which addresses all challenges through a specialized dual-pathway decoder architecture. The Edge Refinement Pathway employs gradient-initialized Edge Enhancement Modules to recover precise boundaries from early features. The Contextual Localization Pathway utilizes our novel Image-based Context Guidance mechanism to achieve intrinsic saliency suppression without external models. An Attentive Fusion Module synergistically combines the two pathways via spatial gating. C3Net achieves state-of-the-art performance with S-measures of 0.898 on COD10K, 0.904 on CAMO, and 0.913 on NC4K, while maintaining efficient processing. C3Net demonstrates that complex, multifaceted detection challenges require architectural innovation, with specialized components working synergistically to achieve comprehensive coverage beyond isolated improvements. Code, model weights, and results are available at https://github.com/Baber-Jan/C3Net. --- ### OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding Authors: Artem Moroz, Vít Zeman, Martin Mikšík, Elizaveta Isianova, Miroslav David, Pavel Burget, Varun Burde Published: 2025-11-16 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2511.12614v1 We introduce a unified, end-to-end framework that seamlessly integrates object detection and pose estimation with a versatile onboarding process. Our pipeline begins with an onboarding stage that generates object representations from either traditional 3D CAD models or, in their absence, by rapidly reconstructing a high-fidelity neural representation (NeRF) from multi-view images. Given a test image, our system first employs the CNOS detector to localize target objects. For each detection, our novel pose estimation module, OPFormer, infers the precise 6D pose. The core of OPFormer is a transformer-based architecture that leverages a foundation model for robust feature extraction. It uniquely learns a comprehensive object representation by jointly encoding multiple template views and enriches these features with explicit 3D geometric priors using Normalized Object Coordinate Space (NOCS). A decoder then establishes robust 2D-3D correspondences to determine the final pose. Evaluated on the challenging BOP benchmarks, our integrated system demonstrates a strong balance between accuracy and efficiency, showcasing its practical applicability in both model-based and model-free scenarios. --- ### Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data Authors: Yunxin Li, Xinyu Chen, Shenyuan Jiang, Haoyuan Shi, Zhenyu Liu, Xuanyu Zhang, Nanhao Deng, Zhenran Xu, Yicheng Ma, Meishan Zhang, Baotian Hu, Min Zhang Published: 2025-11-16 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.12609v2 We present Uni-MoE 2.0 from the Lychee family. As a fully open-source omnimodal large model (OLM), it substantially advances Lychee's Uni-MoE series in language-centric multimodal understanding, reasoning, and generating. Based on the dense LLM, we build Uni-MoE-2.0-Omni from scratch through three core contributions: dynamic-capacity Mixture-of-Experts (MoE) design, a progressive training strategy enhanced with an iterative reinforcement strategy, and a carefully curated multimodal data matching technique. It is capable of omnimodal understanding, as well as generating images, text, and speech. Architecturally, our new MoE framework balances computational efficiency and capability for 10 cross-modal inputs using shared, routed, and null experts, while our Omni-Modality 3D RoPE ensures spatio-temporal cross-modality alignment in the self-attention layer. For training, following cross-modal pretraining, we use a progressive supervised fine-tuning strategy that activates modality-specific experts and is enhanced by balanced data composition and an iterative GSPO-DPO method to stabilise RL training and improve reasoning. Data-wise, the base model, trained on approximately 75B tokens of open-source multimodal data, is equipped with special speech and image generation tokens, allowing it to learn these generative tasks by conditioning its outputs on linguistic cues. Extensive evaluation across 85 benchmarks demonstrates that our model achieves SOTA or highly competitive performance against leading OLMs, surpassing Qwen2.5-Omni (trained with 1.2T tokens) on over 50 of 76 benchmarks. Key strengths include video understanding (+7% avg. of 8), omnimodallity understanding (+7% avg. of 4), and audiovisual reasoning (+4%). It also advances long-form speech processing (reducing WER by 4.2%) and leads in low-level image processing and controllable generation across 5 metrics. --- ### Open-World Test-Time Adaptation with Hierarchical Feature Aggregation and Attention Affine Authors: Ziqiong Liu, Yushun Tang, Junyang Ji, Zhihai He Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12607v1 Test-time adaptation (TTA) refers to adjusting the model during the testing phase to cope with changes in sample distribution and enhance the model's adaptability to new environments. In real-world scenarios, models often encounter samples from unseen (out-of-distribution, OOD) categories. Misclassifying these as known (in-distribution, ID) classes not only degrades predictive accuracy but can also impair the adaptation process, leading to further errors on subsequent ID samples. Many existing TTA methods suffer substantial performance drops under such conditions. To address this challenge, we propose a Hierarchical Ladder Network that extracts OOD features from class tokens aggregated across all Transformer layers. OOD detection performance is enhanced by combining the original model prediction with the output of the Hierarchical Ladder Network (HLN) via weighted probability fusion. To improve robustness under domain shift, we further introduce an Attention Affine Network (AAN) that adaptively refines the self-attention mechanism conditioned on the token information to better adapt to domain drift, thereby improving the classification performance of the model on datasets with domain shift. Additionally, a weighted entropy mechanism is employed to dynamically suppress the influence of low-confidence samples during adaptation. Experimental results on benchmark datasets show that our method significantly improves the performance on the most widely used classification datasets. --- ### Pixels or Positions? Benchmarking Modalities in Group Activity Recognition Authors: Drishya Karki, Merey Ramazanova, Anthony Cioppa, Silvio Giancola, Bernard Ghanem Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12606v3 Group Activity Recognition (GAR) is well studied on the video modality for surveillance and indoor team sports (e.g., volleyball, basketball). Yet, other modalities such as agent positions and trajectories over time, i.e. tracking, remain comparatively under-explored despite being compact, agent-centric signals that explicitly encode spatial interactions. Understanding whether pixel (video) or position (tracking) modalities leads to better group activity recognition is therefore important to drive further research on the topic. However, no standardized benchmark currently exists that aligns broadcast video and tracking data for the same group activities, leading to a lack of apples-to-apples comparison between these modalities for GAR. In this work, we introduce SoccerNet-GAR, a multimodal dataset built from the $64$ matches of the football World Cup 2022. Specifically, the broadcast videos and player tracking modalities for $87{,}939$ group activities are synchronized and annotated with $10$ categories. Furthermore, we define a unified evaluation protocol to benchmark two strong unimodal approaches: (i) competitive video-based classifiers and (ii) tracking-based classifiers leveraging graph neural networks. In particular, our novel role-aware graph architecture for tracking-based GAR directly encodes tactical structure through positional edges connecting players by their on-pitch roles. Our tracking model achieves $77.8\%$ balanced accuracy compared to $60.9\%$ for the best video baseline, while training with $7 \times$ less GPU hours and $479 \times$ fewer parameters ($180K$ vs. $86.3M$). This study provides new insights into the relative strengths of pixels and positions for group activity recognition in sports. --- ### PID-controlled Langevin Dynamics for Faster Sampling of Generative Models Authors: Hongyi Chen, Jianhai Shu, Jingtao Ding, Yong Li, Xiao-Ping Zhang Published: 2025-11-16 Categories: cs.LG, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2511.12603v1 Langevin dynamics sampling suffers from extremely low generation speed, fundamentally limited by numerous fine-grained iterations to converge to the target distribution. We introduce PID-controlled Langevin Dynamics (PIDLD), a novel sampling acceleration algorithm that reinterprets the sampling process using control-theoretic principles. By treating energy gradients as feedback signals, PIDLD combines historical gradients (the integral term) and gradient trends (the derivative term) to efficiently traverse energy landscapes and adaptively stabilize, thereby significantly reducing the number of iterations required to produce high-quality samples. Our approach requires no additional training, datasets, or prior information, making it immediately integrable with any Langevin-based method. Extensive experiments across image generation and reasoning tasks demonstrate that PIDLD achieves higher quality with fewer steps, making Langevin-based generative models more practical for efficiency-critical applications. The implementation can be found at \href{https://github.com/tsinghua-fib-lab/PIDLD}{https://github.com/tsinghua-fib-lab/PIDLD}. --- ### LoRA-Enhanced Vision Transformer for Single Image based Morphing Attack Detection via Knowledge Distillation from EfficientNet Authors: Ria Shekhawat, Sushrut Patwardhan, Raghavendra Ramachandra, Praveen Kumar Chandaliya, Kishor P. Upla Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12602v1 Face Recognition Systems (FRS) are critical for security but remain vulnerable to morphing attacks, where synthetic images blend biometric features from multiple individuals. We propose a novel Single-Image Morphing Attack Detection (S-MAD) approach using a teacher-student framework, where a CNN-based teacher model refines a ViT-based student model. To improve efficiency, we integrate Low-Rank Adaptation (LoRA) for fine-tuning, reducing computational costs while maintaining high detection accuracy. Extensive experiments are conducted on a morphing dataset built from three publicly available face datasets, incorporating ten different morphing generation algorithms to assess robustness. The proposed method is benchmarked against six state-of-the-art S-MAD techniques, demonstrating superior detection performance and computational efficiency. --- ### Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization Authors: Odysseas Boufalis, Jorge Carrasco-Pollo, Joshua Rosenthal, Eduardo Terres-Caballero, Alejandro García-Castellanos Published: 2025-11-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12601v1 Neural network parameterizations exhibit inherent symmetries that yield multiple equivalent minima within the loss landscape. Scale Graph Metanetworks (ScaleGMNs) explicitly leverage these symmetries by proposing an architecture equivariant to both permutation and parameter scaling transformations. Previous work by Ainsworth et al. (2023) addressed permutation symmetries through a computationally intensive combinatorial assignment problem, demonstrating that leveraging permutation symmetries alone can map networks into a shared loss basin. In this work, we extend their approach by also incorporating scaling symmetries, presenting an autoencoder framework utilizing ScaleGMNs as invariant encoders. Experimental results demonstrate that our method aligns Implicit Neural Representations (INRs) and Convolutional Neural Networks (CNNs) under both permutation and scaling symmetries without explicitly solving the assignment problem. This approach ensures that similar networks naturally converge within the same basin, facilitating model merging, i.e., smooth linear interpolation while avoiding regions of high loss. The code is publicly available on our GitHub repository. --- ### Group-Aware Reinforcement Learning for Output Diversity in Large Language Models Authors: Oron Anschel, Alon Shoshan, Adam Botach, Shunit Haviv Hakimi, Asaf Gendler, Emanuel Ben Baruch, Nadav Bhonker, Igor Kviatkovsky, Manoj Aggarwal, Gerard Medioni Published: 2025-11-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12596v1 Large Language Models (LLMs) often suffer from mode collapse, repeatedly generating the same few completions even when many valid answers exist, limiting their diversity across a wide range of tasks. We introduce Group-Aware Policy Optimization (GAPO), a simple extension of the recent and popular Group Relative Policy Optimization (GRPO) that computes rewards over the group as a whole. GAPO enables learning from the group-level properties such as diversity and coverage. We demonstrate GAPO using a frequency-aware reward function that encourages uniform sampling over valid LLM completions, and show that GAPO-trained models produce valid and more diverse model responses. Beyond this setup, GAPO generalizes to open-ended prompts and improves response diversity without compromising accuracy on standard LLM benchmarks (GSM8K, MATH, HumanEval, MMLU-Pro). Our code will be made publicly available. --- ### Seg-VAR: Image Segmentation with Visual Autoregressive Modeling Authors: Rongkun Zheng, Lu Qi, Xi Chen, Yi Wang, Kun Wang, Hengshuang Zhao Published: 2025-11-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12594v1 While visual autoregressive modeling (VAR) strategies have shed light on image generation with the autoregressive models, their potential for segmentation, a task that requires precise low-level spatial perception, remains unexplored. Inspired by the multi-scale modeling of classic Mask2Former-based models, we propose Seg-VAR, a novel framework that rethinks segmentation as a conditional autoregressive mask generation problem. This is achieved by replacing the discriminative learning with the latent learning process. Specifically, our method incorporates three core components: (1) an image encoder generating latent priors from input images, (2) a spatial-aware seglat (a latent expression of segmentation mask) encoder that maps segmentation masks into discrete latent tokens using a location-sensitive color mapping to distinguish instances, and (3) a decoder reconstructing masks from these latents. A multi-stage training strategy is introduced: first learning seglat representations via image-seglat joint training, then refining latent transformations, and finally aligning image-encoder-derived latents with seglat distributions. Experiments show Seg-VAR outperforms previous discriminative and generative methods on various segmentation tasks and validation benchmarks. By framing segmentation as a sequential hierarchical prediction task, Seg-VAR opens new avenues for integrating autoregressive reasoning into spatial-aware vision systems. Code will be available at https://github.com/rkzheng99/Seg-VAR. --- ### Knowledge is Overrated: A zero-knowledge machine learning and cryptographic hashing-based framework for verifiable, low latency inference at the LHC Authors: Pratik Jawahar, Caterina Doglioni, Maurizio Pierini Published: 2025-11-16 Categories: hep-ex, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2511.12592v1 Low latency event-selection (trigger) algorithms are essential components of Large Hadron Collider (LHC) operation. Modern machine learning (ML) models have shown great offline performance as classifiers and could improve trigger performance, thereby improving downstream physics analyses. However, inference on such large models does not satisfy the $40\text{MHz}$ online latency constraint at the LHC. In this work, we propose \texttt{PHAZE}, a novel framework built on cryptographic techniques like hashing and zero-knowledge machine learning (zkML) to achieve low latency inference, via a certifiable, early-exit mechanism from an arbitrarily large baseline model. We lay the foundations for such a framework to achieve nanosecond-order latency and discuss its inherent advantages, such as built-in anomaly detection, within the scope of LHC triggers, as well as its potential to enable a dynamic low-level trigger in the future. --- ### Fine-Grained Representation for Lane Topology Reasoning Authors: Guoqing Xu, Yiheng Li, Yang Yang Published: 2025-11-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12590v2 Precise modeling of lane topology is essential for autonomous driving, as it directly impacts navigation and control decisions. Existing methods typically represent each lane with a single query and infer topological connectivity based on the similarity between lane queries. However, this kind of design struggles to accurately model complex lane structures, leading to unreliable topology prediction. In this view, we propose a Fine-Grained lane topology reasoning framework (TopoFG). It divides the procedure from bird's-eye-view (BEV) features to topology prediction via fine-grained queries into three phases, i.e., Hierarchical Prior Extractor (HPE), Region-Focused Decoder (RFD), and Robust Boundary-Point Topology Reasoning (RBTR). Specifically, HPE extracts global spatial priors from the BEV mask and local sequential priors from in-lane keypoint sequences to guide subsequent fine-grained query modeling. RFD constructs fine-grained queries by integrating the spatial and sequential priors. It then samples reference points in RoI regions of the mask and applies cross-attention with BEV features to refine the query representations of each lane. RBTR models lane connectivity based on boundary-point query features and further employs a topological denoising strategy to reduce matching ambiguity. By integrating spatial and sequential priors into fine-grained queries and applying a denoising strategy to boundary-point topology reasoning, our method precisely models complex lane structures and delivers trustworthy topology predictions. Extensive experiments on the OpenLane-V2 benchmark demonstrate that TopoFG achieves new state-of-the-art performance, with an OLS of 48.0 on subsetA and 45.4 on subsetB. ---