# Research Papers — 2025-11 · bundle page 19 of 197

> Full-text markdown of papers #901–950 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/19
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/18.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/20.md)

### Joint Speech and Text Training for LLM-Based End-to-End Spoken Dialogue State Tracking

Authors: Katia Vendrame, Bolaji Yusuf, Santosh Kesiraju, Šimon Sedláček, Oldřich Plchot, Jan Černocký
Published: 2025-11-27
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2511.22503v1

End-to-end spoken dialogue state tracking (DST) is made difficult by the tandem of having to handle speech input and data scarcity. Combining speech foundation encoders and large language models has been proposed in recent work as to alleviate some of this difficulty. Although this approach has been shown to result in strong spoken DST models, achieving state-of-the-art performance in realistic multi-turn DST, it struggles to generalize across domains and requires annotated spoken DST training data for each domain of interest. However, collecting such data for every target domain is both costly and difficult. Noting that textual DST data is more easily obtained for various domains, in this work, we propose jointly training on available spoken DST data and written textual data from other domains as a way to achieve cross-domain generalization. We conduct experiments which show the efficacy of our proposed method for getting good cross-domain DST performance without relying on spoken training data from the target domains.

---

### What Shape Is Optimal for Masks in Text Removal?

Authors: Hyakka Nakada, Marika Kubota
Published: 2025-11-27
Categories: cs.CV, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.22499v1

The advent of generative models has dramatically improved the accuracy of image inpainting. In particular, by removing specific text from document images, reconstructing original images is extremely important for industrial applications. However, most existing methods of text removal focus on deleting simple scene text which appears in images captured by a camera in an outdoor environment. There is little research dedicated to complex and practical images with dense text. Therefore, we created benchmark data for text removal from images including a large amount of text. From the data, we found that text-removal performance becomes vulnerable against mask profile perturbation. Thus, for practical text-removal tasks, precise tuning of the mask shape is essential. This study developed a method to model highly flexible mask profiles and learn their parameters using Bayesian optimization. The resulting profiles were found to be character-wise masks. It was also found that the minimum cover of a text region is not optimal. Our research is expected to pave the way for a user-friendly guideline for manual masking.

---

### Space Explanations of Neural Network Classification

Authors: Faezeh Labbaf, Tomáš Kolárik, Martin Blicha, Grigory Fedyukovich, Michael Wand, Natasha Sharygina
Published: 2025-11-27
Categories: cs.LG, cs.LO
arXiv: https://arxiv.org/abs/2511.22498v1

We present a novel logic-based concept called Space Explanations for classifying neural networks that gives provable guarantees of the behavior of the network in continuous areas of the input feature space. To automatically generate space explanations, we leverage a range of flexible Craig interpolation algorithms and unsatisfiable core generation. Based on real-life case studies, ranging from small to medium to large size, we demonstrate that the generated explanations are more meaningful than those computed by state-of-the-art.

---

### HW-GNN: Homophily-Aware Gaussian-Window Constrained Graph Spectral Network for Social Network Bot Detection

Authors: Zida Liu, Jun Gao, Zhang Ji, Li Zhao
Published: 2025-11-27
Categories: cs.SI, cs.AI
arXiv: https://arxiv.org/abs/2511.22493v1

Social bots are increasingly polluting online platforms by spreading misinformation and engaging in coordinated manipulation, posing severe threats to cybersecurity. Graph Neural Networks (GNNs) have become mainstream for social bot detection due to their ability to integrate structural and attribute features, with spectral-based approaches demonstrating particular efficacy due to discriminative patterns in the spectral domain. However, current spectral GNN methods face two limitations: (1) their broad-spectrum fitting mechanisms degrade the focus on bot-specific spectral features, and (2) certain domain knowledge valuable for bot detection, e.g., low homophily correlates with high-frequency features, has not been fully incorporated into existing methods. To address these challenges, we propose HW-GNN, a novel homophily-aware graph spectral network with Gaussian window constraints. Our framework introduces two key innovations: (i) a Gaussian-window constrained spectral network that employs learnable Gaussian windows to highlight bot-related spectral features, and (ii) a homophily-aware adaptation mechanism that injects domain knowledge between homophily ratios and frequency features into the Gaussian window optimization process. Through extensive experimentation on multiple benchmark datasets, we demonstrate that HW-GNN achieves state-of-the-art bot detection performance, outperforming existing methods with an average improvement of 4.3% in F1-score, while exhibiting strong plug-in compatibility with existing spectral GNNs.

---

### SciPostGen: Bridging the Gap between Scientific Papers and Poster Layouts

Authors: Shun Inadumi, Shohei Tanaka, Tosho Hirasawa, Atsushi Hashimoto, Koichiro Yoshino, Yoshitaka Ushiku
Published: 2025-11-27
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2511.22490v2

As the number of scientific papers continues to grow, there is a demand for approaches that can effectively convey research findings, with posters serving as a key medium for presenting paper contents. Poster layouts determine how effectively research is communicated and understood, highlighting their growing importance. In particular, a gap remains in understanding how papers correspond to the layouts that present them, which calls for datasets with paired annotations at scale. To bridge this gap, we introduce SciPostGen, a large-scale dataset for understanding and generating poster layouts from scientific papers. Our analyses based on SciPostGen show that paper structures are associated with the number of layout elements in posters. Based on this insight, we explore a framework, Retrieval-Augmented Poster Layout Generation, which retrieves layouts consistent with a given paper and uses them as guidance for layout generation. We conducted experiments under two conditions: with and without layout constraints typically specified by poster creators. The results show that the retriever estimates layouts aligned with paper structures, and our framework generates layouts that also satisfy given constraints. The dataset and code are publicly available at https://omron-sinicx.github.io/paper2layout/.

---

### SciPostGen: Bridging the Gap between Scientific Papers and Poster Layouts

Authors: Shun Inadumi, Shohei Tanaka, Tosho Hirasawa, Atsushi Hashimoto, Koichiro Yoshino, Yoshitaka Ushiku
Published: 2025-11-27
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2511.22490v1

As the number of scientific papers continues to grow, there is a demand for approaches that can effectively convey research findings, with posters serving as a key medium for presenting paper contents. Poster layouts determine how effectively research is communicated and understood, highlighting their growing importance. In particular, a gap remains in understanding how papers correspond to the layouts that present them, which calls for datasets with paired annotations at scale. To bridge this gap, we introduce SciPostGen, a large-scale dataset for understanding and generating poster layouts from scientific papers. Our analyses based on SciPostGen show that paper structures are associated with the number of layout elements in posters. Based on this insight, we explore a framework, Retrieval-Augmented Poster Layout Generation, which retrieves layouts consistent with a given paper and uses them as guidance for layout generation. We conducted experiments under two conditions: with and without layout constraints typically specified by poster creators. The results show that the retriever estimates layouts aligned with paper structures, and our framework generates layouts that also satisfy given constraints.

---

### AI killed the video star. Audio-driven diffusion model for expressive talking head generation

Authors: Baptiste Chopin, Tashvik Dhamija, Pranav Balaji, Yaohui Wang, Antitza Dantcheva
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22488v1

We propose Dimitra++, a novel framework for audio-driven talking head generation, streamlined to learn lip motion, facial expression, as well as head pose motion. Specifically, we propose a conditional Motion Diffusion Transformer (cMDT) to model facial motion sequences, employing a 3D representation. The cMDT is conditioned on two inputs: a reference facial image, which determines appearance, as well as an audio sequence, which drives the motion. Quantitative and qualitative experiments, as well as a user study on two widely employed datasets, i.e., VoxCeleb2 and CelebV-HQ, suggest that Dimitra++ is able to outperform existing approaches in generating realistic talking heads imparting lip motion, facial expression, and head pose.

---

### The Machine Learning Approach to Moment Closure Relations for Plasma: A Review

Authors: Samuel Burles, Enrico Camporeale
Published: 2025-11-27
Categories: physics.plasm-ph, cs.LG
arXiv: https://arxiv.org/abs/2511.22486v4

The requirement for large-scale global simulations of plasma is an ongoing challenge in both space and laboratory plasma physics. Any simulation based on a fluid model inherently requires a closure relation for the high order plasma moments. This review compiles and analyses the recent surge of machine learning approaches developing improved plasma closure models capable of capturing kinetic phenomena within plasma fluid models. We survey two methodological families: neural-network surrogates (from multilayer perceptrons to Fourier neural operators, the latter recently reproducing both linear and non-linear Landau damping online within a fluid solver) and equation-discovery methods such as sparse regression; and organise the studies by whether they are tested offline against reference data or online within a time-evolving solver. We outline the challenges associated with machine-learning closures, including off-diagonal pressure-tensor accuracy, generalisation beyond the training distribution, and stable integration into large-scale simulations, and the directions future research might take to address them.

---

### The Machine Learning Approach to Moment Closure Relations for Plasma: A Review

Authors: Samuel Burles, Enrico Camporeale
Published: 2025-11-27
Categories: physics.plasm-ph, cs.LG
arXiv: https://arxiv.org/abs/2511.22486v1

The requirement for large-scale global simulations of plasma is an ongoing challenge in both space and laboratory plasma physics. Any simulation based on a fluid model inherently requires a closure relation for the high order plasma moments. This review compiles and analyses the recent surge of machine learning approaches developing improved plasma closure models capable of capturing kinetic phenomena within plasma fluid models. The purpose of this review is both to collect and analyse the various methods employed on the plasma closure problem, including both equation discovery methods and neural network surrogate approaches, as well as to provide a general overview of the state of the problem. In particular, we highlight the challenges of developing a data-driven closure as well as the direction future work should take toward addressing these challenges, in the pursuit of a computationally viable large-scale global simulation.

---

### Enhancing Trustworthiness with Mixed Precision: Benchmarks, Opportunities, and Challenges

Authors: Guanxi Lu, Hao Mark Chen, Zhiqiang Que, Wayne Luk, Hongxiang Fan
Published: 2025-11-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.22483v1

Large language models (LLMs) have shown promising performance across various tasks. However, their autoregressive decoding process poses significant challenges for efficient deployment on existing AI hardware. Quantization alleviates memory and compute pressure by compressing weights, activations, and KV caches to low precisions while preserving generation quality. However, existing quantization frameworks typically focus on perplexity or classification accuracy, often omitting critical trustworthiness metrics. This gap introduces risks when applying quantized LLMs to downstream high-stakes domains such as finance and healthcare. In this work, we systematically investigate the impact of quantization on four trustworthiness metrics (adversarial robustness, fairness, machine ethics, and out-of-distribution robustness) and identify the instability across compression ratios and quantization methods. Building on these observations, we develop a novel precision-ensemble voting approach that leverages predictions from mixed-precision variants of the same model and consistently improves performance by up to $5.8\%$ on trustworthiness metrics. Our results highlight the importance of considering trustworthiness when developing model compression techniques and point to research opportunities at the intersection of compression and trustworthiness for safety-critical applications.

---

### Exploring Performance Variations in Finetuned Translators of Ultra-Low Resource Languages: Do Linguistic Differences Matter?

Authors: Isabel Gonçalves, Paulo Cavalin, Claudio Pinhanez
Published: 2025-11-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.22482v1

Finetuning pre-trained language models with small amounts of data is a commonly-used method to create translators for ultra-low resource languages such as endangered Indigenous languages. However, previous works have reported substantially different performances with translators created using similar methodology and data. In this work we systematically explored possible causes of the performance difference, aiming to determine whether it was a product of different cleaning procedures, limitations of the pre-trained models, the size of the base model, or the size of the training dataset, studying both directions of translation. Our studies, using two Brazilian Indigenous languages, related but with significant structural linguistic characteristics, indicated none or very limited influence from those training factors, suggesting differences between languages may play a significant role in the ability to produce translators by fine-tuning pre-trained models.

---

### Adversarial Flow Models

Authors: Shanchuan Lin, Ceyuan Yang, Zhijie Lin, Hao Chen, Haoqi Fan
Published: 2025-11-27
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.22475v3

We present adversarial flow models, a class of generative models that belongs to both the adversarial and flow families. Our method supports native one-step and multi-step generation and is trained with an adversarial objective. Unlike traditional GANs, in which the generator learns an arbitrary transport map between the noise and data distributions, our generator is encouraged to learn a deterministic noise-to-data mapping. This significantly stabilizes adversarial training. Unlike consistency-based methods, our model directly learns one-step or few-step generation without having to learn the intermediate timesteps of the probability flow for propagation. This preserves model capacity and avoids error accumulation. Under the same 1NFE setting on ImageNet-256px, our B/2 model approaches the performance of consistency-based XL/2 models, while our XL/2 model achieves a new best FID of 2.38. We additionally demonstrate end-to-end training of 56-layer and 112-layer models without any intermediate supervision, achieving FIDs of 2.08 and 1.94 with a single forward pass and surpassing the corresponding 28-layer 2NFE and 4NFE counterparts with equal compute and parameters. The code is available at https://github.com/ByteDance-Seed/Adversarial-Flow-Models

---

### Adversarial Flow Models

Authors: Shanchuan Lin, Ceyuan Yang, Zhijie Lin, Hao Chen, Haoqi Fan
Published: 2025-11-27
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.22475v1

We present adversarial flow models, a class of generative models that unifies adversarial models and flow models. Our method supports native one-step or multi-step generation and is trained using the adversarial objective. Unlike traditional GANs, where the generator learns an arbitrary transport plan between the noise and the data distributions, our generator learns a deterministic noise-to-data mapping, which is the same optimal transport as in flow-matching models. This significantly stabilizes adversarial training. Also, unlike consistency-based methods, our model directly learns one-step or few-step generation without needing to learn the intermediate timesteps of the probability flow for propagation. This saves model capacity, reduces training iterations, and avoids error accumulation. Under the same 1NFE setting on ImageNet-256px, our B/2 model approaches the performance of consistency-based XL/2 models, while our XL/2 model creates a new best FID of 2.38. We additionally show the possibility of end-to-end training of 56-layer and 112-layer models through depth repetition without any intermediate supervision, and achieve FIDs of 2.08 and 1.94 using a single forward pass, surpassing their 2NFE and 4NFE counterparts.

---

### Rethinking Cross-Generator Image Forgery Detection through DINOv3

Authors: Zhenglin Huang, Jason Li, Haiquan Wen, Tianxiao Li, Xi Yang, Lu Qi, Bei Peng, Xiaowei Huang, Ming-Hsuan Yang, Guangliang Cheng
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22471v1

As generative models become increasingly diverse and powerful, cross-generator detection has emerged as a new challenge. Existing detection methods often memorize artifacts of specific generative models rather than learning transferable cues, leading to substantial failures on unseen generators. Surprisingly, this work finds that frozen visual foundation models, especially DINOv3, already exhibit strong cross-generator detection capability without any fine-tuning. Through systematic studies on frequency, spatial, and token perspectives, we observe that DINOv3 tends to rely on global, low-frequency structures as weak but transferable authenticity cues instead of high-frequency, generator-specific artifacts. Motivated by this insight, we introduce a simple, training-free token-ranking strategy followed by a lightweight linear probe to select a small subset of authenticity-relevant tokens. This token subset consistently improves detection accuracy across all evaluated datasets. Our study provides empirical evidence and a feasible hypothesis for understanding why foundation models generalize across diverse generators, offering a universal, efficient, and interpretable baseline for image forgery detection.

---

### Hybrid, Unified and Iterative: A Novel Framework for Text-based Person Anomaly Retrieval

Authors: Tien-Huy Nguyen, Huu-Loc Tran, Huu-Phong Phan-Nguyen, Quang-Vinh Dinh
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22470v1

Text-based person anomaly retrieval has emerged as a challenging task, with most existing approaches relying on complex deep-learning techniques. This raises a research question: How can the model be optimized to achieve greater fine-grained features? To address this, we propose a Local-Global Hybrid Perspective (LHP) module integrated with a Vision-Language Model (VLM), designed to explore the effectiveness of incorporating both fine-grained features alongside coarse-grained features. Additionally, we investigate a Unified Image-Text (UIT) model that combines multiple objective loss functions, including Image-Text Contrastive (ITC), Image-Text Matching (ITM), Masked Language Modeling (MLM), and Masked Image Modeling (MIM) loss. Beyond this, we propose a novel iterative ensemble strategy, by combining iteratively instead of using model results simultaneously like other ensemble methods. To take advantage of the superior performance of the LHP model, we introduce a novel feature selection algorithm based on its guidance, which helps improve the model's performance. Extensive experiments demonstrate the effectiveness of our method in achieving state-of-the-art (SOTA) performance on PAB dataset, compared with previous work, with a 9.70\% improvement in R@1, 1.77\% improvement in R@5, and 1.01\% improvement in R@10.

---

### RoadSceneBench: A Lightweight Benchmark for Mid-Level Road Scene Understanding

Authors: Xiyan Liu, Han Wang, Yuhu Wang, Junjie Cai, Zhe Cao, Jianzhong Yang, Zhen Lu
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22466v1

Understanding mid-level road semantics, which capture the structural and contextual cues that link low-level perception to high-level planning, is essential for reliable autonomous driving and digital map construction. However, existing benchmarks primarily target perception tasks such as detection or segmentation, overlooking the reasoning capabilities required to infer road topology and dynamic scene structure. To address this gap, we present RoadSceneBench, a lightweight yet information-rich benchmark designed to evaluate and advance visual reasoning in complex road environments. Unlike large-scale perception datasets, RoadSceneBench emphasizes relational understanding and structural consistency, encouraging models to capture the underlying logic of real-world road scenes. Furthermore, to enhance reasoning reliability, we propose Hierarchical Relational Reward Propagation with Temporal Consistency (HRRP-T), a training framework for Vision-Language Models (VLMs) in which reward signals adaptively promote spatial coherence and semantic alignment throughout the reasoning process. This paradigm enables models to move beyond static recognition toward geometry-aware and temporally consistent reasoning. Extensive experiments demonstrate that our method achieves state-of-the-art performance across diverse road configurations. RoadSceneBench thus provides a compact yet powerful foundation for studying mid-level road semantics and fostering structure-aware autonomous perception. Our dataset is available at https://github.com/XiyanLiu/RoadSceneBench.

---

### An Efficient Embedding Based Ad Retrieval with GPU-Powered Feature Interaction

Authors: Yifan Lei, Jiahua Luo, Tingyu Jiang, Bo Zhang, Lifeng Wang, Dapeng Liu, Zhaoren Wu, Haijie Gu, Huan Yu, Jie Jiang
Published: 2025-11-27
Categories: cs.LG, cs.IR
arXiv: https://arxiv.org/abs/2511.22460v2

In large-scale advertising recommendation systems, retrieval serves as a critical component, aiming to efficiently select a subset of candidate ads relevant to user behaviors from a massive ad inventory for subsequent ranking and recommendation. The Embedding-Based Retrieval (EBR) methods modeled by the dual-tower network are widely used in the industry to maintain both retrieval efficiency and accuracy. However, the dual-tower model has significant limitations: the embeddings of users and ads interact only at the final inner product computation, resulting in insufficient feature interaction capabilities. Although DNN-based models with both user and ad as input features, allowing for early-stage interaction between these features, are introduced in the ranking stage to mitigate this issue, they are computationally infeasible for the retrieval stage. To bridge this gap, this paper proposes an efficient GPU-based feature interaction for the dual-tower network to significantly improve retrieval accuracy while substantially reducing computational costs. Specifically, we introduce a novel compressed inverted list designed for GPU acceleration, enabling efficient feature interaction computation at scale. To the best of our knowledge, this is the first framework in the industry to successfully implement Wide and Deep in a retrieval system. We apply this model to the real-world business scenarios in Tencent Advertising, and experimental results demonstrate that our method outperforms existing approaches in offline evaluation and has been successfully deployed to Tencent's advertising recommendation system, delivering significant online performance gains. This improvement not only validates the effectiveness of the proposed method, but also provides new practical guidance for optimizing large-scale ad retrieval systems.

---

### An Efficient Embedding Based Ad Retrieval with GPU-Powered Feature Interaction

Authors: Yifan Lei, Jiahua Luo, Tingyu Jiang, Bo Zhang, Lifeng Wang, Dapeng Liu, Zhaoren Wu, Haijie Gu, Huan Yu, Jie Jiang
Published: 2025-11-27
Categories: cs.LG, cs.IR
arXiv: https://arxiv.org/abs/2511.22460v1

In large-scale advertising recommendation systems, retrieval serves as a critical component, aiming to efficiently select a subset of candidate ads relevant to user behaviors from a massive ad inventory for subsequent ranking and recommendation. The Embedding-Based Retrieval (EBR) methods modeled by the dual-tower network are widely used in the industry to maintain both retrieval efficiency and accuracy. However, the dual-tower model has significant limitations: the embeddings of users and ads interact only at the final inner product computation, resulting in insufficient feature interaction capabilities. Although DNN-based models with both user and ad as input features, allowing for early-stage interaction between these features, are introduced in the ranking stage to mitigate this issue, they are computationally infeasible for the retrieval stage. To bridge this gap, this paper proposes an efficient GPU-based feature interaction for the dual-tower network to significantly improve retrieval accuracy while substantially reducing computational costs. Specifically, we introduce a novel compressed inverted list designed for GPU acceleration, enabling efficient feature interaction computation at scale. To the best of our knowledge, this is the first framework in the industry to successfully implement Wide and Deep in a retrieval system. We apply this model to the real-world business scenarios in Tencent Advertising, and experimental results demonstrate that our method outperforms existing approaches in offline evaluation and has been successfully deployed to Tencent's advertising recommendation system, delivering significant online performance gains. This improvement not only validates the effectiveness of the proposed method, but also provides new practical guidance for optimizing large-scale ad retrieval systems.

---

### Gaussians on Fire: High-Frequency Reconstruction of Flames

Authors: Jakob Nazarenus, Dominik Michels, Wojtek Palubicki, Simin Kou, Fang-Lue Zhang, Sören Pirk, Reinhard Koch
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22459v2

We propose a method to reconstruct dynamic fire in 3D from a limited set of camera views with a Gaussian-based spatiotemporal representation. Capturing and reconstructing fire and its dynamics is highly challenging due to its volatile nature, transparent quality, and multitude of high-frequency features. Despite these challenges, we aim to reconstruct fire from only three views, which consequently requires solving for under-constrained geometry. We solve this by separating the static background from the dynamic fire region by combining dense multi-view stereo images with monocular depth priors. The fire is initialized as a 3D flow field, obtained by fusing per-view dense optical flow projections. To capture the high frequency features of fire, each 3D Gaussian encodes a lifetime and linear velocity to match the dense optical flow. To ensure sub-frame temporal alignment across cameras we employ a custom hardware synchronization pattern -- allowing us to reconstruct fire with affordable commodity hardware. Our quantitative and qualitative validations across numerous reconstruction experiments demonstrate robust performance for diverse and challenging real fire scenarios.

---

### Gaussians on Fire: High-Frequency Reconstruction of Flames

Authors: Jakob Nazarenus, Dominik Michels, Wojtek Palubicki, Simin Kou, Fang-Lue Zhang, Soren Pirk, Reinhard Koch
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22459v1

We propose a method to reconstruct dynamic fire in 3D from a limited set of camera views with a Gaussian-based spatiotemporal representation. Capturing and reconstructing fire and its dynamics is highly challenging due to its volatile nature, transparent quality, and multitude of high-frequency features. Despite these challenges, we aim to reconstruct fire from only three views, which consequently requires solving for under-constrained geometry. We solve this by separating the static background from the dynamic fire region by combining dense multi-view stereo images with monocular depth priors. The fire is initialized as a 3D flow field, obtained by fusing per-view dense optical flow projections. To capture the high frequency features of fire, each 3D Gaussian encodes a lifetime and linear velocity to match the dense optical flow. To ensure sub-frame temporal alignment across cameras we employ a custom hardware synchronization pattern -- allowing us to reconstruct fire with affordable commodity hardware. Our quantitative and qualitative validations across numerous reconstruction experiments demonstrate robust performance for diverse and challenging real fire scenarios.

---

### ITS3D: Inference-Time Scaling for Text-Guided 3D Diffusion Models

Authors: Zhenglin Zhou, Fan Ma, Xiaobo Xia, Hehe Fan, Yi Yang, Tat-Seng Chua
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22456v1

We explore inference-time scaling in text-guided 3D diffusion models to enhance generative quality without additional training. To this end, we introduce ITS3D, a framework that formulates the task as an optimization problem to identify the most effective Gaussian noise input. The framework is driven by a verifier-guided search algorithm, where the search algorithm iteratively refines noise candidates based on verifier feedback. To address the inherent challenges of 3D generation, we introduce three techniques for improved stability, efficiency, and exploration capability. 1) Gaussian normalization is applied to stabilize the search process. It corrects distribution shifts when noise candidates deviate from a standard Gaussian distribution during iterative updates. 2) The high-dimensional nature of the 3D search space increases computational complexity. To mitigate this, a singular value decomposition-based compression technique is employed to reduce dimensionality while preserving effective search directions. 3) To further prevent convergence to suboptimal local minima, a singular space reset mechanism dynamically updates the search space based on diversity measures. Extensive experiments demonstrate that ITS3D enhances text-to-3D generation quality, which shows the potential of computationally efficient search methods in generative processes. The source code is available at https://github.com/ZhenglinZhou/ITS3D.

---

### Beyond Real versus Fake Towards Intent-Aware Video Analysis

Authors: Saurabh Atreya, Nabyl Quignon, Baptiste Chopin, Abhijit Das, Antitza Dantcheva
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22455v1

The rapid advancement of generative models has led to increasingly realistic deepfake videos, posing significant societal and security risks. While existing detection methods focus on distinguishing real from fake videos, such approaches fail to address a fundamental question: What is the intent behind a manipulated video? Towards addressing this question, we introduce IntentHQ: a new benchmark for human-centered intent analysis, shifting the paradigm from authenticity verification to contextual understanding of videos. IntentHQ consists of 5168 videos that have been meticulously collected and annotated with 23 fine-grained intent-categories, including "Financial fraud", "Indirect marketing", "Political propaganda", as well as "Fear mongering". We perform intent recognition with supervised and self-supervised multi-modality models that integrate spatio-temporal video features, audio processing, and text analysis to infer underlying motivations and goals behind videos. Our proposed model is streamlined to differentiate between a wide range of intent-categories.

---

### Benchmarking machine learning models for multi-class state recognition in double quantum dot data

Authors: Valeria Díaz Moreno, Ryan P Khalili, Daniel Schug, Patrick J. Walsh, Justyna P. Zwolak
Published: 2025-11-27
Categories: cs.CV, cond-mat.mes-hall, cs.LG
arXiv: https://arxiv.org/abs/2511.22451v2

Semiconductor quantum dots (QDs) are a leading platform for scalable quantum processors. However, scaling to large arrays requires reliable, automated tuning strategies for devices' bootstrapping, calibration, and operation, with many tuning aspects depending on accurately identifying QD device states from charge-stability diagrams (CSDs). In this work, we present a comprehensive benchmarking study of four modern machine learning (ML) architectures for multi-class state recognition in double-QD CSDs. We evaluate their performance across different data budgets and normalization schemes using both synthetic and experimental data. We find that the more resource-intensive models -- U-Nets and visual transformers (ViTs) -- achieve the highest MSE score (defined as $1-\mathrm{MSE}$) on synthetic data (over $0.98$) but fail to generalize to experimental data. MDNs are the most computationally efficient and exhibit highly stable training, but with substantially lower peak performance. CNNs offer the most favorable trade-off on experimental CSDs, achieving strong accuracy with two orders of magnitude fewer parameters than the U-Nets and ViTs. Normalization plays a nontrivial role: min-max scaling generally yields higher MSE scores but less stable convergence, whereas z-score normalization produces more predictable training dynamics but at reduced accuracy for most models. Overall, our study shows that CNNs with min-max normalization are a practical approach for QD CSDs.

---

### Benchmarking machine learning models for multi-class state recognition in double duantum dot data

Authors: Valeria Díaz Moreno, Ryan P Khalili, Daniel Schug, Patrick J. Walsh, Justyna P. Zwolak
Published: 2025-11-27
Categories: cs.CV, cond-mat.mes-hall, cs.LG
arXiv: https://arxiv.org/abs/2511.22451v1

Semiconductor quantum dots (QDs) are a leading platform for scalable quantum processors. However, scaling to large arrays requires reliable, automated tuning strategies for devices' bootstrapping, calibration, and operation, with many tuning aspects depending on accurately identifying QD device states from charge-stability diagrams (CSDs). In this work, we present a comprehensive benchmarking study of four modern machine learning (ML) architectures for multi-class state recognition in double-QD CSDs. We evaluate their performance across different data budgets and normalization schemes using both synthetic and experimental data. We find that the more resource-intensive models -- U-Nets and visual transformers (ViTs) -- achieve the highest MSE score (defined as $1-\mathrm{MSE}$) on synthetic data (over $0.98$) but fail to generalize to experimental data. MDNs are the most computationally efficient and exhibit highly stable training, but with substantially lower peak performance. CNNs offer the most favorable trade-off on experimental CSDs, achieving strong accuracy with two orders of magnitude fewer parameters than the U-Nets and ViTs. Normalization plays a nontrivial role: min-max scaling generally yields higher MSE scores but less stable convergence, whereas z-score normalization produces more predictable training dynamics but at reduced accuracy for most models. Overall, our study shows that CNNs with min-max normalization are a practical approach for QD CSDs.

---

### Structured Extraction from Business Process Diagrams Using Vision-Language Models

Authors: Pritam Deka, Barry Devereux
Published: 2025-11-27
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2511.22448v1

Business Process Model and Notation (BPMN) is a widely adopted standard for representing complex business workflows. While BPMN diagrams are often exchanged as visual images, existing methods primarily rely on XML representations for computational analysis. In this work, we present a pipeline that leverages Vision-Language Models (VLMs) to extract structured JSON representations of BPMN diagrams directly from images, without requiring source model files or textual annotations. We also incorporate optical character recognition (OCR) for textual enrichment and evaluate the generated element lists against ground truth data derived from the source XML files. Our approach enables robust component extraction in scenarios where original source files are unavailable. We benchmark multiple VLMs and observe performance improvements in several models when OCR is used for text enrichment. In addition, we conducted extensive statistical analyses of OCR-based enrichment methods and prompt ablation studies, providing a clearer understanding of their impact on model performance.

---

### Do You See What I Say? Generalizable Deepfake Detection based on Visual Speech Recognition

Authors: Maheswar Bora, Tashvik Dhamija, Shukesh Reddy, Baptiste Chopin, Pranav Balaji, Abhijit Das, Antitza Dantcheva
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22443v1

Deepfake generation has witnessed remarkable progress, contributing to highly realistic generated images, videos, and audio. While technically intriguing, such progress has raised serious concerns related to the misuse of manipulated media. To mitigate such misuse, robust and reliable deepfake detection is urgently needed. Towards this, we propose a novel network FauxNet, which is based on pre-trained Visual Speech Recognition (VSR) features. By extracting temporal VSR features from videos, we identify and segregate real videos from manipulated ones. The holy grail in this context has to do with zero-shot detection, i.e., generalizable detection, which we focus on in this work. FauxNet consistently outperforms the state-of-the-art in this setting. In addition, FauxNet is able to attribute - distinguish between generation techniques from which the videos stem. Finally, we propose new datasets, referred to as Authentica-Vox and Authentica-HDTF, comprising about 38,000 real and fake videos in total, the latter created with six recent deepfake generation techniques. We provide extensive analysis and results on the Authentica datasets and FaceForensics++, demonstrating the superiority of FauxNet. The Authentica datasets will be made publicly available.

---

### What Is the Optimal Ranking Score Between Precision and Recall? We Can Always Find It and It Is Rarely $F_1$

Authors: Sébastien Piérard, Adrien Deliège, Marc Van Droogenbroeck
Published: 2025-11-27
Categories: cs.PF, cs.AI, cs.CV, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.22442v2

Ranking methods or models based on their performance is of prime importance but is tricky because performance is fundamentally multidimensional. In the case of classification, precision and recall are scores with probabilistic interpretations that are both important to consider and complementary. The rankings induced by these two scores are often in partial contradiction. In practice, therefore, it is extremely useful to establish a compromise between the two views to obtain a single, global ranking. Over the last fifty years or so, it has been proposed to take a weighted harmonic mean, known as the F-score, F-measure, or $F_β$. Generally speaking, by averaging basic scores, we obtain a score that is intermediate in terms of values. However, there is no guarantee that these scores lead to meaningful rankings and no guarantee that the rankings are good tradeoffs between these base scores. Given the ubiquity of $F_β$ scores in the literature, some clarification is in order. Concretely: (1) We establish that $F_β$-induced rankings are meaningful and define a shortest path between precision- and recall-induced rankings. (2) We frame the problem of finding a tradeoff between two scores as an optimization problem expressed with Kendall rank correlations. We show that $F_1$ and its skew-insensitive version are far from being optimal in that regard. (3) We provide theoretical tools and a closed-form expression to find the optimal value for $β$ for any distribution or set of performances, and we illustrate their use on six case studies. Code is available at https://github.com/pierard/cvpr-2026-optimal-tradeoff-precision-recall.

---

### What Is the Optimal Ranking Score Between Precision and Recall? We Can Always Find It and It Is Rarely $F_1$

Authors: Sébastien Piérard, Adrien Deliège, Marc Van Droogenbroeck
Published: 2025-11-27
Categories: cs.PF, cs.AI, cs.CV, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.22442v1

Ranking methods or models based on their performance is of prime importance but is tricky because performance is fundamentally multidimensional. In the case of classification, precision and recall are scores with probabilistic interpretations that are both important to consider and complementary. The rankings induced by these two scores are often in partial contradiction. In practice, therefore, it is extremely useful to establish a compromise between the two views to obtain a single, global ranking. Over the last fifty years or so,it has been proposed to take a weighted harmonic mean, known as the F-score, F-measure, or $F_β$. Generally speaking, by averaging basic scores, we obtain a score that is intermediate in terms of values. However, there is no guarantee that these scores lead to meaningful rankings and no guarantee that the rankings are good tradeoffs between these base scores. Given the ubiquity of $F_β$ scores in the literature, some clarification is in order. Concretely: (1) We establish that $F_β$-induced rankings are meaningful and define a shortest path between precision- and recall-induced rankings. (2) We frame the problem of finding a tradeoff between two scores as an optimization problem expressed with Kendall rank correlations. We show that $F_1$ and its skew-insensitive version are far from being optimal in that regard. (3) We provide theoretical tools and a closed-form expression to find the optimal value for $β$ for any distribution or set of performances, and we illustrate their use on six case studies.

---

### GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents

Authors: Xinyu Zhang, Yixin Wu, Boyang Zhang, Chenhao Lin, Chao Shen, Michael Backes, Yang Zhang
Published: 2025-11-27
Categories: cs.CR, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.22441v1

Images shared on social media often expose geographic cues. While early geolocation methods required expert effort and lacked generalization, the rise of Large Vision Language Models (LVLMs) now enables accurate geolocation even for ordinary users. However, existing approaches are not optimized for this task. To explore the full potential and associated privacy risks, we present Geo-Detective, an agent that mimics human reasoning and tool use for image geolocation inference. It follows a procedure with four steps that adaptively selects strategies based on image difficulty and is equipped with specialized tools such as visual reverse search, which emulates how humans gather external geographic clues. Experimental results show that GEO-Detective outperforms baseline large vision language models (LVLMs) overall, particularly on images lacking visible geographic features. In country level geolocation tasks, it achieves an improvement of over 11.1% compared to baseline LLMs, and even at finer grained levels, it still provides around a 5.2% performance gain. Meanwhile, when equipped with external clues, GEO-Detective becomes more likely to produce accurate predictions, reducing the "unknown" prediction rate by more than 50.6%. We further explore multiple defense strategies and find that Geo-Detective exhibits stronger robustness, highlighting the need for more effective privacy safeguards.

---

### ABounD: Adversarial Boundary-Driven Few-Shot Learning for Multi-Class Anomaly Detection

Authors: Runzhi Deng, Yundi Hu, Xinshuang Zhang, Zhao Wang, Xixi Liu, Wang-Zhou Dai, Caifeng Shan, Fang Zhao
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22436v2

Few-shot multi-class industrial anomaly detection identifies diverse defects across multiple categories using a single unified model and limited normal samples. Although vision-language models offer strong generalization, modeling multiple distinct category manifolds concurrently without actual anomalous data causes feature space collapse and cross-class interference. Consequently, existing methods often fail to balance scalability and precision, leading to either isolated single-class retraining or excessively loose decision margins. To address this limitation, we present a one-for-all learning framework called ABounD that unites semantic concept anchoring with geometric boundary optimization. This method employs two lightweight mechanisms to resolve multi-class ambiguity. First, the Dynamic Concept Fusion module generates class-adaptive semantic anchors via query-aware hierarchical calibration, disentangling overlapping category concepts. Second, using these anchors, the Adversarial Boundary Forging module constructs a tight, class-tailored decision margin by synthesizing adversarial boundary-level fence features to prevent cross-class boundary blurring. Optimized in a single stage, ABounD removes the requirement for isolated per-category retraining in few-shot settings. Experiments on seven industrial benchmarks show that the proposed method achieves state-of-the-art detection and localization performance for multi-class few-shot anomaly detection while maintaining low computational costs during training and inference.

---

### ABounD: Adversarial Boundary-Driven Few-Shot Learning for Multi-Class Anomaly Detection

Authors: Runzhi Deng, Yundi Hu, Xinshuang Zhang, Zhao Wang, Xixi Liu, Wang-Zhou Dai, Caifeng Shan, Fang Zhao
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22436v1

Few-shot multi-class industrial anomaly detection remains a challenging task. Vision-language models need to be both category-adaptive and sharply discriminative, yet data scarcity often blurs the boundary between normal and abnormal states. This ambiguity leads to missed subtle defects and the rejection of atypical normal samples. We propose ABounD, an Adversarial Boundary-Driven few-shot learning for multi-class anomaly detection, which is a unified learning framework that integrates semantic concept learning with decision boundary shaping. The Dynamic Concept Fusion (DCF) module produces class-adaptive prompts by fusing generalizable priors with class-specific cues, conditioned on image features. Meanwhile, Adversarial Boundary Forging (ABF) sculpts a more precise decision margin by generating boundary-level fence features via PGD-style perturbations. Training is conducted in a single stage under a Concept-Boundary Loss, where ABF provides the main supervisory signal and semantic-spatial regularizers stabilize the optimization. This synergy yields a decision boundary that closely follows normal data while preserving flexibility and robust semantic alignment. Experiments on MVTec-AD and VisA datasets demonstrate state-of-the-art performance in the task of few-shot multi-class anomaly detection.

---

### PISA: Prioritized Invariant Subgraph Aggregation for Out-of-Distribution Generalization on Graphs

Authors: Ali Ghasemi, Farooq Ahmad Wani, Maria Sofia Bucarelli, Fabrizio Silvestri
Published: 2025-11-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.22435v3

Invariant learning on graphs aims to build predictors that rely on causal substructures rather than on environment-specific shortcuts. Current methods extract either a single invariant subgraph (CIGA) or, more recently, a set of diverse invariant subgraphs (SuGAr). We observe that the second half of the multi-subgraph pipeline, "how the extracted subgraphs are combined" has gone essentially unexamined; existing methods average branch predictions uniformly or select one greedily. We show that this is precisely where accuracy is lost. A minimum-variance combination argument establishes that uniform averaging is optimal only when every branch carries the same total error covariance with the ensemble---a knife edge balance that second order exchangeability guarantees and that the diversity regularizer used to obtain multiple subgraphs is explicitly designed to break. We then show that invariance is closed under post composition; because the branches are frozen and read the graph only through their invariant subgraphs, any measurable aggregator of their outputs remains invariant, and the aggregate's environment gap is bounded by the branches' residual invariance violation uniformly over aggregators. Learning the combination rule by plain empirical risk minimization is therefore safe, and aggregator capacity trades off against estimation error rather than robustness. PISA instantiates this with a lightweight instance-conditional MLP over stacked branch logits, trained on frozen branches at negligible cost. Across 15 synthetic and real benchmarks, PISA improves the average over the strongest prior method by 2.96 points on synthetic shifts and 1.74 points on realistic shifts, with per-dataset gains up to 5.90 points, and nearly doubles SuGAr's improvement over ERM on the six DrugOOD tasks (from +2.76 to +5.07 ROC-AUC).

---

### PISA: Prioritized Invariant Subgraph Aggregation

Authors: Ali Ghasemi, Farooq Ahmad Wani, Maria Sofia Bucarelli, Fabrizio Silvestri
Published: 2025-11-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.22435v1

Recent work has extended the invariance principle for out-of-distribution (OOD) generalization from Euclidean to graph data, where challenges arise due to complex structures and diverse distribution shifts in node attributes and topology. To handle these, Chen et al. proposed CIGA (Chen et al., 2022b), which uses causal modeling and an information-theoretic objective to extract a single invariant subgraph capturing causal features. However, this single-subgraph focus can miss multiple causal patterns. Liu et al. (2025) addressed this with SuGAr, which learns and aggregates diverse invariant subgraphs via a sampler and diversity regularizer, improving robustness but still relying on simple uniform or greedy aggregation. To overcome this, the proposed PISA framework introduces a dynamic MLP-based aggregation that prioritizes and combines subgraph representations more effectively. Experiments on 15 datasets, including DrugOOD (Ji et al., 2023), show that PISA achieves up to 5% higher classification accuracy than prior methods.

---

### FastFHE: Packing-Scalable and Depthwise-Separable CNN Inference Over FHE

Authors: Wenbo Song, Xinxin Fan, Quanliang Jing, Shaoye Luo, Wenqi Wei, Chi Lin, Yunfeng Lu, Ling Liu
Published: 2025-11-27
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.22434v1

The deep learning (DL) has been penetrating daily life in many domains, how to keep the DL model inference secure and sample privacy in an encrypted environment has become an urgent and increasingly important issue for various security-critical applications. To date, several approaches have been proposed based on the Residue Number System variant of the Cheon-Kim-Kim-Song (RNS-CKKS) scheme. However, they all suffer from high latency, which severely limits the applications in real-world tasks. Currently, the research on encrypted inference in deep CNNs confronts three main bottlenecks: i) the time and storage costs of convolution calculation; ii) the time overhead of huge bootstrapping operations; and iii) the consumption of circuit multiplication depth. Towards these three challenges, we in this paper propose an efficient and effective mechanism FastFHE to accelerate the model inference while simultaneously retaining high inference accuracy over fully homomorphic encryption. Concretely, our work elaborates four unique novelties. First, we propose a new scalable ciphertext data-packing scheme to save the time and storage consumptions. Second, we work out a depthwise-separable convolution fashion to degrade the computation load of convolution calculation. Third, we figure out a BN dot-product fusion matrix to merge the ciphertext convolutional layer with the batch-normalization layer without incurring extra multiplicative depth. Last but not least, we adopt the low-degree Legendre polynomial to approximate the nonlinear smooth activation function SiLU under the guarantee of tiny accuracy error before and after encrypted inference. Finally, we execute multi-facet experiments to verify the efficiency and effectiveness of our proposed approach.

---

### SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition

Authors: Hongda Liu, Yunfan Liu, Changlu Wang, Yunlong Wang, Zhenan Sun
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22433v3

Recent advances in skeleton-based action recognition increasingly leverage semantic priors from Large Language Models (LLMs) to enrich skeletal representations. However, the LLM is typically queried in isolation from the recognition model and receives no performance feedback. As a result, it often fails to deliver the targeted discriminative cues critical to distinguish similar actions. To overcome these limitations, we propose SkeletonAgent, a novel framework that bridges the recognition model and the LLM through two cooperative agents, i.e., Questioner and Selector. Specifically, the Questioner identifies the most frequently confused classes and supplies them to the LLM as context for more targeted guidance. Conversely, the Selector parses the LLM's response to extract precise joint-level constraints and feeds them back to the recognizer, enabling finer-grained cross-modal alignment. Comprehensive evaluations on five benchmarks, including NTU RGB+D, NTU RGB+D 120, Kinetics-Skeleton, FineGYM, and UAV-Human, demonstrate that SkeletonAgent consistently outperforms state-of-the-art benchmark methods. The code is available at https://github.com/firework8/SkeletonAgent.

---

### SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition

Authors: Hongda Liu, Yunfan Liu, Changlu Wang, Yunlong Wang, Zhenan Sun
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22433v1

Recent advances in skeleton-based action recognition increasingly leverage semantic priors from Large Language Models (LLMs) to enrich skeletal representations. However, the LLM is typically queried in isolation from the recognition model and receives no performance feedback. As a result, it often fails to deliver the targeted discriminative cues critical to distinguish similar actions. To overcome these limitations, we propose SkeletonAgent, a novel framework that bridges the recognition model and the LLM through two cooperative agents, i.e., Questioner and Selector. Specifically, the Questioner identifies the most frequently confused classes and supplies them to the LLM as context for more targeted guidance. Conversely, the Selector parses the LLM's response to extract precise joint-level constraints and feeds them back to the recognizer, enabling finer-grained cross-modal alignment. Comprehensive evaluations on five benchmarks, including NTU RGB+D, NTU RGB+D 120, Kinetics-Skeleton, FineGYM, and UAV-Human, demonstrate that SkeletonAgent consistently outperforms state-of-the-art benchmark methods. The code is available at https://github.com/firework8/SkeletonAgent.

---

### Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation

Authors: Weining Ren, Hongjun Wang, Xiao Tan, Kai Han
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22429v1

We present Fin3R, a simple, effective, and general fine-tuning method for feed-forward 3D reconstruction models. The family of feed-forward reconstruction model regresses pointmap of all input images to a reference frame coordinate system, along with other auxiliary outputs, in a single forward pass. However, we find that current models struggle with fine geometry and robustness due to (\textit{i}) the scarcity of high-fidelity depth and pose supervision and (\textit{ii}) the inherent geometric misalignment from multi-view pointmap regression. Fin3R jointly tackles two issues with an extra lightweight fine-tuning step. We freeze the decoder, which handles view matching, and fine-tune only the image encoder-the component dedicated to feature extraction. The encoder is enriched with fine geometric details distilled from a strong monocular teacher model on large, unlabeled datasets, using a custom, lightweight LoRA adapter. We validate our method on a wide range of models, including DUSt3R, MASt3R, CUT3R, and VGGT. The fine-tuned models consistently deliver sharper boundaries, recover complex structures, and achieve higher geometric accuracy in both single- and multi-view settings, while adding only the tiny LoRA weights, which leave test-time memory and latency virtually unchanged. Project page: \href{http://visual-ai.github.io/fin3r}{https://visual-ai.github.io/fin3r}

---

### Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models

Authors: Minghao Yin, Yukang Cao, Kai Han
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22425v4

We present WUKONG, a novel training-free framework for high-fidelity textured 3D morphing that takes a pair of source and target prompts (image or text) as input. Unlike conventional methods -- which rely on manual correspondence matching and deformation trajectory estimation (limiting generalization and requiring costly preprocessing) -- WUKONG leverages the generative prior of flow-based transformers to produce high-fidelity 3D transitions with rich texture details. To ensure smooth shape transitions, we exploit the inherent continuity of flow-based generative processes and formulate morphing as an optimal transport barycenter problem. We further introduce a sequential initialization strategy to prevent abrupt geometric distortions and preserve identity coherence. For faithful texture preservation, we propose a similarity-guided semantic consistency mechanism that selectively retains high-frequency details and enables precise control over blending dynamics. This empowers WUKONG to support both global texture transitions and identity-preserving texture morphing, catering to diverse generation needs. Extensive quantitative and qualitative evaluations demonstrate that WUKONG significantly outperforms state-of-the-art methods, achieving superior results across diverse geometry and texture variations.

---

### Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models

Authors: Minghao Yin, Yukang Cao, Kai Han
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22425v1

We present WUKONG, a novel training-free framework for high-fidelity textured 3D morphing that takes a pair of source and target prompts (image or text) as input. Unlike conventional methods -- which rely on manual correspondence matching and deformation trajectory estimation (limiting generalization and requiring costly preprocessing) -- WUKONG leverages the generative prior of flow-based transformers to produce high-fidelity 3D transitions with rich texture details. To ensure smooth shape transitions, we exploit the inherent continuity of flow-based generative processes and formulate morphing as an optimal transport barycenter problem. We further introduce a sequential initialization strategy to prevent abrupt geometric distortions and preserve identity coherence. For faithful texture preservation, we propose a similarity-guided semantic consistency mechanism that selectively retains high-frequency details and enables precise control over blending dynamics. This avoids common artifacts like oversmoothing while maintaining semantic fidelity. Extensive quantitative and qualitative evaluations demonstrate that WUKONG significantly outperforms state-of-the-art methods, achieving superior results across diverse geometry and texture variations.

---

### MATCH: Engineering Transparent and Controllable Conversational XAI Systems through Composable Building Blocks

Authors: Sebe Vanbrabant, Gustavo Rovelo Ruiz, Davy Vanacken
Published: 2025-11-27
Categories: cs.HC, cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2511.22420v1

While the increased integration of AI technologies into interactive systems enables them to solve an increasing number of tasks, the black-box problem of AI models continues to spread throughout the interactive system as a whole. Explainable AI (XAI) techniques can make AI models more accessible by employing post-hoc methods or transitioning to inherently interpretable models. While this makes individual AI models clearer, the overarching system architecture remains opaque. This challenge not only pertains to standard XAI techniques but also to human examination and conversational XAI approaches that need access to model internals to interpret them correctly and completely. To this end, we propose conceptually representing such interactive systems as sequences of structural building blocks. These include the AI models themselves, as well as control mechanisms grounded in literature. The structural building blocks can then be explained through complementary explanatory building blocks, such as established XAI techniques like LIME and SHAP. The flow and APIs of the structural building blocks form an unambiguous overview of the underlying system, serving as a communication basis for both human and automated agents, thus aligning human and machine interpretability of the embedded AI models. In this paper, we present our flow-based approach and a selection of building blocks as MATCH: a framework for engineering Multi-Agent Transparent and Controllable Human-centered systems. This research contributes to the field of (conversational) XAI by facilitating the integration of interpretability into existing interactive systems.

---

### StyleFusion360: View-Consistent Head Stylization via Adaptive Style Modulation

Authors: Furkan Guzelant, Arda Goktogan, Tarık Kaya, Aysegul Dundar
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22411v2

3D head stylization enables expressive reimagining of human faces for creative visual experiences in digital media. Existing 3D-aware methods often require computationally intensive optimization or per-style fine-tuning, limiting flexibility and user control. To overcome these challenges, we introduce StyleFusion360, a diffusion-based framework for multi-view consistent, identity-preserving 3D head stylization from a single style reference image, without per-style training. Our approach enhances the Style Fusion Attention mechanism with a style-conditioned key modulation mechanism that aligns content and style representations for fine-grained and controllable stylization. We further provide a user-controllable slider for adjusting stylization intensity. In addition, StyleFusion360 supports local multi-edit stylization, enabling targeted edits such as modifying hair or eyes independently. Extensive experiments on FFHQ and RenderMe360 demonstrate that StyleFusion360 produces high-quality, controllable, and visually compelling stylizations, outperforming state-of-the-art GAN- and diffusion-based methods across diverse style domains.

---

### DiffStyle360: Diffusion-Based 360° Head Stylization via Style Fusion Attention

Authors: Furkan Guzelant, Arda Goktogan, Tarık Kaya, Aysegul Dundar
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22411v1

3D head stylization has emerged as a key technique for reimagining realistic human heads in various artistic forms, enabling expressive character design and creative visual experiences in digital media. Despite the progress in 3D-aware generation, existing 3D head stylization methods often rely on computationally expensive optimization or domain-specific fine-tuning to adapt to new styles. To address these limitations, we propose DiffStyle360, a diffusion-based framework capable of producing multi-view consistent, identity-preserving 3D head stylizations across diverse artistic domains given a single style reference image, without requiring per-style training. Building upon the 3D-aware DiffPortrait360 architecture, our approach introduces two key components: the Style Appearance Module, which disentangles style from content, and the Style Fusion Attention mechanism, which adaptively balances structure preservation and stylization fidelity in the latent space. Furthermore, we employ a 3D GAN-generated multi-view dataset for robust fine-tuning and introduce a temperaturebased key scaling strategy to control stylization intensity during inference. Extensive experiments on FFHQ and RenderMe360 demonstrate that DiffStyle360 achieves superior style quality, outperforming state-of-the-art GAN- and diffusion-based stylization methods across challenging style domains.

---

### Improving Stochastic Action-Constrained Reinforcement Learning via Truncated Distributions

Authors: Roland Stolz, Michael Eichelbeck, Matthias Althoff
Published: 2025-11-27
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2511.22406v1

In reinforcement learning (RL), it is often advantageous to consider additional constraints on the action space to ensure safety or action relevance. Existing work on such action-constrained RL faces challenges regarding effective policy updates, computational efficiency, and predictable runtime. Recent work proposes to use truncated normal distributions for stochastic policy gradient methods. However, the computation of key characteristics, such as the entropy, log-probability, and their gradients, becomes intractable under complex constraints. Hence, prior work approximates these using the non-truncated distributions, which severely degrades performance. We argue that accurate estimation of these characteristics is crucial in the action-constrained RL setting, and propose efficient numerical approximations for them. We also provide an efficient sampling strategy for truncated policy distributions and validate our approach on three benchmark environments, which demonstrate significant performance improvements when using accurate estimations.

---

### UAV-MM3D: A Large-Scale Synthetic Benchmark for 3D Perception of Unmanned Aerial Vehicles with Multi-Modal Data

Authors: Longkun Zou, Jiale Wang, Rongqin Liang, Hai Wu, Ke Chen, Yaowei Wang
Published: 2025-11-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.22404v1

Accurate perception of UAVs in complex low-altitude environments is critical for airspace security and related intelligent systems. Developing reliable solutions requires large-scale, accurately annotated, and multimodal data. However, real-world UAV data collection faces inherent constraints due to airspace regulations, privacy concerns, and environmental variability, while manual annotation of 3D poses and cross-modal correspondences is time-consuming and costly. To overcome these challenges, we introduce UAV-MM3D, a high-fidelity multimodal synthetic dataset for low-altitude UAV perception and motion understanding. It comprises 400K synchronized frames across diverse scenes (urban areas, suburbs, forests, coastal regions) and weather conditions (clear, cloudy, rainy, foggy), featuring multiple UAV models (micro, small, medium-sized) and five modalities - RGB, IR, LiDAR, Radar, and DVS (Dynamic Vision Sensor). Each frame provides 2D/3D bounding boxes, 6-DoF poses, and instance-level annotations, enabling core tasks related to UAVs such as 3D detection, pose estimation, target tracking, and short-term trajectory forecasting. We further propose LGFusionNet, a LiDAR-guided multimodal fusion baseline, and a dedicated UAV trajectory prediction baseline to facilitate benchmarking. With its controllable simulation environment, comprehensive scenario coverage, and rich annotations, UAV3D offers a public benchmark for advancing 3D perception of UAVs.

---

### Mapping Clinical Doubt: Locating Linguistic Uncertainty in LLMs

Authors: Srivarshinee Sridhar, Raghav Kaushik Ravi, Kripabandhu Ghosh
Published: 2025-11-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.22402v1

Large Language Models (LLMs) are increasingly used in clinical settings, where sensitivity to linguistic uncertainty can influence diagnostic interpretation and decision-making. Yet little is known about where such epistemic cues are internally represented within these models. Distinct from uncertainty quantification, which measures output confidence, this work examines input-side representational sensitivity to linguistic uncertainty in medical text. We curate a contrastive dataset of clinical statements varying in epistemic modality (e.g., 'is consistent with' vs. 'may be consistent with') and propose Model Sensitivity to Uncertainty (MSU), a layerwise probing metric that quantifies activation-level shifts induced by uncertainty cues. Our results show that LLMs exhibit structured, depth-dependent sensitivity to clinical uncertainty, suggesting that epistemic information is progressively encoded in deeper layers. These findings reveal how linguistic uncertainty is internally represented in LLMs, offering insight into their interpretability and epistemic reliability.

---

### Asking like Socrates: Socrates helps VLMs understand remote sensing images

Authors: Run Shao, Ziyu Li, Zhaoyang Zhang, Linrui Xu, Xinran He, Hongyuan Yuan, Bolei He, Yongxing Dai, Yiming Yan, Yijun Chen, Wang Guo, Haifeng Li
Published: 2025-11-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.22396v2

Recent multimodal reasoning models, inspired by DeepSeek-R1, have significantly advanced vision-language systems. However, in remote sensing (RS) tasks, we observe widespread pseudo reasoning: models narrate the process of reasoning rather than genuinely reason toward the correct answer based on visual evidence. We attribute this to the Glance Effect, where a single, coarse perception of large-scale RS imagery results in incomplete understanding and reasoning based on linguistic self-consistency instead of visual evidence. To address this, we propose RS-EoT (Remote Sensing Evidence-of-Thought), a language-driven, iterative visual evidence-seeking paradigm. To instill this paradigm, we propose SocraticAgent, a self-play multi-agent system that synthesizes reasoning traces via alternating cycles of reasoning and visual inspection. To enhance and generalize these patterns, we propose a two-stage progressive RL strategy: first, RL on fine-grained Grounding tasks to enhance RS-EoT capabilities, followed by RL on RS VQA to generalize to broader understanding scenarios. Experiments show RS-EoT achieves state-of-the-art performance on multiple RS VQA and grounding benchmarks. Analyses reveal clear iterative cycles of reasoning and evidence seeking, confirming RS-EoT mitigates the Glance Effect and enables genuine evidence-grounded reasoning. Our code, data, and models are available at https://geox-lab.github.io/Asking_like_Socrates

---

### Asking like Socrates: Socrates helps VLMs understand remote sensing images

Authors: Run Shao, Ziyu Li, Zhaoyang Zhang, Linrui Xu, Xinran He, Hongyuan Yuan, Bolei He, Yongxing Dai, Yiming Yan, Yijun Chen, Wang Guo, Haifeng Li
Published: 2025-11-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.22396v1

Recent multimodal reasoning models, inspired by DeepSeek-R1, have significantly advanced vision-language systems. However, in remote sensing (RS) tasks, we observe widespread pseudo reasoning: models narrate the process of reasoning rather than genuinely reason toward the correct answer based on visual evidence. We attribute this to the Glance Effect, where a single, coarse perception of large-scale RS imagery results in incomplete understanding and reasoning based on linguistic self-consistency instead of visual evidence. To address this, we propose RS-EoT (Remote Sensing Evidence-of-Thought), a language-driven, iterative visual evidence-seeking paradigm. To instill this paradigm, we propose SocraticAgent, a self-play multi-agent system that synthesizes reasoning traces via alternating cycles of reasoning and visual inspection. To enhance and generalize these patterns, we propose a two-stage progressive RL strategy: first, RL on fine-grained Grounding tasks to enhance RS-EoT capabilities, followed by RL on RS VQA to generalize to broader understanding scenarios. Experiments show RS-EoT achieves state-of-the-art performance on multiple RS VQA and grounding benchmarks. Analyses reveal clear iterative cycles of reasoning and evidence seeking, confirming RS-EoT mitigates the Glance Effect and enables genuine evidence-grounded reasoning. Our code, data, and models are available at https://geox-lab.github.io/Asking_like_Socrates

---

### TS2Vec-Ensemble: An Enhanced Self-Supervised Framework for Time Series Forecasting

Authors: Ganeshan Niroshan, Uthayasanker Thayasivam
Published: 2025-11-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.22395v1

Self-supervised representation learning, particularly through contrastive methods like TS2Vec, has advanced the analysis of time series data. However, these models often falter in forecasting tasks because their objective functions prioritize instance discrimination over capturing the deterministic patterns, such as seasonality and trend, that are critical for accurate prediction. This paper introduces TS2Vec-Ensemble, a novel hybrid framework designed to bridge this gap. Our approach enhances the powerful, implicitly learned dynamics from a pretrained TS2Vec encoder by fusing them with explicit, engineered time features that encode periodic cycles. This fusion is achieved through a dual-model ensemble architecture, where two distinct regression heads -- one focused on learned dynamics and the other on seasonal patterns -- are combined using an adaptive weighting scheme. The ensemble weights are optimized independently for each forecast horizon, allowing the model to dynamically prioritize short-term dynamics or long-term seasonality as needed. We conduct extensive experiments on the ETT benchmark datasets for both univariate and multivariate forecasting. The results demonstrate that TS2Vec-Ensemble consistently and significantly outperforms the standard TS2Vec baseline and other state-of-the-art models, validating our hypothesis that a hybrid of learned representations and explicit temporal priors is a superior strategy for long-horizon time series forecasting.

---

### Who is Afraid of Minimal Revision?

Authors: Edoardo Baccini, Zoé Christoff, Nina Gierasimczuk, Rineke Verbrugge
Published: 2025-11-27
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2511.22386v1

The principle of minimal change in belief revision theory requires that, when accepting new information, one keeps one's belief state as close to the initial belief state as possible. This is precisely what the method known as minimal revision does. However, unlike less conservative belief revision methods, minimal revision falls short in learning power: It cannot learn everything that can be learned by other learning methods. We begin by showing that, despite this limitation, minimal revision is still a successful learning method in a wide range of situations. Firstly, it can learn any problem that is finitely identifiable. Secondly, it can learn with positive and negative data, as long as one considers finitely many possibilities. We then characterize the prior plausibility assignments (over finitely many possibilities) that enable one to learn via minimal revision, and do the same for conditioning and lexicographic upgrade. Finally, we show that not all of our results still hold when learning from possibly erroneous information.

---

### Graded Distributed Belief

Authors: Emiliano Lorini, Dmitry Rozplokhas
Published: 2025-11-27
Categories: cs.LO, cs.AI
arXiv: https://arxiv.org/abs/2511.22381v1

We introduce a new logic of graded distributed belief that allows us to express the fact that a group of agents distributively believe that a certain fact holds with at least strength k. We interpret our logic by means of computationally grounded semantics relying on the concept of belief base. The strength of the group's distributed belief is directly computed from the group's belief base after having merged its members' individual belief bases. We illustrate our logic with an intuitive example, formalizing the notion of epistemic disagreement. We also provide a sound and complete Hilbert-style axiomatization, decidability result obtained via filtration, and a tableaux-based decision procedure that allows us to state PSPACE-completeness for our logic.

---