# Research Papers — 2025-12 · bundle page 157 of 175 > Full-text markdown of papers #7801–7850 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-12/page/157 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/156.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/158.md) ### Different types of syntactic agreement recruit the same units within large language models Authors: Daria Kryvosheieva, Andrea de Varda, Evelina Fedorenko, Greta Tuckute Published: 2025-12-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.03676v2 Large language models (LLMs) can reliably distinguish grammatical from ungrammatical sentences, but how grammatical knowledge is represented within the models remains an open question. We investigate whether different syntactic phenomena recruit shared or distinct components in LLMs. Using a functional localization approach inspired by cognitive neuroscience, we identify the LLM units most responsive to 67 English syntactic phenomena in seven open-weight models. These units are consistently recruited across sentences containing the phenomena and causally support the models' syntactic performance. Critically, different types of syntactic agreement (e.g., subject-verb, anaphor, determiner-noun) recruit overlapping sets of units, suggesting that agreement constitutes a meaningful functional category for LLMs. This pattern holds in English, Russian, and Chinese; and further, in a cross-lingual analysis of 57 diverse languages, structurally more similar languages share more units for subject-verb agreement. Taken together, these findings reveal that syntactic agreement-a critical marker of syntactic dependencies-constitutes a meaningful category within LLMs' representational spaces. --- ### ConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers Authors: Feice Huang, Zuliang Han, Xing Zhou, Yihuang Chen, Lifei Zhu, Haoqian Wang Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03673v1 Diffusion transformers have demonstrated strong capabilities in generating high-quality images. However, as model size increases, the growing memory footprint and inference latency pose significant challenges for practical deployment. Recent studies in large language models (LLMs) show that rotation-based techniques can smooth outliers and enable 4-bit quantization, but these approaches often incur substantial overhead and struggle with row-wise outliers in diffusion transformers. To address these challenges, we propose ConvRot, a group-wise rotation-based quantization method that leverages regular Hadamard transform (RHT) to suppress both row-wise and column-wise outliers while reducing complexity from quadratic to linear. Building on this, we design ConvLinear4bit, a plug-and-play module that integrates rotation, quantization, GEMM, and dequantization, enabling W4A4 inference without retraining and preserving visual quality. Experiments on FLUX.1-dev demonstrate a 2.26$\times$ speedup and 4.05$\times$ memory reduction while maintaining image fidelity. To our knowledge, this is the first application of rotation-based quantization for plug-and-play W4A4 inference in diffusion transformers. --- ### Evaluating Hydro-Science and Engineering Knowledge of Large Language Models Authors: Shiruo Hu, Wenbo Shan, Yingjia Li, Zhiqi Wan, Xinpeng Yu, Yunjia Qi, Haotian Xia, Yang Xiao, Dingxiao Liu, Jiaru Wang, Chenxu Gong, Ruixi Zhang et al. Published: 2025-12-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.03672v1 Hydro-Science and Engineering (Hydro-SE) is a critical and irreplaceable domain that secures human water supply, generates clean hydropower energy, and mitigates flood and drought disasters. Featuring multiple engineering objectives, Hydro-SE is an inherently interdisciplinary domain that integrates scientific knowledge with engineering expertise. This integration necessitates extensive expert collaboration in decision-making, which poses difficulties for intelligence. With the rapid advancement of large language models (LLMs), their potential application in the Hydro-SE domain is being increasingly explored. However, the knowledge and application abilities of LLMs in Hydro-SE have not been sufficiently evaluated. To address this issue, we propose the Hydro-SE LLM evaluation benchmark (Hydro-SE Bench), which contains 4,000 multiple-choice questions. Hydro-SE Bench covers nine subfields and enables evaluation of LLMs in aspects of basic conceptual knowledge, engineering application ability, and reasoning and calculation ability. The evaluation results on Hydro-SE Bench show that the accuracy values vary among 0.74 to 0.80 for commercial LLMs, and among 0.41 to 0.68 for small-parameter LLMs. While LLMs perform well in subfields closely related to natural and physical sciences, they struggle with domain-specific knowledge such as industry standards and hydraulic structures. Model scaling mainly improves reasoning and calculation abilities, but there is still great potential for LLMs to better handle problems in practical engineering application. This study highlights the strengths and weaknesses of LLMs for Hydro-SE tasks, providing model developers with clear training targets and Hydro-SE researchers with practical guidance for applying LLMs. --- ### Generative AI Practices, Literacy, and Divides: An Empirical Analysis in the Italian Context Authors: Beatrice Savoldi, Giuseppe Attanasio, Olga Gorodetskaya, Marta Marchiori Manerba, Elisa Bassignana, Silvia Casola, Matteo Negri, Tommaso Caselli, Luisa Bentivogli, Alan Ramponi, Arianna Muti, Nicoletta Balbo et al. Published: 2025-12-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.03671v2 The rise of generative AI (GenAI) chatbots accessible via conversational interfaces is transforming digital interactions and holds economic promise. However, these tools might deepen existing inequalities -- not only through uneven, socially stratified adoption, but through differentials in their purposeful, critical use. Drawing on original survey data from 1,906 Italian-speaking adults, we provide a comprehensive analysis of GenAI adoption, literacy, and usage patterns. Our findings show that GenAI is supporting diversified personal and professional activities and replacing traditional information-seeking tools. Yet less-educated and older individuals, and those with lower technology familiarity, are less likely to adopt it; 40% cite competence barriers as a key obstacle. Among users, AI training emerges as the primary predictor of purposeful, capital-enhancing engagement -- content creation, learning, and creativity enhancement -- while more passive, recreational uses (e.g., companionship, information seeking) remain insensitive to competence levels. We thus highlight digital literacy as a lever for how people leverage GenAI, not just whether they use it. Finally, gender operates as a persistent cross-cutting divide, shaping both adoption and usage frequency. These findings challenge the assumption that high accessibility translates into broadly shared gains. Rather, they offer a granular, multi-level account of emerging disparities in the GenAI era -- with implications for how this technology may ultimately drive outcomes and benefit divides. --- ### Colon-X: Advancing Intelligent Colonoscopy toward Clinical Reasoning Authors: Ge-Peng Ji, Jingyi Liu, Deng-Ping Fan, Huazhu Fu, Nick Barnes Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03667v2 In this study, we present Colon-X, an open initiative aimed at advancing multimodal intelligence in colonoscopy. We begin by constructing ColonVQA, the most comprehensive multimodal dataset ever built for colonoscopy, featuring over 1.1M+ visual question answering entries across 76 clinical findings and 18 multimodal tasks. Beyond serving as a community-wide data foundation, we further investigate a critical yet underexplored transition in colonoscopy - evolving from multimodal understanding to clinical reasoning: (a) To capture the current landscape of multimodal understanding behaviors, we systematically assess the generalizability of 22 multimodal large language models and examine their reliability under human-induced perturbations. The results reveal that clinical outputs from leading MLLMs remain far from robust and trustworthy. (b) To narrow this gap, we further explore reasoning-centric intelligence tailored for colonoscopy. Specifically, we curate ColonReason, a clinically grounded reasoning dataset annotated through a multi-agent debating pipeline, and develop ColonR1, the first R1-styled model that mitigates reward information collapse through task-adaptive rewards and gradient-stable policy optimization. Under data-scarce conditions, our ColonR1 achieves 56.61% overall accuracy, outperforming supervised fine-tuning by 25.22%, and sets a new reasoning-enabled baseline for multimodal colonoscopy analysis. All data and model resources are publicly available at https://github.com/ai4colonoscopy/Colon-X. --- ### ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos Authors: Qi'ao Xu, Tianwen Qian, Yuqian Fu, Kailing Li, Yang Jiao, Jiacheng Zhang, Xiaoling Wang, Liang He Published: 2025-12-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.03666v2 A core capability towards general embodied intelligence lies in localizing task-relevant objects from an egocentric perspective, formulated as Spatio-Temporal Video Grounding (STVG). Despite recent progress, existing STVG studies remain largely confined to object-centric and descriptive instructions, neglecting the task-oriented reasoning that is crucial for embodied agents to accomplish goal-directed interactions. To bridge this gap, we introduce \textbf{ToG-Bench}, the first task-oriented spatio-temporal video grounding benchmark for egocentric videos. ToG-Bench is characterized by three key features: (1) \textbf{Task-oriented Grounding}, which requires identifying and localizing objects based on intended tasks rather than straightforward descriptions; (2) \textbf{Explicit-Implicit Dual Grounding}, where target objects can be either explicitly mentioned or implicitly inferred by contextual reasoning; (3) \textbf{One-to-Many Grounding}, where a single instruction may correspond to multiple objects involved in task execution. Built upon videos sourced from ScanNet, ToG-Bench comprises 100 annotated clips with 2,704 task-oriented grounding instructions, constructed via a semi-automated pipeline that combines foundation model annotation and human refinement. In addition, we introduce a set of task-level evaluation metrics tailored for multi-object and explicit-implicit object grounding, and systematically benchmark seven state-of-the-art MLLMs. Extensive experiments reveal the intrinsic challenges of task-oriented STVG and substantial performance gaps across explicit-implicit and multi-object grounding, highlighting the difficulty of bridging perception and interaction in embodied scenarios. Data and code will be released at: \href{https://github.com/qaxuDev/ToG-Bench}{https://github.com/qaxuDev/ToG-Bench}.. --- ### Multi-Scale Visual Prompting for Lightweight Small-Image Classification Authors: Salim Khazem Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03663v1 Visual prompting has recently emerged as an efficient strategy to adapt vision models using lightweight, learnable parameters injected into the input space. However, prior work mainly targets large Vision Transformers and high-resolution datasets such as ImageNet. In contrast, small-image benchmarks like MNIST, Fashion-MNIST, and CIFAR-10 remain widely used in education, prototyping, and research, yet have received little attention in the context of prompting. In this paper, we introduce \textbf{Multi-Scale Visual Prompting (MSVP)}, a simple and generic module that learns a set of global, mid-scale, and local prompt maps fused with the input image via a lightweight $1 \times 1$ convolution. MSVP is backbone-agnostic, adds less than $0.02\%$ parameters, and significantly improves performance across CNN and Vision Transformer backbones. We provide a unified benchmark on MNIST, Fashion-MNIST, and CIFAR-10 using a simple CNN, ResNet-18, and a small Vision Transformer. Our method yields consistent improvements with negligible computational overhead. We further include ablations on prompt scales, fusion strategies, and backbone architectures, along with qualitative analyzes using prompt visualizations and Grad-CAM. Our results demonstrate that multi-scale prompting provides an effective inductive bias even on low-resolution images. --- ### Dynamically Scaled Activation Steering Authors: Alex Ferrando, Xavier Suau, Jordi Gonzàlez, Pau Rodriguez Published: 2025-12-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.03661v2 Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs, degrading model performance when steering is unnecessary. We introduce Dynamically Scaled Activation Steering (DSAS), a method-agnostic steering framework that decouples when to steer from how to steer. DSAS adaptively modulates the strength of existing steering transformations across layers and inputs, intervening strongly only when undesired behavior is detected. At generation time, DSAS computes context-dependent scaling factors that selectively adjust the strength of any steering method. We also show how DSAS can be jointly optimized end-to-end together with the steering function. When combined with existing steering methods, DSAS consistently improves the Pareto front with respect to steering alone, achieving a better trade-off between toxicity mitigation and utility preservation. We further demonstrate DSAS's generality by applying it to a text-to-image diffusion model, showing how adaptive steering allows the modulation of specific concepts. Finally, DSAS introduces minimal computational overhead while improving interpretability, pinpointing which tokens require steering and by how much. --- ### Cyclical Temporal Encoding and Hybrid Deep Ensembles for Multistep Energy Forecasting Authors: Salim Khazem, Houssam Kanso Published: 2025-12-03 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.03656v1 Accurate electricity consumption forecasting is essential for demand management and smart grid operations. This paper introduces a unified deep learning framework that integrates cyclical temporal encoding with hybrid LSTM-CNN architectures to enhance multistep energy forecasting. We systematically transform calendar-based attributes using sine cosine encodings to preserve periodic structure and evaluate their predictive relevance through correlation analysis. To exploit both long-term seasonal effects and short-term local patterns, we employ an ensemble model composed of an LSTM, a CNN, and a meta-learner of MLP regressors specialized for each forecast horizon. Using a one year national consumption dataset, we conduct an extensive experimental study including ablation analyses with and without cyclical encodings and calendar features and comparisons with established baselines from the literature. Results demonstrate consistent improvements across all seven forecast horizons, with our hybrid model achieving lower RMSE and MAE than individual architectures and prior methods. These findings confirm the benefit of combining cyclical temporal representations with complementary deep learning structures. To our knowledge, this is the first work to jointly evaluate temporal encodings, calendar-based features, and hybrid ensemble architectures within a unified short-term energy forecasting framework. --- ### Conditional updates of neural network weights for increased out of training performance Authors: Jan Saynisch-Wagner, Saran Rajendran Sari Published: 2025-12-03 Categories: cs.LG, physics.ao-ph, physics.data-an arXiv: https://arxiv.org/abs/2512.03653v1 This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main steps: 1) Retrain the neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. 2) Choose reasonable predictors and derive a regression between the predictors and the weight anomalies. 3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three use cases from the climate sciences, which include successful temporal, spatial and cross-domain extrapolations of neural networks. --- ### Optical Context Compression Is Just (Bad) Autoencoding Authors: Ivan Yee Lee, Cheng Yang, Taylor Berg-Kirkpatrick Published: 2025-12-03 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.03643v2 DeepSeek-OCR shows that rendered text can be reconstructed from a small number of vision tokens, sparking excitement about using vision as a compression medium for long textual contexts. But this pipeline requires rendering token embeddings to pixels and compressing from there -- discarding learned representations in favor of an image the vision encoder must then recover from. We ask whether this detour helps. Comparing DeepSeek-OCR's vision encoder against near-zero-parameter mean pooling and a learned hierarchical encoder, we find it does not. For reconstruction, simple direct methods match or surpass vision at every compression ratio. For language modeling, vision performs comparably to truncation -- a baseline that simply discards context -- and loses to the hierarchical encoder at every compression ratio. As expected, all compression methods outperform truncation for factual recall, but vision never surpasses the best direct baseline. The excitement around optical context compression outpaces the evidence. Code and checkpoints are available at https://github.com/ivnle/bad-autoencoding. --- ### MKSNet: Advanced Small Object Detection in Remote Sensing Imagery with Multi-Kernel and Dual Attention Mechanisms Authors: Jiahao Zhang, Xiao Zhao, Guangyu Gao Published: 2025-12-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.03640v1 Deep convolutional neural networks (DCNNs) have substantially advanced object detection capabilities, particularly in remote sensing imagery. However, challenges persist, especially in detecting small objects where the high resolution of these images and the small size of target objects often result in a loss of critical information in the deeper layers of conventional CNNs. Additionally, the extensive spatial redundancy and intricate background details typical in remote-sensing images tend to obscure these small targets. To address these challenges, we introduce Multi-Kernel Selection Network (MKSNet), a novel network architecture featuring a novel Multi-Kernel Selection mechanism. The MKS mechanism utilizes large convolutional kernels to effectively capture an extensive range of contextual information. This innovative design allows for adaptive kernel size selection, significantly enhancing the network's ability to dynamically process and emphasize crucial spatial details for small object detection. Furthermore, MKSNet also incorporates a dual attention mechanism, merging spatial and channel attention modules. The spatial attention module adaptively fine-tunes the spatial weights of feature maps, focusing more intensively on relevant regions while mitigating background noise. Simultaneously, the channel attention module optimizes channel information selection, improving feature representation and detection accuracy. Empirical evaluations on the DOTA-v1.0 and HRSC2016 benchmark demonstrate that MKSNet substantially surpasses existing state-of-the-art models in detecting small objects in remote sensing images. These results highlight MKSNet's superior ability to manage the complexities associated with multi-scale and high-resolution image data, confirming its effectiveness and innovation in remote sensing object detection. --- ### AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers Authors: Kohei Yamamoto, Kosuke Okusa Published: 2025-12-03 Categories: cs.SD, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.03637v2 Transformer-based audio self-supervised learning (SSL) models commonly use spectrograms, vision-style Transformers, and masked modeling objectives. However, convolutional patchification with temporal downsampling lowers the effective Nyquist frequency and introduces aliasing, while naïve low-pass filtering may remove task-relevant high-frequency cues. We present AaSP, an aliasing-aware self-supervised pre-training framework for audio spectrogram transformers. AaSP combines an aliasing-aware patch representation, teacher-student masked modeling, a cross-attention predictor, and multi-mask contrastive regularization to learn representations that integrate features from alias-prone modulation bands while remaining stable across masked views. Its patch-embedding module, Aliasing-aware Patch Embedding (AaPE), augments standard patch tokens with features from alias-prone modulation bands using a band-limited complex sinusoidal kernel with a two-sided exponential window. The kernel's frequency and decay parameters are estimated from the input, enabling adaptive subband analysis whose outputs are fused with standard patch tokens. We pre-train on AudioSet and evaluate the learned representations by fine-tuning and linear evaluation on acoustic/environmental, speech, and music recognition benchmarks. Under fine-tuning, the full AaSP framework achieves state-of-the-art results on AS-20K, ESC-50, and NSynth among compared self-supervised baselines, while remaining competitive elsewhere. Linear evaluation shows a similar trend, including gains on US8K and NSynth. Overall, AaSP learns representations that are more stable under aliasing-sensitive temporal perturbations and competitive for downstream transfer. --- ### AlignCheck: a Semantic Open-Domain Metric for Factual Consistency Assessment Authors: Ahmad Aghaebrahimian Published: 2025-12-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.03634v1 Large Language Models have significantly advanced natural language processing tasks, but remain prone to generating incorrect or misleading but plausible arguments. This issue, known as hallucination, is particularly concerning in high-stakes domains like clinical applications, where factual inaccuracies can have severe consequences. Existing evaluation metrics fail to adequately assess factual consistency and lack interpretability, making diagnosing and mitigating errors difficult. We propose an interpretable framework for factual consistency assessment for in-domain and open-domain texts to address these limitations. Our approach decomposes text into atomic facts and introduces a flexible, schema-free methodology. Unlike previous methods with an absolute metric, we incorporate a weighted metric to enhance factual evaluation. Additionally, we propose a mechanism to control assessment complexity in intricate domains. We benchmark our approach on popular general and clinical datasets and release our code to support fact-aware model training in future research. --- ### MemVerse: Multimodal Memory for Lifelong Learning Agents Authors: Junming Liu, Yifei Sun, Weihua Cheng, Haodong Lei, Yirong Chen, Licheng Wen, Xuemeng Yang, Daocheng Fu, Pinlong Cai, Nianchen Deng, Yi Yu, Shuyue Hu et al. Published: 2025-12-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.03627v2 Despite rapid progress in large-scale language and vision models, AI agents still suffer from a fundamental limitation: they cannot remember. Without reliable memory, agents catastrophically forget past experiences, struggle with long-horizon reasoning, and fail to operate coherently in multimodal or interactive environments. We introduce MemVerse, a model-agnostic, plug-and-play memory framework that bridges fast parametric recall with hierarchical retrieval-based memory, enabling scalable and adaptive multimodal intelligence. MemVerse maintains short-term memory for recent context while transforming raw multimodal experiences into structured long-term memories organized as hierarchical knowledge graphs. This design supports continual consolidation, adaptive forgetting, and bounded memory growth. To handle real-time demands, MemVerse introduces a periodic distillation mechanism that compresses essential knowledge from long-term memory into the parametric model, allowing fast, differentiable recall while preserving interpretability. Extensive experiments demonstrate that MemVerse significantly improves multimodal reasoning and continual learning efficiency, empowering agents to remember, adapt, and reason coherently across extended interactions. --- ### FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Features Authors: Zhigang Yang, Yuan Liu, Jiawei Zhang, Puning Zhang, Xinqiang Ma Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03625v1 Although the remarkable performance of deep neural networks (DNNs) in image classification, their vulnerability to adversarial attacks remains a critical challenge. Most existing detection methods rely on complex and poorly interpretable architectures, which compromise interpretability and generalization. To address this, we propose FeatureLens, a lightweight framework that acts as a lens to scrutinize anomalies in image features. Comprising an Image Feature Extractor (IFE) and shallow classifiers (e.g., SVM, MLP, or XGBoost) with model sizes ranging from 1,000 to 30,000 parameters, FeatureLens achieves high detection accuracy ranging from 97.8% to 99.75% in closed-set evaluation and 86.17% to 99.6% in generalization evaluation across FGSM, PGD, CW, and DAmageNet attacks, using only 51 dimensional features. By combining strong detection performance with excellent generalization, interpretability, and computational efficiency, FeatureLens offers a practical pathway toward transparent and effective adversarial defense. --- ### The promising potential of vision language models for the generation of textual weather forecasts Authors: Edward C. C. Steele, Dinesh Mane, Emilio Monti, Luis Orus, Rebecca Chantrill-Cheyette, Matthew Couch, Kirstine I. Dale, Simon Eaton, Govindarajan Rangarajan, Amir Majlesi, Steven Ramsdale, Michael Sharpe et al. Published: 2025-12-03 Categories: cs.LG, cs.AI, physics.ao-ph arXiv: https://arxiv.org/abs/2512.03623v1 Despite the promising capability of multimodal foundation models, their application to the generation of meteorological products and services remains nascent. To accelerate aspiration and adoption, we explore the novel use of a vision language model for writing the iconic Shipping Forecast text directly from video-encoded gridded weather data. These early results demonstrate promising scalable technological opportunities for enhancing production efficiency and service innovation within the weather enterprise and beyond. --- ### ReCamDriving: LiDAR-Free Camera-Controlled Video Synthesis for Novel Trajectories Authors: Yaokun Li, Shuaixian Wang, Mantang Guo, Jiehui Huang, Taojun Ding, Mu Hu, Kaixuan Wang, Shaojie Shen, Guang Tan Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03621v3 Synthesizing multi-pass videos is important for autonomous driving. While current repair-based methods often struggle with out-of-distribution artifacts, camera-controlled methods often produce 3D-inconsistent results due to sparse LiDAR cues. We propose ReCamDriving, a purely vision-based framework that achieves camera-controlled generation by leveraging dense, structurally complete 3DGS renderings as geometric guidance. Specifically, to prevent the model from overfitting to a trivial repair solution when conditioning on 3DGS renderings, we adopt a two-stage progressive training paradigm: the first stage uses camera poses for coarse control, while the second stage incorporates 3DGS renderings for fine-grained viewpoint and geometric guidance. Furthermore, to align training and inference camera transformation patterns, we propose a 3DGS-based cross-trajectory data curation strategy, enabling consistent lateral-trajectory supervision from single-pass videos. Based on this strategy, we construct the ParaDrive dataset, containing approximately 110K parallel-trajectory video pairs. Extensive experiments demonstrate that ReCamDriving achieves state-of-the-art camera controllability and structural consistency. --- ### SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting Authors: Hanxiu Zhang, Yue Zheng Published: 2025-12-03 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.03620v1 The protection of Intellectual Property (IP) in Large Language Models (LLMs) represents a critical challenge in contemporary AI research. While fingerprinting techniques have emerged as a fundamental mechanism for detecting unauthorized model usage, existing methods -- whether behavior-based or structural -- suffer from vulnerabilities such as false claim attacks or susceptible to weight manipulations. To overcome these limitations, we propose SELF, a novel intrinsic weight-based fingerprinting scheme that eliminates dependency on input and inherently resists false claims. SELF achieves robust IP protection through two key innovations: 1) unique, scalable and transformation-invariant fingerprint extraction via singular value and eigenvalue decomposition of LLM attention weights, and 2) effective neural network-based fingerprint similarity comparison based on few-shot learning and data augmentation. Experimental results demonstrate SELF maintains high IP infringement detection accuracy while showing strong robustness against various downstream modifications, including quantization, pruning, and fine-tuning attacks. Our code is available at https://github.com/HanxiuZhang/SELF_v2. --- ### LAMP: Language-Assisted Motion Planning for Controllable Video Generation Authors: Muhammed Burak Kizil, Enes Sanli, Niloy J. Mitra, Erkut Erdem, Aykut Erdem, Duygu Ceylan Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03619v4 Video generation has achieved remarkable progress in visual fidelity and controllability, enabling conditioning on text, layout, or motion. Among these, motion control - specifying object dynamics and camera trajectories - is essential for composing complex, cinematic scenes, yet existing interfaces remain limited. We introduce LAMP that leverages large language models (LLMs) as motion planners to translate natural language descriptions into explicit 3D trajectories for dynamic objects and (relatively defined) cameras. LAMP defines a motion domain-specific language (DSL), inspired by cinematography conventions. By harnessing program synthesis capabilities of LLMs, LAMP generates structured motion programs from natural language, which are deterministically mapped to 3D trajectories. We construct a large-scale procedural dataset pairing natural text descriptions with corresponding motion programs and 3D trajectories. Experiments demonstrate LAMP's improved performance in motion controllability and alignment with user intent compared to state-of-the-art alternatives establishing the first framework for generating both object and camera motions directly from natural language specifications. Code, models and data are available on our project page. --- ### CoGraM: Context-sensitive granular optimization method with rollback for robust model fusion Authors: Julius Lenz Published: 2025-12-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.03610v2 Merging neural networks without retraining is central to federated and distributed learning. Common methods such as weight averaging or Fisher merging often lose accuracy and are unstable across seeds. CoGraM (Contextual Granular Merging) is a multi-stage, context-sensitive, loss-based, and iterative optimization method across layers, neurons, and weight levels that aligns decisions with loss differences and thresholds and prevents harmful updates through rollback. CoGraM is an optimization method that addresses the weaknesses of methods such as Fisher and can significantly improve the merged network. --- ### KVNAND: Efficient On-Device Large Language Model Inference Using DRAM-Free In-Flash Computing Authors: Lishuo Deng, Shaojie Xu, Jinwu Chen, Changwei Yan, Jiajie Wang, Zhe Jiang, Weiwei Shan Published: 2025-12-03 Categories: cs.AR, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2512.03608v1 Deploying large language models (LLMs) on edge devices enables personalized agents with strong privacy and low cost. However, with tens to hundreds of billions of parameters, single-batch autoregressive inference suffers from extremely low arithmetic intensity, creating severe weight-loading and bandwidth pressures on resource-constrained platforms. Recent in-flash computing (IFC) solutions alleviate this bottleneck by co-locating weight-related linear computations in the decode phase with flash, yet still rely on DRAM for the key-value (KV) cache. As context length grows, the KV cache can exceed model weights in size, imposing prohibitive DRAM cost and capacity requirements. Attempts to offload KV cache to flash suffer from severe performance penalties. We propose KVNAND, the first DRAM-free, IFC-based architecture that stores both model weights and KV cache entirely in compute-enabled 3D NAND flash. KVNAND addresses the fundamental performance challenges of flash under intensive KV cache access by leveraging IFC for all memory-bound operations to reduce data transfer overhead, introducing head-group parallelism to boost throughput, and employing page-level KV cache mapping to align token access patterns with flash organization. In addition, we propose a design space exploration framework that evaluates discrete and compact KVNAND variants to balance weight and KV placement, automatically identifying the optimal design trade-off. These techniques mitigate latency, energy, and reliability concerns, turning flash into a practical medium for long-context KV storage. Evaluations on MHA 7B and GQA 70B LLMs show that KVNAND achieves 1.98\(\times\)/1.94\(\times\)/2.05\(\times\) geomean speedup at 128/1K/10K-token contexts compared to DRAM-equipped IFC designs and addresses out-of-memory failures at 100K context length. --- ### DeepRule: An Integrated Framework for Automated Business Rule Generation via Deep Predictive Modeling and Hybrid Search Optimization Authors: Yusen Wu, Xiaotie Deng Published: 2025-12-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.03607v1 This paper proposes DeepRule, an integrated framework for automated business rule generation in retail assortment and pricing optimization. Addressing the systematic misalignment between existing theoretical models and real-world economic complexities, we identify three critical gaps: (1) data modality mismatch where unstructured textual sources (e.g. negotiation records, approval documents) impede accurate customer profiling; (2) dynamic feature entanglement challenges in modeling nonlinear price elasticity and time-varying attributes; (3) operational infeasibility caused by multi-tier business constraints. Our framework introduces a tri-level architecture for above challenges. We design a hybrid knowledge fusion engine employing large language models (LLMs) for deep semantic parsing of unstructured text, transforming distributor agreements and sales assessments into structured features while integrating managerial expertise. Then a game-theoretic constrained optimization mechanism is employed to dynamically reconcile supply chain interests through bilateral utility functions, encoding manufacturer-distributor profit redistribution as endogenous objectives under hierarchical constraints. Finally an interpretable decision distillation interface leveraging LLM-guided symbolic regression to find and optimize pricing strategies and auditable business rules embeds economic priors (e.g. non-negative elasticity) as hard constraints during mathematical expression search. We validate the framework in real retail environments achieving higher profits versus systematic B2C baselines while ensuring operational feasibility. This establishes a close-loop pipeline unifying unstructured knowledge injection, multi-agent optimization, and interpretable strategy synthesis for real economic intelligence. --- ### Observation-driven correction of numerical weather prediction for marine winds Authors: Matteo Peduto, Qidong Yang, Jonathan Giezendanner, Devis Tuia, Sherrie Wang Published: 2025-12-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.03606v2 Accurate marine wind forecasts are essential for safe navigation, ship routing, and energy operations, yet they remain challenging because observations over the ocean are sparse, heterogeneous, and temporally variable. We present an observation-informed correction approach for global numerical weather prediction (NWP) of marine winds. Rather than forecasting winds directly, we learn local correction patterns by assimilating the latest in-situ observations to adjust the Global Forecast System (GFS) output. We propose ORCA (Observation-informed Real-time Correction with Attention), a transformer-based deep learning architecture that (i) handles irregular and time-varying observation sets through masking and set-based attention mechanisms, (ii) conditions predictions on recent observation--forecast pairs via cross-attention, and (iii) employs cyclical time embeddings and coordinate-aware location representations to enable single-pass inference at arbitrary spatial coordinates. We evaluate ORCA over the Atlantic Ocean using observations from the International Comprehensive Ocean-Atmosphere Data Set (ICOADS) as reference. ORCA reduces GFS 10-meter wind error at all lead times up to 48 hours, achieving 45% improvement at 1-hour lead time and 13% improvement at 48-hour lead time. Spatial analyses reveal the most persistent improvements along coastlines and shipping routes, where observations are most abundant. The tokenized architecture naturally accommodates heterogeneous observing platforms (ships, buoys, tide gauges, and coastal stations) and produces both site-specific predictions and basin-scale gridded products in a single forward pass. These results demonstrate a practical, low-latency post-processing approach that complements NWP by learning to correct systematic forecast errors. --- ### Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding Authors: Haoran Zhou, Gim Hee Lee Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03601v1 Recent advancements in foundation models for 2D vision have substantially improved the analysis of dynamic scenes from monocular videos. However, despite their strong generalization capabilities, these models often lack 3D consistency, a fundamental requirement for understanding scene geometry and motion, thereby causing severe spatial misalignment and temporal flickering in complex 3D environments. In this paper, we present Motion4D, a novel framework that addresses these challenges by integrating 2D priors from foundation models into a unified 4D Gaussian Splatting representation. Our method features a two-part iterative optimization framework: 1) Sequential optimization, which updates motion and semantic fields in consecutive stages to maintain local consistency, and 2) Global optimization, which jointly refines all attributes for long-term coherence. To enhance motion accuracy, we introduce a 3D confidence map that dynamically adjusts the motion priors, and an adaptive resampling process that inserts new Gaussians into under-represented regions based on per-pixel RGB and semantic errors. Furthermore, we enhance semantic coherence through an iterative refinement process that resolves semantic inconsistencies by alternately optimizing the semantic fields and updating prompts of SAM2. Extensive evaluations demonstrate that our Motion4D significantly outperforms both 2D foundation models and existing 3D-based approaches across diverse scene understanding tasks, including point-based tracking, video object segmentation, and novel view synthesis. Our code is available at https://hrzhou2.github.io/motion4d-web/. --- ### Memory-Guided Point Cloud Completion for Dental Reconstruction Authors: Jianan Sun, Yukang Huang, Dongzhihan Wang, Mingyu Fan Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03598v1 Partial dental point clouds often suffer from large missing regions caused by occlusion and limited scanning views, which bias encoder-only global features and force decoders to hallucinate structures. We propose a retrieval-augmented framework for tooth completion that integrates a prototype memory into standard encoder--decoder pipelines. After encoding a partial input into a global descriptor, the model retrieves the nearest manifold prototype from a learnable memory and fuses it with the query feature through confidence-gated weighting before decoding. The memory is optimized end-to-end and self-organizes into reusable tooth-shape prototypes without requiring tooth-position labels, thereby providing structural priors that stabilize missing-region inference and free decoder capacity for detail recovery. The module is plug-and-play and compatible with common completion backbones, while keeping the same training losses. Experiments on a self-processed Teeth3DS benchmark demonstrate consistent improvements in Chamfer Distance, with visualizations showing sharper cusps, ridges, and interproximal transitions. Our approach provides a simple yet effective way to exploit cross-sample regularities for more accurate and faithful dental point-cloud completion. --- ### HBFormer: A Hybrid-Bridge Transformer for Microtumor and Miniature Organ Segmentation Authors: Fuchen Zheng, Xinyi Chen, Weixuan Li, Quanjun Li, Junhua Zhou, Xiaojiao Guo, Xuhang Chen, Chi-Man Pun, Shoujun Zhou Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03597v1 Medical image segmentation is a cornerstone of modern clinical diagnostics. While Vision Transformers that leverage shifted window-based self-attention have established new benchmarks in this field, they are often hampered by a critical limitation: their localized attention mechanism struggles to effectively fuse local details with global context. This deficiency is particularly detrimental to challenging tasks such as the segmentation of microtumors and miniature organs, where both fine-grained boundary definition and broad contextual understanding are paramount. To address this gap, we propose HBFormer, a novel Hybrid-Bridge Transformer architecture. The 'Hybrid' design of HBFormer synergizes a classic U-shaped encoder-decoder framework with a powerful Swin Transformer backbone for robust hierarchical feature extraction. The core innovation lies in its 'Bridge' mechanism, a sophisticated nexus for multi-scale feature integration. This bridge is architecturally embodied by our novel Multi-Scale Feature Fusion (MFF) decoder. Departing from conventional symmetric designs, the MFF decoder is engineered to fuse multi-scale features from the encoder with global contextual information. It achieves this through a synergistic combination of channel and spatial attention modules, which are constructed from a series of dilated and depth-wise convolutions. These components work in concert to create a powerful feature bridge that explicitly captures long-range dependencies and refines object boundaries with exceptional precision. Comprehensive experiments on challenging medical image segmentation datasets, including multi-organ, liver tumor, and bladder tumor benchmarks, demonstrate that HBFormer achieves state-of-the-art results, showcasing its outstanding capabilities in microtumor and miniature organ segmentation. Code and models are available at: https://github.com/lzeeorno/HBFormer. --- ### Frequency-Decomposed Avatar Representation for Varying Camera Distances Authors: David Svitov, Pietro Morerio, Lourdes Agapito, Alessio Del Bue Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03593v2 We present a CloseUpAvatar - a novel approach for articulated human avatar representation supporting a wider range of camera motions, while preserving rendering quality for close-up views. CloseUpAvatar represents an avatar as a set of textured planes with frequency-decomposed learnable textures for low and high-frequency detail. The method automatically switches to high-frequency textures when the camera comes close to the avatar's surface and gradually reduces their impact as the camera moves farther away. Such parametrization of the avatar enables CloseUpAvatar to adjust rendering quality based on camera distance ensuring realistic rendering across a wider range of camera orientations than previous approaches. We provide experiments on the ActorsHQ dataset with high-resolution input images and the THuman4.0 dataset with diverse articulated poses. CloseUpAvatar demonstrates both qualitative and quantitative improvements over existing methods in rendering from novel wide range camera positions, while maintaining high FPS by limiting the number of required primitives. --- ### Harnessing Hypergraphs in Geometric Deep Learning for 3D RNA Inverse Folding Authors: Guang Yang, Lei Fan Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03592v1 The RNA inverse folding problem, a key challenge in RNA design, involves identifying nucleotide sequences that can fold into desired secondary structures, which are critical for ensuring molecular stability and function. The inherent complexity of this task stems from the intricate relationship between sequence and structure, making it particularly challenging. In this paper, we propose a framework, named HyperRNA, a generative model with an encoder-decoder architecture that leverages hypergraphs to design RNA sequences. Specifically, our HyperRNA model consists of three main components: preprocessing, encoding and decoding. In the preprocessing stage, graph structures are constructed by extracting the atom coordinates of RNA backbone based on 3-bead coarse-grained representation. The encoding stage processes these graphs, capturing higher order dependencies and complex biomolecular interactions using an attention embedding module and a hypergraph-based encoder. Finally, the decoding stage generates the RNA sequence in an autoregressive manner. We conducted quantitative and qualitative experiments on the PDBBind and RNAsolo datasets to evaluate the inverse folding task for RNA sequence generation and RNA-protein complex sequence generation. The experimental results demonstrate that HyperRNA not only outperforms existing RNA design methods but also highlights the potential of leveraging hypergraphs in RNA engineering. --- ### Beyond Boundary Frames: Talking-Head Inbetweening via Context-Aware Motion Modeling Authors: Yuchen Deng, Hai-Tao Zheng, Jie Wang, Xiaotian Li, Feidiao Yang, Yuxing Han Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03590v3 Existing talking-head generation methods primarily target open-ended generation rather than bridging two existing video segments. In this paper, we study talking-head inbetweening, a practical editing task that aims to generate realistic intermediate frames under fixed endpoint constraints. Unlike generic video inbetweening, this task requires recovering subtle speech-driven facial dynamics over long temporal gaps, where the boundary frames alone provide insufficient guidance for realistic motion recovery. To address this problem, we propose BBF (Beyond Boundary Frames), a unified context-aware framework for talking-head inbetweening. BBF consists of three complementary components: Endpoint Anchoring for preserving endpoint consistency, Motion Evolution Modeling for capturing plausible temporal transitions from surrounding visual context, and Speech Dynamics Refinement for injecting fine-grained speech-driven facial dynamics from speech audio. A progressive optimization strategy further balances structural consistency and motion refinement during denoising. Extensive experiments on the talking-head benchmarks HDTF and Hallo3 demonstrate that BBF consistently achieves state-of-the-art performance. In particular, BBF surpasses the strongest baseline on Hallo3 by 23.3% in FID and 36.5% in FVD. Moreover, BBF demonstrates strong generalization on generic video inbetweening benchmarks. --- ### Federated Learning and Trajectory Compression for Enhanced AIS Coverage Authors: Thomas Gräupl, Andreas Reisenbauer, Marcel Hecko, Anil Rasouli, Anita Graser, Melitta Dragaschnig, Axel Weissenfeld, Gilles Dejaegere, Mahmoud Sakr Published: 2025-12-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.03584v1 This paper presents the VesselEdge system, which leverages federated learning and bandwidth-constrained trajectory compression to enhance maritime situational awareness by extending AIS coverage. VesselEdge transforms vessels into mobile sensors, enabling real-time anomaly detection and efficient data transmission over low-bandwidth connections. The system integrates the M3fed model for federated learning and the BWC-DR-A algorithm for trajectory compression, prioritizing anomalous data. Preliminary results demonstrate the effectiveness of VesselEdge in improving AIS coverage and situational awareness using historical data. --- ### Fine-grained Narrative Classification in Biased News Articles Authors: Zeba Afroz, Harsh Vardhan, Pawan Bhakuni, Aanchal Punia, Rajdeep Kumar, Md. Shad Akhtar Published: 2025-12-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.03582v1 Narratives are the cognitive and emotional scaffolds of propaganda. They organize isolated persuasive techniques into coherent stories that justify actions, attribute blame, and evoke identification with ideological camps. In this paper, we propose a novel fine-grained narrative classification in biased news articles. We also explore article-bias classification as the precursor task to narrative classification and fine-grained persuasive technique identification. We develop INDI-PROP, the first ideologically grounded fine-grained narrative dataset with multi-level annotation for analyzing propaganda in Indian news media. Our dataset INDI-PROP comprises 1,266 articles focusing on two polarizing socio-political events in recent times: CAA and the Farmers' protest. Each article is annotated at three hierarchical levels: (i) ideological article-bias (pro-government, pro-opposition, neutral), (ii) event-specific fine-grained narrative frames anchored in ideological polarity and communicative intent, and (iii) persuasive techniques. We propose FANTA and TPTC, two GPT-4o-mini guided multi-hop prompt-based reasoning frameworks for the bias, narrative, and persuasive technique classification. FANTA leverages multi-layered communicative phenomena by integrating information extraction and contextual framing for hierarchical reasoning. On the other hand, TPTC adopts systematic decomposition of persuasive cues via a two-stage approach. Our evaluation suggests substantial improvement over underlying baselines in each case. --- ### Dynamic Optical Test for Bot Identification (DOT-BI): A simple check to identify bots in surveys and online processes Authors: Malte Bleeker, Mauro Gotsch Published: 2025-12-03 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2512.03580v1 We propose the Dynamic Optical Test for Bot Identification (DOT-BI): a quick and easy method that uses human perception of motion to differentiate between human respondents and automated systems in surveys and online processes. In DOT-BI, a 'hidden' number is displayed with the same random black-and-white pixel texture as its background. Only the difference in motion and scale between the number and the background makes the number perceptible to humans across frames, while frame-by-frame algorithmic processing yields no meaningful signal. We conducted two preliminary assessments. Firstly, state-of-the-art, video-capable, multimodal models (GPT-5-Thinking and Gemini 2.5 Pro) fail to extract the correct value, even when given explicit instructions about the mechanism. Secondly, in an online survey (n=182), 99.5% (181/182) of participants solved the task, with an average end-to-end completion time of 10.7 seconds; a supervised lab study (n=39) found no negative effects on perceived ease-of-use or completion time relative to a control. We release code to generate tests and 100+ pre-rendered variants to facilitate adoption in surveys and online processes. --- ### Optimal Transportation and Alignment Between Gaussian Measures Authors: Sanjit Dandapanthula, Aleksandr Podkopaev, Shiva Prasad Kasiviswanathan, Aaditya Ramdas, Ziv Goldfeld Published: 2025-12-03 Categories: cs.LG, math.PR, math.ST arXiv: https://arxiv.org/abs/2512.03579v2 Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for comparing, transforming, and aggregating heterogeneous datasets---tasks ubiquitous in data science and machine learning. Because these frameworks are computationally expensive, large-scale applications often rely on closed-form solutions for Gaussian distributions under quadratic cost. This work provides a comprehensive treatment of Gaussian, quadratic cost OT and inner product GW (IGW) alignment, closing several gaps in the literature to broaden applicability. First, we treat the open problem of IGW alignment between uncentered Gaussians on separable Hilbert spaces by giving an exact variational characterization through a quadratic optimization over isometries and co-isometries (orthogonal matrices in finite dimensions), for which we derive tight analytic upper and lower bounds. If at least one Gaussian measure is centered, the solution reduces to a fully closed-form expression, which we further extend to an analytic solution for the IGW barycenter between centered Gaussians. We also present a reduction of Gaussian multimarginal OT with pairwise quadratic costs to a tractable optimization problem and prove that every second-order stationary point of this problem is globally optimal. To demonstrate utility, we compare embedding distributions of already-trained language-model distillations and cluster synthetic users using covariance spectra of their text embeddings. --- ### When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate Authors: Florent Forest, Amaury Wei, Olga Fink Published: 2025-12-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.03578v3 Time series extrinsic regression (TSER) refers to the task of predicting a continuous target variable from an input time series. It appears in many domains, including healthcare, finance, environmental monitoring, and engineering. In these settings, accurate predictions and trustworthy reasoning are both essential. Although state-of-the-art TSER models achieve strong predictive performance, they typically operate as black boxes, making it difficult to understand which temporal patterns drive their decisions. Post-hoc interpretability techniques, such as feature attribution, aim to to explain how the model arrives at its predictions, but often produce coarse, noisy, or unstable explanations. Recently, inherently interpretable approaches based on concepts, additive decompositions, or symbolic regression, have emerged as promising alternatives. However, these approaches remain limited: they require explicit supervision on the concepts themselves, often cannot capture interactions between time-series features, lack expressiveness for complex temporal patterns, and struggle to scale to high-dimensional multivariate data. To address these limitations, we propose MAGNETS (Mask-and-AGgregate NEtwork for Time Series), an inherently interpretable neural architecture for TSER. MAGNETS learns a compact set of human-understandable concepts without requiring any annotations. Each concept corresponds to a learned, mask-based aggregation over selected input features, explicitly revealing both which features drive predictions and when they matter in the sequence. Predictions are formed as combinations of these learned concepts through a transparent, additive structure, enabling clear insight into the model's decision process. The code implementation and datasets are publicly available at https://github.com/FlorentF9/MAGNETS. --- ### Cross-Stain Contrastive Learning for Paired Immunohistochemistry and Histopathology Slide Representation Learning Authors: Yizhi Zhang, Lei Fan, Zhulin Tao, Donglin Di, Yang Song, Sidong Liu, Cong Cong Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03577v1 Universal, transferable whole-slide image (WSI) representations are central to computational pathology. Incorporating multiple markers (e.g., immunohistochemistry, IHC) alongside H&E enriches H&E-based features with diverse, biologically meaningful information. However, progress is limited by the scarcity of well-aligned multi-stain datasets. Inter-stain misalignment shifts corresponding tissue across slides, hindering consistent patch-level features and degrading slide-level embeddings. To address this, we curated a slide-level aligned, five-stain dataset (H&E, HER2, KI67, ER, PGR) to enable paired H&E-IHC learning and robust cross-stain representation. Leveraging this dataset, we propose Cross-Stain Contrastive Learning (CSCL), a two-stage pretraining framework with a lightweight adapter trained using patch-wise contrastive alignment to improve the compatibility of H&E features with corresponding IHC-derived contextual cues, and slide-level representation learning with Multiple Instance Learning (MIL), which uses a cross-stain attention fusion module to integrate stain-specific patch features and a cross-stain global alignment module to enforce consistency among slide-level embeddings across different stains. Experiments on cancer subtype classification, IHC biomarker status classification, and survival prediction show consistent gains, yielding high-quality, transferable H&E slide-level representations. The code and data are available at https://github.com/lily-zyz/CSCL. --- ### UniComp: Rethinking Video Compression Through Informational Uniqueness Authors: Chao Yuan, Shimin Chen, Minliang Lin, Limeng Qiao, Guanglu Wan, Lin Ma Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03575v2 Distinct from attention-based compression methods, this paper presents an information uniqueness driven video compression framework, termed UniComp, which aims to maximize the information fidelity of video representations under constrained computational budgets. Starting from the information-theoretic perspective, we formulate the vision compression as an optimization problem that minimizes conditional entropy (reconstruction error) between retained and full tokens. To achieve this, we introduce the notion of information uniqueness to measure intrinsic redundancy among tokens to link with reconstruction error. Based on uniqueness, we design three modules-Frame Group Fusion, Token Allocation, and Spatial Dynamic Compression-that progressively perform semantic frame grouping, adaptive resource allocation, and fine-grained spatial compression. Extensive experiments demonstrate that UniComp consistently outperforms existing compression methods in preserving essential visual tokens under limited computational budgets, highlighting the pivotal role of information uniqueness in token compression efficacy. --- ### Global-Local Aware Scene Text Editing Authors: Fuxiang Yang, Tonghua Su, Donglin Di, Yin Chen, Xiangqian Wu, Zhongjie Wang, Lei Fan Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03574v1 Scene Text Editing (STE) involves replacing text in a scene image with new target text while preserving both the original text style and background texture. Existing methods suffer from two major challenges: inconsistency and length-insensitivity. They often fail to maintain coherence between the edited local patch and the surrounding area, and they struggle to handle significant differences in text length before and after editing. To tackle these challenges, we propose an end-to-end framework called Global-Local Aware Scene Text Editing (GLASTE), which simultaneously incorporates high-level global contextual information along with delicate local features. Specifically, we design a global-local combination structure, joint global and local losses, and enhance text image features to ensure consistency in text style within local patches while maintaining harmony between local and global areas. Additionally, we express the text style as a vector independent of the image size, which can be transferred to target text images of various sizes. We use an affine fusion to fill target text images into the editing patch while maintaining their aspect ratio unchanged. Extensive experiments on real-world datasets validate that our GLASTE model outperforms previous methods in both quantitative metrics and qualitative results and effectively mitigates the two challenges. --- ### EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths Authors: Zhening Li, Armando Solar-Lezama, Yisong Yue, Stephan Zheng Published: 2025-12-03 Categories: cs.AI, cs.LG, cs.PL arXiv: https://arxiv.org/abs/2512.03571v1 We introduce a new approach to agent programming, the development of LLM-based agents. Current approaches to agent programming often entangle two aspects of agent design: the core workflow logic and the inference-time strategy (e.g., tree search). We introduce "probabilistic angelic nondeterminism" ("PAN"), a programming model that disentangles these two concerns, allowing the programmer to describe the agent workflow and independently experiment with different inference-time strategies by simply changing a few inputs. We provide an implementation of PAN in Python as the EnCompass framework, which uses a Python decorator to compile agent workflow programs into a search space. We present three case studies that demonstrate how the framework lets the programmer quickly improve the reliability of an agent and easily switch between different inference-time strategies, all with little additional coding. --- ### Machine Learning to Predict Slot Usage in TSCH Wireless Sensor Networks Authors: Stefano Scanzio, Gabriele Formis, Tullio Facchinetti, Gianluca Cena Published: 2025-12-03 Categories: cs.NI, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.03570v1 Wireless sensor networks (WSNs) are employed across a wide range of industrial applications where ultra-low power consumption is a critical prerequisite. At the same time, these systems must maintain a certain level of determinism to ensure reliable and predictable operation. In this view, time slotted channel hopping (TSCH) is a communication technology that meets both conditions, making it an attractive option for its usage in industrial WSNs. This work proposes the use of machine learning to learn the traffic pattern generated in networks based on the TSCH protocol, in order to turn nodes into a deep sleep state when no transmission is planned and thus to improve the energy efficiency of the WSN. The ability of machine learning models to make good predictions at different network levels in a typical tree network topology was analyzed in depth, showing how their capabilities degrade while approaching the root of the tree. The application of these models on simulated data based on an accurate modeling of wireless sensor nodes indicates that the investigated algorithms can be suitably used to further and substantially reduce the power consumption of a TSCH network. --- ### GAOT: Generating Articulated Objects Through Text-Guided Diffusion Models Authors: Hao Sun, Lei Fan, Donglin Di, Shaohui Liu Published: 2025-12-03 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2512.03566v1 Articulated object generation has seen increasing advancements, yet existing models often lack the ability to be conditioned on text prompts. To address the significant gap between textual descriptions and 3D articulated object representations, we propose GAOT, a three-phase framework that generates articulated objects from text prompts, leveraging diffusion models and hypergraph learning in a three-step process. First, we fine-tune a point cloud generation model to produce a coarse representation of objects from text prompts. Given the inherent connection between articulated objects and graph structures, we design a hypergraph-based learning method to refine these coarse representations, representing object parts as graph vertices. Finally, leveraging a diffusion model, the joints of articulated objects-represented as graph edges-are generated based on the object parts. Extensive qualitative and quantitative experiments on the PartNet-Mobility dataset demonstrate the effectiveness of our approach, achieving superior performance over previous methods. --- ### Towards Irreversible Machine Unlearning for Diffusion Models Authors: Xun Yuan, Zilong Zhao, Jiayu Li, Aryan Pasikhani, Prosanta Gope, Biplab Sikdar Published: 2025-12-03 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2512.03564v1 Diffusion models are renowned for their state-of-the-art performance in generating synthetic images. However, concerns related to safety, privacy, and copyright highlight the need for machine unlearning, which can make diffusion models forget specific training data and prevent the generation of sensitive or unwanted content. Current machine unlearning methods for diffusion models are primarily designed for conditional diffusion models and focus on unlearning specific data classes or features. Among these methods, finetuning-based machine unlearning methods are recognized for their efficiency and effectiveness, which update the parameters of pre-trained diffusion models by minimizing carefully designed loss functions. However, in this paper, we propose a novel attack named Diffusion Model Relearning Attack (DiMRA), which can reverse the finetuning-based machine unlearning methods, posing a significant vulnerability of this kind of technique. Without prior knowledge of the unlearning elements, DiMRA optimizes the unlearned diffusion model on an auxiliary dataset to reverse the unlearning, enabling the model to regenerate previously unlearned elements. To mitigate this vulnerability, we propose a novel machine unlearning method for diffusion models, termed as Diffusion Model Unlearning by Memorization (DiMUM). Unlike traditional methods that focus on forgetting, DiMUM memorizes alternative data or features to replace targeted unlearning data or features in order to prevent generating such elements. In our experiments, we demonstrate the effectiveness of DiMRA in reversing state-of-the-art finetuning-based machine unlearning methods for diffusion models, highlighting the need for more robust solutions. We extensively evaluate DiMUM, demonstrating its superior ability to preserve the generative performance of diffusion models while enhancing robustness against DiMRA. --- ### State Space Models for Bioacoustics: A Comparative Evaluation with Transformers Authors: Chengyu Tang, Sanjeev Baskiyar Published: 2025-12-03 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2512.03563v2 In this study, we evaluate the efficacy of the Mamba architecture bioacoustics by introducing BioMamba, a Mamba-based audio representation model for wildlife sounds. We pre-train a BioMamba using self-supervised learning on a large audio corpus and evaluate it on the BEANS benchmark across diverse classification and detection tasks. Compared to the state-of-the-art Transformer-based model (AVES), BioMamba achieves comparable performance while significantly reducing VRAM consumption. Our results demonstrate Mamba's potential as a computationally efficient alternative for real-world environmental monitoring. --- ### Reason-Plan-ReAct: A Reasoner-Planner Supervising a ReAct Executor for Complex Enterprise Tasks Authors: Gianni Molinari, Fabio Ciravegna Published: 2025-12-03 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.03560v1 Despite recent advances, autonomous agents often struggle to solve complex tasks in enterprise domains that require coordinating multiple tools and processing diverse data sources. This struggle is driven by two main limitations. First, single-agent architectures enforce a monolithic plan-execute loop, which directly causes trajectory instability. Second, the requirement to use local open-weight models for data privacy introduces smaller context windows leading to the rapid consumption of context from large tool outputs. To solve this problem we introduce RP-ReAct (Reasoner Planner-ReAct), a novel multi-agent approach that fundamentally decouples strategic planning from low-level execution to achieve superior reliability and efficiency. RP-ReAct consists of a Reasoner Planner Agent (RPA), responsible for planning each sub-step, continuously analysing the execution results using the strong reasoning capabilities of a Large Reasoning Model, and one or multiple Proxy-Execution Agent (PEA) that translates sub-steps into concrete tool interactions using a ReAct approach. Crucially, we incorporate a context-saving strategy within the PEA to mitigate context window overflow by managing large tool outputs via external storage and on-demand access. We evaluate RP-ReAct, on the challenging, multi-domain ToolQA benchmark using a diverse set of six open-weight reasoning models. Our empirical results show that RP-ReAct achieves superior performance and improved generalization ability over state-of-the-art baselines when addressing diverse complex tasks across the evaluated domains. Furthermore we establish the enhanced robustness and stability of our approach across different model scales, paving the way for effective and deployable agentic solutions for enterprises. --- ### CartoMapQA: A Fundamental Benchmark Dataset Evaluating Vision-Language Models on Cartographic Map Understanding Authors: Huy Quang Ung, Guillaume Habault, Yasutaka Nishimura, Hao Niu, Roberto Legaspi, Tomoki Oya, Ryoichi Kojima, Masato Taya, Chihiro Ono, Atsunori Minamikawa, Yan Liu Published: 2025-12-03 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2512.03558v1 The rise of Visual-Language Models (LVLMs) has unlocked new possibilities for seamlessly integrating visual and textual information. However, their ability to interpret cartographic maps remains largely unexplored. In this paper, we introduce CartoMapQA, a benchmark specifically designed to evaluate LVLMs' understanding of cartographic maps through question-answering tasks. The dataset includes over 2000 samples, each composed of a cartographic map, a question (with open-ended or multiple-choice answers), and a ground-truth answer. These tasks span key low-, mid- and high-level map interpretation skills, including symbol recognition, embedded information extraction, scale interpretation, and route-based reasoning. Our evaluation of both open-source and proprietary LVLMs reveals persistent challenges: models frequently struggle with map-specific semantics, exhibit limited geospatial reasoning, and are prone to Optical Character Recognition (OCR)-related errors. By isolating these weaknesses, CartoMapQA offers a valuable tool for guiding future improvements in LVLM architectures. Ultimately, it supports the development of models better equipped for real-world applications that depend on robust and reliable map understanding, such as navigation, geographic search, and urban planning. Our source code and data are openly available to the research community at: https://github.com/ungquanghuy-kddi/CartoMapQA.git --- ### RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL Authors: Yinzhou Tang, Yu Shang, Yinuo Chen, Bingwen Wei, Xin Zhang, Shu'ang Yu, Liangzhi Shi, Chao Yu, Chen Gao, Wei Wu, Yong Li Published: 2025-12-03 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.03556v1 Achieving generalizable embodied policies remains a key challenge. Traditional policy learning paradigms, including both Imitation Learning (IL) and Reinforcement Learning (RL), struggle to cultivate generalizability across diverse scenarios. While IL policies often overfit to specific expert trajectories, RL suffers from the inherent lack of a unified and general reward signal necessary for effective multi-scene generalization. We posit that the world model is uniquely capable of serving as a universal environment proxy to address this limitation. However, current world models primarily focus on their ability to predict observations and still rely on task-specific, handcrafted reward functions, thereby failing to provide a truly general training environment. Toward this problem, we propose RoboScape-R, a framework leveraging the world model to serve as a versatile, general-purpose proxy for the embodied environment within the RL paradigm. We introduce a novel world model-based general reward mechanism that generates ''endogenous'' rewards derived from the model's intrinsic understanding of real-world state transition dynamics. Extensive experiments demonstrate that RoboScape-R effectively addresses the limitations of traditional RL methods by providing an efficient and general training environment that substantially enhances the generalization capability of embodied policies. Our approach offers critical insights into utilizing the world model as an online training strategy and achieves an average 37.5% performance improvement over baselines under out-of-domain scenarios. --- ### Dynamic Content Moderation in Livestreams: Combining Supervised Classification with MLLM-Boosted Similarity Matching Authors: Wei Chee Yew, Hailun Xu, Sanjay Saha, Xiaotian Fan, Hiok Hian Ong, David Yuchen Wang, Kanchan Sarkar, Zhenheng Yang, Danhui Guan Published: 2025-12-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.03553v3 Content moderation remains a critical yet challenging task for large-scale user-generated video platforms, especially in livestreaming environments where moderation must be timely, multimodal, and robust to evolving forms of unwanted content. We present a hybrid moderation framework deployed at production scale that combines supervised classification for known violations with reference-based similarity matching for novel or subtle cases. This hybrid design enables robust detection of both explicit violations and novel edge cases that evade traditional classifiers. Multimodal inputs (text, audio, visual) are processed through both pipelines, with a multimodal large language model (MLLM) distilling knowledge into each to boost accuracy while keeping inference lightweight. In production, the classification pipeline achieves 67% recall at 80% precision, and the similarity pipeline achieves 76% recall at 80% precision. Large-scale A/B tests show a 6-8% reduction in user views of unwanted livestreams}. These results demonstrate a scalable and adaptable approach to multimodal content governance, capable of addressing both explicit violations and emerging adversarial behaviors. --- ### PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks Authors: Yuki Orimo, Iori Kurata, Hodaka Mori, Ryuhei Okuno, Ryohto Sawada, Daisuke Okanohara Published: 2025-12-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.03549v1 We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates its own actions and their outcomes from an independent context and provides feedback, namely self-assessment and self-feedback. This design enables PARC to detect and correct high-level strategic errors and sustain progress without human intervention. We evaluate PARC across computational science and data science tasks. In materials science, it autonomously reproduces key results from studies on lithium-ion conduction and alloy segregation. In particular, it coordinates dozens of parallel simulation tasks, each requiring roughly 43 hours of computation, managing orchestration, monitoring, and error correction end-to-end. In Kaggle-based experiments, starting from minimal natural-language instructions, PARC conducts data analysis and implements search strategies, producing solutions competitive with human-engineered baselines. These results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback to enable AI systems capable of independent, large-scale scientific and analytical work. --- ### A Learning-based Control Methodology for Transitioning VTOL UAVs Authors: Zexin Lin, Yebin Zhong, Hanwen Wan, Jiu Cheng, Zhenglong Sun, Xiaoqiang Ji Published: 2025-12-03 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.03548v1 Transition control poses a critical challenge in Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL UAV) development due to the tilting rotor mechanism, which shifts the center of gravity and thrust direction during transitions. Current control methods' decoupled control of altitude and position leads to significant vibration, and limits interaction consideration and adaptability. In this study, we propose a novel coupled transition control methodology based on reinforcement learning (RL) driven controller. Besides, contrasting to the conventional phase-transition approach, the ST3M method demonstrates a new perspective by treating cruise mode as a special case of hover. We validate the feasibility of applying our method in simulation and real-world environments, demonstrating efficient controller development and migration while accurately controlling UAV position and attitude, exhibiting outstanding trajectory tracking and reduced vibrations during the transition process. --- ### V-ITI: Mitigating Hallucinations in Multimodal Large Language Models via Visual Inference-Time Intervention Authors: Nan Sun, Zhenyu Zhang, Xixun Lin, Kun Wang, Yanmin Shang, Naibin Gu, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang, Yanan Cao Published: 2025-12-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.03542v1 Multimodal Large Language Models (MLLMs) excel in numerous vision-language tasks yet suffer from hallucinations, producing content inconsistent with input visuals, that undermine reliability in precision-sensitive domains. This issue stems from a fundamental problem of visual neglect, where models fail to adequately prioritize input images. Existing methods typically alleviate hallucinations by intervening in the attention score or output logits, focusing on "how to intervene" but overlooking the prerequisite "when to intervene", which leads to the "over-intervention" problem and subsequently introduces new hallucinations and unnecessary computational overhead. To address this gap, we first investigate the mechanism of visual neglect and reveal it can be accurately detected via head-level activation patterns in MLLMs. We thus propose V-ITI, a lightweight visual inference-time intervention framework integrating a Visual Neglect Detector that identifies visual neglect via head-level discriminative probes and a Visual Recall Intervenor that modulates activations with prestored visual activation information only when the visual neglect is detected. Extensive experiments across eight benchmarks and different MLLM families demonstrate that V-ITI consistently mitigates vision-related hallucinations while preserving general task performance. ---