# Research Papers — 2025-12 · bundle page 126 of 175 > Full-text markdown of papers #6251–6300 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/126 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/125.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/127.md) ### LongCat-Image Technical Report Authors: Meituan LongCat Team, Hanghang Ma, Haoxian Tan, Jiale Huang, Junqiang Wu, Jun-Yan He, Lishuai Gao, Songlin Xiao, Xiaoming Wei, Xiaoqi Ma, Xunliang Cai, Yayong Guan et al. Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07584v1 We introduce LongCat-Image, a pioneering open-source and bilingual (Chinese-English) foundation model for image generation, designed to address core challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility prevalent in current leading models. 1) We achieve this through rigorous data curation strategies across the pre-training, mid-training, and SFT stages, complemented by the coordinated use of curated reward models during the RL phase. This strategy establishes the model as a new state-of-the-art (SOTA), delivering superior text-rendering capabilities and remarkable photorealism, and significantly enhancing aesthetic quality. 2) Notably, it sets a new industry standard for Chinese character rendering. By supporting even complex and rare characters, it outperforms both major open-source and commercial solutions in coverage, while also achieving superior accuracy. 3) The model achieves remarkable efficiency through its compact design. With a core diffusion model of only 6B parameters, it is significantly smaller than the nearly 20B or larger Mixture-of-Experts (MoE) architectures common in the field. This ensures minimal VRAM usage and rapid inference, significantly reducing deployment costs. Beyond generation, LongCat-Image also excels in image editing, achieving SOTA results on standard benchmarks with superior editing consistency compared to other open-source works. 4) To fully empower the community, we have established the most comprehensive open-source ecosystem to date. We are releasing not only multiple model versions for text-to-image and image editing, including checkpoints after mid-training and post-training stages, but also the entire toolchain of training procedure. We believe that the openness of LongCat-Image will provide robust support for developers and researchers, pushing the frontiers of visual content creation. --- ### Complementary Learning Approach for Text Classification using Large Language Models Authors: Navid Asgari, Benjamin M. Cole Published: 2025-12-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.07583v2 In this study, we propose a structured methodology that utilizes large language models (LLMs) in a cost-efficient and parsimonious manner, integrating the strengths of scholars and machines while offsetting their respective weaknesses. Our methodology, facilitated through a chain of thought and few-shot learning prompting from computer science, extends best practices for co-author teams in qualitative research to human-machine teams in quantitative research. This allows humans to utilize abductive reasoning and natural language to interrogate not just what the machine has done but also what the human has done. Our method highlights how scholars can manage inherent weaknesses OF LLMs using careful, low-cost techniques. We demonstrate how to use the methodology to interrogate human-machine rating discrepancies for a sample of 1,934 press releases announcing pharmaceutical alliances (1990-2017). --- ### When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs Authors: Yahong Wang, Juncheng Wu, Zhangkai Ni, Longzhen Yang, Yihang Liu, Chengmei Yang, Ying Wen, Lianghua He, Xianfeng Tang, Hui Liu, Yuyin Zhou Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07580v2 Vision Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising solution for accelerating inference, this paper, however, identifies a key observation: in deeper layers (e.g., beyond the 20th), existing training-free pruning methods perform no better than random pruning. We hypothesize that this degradation is caused by \textbf{``vanishing token information''}, where visual tokens progressively lose their salience with increasing network depth. To validate this hypothesis, we quantify a token's information content by measuring the change in the model output probabilities upon its removal. Using this proposed metric, our analysis of the information of visual tokens across layers reveals three key findings: (1) As layers deepen, the information of visual tokens gradually becomes uniform and eventually vanishes at an intermediate layer, which we term as ``information horizon", beyond which the visual tokens become redundant; (2) The position of this horizon is not static; it extends deeper for visually intensive tasks, such as Optical Character Recognition (OCR), compared to more general tasks like Visual Question Answering (VQA); (3) This horizon is also strongly correlated with model capacity, as stronger VLLMs (e.g., Qwen2.5-VL) employ deeper visual tokens than weaker models (e.g., LLaVA-1.5). Based on our findings, we show that simple random pruning in deep layers efficiently balances performance and efficiency. Moreover, integrating random pruning consistently enhances existing methods. Using DivPrune with random pruning achieves state-of-the-art results, maintaining 96.9\% of Qwen-2.5-VL-7B performance while pruning 50\% of visual tokens. The code is available at https://github.com/YahongWang1/Information-Horizon. --- ### $φ$-Table: A Statistical Explanation for Global SHAP Authors: Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh Published: 2025-12-08 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2512.07578v3 Global SHAP explanations are typically presented as feature-importance rankings, which identify variables that matter to a black-box model but do not indicate whether their effects admit clear directional summaries, how uncertain those summaries are, or how faithfully they represent the fitted response. This paper proposes the $φ$-table, a SHAP-based statistical explanation table for tabular black-box regression models. The procedure selects features by SHAP importance and fits a standardized linear surrogate to the fitted model response $f(X)$, reporting SHAP importance together with model-response coefficients, uncertainty summaries, surrogate fidelity, and bootstrap coefficient stability. The resulting coefficients are interpreted as projections of the fitted model response onto the SHAP-selected feature set. Across synthetic, semi-synthetic, and real-data experiments, the $φ$-table extends ranking-only SHAP into a statistical global explanation by exposing direction, uncertainty, fidelity, and stability as distinct components of fitted model behavior. --- ### R2MF-Net: A Recurrent Residual Multi-Path Fusion Network for Robust Multi-directional Spine X-ray Segmentation Authors: Xuecheng Li, Weikuan Jia, Komildzhon Sharipov, Sharipov Hotam Beknazarovich, Farzona S. Ataeva, Qurbonaliev Alisher, Yuanjie Zheng Published: 2025-12-08 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.07576v1 Accurate segmentation of spinal structures in X-ray images is a prerequisite for quantitative scoliosis assessment, including Cobb angle measurement, vertebral translation estimation and curvature classification. In routine practice, clinicians acquire coronal, left-bending and right-bending radiographs to jointly evaluate deformity severity and spinal flexibility. However, the segmentation step remains heavily manual, time-consuming and non-reproducible, particularly in low-contrast images and in the presence of rib shadows or overlapping tissues. To address these limitations, this paper proposes R2MF-Net, a recurrent residual multi-path encoder--decoder network tailored for automatic segmentation of multi-directional spine X-ray images. The overall design consists of a coarse segmentation network and a fine segmentation network connected in cascade. Both stages adopt an improved Inception-style multi-branch feature extractor, while a recurrent residual jump connection (R2-Jump) module is inserted into skip paths to gradually align encoder and decoder semantics. A multi-scale cross-stage skip (MC-Skip) mechanism allows the fine network to reuse hierarchical representations from multiple decoder levels of the coarse network, thereby strengthening the stability of segmentation across imaging directions and contrast conditions. Furthermore, a lightweight spatial-channel squeeze-and-excitation block (SCSE-Lite) is employed at the bottleneck to emphasize spine-related activations and suppress irrelevant structures and background noise. We evaluate R2MF-Net on a clinical multi-view radiograph dataset comprising 228 sets of coronal, left-bending and right-bending spine X-ray images with expert annotations. --- ### Precise Liver Tumor Segmentation in CT Using a Hybrid Deep Learning-Radiomics Framework Authors: Xuecheng Li, Weikuan Jia, Komildzhon Sharipov, Alimov Ruslan, Lutfuloev Mazbutdzhon, Ismoilov Shuhratjon, Yuanjie Zheng Published: 2025-12-08 Categories: eess.IV, cs.CR, cs.CV arXiv: https://arxiv.org/abs/2512.07574v1 Accurate three-dimensional delineation of liver tumors on contrast-enhanced CT is a prerequisite for treatment planning, navigation and response assessment, yet manual contouring is slow, observer-dependent and difficult to standardise across centres. Automatic segmentation is complicated by low lesion-parenchyma contrast, blurred or incomplete boundaries, heterogeneous enhancement patterns, and confounding structures such as vessels and adjacent organs. We propose a hybrid framework that couples an attention-enhanced cascaded U-Net with handcrafted radiomics and voxel-wise 3D CNN refinement for joint liver and liver-tumor segmentation. First, a 2.5D two-stage network with a densely connected encoder, sub-pixel convolution decoders and multi-scale attention gates produces initial liver and tumor probability maps from short stacks of axial slices. Inter-slice temporal consistency is then enforced by a simple three-slice refinement rule along the cranio-caudal direction, which restores thin and tiny lesions while suppressing isolated noise. Next, 728 radiomic descriptors spanning intensity, texture, shape, boundary and wavelet feature groups are extracted from candidate lesions and reduced to 20 stable, highly informative features via multi-strategy feature selection; a random forest classifier uses these features to reject false-positive regions. Finally, a compact 3D patch-based CNN derived from AlexNet operates in a narrow band around the tumor boundary to perform voxel-level relabelling and contour smoothing. --- ### A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification Authors: Nicolas Calbucura, Jose Guillen, Valentin Barriere Published: 2025-12-08 Categories: cs.CL, cs.MM arXiv: https://arxiv.org/abs/2512.07571v3 This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tuned for a specific classification task. A classical issue with the fusion of many embeddings from audio with text is the large length of the audio sequence compared to the text one. Our method benefits from an existing speech tokenizer trained for Audio Speech Recognition that output long sequences of tokens from a large vocabulary, making it difficult to integrate it at low cost in a large language model. By applying a simple lasso-based feature selection on multimodal Bag-of-Words representation, we retain only the most important audio tokens for the task, and adapt the language model to them with a self-supervised language modeling objective, before fine-tuning it on the downstream task. We show this helps to improve the performances compared to an unimodal model, to a bigger SpeechLM or to integrating audio via a learned representation. We demonstrate its effectiveness on Argumentative Fallacy Detection and Classification tasks where audio was previously believed counterproductive, and affective computing tasks on a widely-used dataset. We also provide an in-depth analysis of the method, showing that even a random audio token selection helps enhancing the unimodal model. Our code is available (online)(https://github.com/salocinc/EMNLP26SpeechTokLLM/). --- ### Weighted Contrastive Learning for Anomaly-Aware Time-Series Forecasting Authors: Joel Ekstrand, Tor Mattsson, Zahra Taghiyarrenani, Slawomir Nowaczyk, Jens Lundström, Mikael Lindén Published: 2025-12-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.07569v2 Reliable forecasting of multivariate time series under anomalous conditions is crucial in applications such as ATM cash logistics, where sudden demand shifts can disrupt operations. Modern deep forecasters achieve high accuracy on normal data but often fail when distribution shifts occur. We propose Weighted Contrastive Adaptation (WECA), a Weighted contrastive objective that aligns normal and anomaly-augmented representations, preserving anomaly-relevant information while maintaining consistency under benign variations. Evaluations on a nationwide ATM transaction dataset with domain-informed anomaly injection show that WECA improves SMAPE on anomaly-affected data by 6.1 percentage points compared to a normally trained baseline, with negligible degradation on normal data. These results demonstrate that WECA enhances forecasting reliability under anomalies without sacrificing performance during regular operations. --- ### Dual-Stream Cross-Modal Representation Learning via Residual Semantic Decorrelation Authors: Xuecheng Li, Weikuan Jia, Alisher Kurbonaliev, Qurbonaliev Alisher, Khudzhamkulov Rustam, Ismoilov Shuhratjon, Eshmatov Javhariddin, Yuanjie Zheng Published: 2025-12-08 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2512.07568v1 Cross-modal learning has become a fundamental paradigm for integrating heterogeneous information sources such as images, text, and structured attributes. However, multimodal representations often suffer from modality dominance, redundant information coupling, and spurious cross-modal correlations, leading to suboptimal generalization and limited interpretability. In particular, high-variance modalities tend to overshadow weaker but semantically important signals, while naïve fusion strategies entangle modality-shared and modality-specific factors in an uncontrolled manner. This makes it difficult to understand which modality actually drives a prediction and to maintain robustness when some modalities are noisy or missing. To address these challenges, we propose a Dual-Stream Residual Semantic Decorrelation Network (DSRSD-Net), a simple yet effective framework that disentangles modality-specific and modality-shared information through residual decomposition and explicit semantic decorrelation constraints. DSRSD-Net introduces: (1) a dual-stream representation learning module that separates intra-modal (private) and inter-modal (shared) latent factors via residual projection; (2) a residual semantic alignment head that maps shared factors from different modalities into a common space using a combination of contrastive and regression-style objectives; and (3) a decorrelation and orthogonality loss that regularizes the covariance structure of the shared space while enforcing orthogonality between shared and private streams, thereby suppressing cross-modal redundancy and preventing feature collapse. Experimental results on two large-scale educational benchmarks demonstrate that DSRSD-Net consistently improves next-step prediction and final outcome prediction over strong single-modality, early-fusion, late-fusion, and co-attention baselines. --- ### Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models Authors: Kassoum Sanogo, Renzo Ardiccioni Published: 2025-12-08 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.07564v1 Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through uncertainty-guided visual re-attention. Our method combines multidimensional uncertainty quantification (token entropy, attention dispersion, semantic consistency, claim confidence) with attention-guided cropping of under-explored regions. Operating entirely with frozen, pretrained VLMs, our framework requires no gradient updates. We validate our approach on the POPE and MMHAL BENCH benchmarks using the Qwen2.5-VL-7B (23) architecture. Experimental results demonstrate that our method reduces hallucination rates by 9.8 percentage points compared to the baseline, while improving object existence accuracy by 4.7 points on adversarial splits. Furthermore, qualitative analysis confirms that uncertainty-guided re-attention successfully grounds corrections in visual evidence where standard decoding fails. We validate our approach on Qwen2.5-VL-7B (23), with plans to extend validation across diverse architectures in future versions. We release our code and methodology to facilitate future research in trustworthy multimodal systems. --- ### ReLaX: Reasoning with Latent Exploration for Large Reasoning Models Authors: Shimin Zhang, Xianwei Chen, Yufan Shen, Ziyuan Ye, Jibin Wu Published: 2025-12-08 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.07558v2 Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated remarkable potential in enhancing the reasoning capability of Large Reasoning Models (LRMs). However, RLVR often drives the policy toward over-determinism, resulting in ineffective exploration and premature policy convergence. While promoting token-level diversity has shown promise in mitigating entropy collapse, we argue that the latent dynamics underlying token generation encode a far richer computational structure for steering policy optimization toward a more effective exploration-exploitation tradeoff. To enable tractable analysis and intervention of the latent dynamics of LRMs, we leverage Koopman operator theory to obtain a linearized representation of their hidden state dynamics. This enables us to introduce Dynamic Spectral Dispersion (DSD), a new metric to quantify the heterogeneity of the model's latent dynamics, serving as a direct indicator of policy exploration. Building upon these foundations, we propose Reasoning with Latent eXploration (ReLaX), a framework that explicitly incorporates latent dynamics to regulate exploration and exploitation during policy optimization. Comprehensive experiments across a wide range of multimodal and text-only reasoning benchmarks show that ReLaX consistently incentivizes reasoning capability and outperforms existing token-level methods. Our project is available at https://github.com/ZhangShimin1/ReLaX. --- ### On Conditional Independence Graph Learning From Multi-Attribute Gaussian Dependent Time Series Authors: Jitendra K. Tugnait Published: 2025-12-08 Categories: stat.ML, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2512.07557v1 Estimation of the conditional independence graph (CIG) of high-dimensional multivariate Gaussian time series from multi-attribute data is considered. Existing methods for graph estimation for such data are based on single-attribute models where one associates a scalar time series with each node. In multi-attribute graphical models, each node represents a random vector or vector time series. In this paper we provide a unified theoretical analysis of multi-attribute graph learning for dependent time series using a penalized log-likelihood objective function formulated in the frequency domain using the discrete Fourier transform of the time-domain data. We consider both convex (sparse-group lasso) and non-convex (log-sum and SCAD group penalties) penalty/regularization functions. We establish sufficient conditions in a high-dimensional setting for consistency (convergence of the inverse power spectral density to true value in the Frobenius norm), local convexity when using non-convex penalties, and graph recovery. We do not impose any incoherence or irrepresentability condition for our convergence results. We also empirically investigate selection of the tuning parameters based on the Bayesian information criterion, and illustrate our approach using numerical examples utilizing both synthetic and real data. --- ### Performance of the SafeTerm AI-Based MedDRA Query System Against Standardised MedDRA Queries Authors: Francois Vandenhende, Anna Georgiou, Michalis Georgiou, Theodoros Psaras, Ellie Karekla, Elena Hadjicosta Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07552v1 In pre-market drug safety review, grouping related adverse event terms into SMQs or OCMQs is critical for signal detection. We assess the performance of SafeTerm Automated Medical Query (AMQ) on MedDRA SMQs. The AMQ is a novel quantitative artificial intelligence system that understands and processes medical terminology and automatically retrieves relevant MedDRA Preferred Terms (PTs) for a given input query, ranking them by a relevance score (0-1) using multi-criteria statistical methods. The system (SafeTerm) embeds medical query terms and MedDRA PTs in a multidimensional vector space, then applies cosine similarity, and extreme-value clustering to generate a ranked list of PTs. Validation was conducted against tier-1 SMQs (110 queries, v28.1). Precision, recall and F1 were computed at multiple similarity-thresholds, defined either manually or using an automated method. High recall (94%)) is achieved at moderate similarity thresholds, indicative of good retrieval sensitivity. Higher thresholds filter out more terms, resulting in improved precision (up to 89%). The optimal threshold (0.70)) yielded an overall recall of (48%) and precision of (45%) across all 110 queries. Restricting to narrow-term PTs achieved slightly better performance at an increased (+0.05) similarity threshold, confirming increased relatedness of narrow versus broad terms. The automatic threshold (0.66) selection prioritizes recall (0.58) to precision (0.29). SafeTerm AMQ achieves comparable, satisfactory performance on SMQs and sanitized OCMQs. It is therefore a viable supplementary method for automated MedDRA query generation, balancing recall and precision. We recommend using suitable MedDRA PT terminology in query formulation and applying the automated threshold method to optimise recall. Increasing similarity scores allows refined, narrow terms selection. --- ### MoCoRP: Modeling Consistent Relations between Persona and Response for Persona-based Dialogue Authors: Kyungro Lee, Dongha Choi, Hyunju Lee Published: 2025-12-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.07544v1 As dialogue systems become increasingly important across various domains, a key challenge in persona-based dialogue is generating engaging and context-specific interactions while ensuring the model acts with a coherent personality. However, existing persona-based dialogue datasets lack explicit relations between persona sentences and responses, which makes it difficult for models to effectively capture persona information. To address these issues, we propose MoCoRP (Modeling Consistent Relations between Persona and Response), a framework that incorporates explicit relations into language models. MoCoRP leverages an NLI expert to explicitly extract the NLI relations between persona sentences and responses, enabling the model to effectively incorporate appropriate persona information from the context into its responses. We applied this framework to pre-trained models like BART and further extended it to modern large language models (LLMs) through alignment tuning. Experimental results on the public datasets ConvAI2 and MPChat demonstrate that MoCoRP outperforms existing baselines, achieving superior persona consistency and engaging, context-aware dialogue generation. Furthermore, our model not only excels in quantitative metrics but also shows significant improvements in qualitative aspects. These results highlight the effectiveness of explicitly modeling persona-response relations in persona-based dialogue. The source codes of MoCoRP are available at https://github.com/DMCB-GIST/MoCoRP. --- ### Over-representation of phonological features in basic vocabulary doesn't replicate when controlling for spatial and phylogenetic effects Authors: Frederic Blum Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07543v2 The statistical over-representation of phonological features in the basic vocabulary of languages is often interpreted as reflecting potentially universal sound symbolic patterns. However, most of those results have not been tested explicitly for reproducibility and might be prone to biases in the study samples or models. Many studies on the topic do not adequately control for genealogical and areal dependencies between sampled languages, casting doubts on the robustness of the results. In this study, we test the robustness of a recent study on sound symbolism of basic vocabulary concepts which analyzed 245 languages.The new sample includes data on 2864 languages from Lexibank. We modify the original model by adding statistical controls for spatial and phylogenetic dependencies between languages. The new results show that most of the previously observed patterns are not robust, and in fact many patterns disappear completely when adding the genealogical and areal controls. A small number of patterns, however, emerges as highly stable even with the new sample. Through the new analysis, we are able to assess the distribution of sound symbolism on a larger scale than previously. The study further highlights the need for testing all universal claims on language for robustness on various levels. --- ### RRAEDy: Adaptive Latent Linearization of Nonlinear Dynamical Systems Authors: Jad Mounayer, Sebastian Rodriguez, Jerome Tomezyk, Chady Ghnatios, Francisco Chinesta Published: 2025-12-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.07542v1 Most existing latent-space models for dynamical systems require fixing the latent dimension in advance, they rely on complex loss balancing to approximate linear dynamics, and they don't regularize the latent variables. We introduce RRAEDy, a model that removes these limitations by discovering the appropriate latent dimension, while enforcing both regularized and linearized dynamics in the latent space. Built upon Rank-Reduction Autoencoders (RRAEs), RRAEDy automatically rank and prune latent variables through their singular values while learning a latent Dynamic Mode Decomposition (DMD) operator that governs their temporal progression. This structure-free yet linearly constrained formulation enables the model to learn stable and low-dimensional dynamics without auxiliary losses or manual tuning. We provide theoretical analysis demonstrating the stability of the learned operator and showcase the generality of our model by proposing an extension that handles parametric ODEs. Experiments on canonical benchmarks, including the Van der Pol oscillator, Burgers' equation, 2D Navier-Stokes, and Rotating Gaussians, show that RRAEDy achieves accurate and robust predictions. Our code is open-source and available at https://github.com/JadM133/RRAEDy. We also provide a video summarizing the main results at https://youtu.be/ox70mSSMGrM. --- ### High-Dimensional Change Point Detection via Graph Spanning Ratio Authors: Katerina Papagiannouli, Yang-wen Sun, Vladimir Spokoiny Published: 2025-12-08 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.07541v3 Inspired by graph-based methodologies, we introduce a novel graph-spanning algorithm designed to identify changes in both offline and online data across low to high dimensions. This versatile approach is applicable to Euclidean and graph-structured data with unknown distributions, while maintaining control over error probabilities. Theoretically, we demonstrate that the algorithm achieves high detection power when the magnitude of the change surpasses the lower bound of the minimax separation rate, which scales on the order of $\sqrt{nd}$. Our method outperforms other techniques in terms of accuracy for both Gaussian and non-Gaussian data. Notably, it maintains strong detection power even with small observation windows, making it particularly effective for online environments where timely and precise change detection is critical. --- ### Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine Translation Evaluation Authors: Boxuan Lyu, Haiyue Song, Hidetaka Kamigaito, Chenchen Ding, Hideki Tanaka, Masao Utiyama, Kotaro Funakoshi, Manabu Okumura Published: 2025-12-08 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.07540v4 Error Span Detection (ESD) extends automatic machine translation (MT) evaluation by localizing translation errors and labeling their severity. Current generative ESD methods typically use Maximum a Posteriori (MAP) decoding, assuming that the model-estimated probabilities are perfectly correlated with similarity to the human annotation, but we often observe higher likelihood assigned to an incorrect annotation than to the human one. We instead apply Minimum Bayes Risk (MBR) decoding to generative ESD. We use a sentence- or span-level similarity function for MBR decoding, which selects candidate hypotheses based on their approximate similarity to the human annotation. Experimental results on the WMT24 Metrics Shared Task show that MBR decoding significantly improves span-level performance and generally matches or outperforms MAP at the system and sentence levels. To reduce the computational cost of MBR decoding, we further distill its decisions into a model decoded via greedy search, removing the inference-time latency bottleneck. --- ### FRWKV:Frequency-Domain Linear Attention for Long-Term Time Series Forecasting Authors: Qingyuan Yang, Shizhuo Deng, Dongyue Chen, Da Teng, Zehua Gan Published: 2025-12-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.07539v2 Traditional Transformers face a major bottleneck in long-sequence time series forecasting due to their quadratic complexity $(\mathcal{O}(T^2))$ and their limited ability to effectively exploit frequency-domain information. Inspired by RWKV's $\mathcal{O}(T)$ linear attention and frequency-domain modeling, we propose FRWKV, a frequency-domain linear-attention framework that overcomes these limitations. Our model integrates linear attention mechanisms with frequency-domain analysis, achieving $\mathcal{O}(T)$ computational complexity in the attention path while exploiting spectral information to enhance temporal feature representations for scalable long-sequence modeling. Across eight real-world datasets, FRWKV achieves a first-place average rank. Our ablation studies confirm the critical roles of both the linear attention and frequency-encoder components. This work demonstrates the powerful synergy between linear attention and frequency analysis, establishing a new paradigm for scalable time series modeling. Code is available at this repository: https://github.com/yangqingyuan-byte/FRWKV. --- ### SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents Authors: Michelle Wastl, Jannis Vamvas, Rico Sennrich Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07538v3 Recognizing semantic differences across documents is crucial for text generation evaluation and content alignment, especially in cross-lingual settings. However, as a standalone task, it has received little attention. We address this by introducing SwissGov-RSD, the first naturalistic, document-level, cross-lingual dataset for semantic difference recognition. It encompasses a total of 224 multi-parallel documents in English--German, English--French, and English--Italian with token-level difference annotations by human annotators. We evaluate a variety of open-source and closed-source large language models as well as encoder models across different fine-tuning settings on this new benchmark. Our results show that current automatic approaches perform poorly compared to their performance on monolingual, sentence-level, and synthetic benchmarks, revealing a considerable gap for both LLMs and encoder models. We make our code and dataset publicly available. --- ### VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection Authors: Yuzhou Nie, Hongwei Li, Chengquan Guo, Ruizhe Jiang, Zhun Wang, Bo Li, Dawn Song, Wenbo Guo Published: 2025-12-08 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.07533v1 We propose VulnLLM-R, the~\emph{first specialized reasoning LLM} for vulnerability detection. Our key insight is that LLMs can reason about program states and analyze the potential vulnerabilities, rather than simple pattern matching. This can improve the model's generalizability and prevent learning shortcuts. However, SOTA reasoning LLMs are typically ultra-large, closed-source, or have limited performance in vulnerability detection. To address this, we propose a novel training recipe with specialized data selection, reasoning data generation, reasoning data filtering and correction, and testing-phase optimization. Using our proposed methodology, we train a reasoning model with seven billion parameters. Through extensive experiments on SOTA datasets across Python, C/C++, and Java, we show that VulnLLM-R has superior effectiveness and efficiency than SOTA static analysis tools and both open-source and commercial large reasoning models. We further conduct a detailed ablation study to validate the key designs in our training recipe. Finally, we construct an agent scaffold around our model and show that it outperforms CodeQL and AFL++ in real-world projects. Our agent further discovers a set of zero-day vulnerabilities in actively maintained repositories. This work represents a pioneering effort to enable real-world, project-level vulnerability detection using AI agents powered by specialized reasoning models. The code is available at~\href{https://github.com/ucsb-mlsec/VulnLLM-R}{github}. --- ### Model-Based Reinforcement Learning Under Confounding Authors: Nishanth Venkatesh, Andreas A. Malikopoulos Published: 2025-12-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.07528v1 We investigate model-based reinforcement learning in contextual Markov decision processes (C-MDPs) in which the context is unobserved and induces confounding in the offline dataset. In such settings, conventional model-learning methods are fundamentally inconsistent, as the transition and reward mechanisms generated under a behavioral policy do not correspond to the interventional quantities required for evaluating a state-based policy. To address this issue, we adapt a proximal off-policy evaluation approach that identifies the confounded reward expectation using only observable state-action-reward trajectories under mild invertibility conditions on proxy variables. When combined with a behavior-averaged transition model, this construction yields a surrogate MDP whose Bellman operator is well defined and consistent for state-based policies, and which integrates seamlessly with the maximum causal entropy (MaxCausalEnt) model-learning framework. The proposed formulation enables principled model learning and planning in confounded environments where contextual information is unobserved, unavailable, or impractical to collect. --- ### From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images Authors: Fei Yu, Yu Liu, Luyang Tang, Mingchao Sun, Zengye Ge, Rui Bu, Yuchao Jin, Haisen Zhao, He Sun, Yangyan Li, Mu Xu, Wenzheng Chen et al. Published: 2025-12-08 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2512.07527v3 City-scale 3D reconstruction from satellite imagery presents the challenge of extreme viewpoint extrapolation, where our goal is to synthesize ground-level novel views from sparse orbital images with minimal parallax. This requires inferring nearly $90^\circ$ viewpoint gaps from image sources with severely foreshortened facades and flawed textures, causing state-of-the-art reconstruction engines such as NeRF and 3DGS to fail. To address this problem, we propose two design choices tailored for city structures and satellite inputs. First, we model city geometry as a 2.5D height map, implemented as a Z-monotonic signed distance field (SDF) that matches urban building layouts from top-down viewpoints. This stabilizes geometry optimization under sparse, off-nadir satellite views and yields a watertight mesh with crisp roofs and clean, vertically extruded facades. Second, we paint the mesh appearance from satellite images via differentiable rendering techniques. While the satellite inputs may contain long-range, blurry captures, we further train a generative texture restoration network to enhance the appearance, recovering high-frequency, plausible texture details from degraded inputs. Our method's scalability and robustness are demonstrated through extensive experiments on large-scale urban reconstruction. For example, in our teaser figure, we reconstruct a $4\,\mathrm{km}^2$ real-world region from only a few satellite images, achieving state-of-the-art performance in synthesizing photorealistic ground views. The resulting models are not only visually compelling but also serve as high-fidelity, application-ready assets for downstream tasks like urban planning and simulation. Project page can be found at https://pku-vcl-geometry.github.io/Orbit2Ground/. --- ### Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs Authors: Xiaoran Liu, Yuerong Song, Zhigeng Liu, Zengfeng Huang, Qipeng Guo, Zhaoxiang Liu, Shiguo Lian, Ziwei He, Xipeng Qiu Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07525v1 Rotary Position Embeddings (RoPE) have become a standard for encoding sequence order in Large Language Models (LLMs) by applying rotations to query and key vectors in the complex plane. Standard implementations, however, utilize only the real component of the complex-valued dot product for attention score calculation. This simplification discards the imaginary component, which contains valuable phase information, leading to a potential loss of relational details crucial for modeling long-context dependencies. In this paper, we propose an extension that re-incorporates this discarded imaginary component. Our method leverages the full complex-valued representation to create a dual-component attention score. We theoretically and empirically demonstrate that this approach enhances the modeling of long-context dependencies by preserving more positional information. Furthermore, evaluations on a suite of long-context language modeling benchmarks show that our method consistently improves performance over the standard RoPE, with the benefits becoming more significant as context length increases. The code is available at https://github.com/OpenMOSS/rope_pp. --- ### LIME: Making LLM Data More Efficient with Linguistic Metadata Embeddings Authors: Sebastian Sztwiertnia, Felix Friedrich, Kristian Kersting, Patrick Schramowski, Björn Deiseroth Published: 2025-12-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.07522v1 Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential as a direct training signal remains under-explored. We challenge this status quo and propose LIME (Linguistic Metadata Embeddings), a method that enriches token embeddings with metadata capturing syntax, semantics, and contextual properties. LIME substantially improves pre-training efficiency. Specifically, it adapts up to 56% faster to the training data distribution, while introducing only 0.01% additional parameters at negligible compute overhead. Beyond efficiency, LIME improves tokenization, leading to remarkably stronger language modeling capabilities and generative task performance. These benefits persist across model scales (500M to 2B). In addition, we develop a variant with shifted metadata, LIME+1, that can guide token generation. Given prior metadata for the next token, LIME+1 improves reasoning performance by up to 38% and arithmetic accuracy by up to 35%. --- ### Machine Learning: Progress and Prospects Authors: Alexander Gammerman Published: 2025-12-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.07519v1 This Inaugural Lecture was given at Royal Holloway University of London in 1996. It covers an introduction to machine learning and describes various theoretical advances and practical projects in the field. The Lecture here is presented in its original format, but a few remarks have been added in 2025 to reflect recent developments, and the list of references has been updated to enhance the convenience and accuracy for readers. When did machine learning start? Maybe a good starting point is 1949, when Claude Shannon proposed a learning algorithm for chess-playing programs. Or maybe we should go back to the 1930s when Ronald Fisher developed discriminant analysis - a type of learning where the problem is to construct a decision rule that separates two types of vectors. Or could it be the 18th century when David Hume discussed the idea of induction? Or the 14th century, when William of Ockham formulated the principle of "simplicity" known as "Ockham's razor" (Ockham, by the way, is a small village not far from Royal Holloway). Or it may be that, like almost everything else in Western civilisation and culture, the origin of these ideas lies in the Mediterranean. After all, it was Aristotle who said that "we learn some things only by doing things". The field of machine learning has been greatly influenced by other disciplines and the subject is in itself not a very homogeneous discipline, but includes separate, overlapping subfields. There are many parallel lines of research in ML: inductive learning, neural networks, clustering, and theories of learning. They are all part of the more general field of machine learning. --- ### TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG Authors: Pengqian Lu, Jie Lu, Anjin Liu, Guangquan Zhang Published: 2025-12-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.07515v4 Detecting hallucinations in Retrieval-Augmented Generation remains a challenge. Prior approaches attribute hallucinations to a binary conflict between internal knowledge stored in FFNs and the retrieved context. However, this perspective is incomplete, failing to account for the impact of other components of the LLM, such as the user query, previously generated tokens, the self token, and the final LayerNorm adjustment. To comprehensively capture the impact of these components on hallucination detection, we propose TPA which mathematically attributes each token's probability to seven distinct sources: Query, RAG Context, Past Token, Self Token, FFN, Final LayerNorm, and Initial Embedding. This attribution quantifies how each source contributes to the generation of the next token. Specifically, we aggregate these attribution scores by Part-of-Speech (POS) tags to quantify the contribution of each model component to the generation of specific linguistic categories within a response. By leveraging these patterns, such as detecting anomalies where Nouns rely heavily on LayerNorm, TPA effectively identifies hallucinated responses. Extensive experiments show that TPA achieves state-of-the-art performance. --- ### MeshRipple: Structured Autoregressive Generation of Artist-Meshes Authors: Junkai Lin, Hang Long, Huipeng Guo, Jielei Zhang, JiaYi Yang, Tianle Guo, Yang Yang, Jianwen Li, Wenxiao Zhang, Matthias Nießner, Wei Yang Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07514v2 Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks long-range geometric dependencies, producing holes and fragmented components. To address this critical limitation, we introduce MeshRipple, which expands a mesh outward from an active generation frontier, akin to a ripple on a surface. MeshRipple rests on three key innovations: a frontier-aware BFS tokenization that aligns the generation order with surface topology; an expansive prediction strategy that maintains coherent, connected surface growth; and a sparse-attention global memory that provides an effectively unbounded receptive field to resolve long-range topological dependencies. This integrated design enables MeshRipple to generate meshes with high surface fidelity and topological completeness, outperforming strong recent baselines. --- ### Exploring possible vector systems for faster training of neural networks with preconfigured latent spaces Authors: Nikita Gabdullin Published: 2025-12-08 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.07509v2 The overall neural network (NN) performance is closely related to the properties of its embedding distribution in latent space (LS). It has recently been shown that predefined vector systems, specifically An root system vectors, can be used as targets for latent space configurations (LSC) to ensure the desired LS structure. One of the main LSC advantage is the possibility of training classifier NNs without classification layers, which facilitates training NNs on datasets with extremely large numbers of classes. This paper provides a more general overview of possible vector systems for NN training along with their properties and methods for vector system construction. These systems are used to configure LS of encoders and visual transformers to significantly speed up ImageNet-1K and 50k-600k classes LSC training. It is also shown that using the minimum number of LS dimensions for a specific number of classes results in faster convergence. The latter has potential advantages for reducing the size of vector databases used to store NN embeddings. --- ### ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points Authors: Ryota Okumura, Kaede Shiohara, Toshihiko Yamasaki Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07504v1 Recent text-to-image models, such as Stable Diffusion, have achieved impressive visual quality, yet they often suffer from geometric inconsistencies that undermine the structural realism of generated scenes. One prominent issue is vanishing point inconsistency, where projections of parallel lines fail to converge correctly in 2D space. This leads to structurally implausible geometry that degrades spatial realism, especially in architectural scenes. We propose ControlVP, a user-guided framework for correcting vanishing point inconsistencies in generated images. Our approach extends a pre-trained diffusion model by incorporating structural guidance derived from building contours. We also introduce geometric constraints that explicitly encourage alignment between image edges and perspective cues. Our method enhances global geometric consistency while maintaining visual fidelity comparable to the baselines. This capability is particularly valuable for applications that require accurate spatial structure, such as image-to-3D reconstruction. The dataset and source code are available at https://github.com/RyotaOkumura/ControlVP . --- ### SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation Authors: Yao Teng, Zhihuan Jiang, Han Shi, Xian Liu, Xuefei Ning, Guohao Dai, Yu Wang, Zhenguo Li, Xihui Liu Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07503v1 Large autoregressive models can generate high-quality, high-resolution images but suffer from slow generation speed, because these models require hundreds to thousands of sequential forward passes for next-token prediction during inference. To accelerate autoregressive text-to-image generation, we propose Speculative Jacobi Decoding++ (SJD++), a training-free probabilistic parallel decoding algorithm. Unlike traditional next-token prediction, SJD++ performs multi-token prediction in each forward pass, drastically reducing generation steps. Specifically, it integrates the iterative multi-token prediction mechanism from Jacobi decoding, with the probabilistic drafting-and-verification mechanism from speculative sampling. More importantly, for further acceleration, SJD++ reuses high-confidence draft tokens after each verification phase instead of resampling them all. We conduct extensive experiments on several representative autoregressive text-to-image generation models and demonstrate that SJD++ achieves $2\times$ to $3\times$ inference latency reduction and $2\times$ to $7\times$ step compression, while preserving visual quality with no observable degradation. --- ### AutoICE: Automatically Synthesizing Verifiable C Code via LLM-driven Evolution Authors: Weilin Luo, Xueyi Liang, Haotian Deng, Yanan Liu, Hai Wan Published: 2025-12-08 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.07501v1 Automatically synthesizing verifiable code from natural language requirements ensures software correctness and reliability while significantly lowering the barrier to adopting the techniques of formal methods. With the rise of large language models (LLMs), long-standing efforts at autoformalization have gained new momentum. However, existing approaches suffer from severe syntactic and semantic errors due to the scarcity of domain-specific pre-training corpora and often fail to formalize implicit knowledge effectively. In this paper, we propose AutoICE, an LLM-driven evolutionary search for synthesizing verifiable C code. It introduces the diverse individual initialization and the collaborative crossover to enable diverse iterative updates, thereby mitigating error propagation inherent in single-agent iterations. Besides, it employs the self-reflective mutation to facilitate the discovery of implicit knowledge. Evaluation results demonstrate the effectiveness of AutoICE: it successfully verifies $90.36$\% of code, outperforming the state-of-the-art (SOTA) approach. Besides, on a developer-friendly dataset variant, AutoICE achieves a $88.33$\% verification success rate, significantly surpassing the $65$\% success rate of the SOTA approach. --- ### MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformer Authors: Penghui Liu, Jiangshan Wang, Yutong Shen, Shanhui Mo, Chenyang Qi, Yue Ma Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07500v2 Multi-object video motion transfer poses significant challenges for Diffusion Transformer (DiT) architectures due to inherent motion entanglement and lack of object-level control. We present MultiMotion, a novel unified framework that overcomes these limitations. Our core innovation is Maskaware Attention Motion Flow (AMF), which utilizes SAM2 masks to explicitly disentangle and control motion features for multiple objects within the DiT pipeline. Furthermore, we introduce RectPC, a high-order predictor-corrector solver for efficient and accurate sampling, particularly beneficial for multi-entity generation. To facilitate rigorous evaluation, we construct the first benchmark dataset specifically for DiT-based multi-object motion transfer. MultiMotion demonstrably achieves precise, semantically aligned, and temporally coherent motion transfer for multiple distinct objects, maintaining DiT's high quality and scalability. The code is in the supp. --- ### Towards Robust DeepFake Detection under Unstable Face Sequences: Adaptive Sparse Graph Embedding with Order-Free Representation and Explicit Laplacian Spectral Prior Authors: Chih-Chung Hsu, Shao-Ning Chen, Chia-Ming Lee, Yi-Fang Wang, Yi-Shiuan Chou Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07498v1 Ensuring the authenticity of video content remains challenging as DeepFake generation becomes increasingly realistic and robust against detection. Most existing detectors implicitly assume temporally consistent and clean facial sequences, an assumption that rarely holds in real-world scenarios where compression artifacts, occlusions, and adversarial attacks destabilize face detection and often lead to invalid or misdetected faces. To address these challenges, we propose a Laplacian-Regularized Graph Convolutional Network (LR-GCN) that robustly detects DeepFakes from noisy or unordered face sequences, while being trained only on clean facial data. Our method constructs an Order-Free Temporal Graph Embedding (OF-TGE) that organizes frame-wise CNN features into an adaptive sparse graph based on semantic affinities. Unlike traditional methods constrained by strict temporal continuity, OF-TGE captures intrinsic feature consistency across frames, making it resilient to shuffled, missing, or heavily corrupted inputs. We further impose a dual-level sparsity mechanism on both graph structure and node features to suppress the influence of invalid faces. Crucially, we introduce an explicit Graph Laplacian Spectral Prior that acts as a high-pass operator in the graph spectral domain, highlighting structural anomalies and forgery artifacts, which are then consolidated by a low-pass GCN aggregation. This sequential design effectively realizes a task-driven spectral band-pass mechanism that suppresses background information and random noise while preserving manipulation cues. Extensive experiments on FF++, Celeb-DFv2, and DFDC demonstrate that LR-GCN achieves state-of-the-art performance and significantly improved robustness under severe global and local disruptions, including missing faces, occlusions, and adversarially perturbed face detections. --- ### How Do LLMs Fail In Agentic Scenarios? A Qualitative Analysis of Success and Failure Scenarios of Various LLMs in Agentic Simulations Authors: JV Roig Published: 2025-12-08 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2512.07497v2 We investigate how large language models (LLMs) fail when operating as autonomous agents with tool-use capabilities. Using the Kamiwaza Agentic Merit Index (KAMI) v0.1 benchmark, we analyze 900 execution traces from three representative models - Granite 4 Small, Llama 4 Maverick, and DeepSeek V3.1 - across filesystem, text extraction, CSV analysis, and SQL scenarios. Rather than focusing on aggregate scores, we perform fine-grained, per-trial behavioral analysis to surface the strategies that enable successful multi-step tool execution and the recurrent failure modes that undermine reliability. Our findings show that model scale alone does not predict agentic robustness: Llama 4 Maverick (400B) performs only marginally better than Granite 4 Small (32B) in some uncertainty-driven tasks, while DeepSeek V3.1's superior reliability derives primarily from post-training reinforcement learning rather than architecture or size. Across models, we identify four recurring failure archetypes: premature action without grounding, over-helpfulness that substitutes missing entities, vulnerability to distractor-induced context pollution, and fragile execution under load. These patterns highlight the need for agentic evaluation methods that emphasize interactive grounding, recovery behavior, and environment-aware adaptation, suggesting that reliable enterprise deployment requires not just stronger models but deliberate training and design choices that reinforce verification, constraint discovery, and adherence to source-of-truth data. --- ### Efficient Low-Tubal-Rank Tensor Estimation via Alternating Preconditioned Gradient Descent Authors: Zhiyu Liu, Zhi Han, Yandong Tang, Jun Fan, Yao Wang Published: 2025-12-08 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2512.07490v3 The problem of low-tubal-rank tensor estimation is a fundamental task with wide applications across high-dimensional signal processing, machine learning, and image science. Traditional approaches tackle such a problem by performing tensor singular value decomposition, which is computationally expensive and becomes infeasible for large-scale tensors. Recent approaches address this issue by factorizing the tensor into two smaller factor tensors and solving the resulting problem using gradient descent. However, this kind of approach requires an accurate estimate of the tensor rank, and when the rank is overestimated, the convergence of gradient descent and its variants slows down significantly or even diverges. To address this problem, we propose an Alternating Preconditioned Gradient Descent (APGD) algorithm, which accelerates convergence in the over-parameterized setting by adding a preconditioning term to the original gradient and updating these two factors alternately. Based on certain geometric assumptions on the objective function, we establish linear convergence guarantees for more general low-tubal-rank tensor estimation problems. Then we further analyze the specific cases of low-tubal-rank tensor factorization and low-tubal-rank tensor recovery. Our theoretical results show that APGD achieves linear convergence even under over-parameterization, and the convergence rate is independent of the tensor condition number. Extensive simulations on synthetic data are carried out to validate our theoretical assertions. --- ### Artificial Intelligence and Nuclear Weapons Proliferation: The Technological Arms Race for (In)visibility Authors: David M. Allison, Stephen Herzog Published: 2025-12-08 Categories: cs.CY, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2512.07487v1 A robust nonproliferation regime has contained the spread of nuclear weapons to just nine states. Yet, emerging and disruptive technologies are reshaping the landscape of nuclear risks, presenting a critical juncture for decision makers. This article lays out the contours of an overlooked but intensifying technological arms race for nuclear (in)visibility, driven by the interplay between proliferation-enabling technologies (PETs) and detection-enhancing technologies (DETs). We argue that the strategic pattern of proliferation will be increasingly shaped by the innovation pace in these domains. Artificial intelligence (AI) introduces unprecedented complexity to this equation, as its rapid scaling and knowledge substitution capabilities accelerate PET development and challenge traditional monitoring and verification methods. To analyze this dynamic, we develop a formal model centered on a Relative Advantage Index (RAI), quantifying the shifting balance between PETs and DETs. Our model explores how asymmetric technological advancement, particularly logistic AI-driven PET growth versus stepwise DET improvements, expands the band of uncertainty surrounding proliferation detectability. Through replicable scenario-based simulations, we evaluate the impact of varying PET growth rates and DET investment strategies on cumulative nuclear breakout risk. We identify a strategic fork ahead, where detection may no longer suffice without broader PET governance. Governments and international organizations should accordingly invest in policies and tools agile enough to keep pace with tomorrow's technology. --- ### Materium: An Autoregressive Approach for Material Generation Authors: Niklas Dobberstein, Jan Hamaekers Published: 2025-12-08 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2512.07486v1 We present Materium: an autoregressive transformer for generating crystal structures that converts 3D material representations into token sequences. These sequences include elements with oxidation states, fractional coordinates and lattice parameters. Unlike diffusion approaches, which refine atomic positions iteratively through many denoising steps, Materium places atoms at precise fractional coordinates, enabling fast, scalable generation. With this design, the model can be trained in a few hours on a single GPU and generate samples much faster on GPUs and CPUs than diffusion-based approaches. The model was trained and evaluated using multiple properties as conditions, including fundamental properties, such as density and space group, as well as more practical targets, such as band gap and magnetic density. In both single and combined conditions, the model performs consistently well, producing candidates that align with the requested inputs. --- ### From Real-World Traffic Data to Relevant Critical Scenarios Authors: Florian Lüttner, Nicole Neis, Daniel Stadler, Robin Moss, Mirjam Fehling-Kaschek, Matthias Pfriem, Alexander Stolz, Jens Ziehn Published: 2025-12-08 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.07482v1 The reliable operation of autonomous vehicles, automated driving functions, and advanced driver assistance systems across a wide range of relevant scenarios is critical for their development and deployment. Identifying a near-complete set of relevant driving scenarios for such functionalities is challenging due to numerous degrees of freedom involved, each affecting the outcomes of the driving scenario differently. Moreover, with increasing technical complexity of new functionalities, the number of potentially relevant, particularly "unknown unsafe" scenarios is increasing. To enhance validation efficiency, it is essential to identify relevant scenarios in advance, starting with simpler domains like highways before moving to more complex environments such as urban traffic. To address this, this paper focuses on analyzing lane change scenarios in highway traffic, which involve multiple degrees of freedom and present numerous safetyrelevant scenarios. We describe the process of data acquisition and processing of real-world data from public highway traffic, followed by the application of criticality measures on trajectory data to evaluate scenarios, as conducted within the AVEAS project (www.aveas.org). By linking the calculated measures to specific lane change driving scenarios and the conditions under which the data was collected, we facilitate the identification of safetyrelevant driving scenarios for various applications. Further, to tackle the extensive range of "unknown unsafe" scenarios, we propose a way to generate relevant scenarios by creating synthetic scenarios based on recorded ones. Consequently, we demonstrate and evaluate a processing chain that enables the identification of safety-relevant scenarios, the development of data-driven methods for extracting these scenarios, and the generation of synthetic critical scenarios via sampling on highways. --- ### Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance Authors: Naifu Xue, Zhaoyang Jia, Jiahao Li, Bin Li, Zihan Zheng, Yuan Zhang, Yan Lu Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07480v2 While traditional and neural video codecs (NVCs) have achieved remarkable rate-distortion performance, improving perceptual quality at low bitrates remains challenging. Some NVCs incorporate perceptual or adversarial objectives but still suffer from artifacts due to limited generation capacity, whereas others leverage pretrained diffusion models to improve quality at the cost of heavy sampling complexity. To overcome these challenges, we propose S2VC, a Single-Step diffusion based Video Codec that integrates a conditional coding framework with an efficient single-step diffusion generator, enabling realistic reconstruction at low bitrates with reduced sampling cost. Recognizing the importance of semantic conditioning in single-step diffusion, we introduce Contextual Semantic Guidance to extract frame-adaptive semantics from buffered features. It replaces text captions with efficient, fine-grained conditioning, thereby improving generation realism. In addition, Temporal Consistency Guidance is incorporated into the diffusion U-Net to enforce temporal coherence across frames and ensure stable generation. Extensive experiments show that S2VC delivers state-of-the-art perceptual quality with an average 52.73% bitrate saving over prior perceptual methods, underscoring the promise of single-step diffusion for efficient, high-quality video compression. Project: https://onedc-codec.github.io/s2vc/ --- ### Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization Authors: Jianghao Su, Xia Zeng, Luhui Liu, Chao Luo, Ye Chen, Zhuoran Zhuang Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07478v2 Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks. Agentic Reinforcement Learning (Agentic RL) optimizes such models over full tool-interaction trajectories, but two key challenges hinder effectiveness: (1) Sparse, non-instructive rewards, such as binary 0-1 verifiable signals, provide limited guidance for intermediate steps and slow convergence; (2) Gradient degradation in Group Relative Policy Optimization (GRPO), where identical rewards within a rollout group yield zero advantage, which reducing sample efficiency. To address these challenges, we propose two complementary techniques: Progressive Reward Shaping (PRS) and Value-based Sampling Policy Optimization (VSPO). PRS is a curriculum-inspired reward design that introduces dense, stage-wise feedback - encouraging models to first master parseable and properly formatted tool calls, then optimize for factual correctness and answer quality. We instantiate PRS for short-form QA (with a length-aware BLEU to fairly score concise answers) and long-form QA (with LLM-as-a-Judge scoring to prevent reward hacking). VSPO is an enhanced GRPO variant that replaces zero advantages samples with prompts selected by a task-value metric balancing difficulty and uncertainty, and applies value-smoothing clipping to stabilize gradient updates. Experiments on multiple short-form and long-form QA benchmarks show that PRS consistently outperforms traditional binary rewards, and VSPO achieves superior stability, faster convergence, and higher final performance compared to SFT, PPO and GRPO baselines. Together, PRS and VSPO yield LLM-based TIR agents that generalize better across domains. --- ### Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels Authors: Yifei Huang, Tianyu Yan, Sitong Gong, Xiwei Gao, Caixin Kang, Ruicong Liu, Huchuan Lu, Bo Zheng Published: 2025-12-08 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2512.07474v1 We present the Living Novel, an end-to-end system that transforms any literary work into an immersive, multi-character conversational experience. This system is designed to solve two fundamental challenges for LLM-driven characters. Firstly, generic LLMs suffer from persona drift, often failing to stay in character. Secondly, agents often exhibit abilities that extend beyond the constraints of the story's world and logic, leading to both narrative incoherence (spoiler leakage) and robustness failures (frame-breaking). To address these challenges, we introduce a novel two-stage training pipeline. Our Deep Persona Alignment (DPA) stage uses data-free reinforcement finetuning to instill deep character fidelity. Our Coherence and Robustness Enhancing (CRE) stage then employs a story-time-aware knowledge graph and a second retrieval-grounded training pass to architecturally enforce these narrative constraints. We validate our system through a multi-phase evaluation using Jules Verne's Twenty Thousand Leagues Under the Sea. A lab study with a detailed ablation of system components is followed by a 5-day in-the-wild diary study. Our DPA pipeline helps our specialized model outperform GPT-4o on persona-specific metrics, and our CRE stage achieves near-perfect performance in coherence and robustness measures. Our study surfaces practical design guidelines for AI-driven narrative systems: we find that character-first self-training is foundational for believability, while explicit story-time constraints are crucial for sustaining coherent, interruption-resilient mobile-web experiences. --- ### Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation Authors: Siyu Xu, Zijian Wang, Yunke Wang, Chenghao Xia, Tao Huang, Chang Xu Published: 2025-12-08 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2512.07472v1 Vision-Language-Action (VLA) models have shown great performance in robotic manipulation by mapping visual observations and language instructions directly to actions. However, they remain brittle under distribution shifts: when test scenarios change, VLAs often reproduce memorized trajectories instead of adapting to the updated scene, which is a failure mode we refer to as the "Memory Trap". This limitation stems from the end-to-end design, which lacks explicit 3D spatial reasoning and prevents reliable identification of actionable regions in unfamiliar environments. To compensate for this missing spatial understanding, 3D Spatial Affordance Fields (SAFs) can provide a geometric representation that highlights where interactions are physically feasible, offering explicit cues about regions the robot should approach or avoid. We therefore introduce Affordance Field Intervention (AFI), a lightweight hybrid framework that uses SAFs as an on-demand plug-in to guide VLA behavior. Our system detects memory traps through proprioception, repositions the robot to recent high-affordance regions, and proposes affordance-driven waypoints that anchor VLA-generated actions. A SAF-based scorer then selects trajectories with the highest cumulative affordance. Extensive experiments demonstrate that our method achieves an average improvement of 23.5% across different VLA backbones ($π_{0}$ and $π_{0.5}$) under out-of-distribution scenarios on real-world robotic platforms, and 20.2% on the LIBERO-Pro benchmark, validating its effectiveness in enhancing VLA robustness to distribution shifts. --- ### VideoCoF: Unified Video Editing with Temporal Reasoner Authors: Xiangpeng Yang, Ji Xie, Yiyuan Yang, Yue Ma, Yan Huang, Min Xu, Qiang Wu Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07469v2 Existing video editing methods face a critical trade-off: expert models offer precision but rely on task-specific priors like masks, hindering unification; conversely, unified temporal in-context learning models are mask-free but lack explicit spatial cues, leading to weak instruction-to-region mapping and imprecise localization. To resolve this conflict, we propose VideoCoF, a novel Chain-of-Frames approach inspired by Chain-of-Thought reasoning. VideoCoF enforces a ``see, reason, then edit" procedure by compelling the video diffusion model to first predict reasoning tokens (edit-region latents) before generating the target video tokens. This explicit reasoning step removes the need for user-provided masks while achieving precise instruction-to-region alignment and fine-grained video editing. Furthermore, we introduce a RoPE alignment strategy that leverages these reasoning tokens to ensure motion alignment and enable length extrapolation beyond the training duration. We demonstrate that with a minimal data cost of only 50k video pairs, VideoCoF achieves state-of-the-art performance on VideoCoF-Bench, validating the efficiency and effectiveness of our approach. Our code, weight, data are available at https://github.com/knightyxp/VideoCoF. --- ### Parallel Algorithms for Structured Sparse Support Vector Machines: Application in Music Genre Classification Authors: Rongmei Liang, Zizheng Liu, Xiaofei Wu, Jingwen Tu Published: 2025-12-08 Categories: cs.LG, stat.AP, stat.CO arXiv: https://arxiv.org/abs/2512.07463v2 Mathematical modelling, particularly through approaches such as structured sparse support vector machines (SS-SVM), plays a crucial role in processing data with complex feature structures, yet efficient algorithms for distributed large-scale data remain lacking. To address this gap, this paper proposes a unified optimization framework based on a consensus structure. This framework is not only applicable to various loss functions and combined regularization terms but can also be effectively extended to non-convex regularizers, demonstrating strong scalability. Building upon this framework, we develop a distributed parallel alternating direction method of multipliers (ADMM) algorithm to efficiently solve SS-SVMs under distributed data storage. To ensure convergence, we incorporate a Gaussian back-substitution technique. Additionally, for completeness, we introduce a family of sparse group Lasso support vector machine (SGL-SVM) and apply it to music information retrieval. Theoretical analysis confirms that the computational complexity of the proposed algorithm is independent of the choice of regularization terms and loss functions, underscoring the universality of the parallel approach. Experiments on both synthetic and real-world music archive datasets validate the reliability, stability, and efficiency of our algorithm. --- ### Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamics Authors: Trung-Kiet Huynh, Duy-Minh Dao-Sy, Thanh-Bang Cao, Phong-Hao Le, Hong-Dan Nguyen, Phu-Quy Nguyen-Lam, Minh-Luan Nguyen-Vo, Hong-Phat Pham, Phu-Hoa Pham, Thien-Kim Than, Chi-Nguyen Tran, Huy Tran et al. Published: 2025-12-08 Categories: cs.MA, cs.AI, cs.GT, cs.LG, math.DS arXiv: https://arxiv.org/abs/2512.07462v2 As Large Language Models (LLMs) increasingly operate as autonomous decision-makers in interactive and multi-agent systems and human societies, understanding their strategic behaviour has profound implications for safety, coordination, and the design of AI-driven social and economic infrastructures. Assessing such behaviour requires methods that capture not only what LLMs output, but the underlying intentions that guide their decisions. In this work, we extend the FAIRGAME framework to systematically evaluate LLM behaviour in repeated social dilemmas through two complementary advances: a payoff-scaled Prisoners Dilemma isolating sensitivity to incentive magnitude, and an integrated multi-agent Public Goods Game with dynamic payoffs and multi-agent histories. These environments reveal consistent behavioural signatures across models and languages, including incentive-sensitive cooperation, cross-linguistic divergence and end-game alignment toward defection. To interpret these patterns, we train traditional supervised classification models on canonical repeated-game strategies and apply them to FAIRGAME trajectories, showing that LLMs exhibit systematic, model- and language-dependent behavioural intentions, with linguistic framing at times exerting effects as strong as architectural differences. Together, these findings provide a unified methodological foundation for auditing LLMs as strategic agents and reveal systematic cooperation biases with direct implications for AI governance, collective decision-making, and the design of safe multi-agent systems. --- ### Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning Authors: Tong Wu, Yang Liu, Jun Bai, Zixia Jia, Shuyi Zhang, Ziyong Lin, Yanting Wang, Song-Chun Zhu, Zilong Zheng Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07461v3 We introduce Native Parallel Reasoner (NPR), a teacher-free framework that enables Large Language Models (LLMs) to self-evolve genuine parallel reasoning capabilities. NPR transforms the model from sequential emulation to native parallel cognition through three key innovations: 1) a self-distilled progressive training paradigm that transitions from ``cold-start'' format discovery to strict topological constraints without external supervision; 2) a novel Parallel-Aware Policy Optimization (PAPO) algorithm that optimizes branching policies directly within the execution graph, allowing the model to learn adaptive decomposition via trial and error; and 3) a robust NPR Engine that refactors memory management and flow control of SGLang to enable stable, large-scale parallel RL training. Across eight reasoning benchmarks, NPR trained on Qwen3-4B achieves performance gains of up to 24.5% and inference speedups up to 4.6x. Unlike prior baselines that often fall back to autoregressive decoding, NPR demonstrates 100% genuine parallel execution, establishing a new standard for self-evolving, efficient, and scalable agentic reasoning. --- ### Human Geometry Distribution for 3D Animation Generation Authors: Xiangjun Tang, Biao Zhang, Peter Wonka Published: 2025-12-08 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2512.07459v1 Generating realistic human geometry animations remains a challenging task, as it requires modeling natural clothing dynamics with fine-grained geometric details under limited data. To address these challenges, we propose two novel designs. First, we propose a compact distribution-based latent representation that enables efficient and high-quality geometry generation. We improve upon previous work by establishing a more uniform mapping between SMPL and avatar geometries. Second, we introduce a generative animation model that fully exploits the diversity of limited motion data. We focus on short-term transitions while maintaining long-term consistency through an identity-conditioned design. These two designs formulate our method as a two-stage framework: the first stage learns a latent space, while the second learns to generate animations within this latent space. We conducted experiments on both our latent space and animation model. We demonstrate that our latent space produces high-fidelity human geometry surpassing previous methods ($90\%$ lower Chamfer Dist.). The animation model synthesizes diverse animations with detailed and natural dynamics ($2.2 \times$ higher user study score), achieving the best results across all evaluation metrics. --- ### Optimized Machine Learning Methods for Studying the Thermodynamic Behavior of Complex Spin Systems Authors: Dmitrii Kapitan, Pavel Ovchinnikov, Konstantin Soldatov, Petr Andriushchenko, Vitalii Kapitan Published: 2025-12-08 Categories: physics.comp-ph, cond-mat.dis-nn, cs.LG arXiv: https://arxiv.org/abs/2512.07458v1 This paper presents a systematic study of the application of convolutional neural networks (CNNs) as an efficient and versatile tool for the analysis of critical and low-temperature phase states in spin system models. The problem of calculating the dependence of the average energy on the spatial distribution of exchange integrals for the Edwards-Anderson model on a square lattice with frustrated interactions is considered. We further construct a single convolutional classifier of phase states of the ferromagnetic Ising model on square, triangular, honeycomb, and kagome lattices, trained on configurations generated by the Swendsen-Wang cluster algorithm. Computed temperature profiles of the averaged posterior probability of the high-temperature phase form clear S-shaped curves that intersect in the vicinity of the theoretical critical temperatures and allow one to determine the critical temperature for the kagome lattice without additional retraining. It is shown that convolutional models substantially reduce the root-mean-square error (RMSE) compared with fully connected architectures and efficiently capture complex correlations between thermodynamic characteristics and the structure of magnetic correlated systems. --- ### Persian-Phi: Efficient Cross-Lingual Adaptation of Compact LLMs via Curriculum Learning Authors: Amir Mohammad Akhlaghi, Amirhossein Shabani, Mostafa Abdolmaleki, Saeed Reza Kheradpisheh Published: 2025-12-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.07454v1 The democratization of AI is currently hindered by the immense computational costs required to train Large Language Models (LLMs) for low-resource languages. This paper presents Persian-Phi, a 3.8B parameter model that challenges the assumption that robust multilingual capabilities require massive model sizes or multilingual baselines. We demonstrate how Microsoft Phi-3 Mini -- originally a monolingual English model -- can be effectively adapted to Persian through a novel, resource-efficient curriculum learning pipeline. Our approach employs a unique "warm-up" stage using bilingual narratives (Tiny Stories) to align embeddings prior to heavy training, followed by continual pretraining and instruction tuning via Parameter-Efficient Fine-Tuning (PEFT). Despite its compact size, Persian-Phi achieves competitive results on Open Persian LLM Leaderboard in HuggingFace. Our findings provide a validated, scalable framework for extending the reach of state-of-the-art LLMs to underrepresented languages with minimal hardware resources. The Persian-Phi model is publicly available at https://huggingface.co/amirakhlaghiqqq/PersianPhi. ---