# Research Papers — 2025-12 · bundle page 26 of 175 > Full-text markdown of papers #1251–1300 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/26 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/25.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/27.md) ### Towards Responsible and Explainable AI Agents with Consensus-Driven Reasoning Authors: Eranga Bandara, Tharaka Hewa, Ross Gore, Sachin Shetty, Ravi Mukkamala, Peter Foytik, Abdul Rahman, Safdar H. Bouk, Xueping Liang, Amin Hass, Sachini Rajapakse, Ng Wee Keong et al. Published: 2025-12-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.21699v1 Agentic AI represents a major shift in how autonomous systems reason, plan, and execute multi-step tasks through the coordination of Large Language Models (LLMs), Vision Language Models (VLMs), tools, and external services. While these systems enable powerful new capabilities, increasing autonomy introduces critical challenges related to explainability, accountability, robustness, and governance, especially when agent outputs influence downstream actions or decisions. Existing agentic AI implementations often emphasize functionality and scalability, yet provide limited mechanisms for understanding decision rationale or enforcing responsibility across agent interactions. This paper presents a Responsible(RAI) and Explainable(XAI) AI Agent Architecture for production-grade agentic workflows based on multi-model consensus and reasoning-layer governance. In the proposed design, a consortium of heterogeneous LLM and VLM agents independently generates candidate outputs from a shared input context, explicitly exposing uncertainty, disagreement, and alternative interpretations. A dedicated reasoning agent then performs structured consolidation across these outputs, enforcing safety and policy constraints, mitigating hallucinations and bias, and producing auditable, evidence-backed decisions. Explainability is achieved through explicit cross-model comparison and preserved intermediate outputs, while responsibility is enforced through centralized reasoning-layer control and agent-level constraints. We evaluate the architecture across multiple real-world agentic AI workflows, demonstrating that consensus-driven reasoning improves robustness, transparency, and operational trust across diverse application domains. This work provides practical guidance for designing agentic AI systems that are autonomous and scalable, yet responsible and explainable by construction. --- ### FUSE: Unifying Spectral and Semantic Cues for Robust AI-Generated Image Detection Authors: Md. Zahid Hossain, Most. Sharmin Sultana Samu, Md. Kamrozzaman Bhuiyan, Farhad Uz Zaman, Md. Rakibul Islam Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21695v1 The fast evolution of generative models has heightened the demand for reliable detection of AI-generated images. To tackle this challenge, we introduce FUSE, a hybrid system that combines spectral features extracted through Fast Fourier Transform with semantic features obtained from the CLIP's Vision encoder. The features are fused into a joint representation and trained progressively in two stages. Evaluations on GenImage, WildFake, DiTFake, GPT-ImgEval and Chameleon datasets demonstrate strong generalization across multiple generators. Our FUSE (Stage 1) model demonstrates state-of-the-art results on the Chameleon benchmark. It also attains 91.36% mean accuracy on the GenImage dataset, 88.71% accuracy across all tested generators, and a mean Average Precision of 94.96%. Stage 2 training further improves performance for most generators. Unlike existing methods, which often perform poorly on high-fidelity images in Chameleon, our approach maintains robustness across diverse generators. These findings highlight the benefits of integrating spectral and semantic features for generalized detection of images generated by AI. --- ### BeHGAN: Bengali Handwritten Word Generation from Plain Text Using Generative Adversarial Networks Authors: Md. Rakibul Islam, Md. Kamrozzaman Bhuiyan, Safwan Muntasir, Arifur Rahman Jawad, Most. Sharmin Sultana Samu Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21694v1 Handwritten Text Recognition (HTR) is a well-established research area. In contrast, Handwritten Text Generation (HTG) is an emerging field with significant potential. This task is challenging due to the variation in individual handwriting styles. A large and diverse dataset is required to generate realistic handwritten text. However, such datasets are difficult to collect and are not readily available. Bengali is the fifth most spoken language in the world. While several studies exist for languages such as English and Arabic, Bengali handwritten text generation has received little attention. To address this gap, we propose a method for generating Bengali handwritten words. We developed and used a self-collected dataset of Bengali handwriting samples. The dataset includes contributions from approximately five hundred individuals across different ages and genders. All images were pre-processed to ensure consistency and quality. Our approach demonstrates the ability to produce diverse handwritten outputs from input plain text. We believe this work contributes to the advancement of Bengali handwriting generation and can support further research in this area. --- ### Prior-AttUNet: Retinal OCT Fluid Segmentation Based on Normal Anatomical Priors and Attention Gating Authors: Li Yang, Yuting Liu Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21693v1 Accurate segmentation of macular edema, a hallmark pathological feature in vision-threatening conditions such as age-related macular degeneration and diabetic macular edema, is essential for clinical diagnosis and management. To overcome the challenges of segmenting fluid regions in optical coherence tomography (OCT) images-notably ambiguous boundaries and cross-device heterogeneity-this study introduces Prior-AttUNet, a segmentation model augmented with generative anatomical priors. The framework adopts a hybrid dual-path architecture that integrates a generative prior pathway with a segmentation network. A variational autoencoder supplies multi-scale normative anatomical priors, while the segmentation backbone incorporates densely connected blocks and spatial pyramid pooling modules to capture richer contextual information. Additionally, a novel triple-attention mechanism, guided by anatomical priors, dynamically modulates feature importance across decoding stages, substantially enhancing boundary delineation. Evaluated on the public RETOUCH benchmark, Prior-AttUNet achieves excellent performance across three OCT imaging devices (Cirrus, Spectralis, and Topcon), with mean Dice similarity coefficients of 93.93%, 95.18%, and 93.47%, respectively. The model maintains a low computational cost of 0.37 TFLOPs, striking an effective balance between segmentation precision and inference efficiency. These results demonstrate its potential as a reliable tool for automated clinical analysis. --- ### ShinyNeRF: Digitizing Anisotropic Appearance in Neural Radiance Fields Authors: Albert Barreiro, Roger Marí, Rafael Redondo, Gloria Haro, Carles Bosch Published: 2025-12-25 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2512.21692v2 Recent advances in digitization technologies have transformed the preservation and dissemination of cultural heritage. In this vein, Neural Radiance Fields (NeRF) have emerged as a leading technology for 3D digitization, delivering representations with exceptional realism. However, existing methods struggle to accurately model anisotropic specular surfaces, typically observed, for example, on brushed metals. In this work, we introduce ShinyNeRF, a novel framework capable of handling both isotropic and anisotropic reflections. Our method is capable of jointly estimating surface normals, tangents, specular concentration, and anisotropy magnitudes of an Anisotropic Spherical Gaussian (ASG) distribution, by learning an approximation of the outgoing radiance as an encoded mixture of isotropic von Mises-Fisher (vMF) distributions. Experimental results show that ShinyNeRF not only achieves state-of-the-art performance on digitizing anisotropic specular reflections, but also offers plausible physical interpretations and editing of material properties compared to existing methods. --- ### Analyzing the Mechanism of Attention Collapse in VGGT from a Dynamics Perspective Authors: Huan Li, Longjun Luo, Yuling Shi, Xiaodong Gu Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21691v1 Visual Geometry Grounded Transformer (VGGT) delivers state-of-the-art feed-forward 3D reconstruction, yet its global self-attention layer suffers from a drastic collapse phenomenon when the input sequence exceeds a few hundred frames: attention matrices rapidly become near rank-one, token geometry degenerates to an almost one-dimensional subspace, and reconstruction error accumulates super-linearly.In this report,we establish a rigorous mathematical explanation of the collapse by viewing the global-attention iteration as a degenerate diffusion process.We prove that,in VGGT, the token-feature flow converges toward a Dirac-type measure at a $O(1/L)$ rate, where $L$ is the layer index, yielding a closed-form mean-field partial differential equation that precisely predicts the empirically observed rank profile.The theory quantitatively matches the attention-heat-map evolution and a series of experiments outcomes reported in relevant works and explains why its token-merging remedy -- which periodically removes redundant tokens -- slows the effective diffusion coefficient and thereby delays collapse without additional training.We believe the analysis provides a principled lens for interpreting future scalable 3D-vision transformers,and we highlight its potential for multi-modal generalization. --- ### RIPCN: A Road Impedance Principal Component Network for Probabilistic Traffic Flow Forecasting Authors: Haochen Lv, Yan Lin, Shengnan Guo, Xiaowei Mao, Hong Nie, Letian Gong, Youfang Lin, Huaiyu Wan Published: 2025-12-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.21685v1 Accurate traffic flow forecasting is crucial for intelligent transportation services such as navigation and ride-hailing. In such applications, uncertainty estimation in forecasting is important because it helps evaluate traffic risk levels, assess forecast reliability, and provide timely warnings. As a result, probabilistic traffic flow forecasting (PTFF) has gained significant attention, as it produces both point forecasts and uncertainty estimates. However, existing PTFF approaches still face two key challenges: (1) how to uncover and model the causes of traffic flow uncertainty for reliable forecasting, and (2) how to capture the spatiotemporal correlations of uncertainty for accurate prediction. To address these challenges, we propose RIPCN, a Road Impedance Principal Component Network that integrates domain-specific transportation theory with spatiotemporal principal component learning for PTFF. RIPCN introduces a dynamic impedance evolution network that captures directional traffic transfer patterns driven by road congestion level and flow variability, revealing the direct causes of uncertainty and enhancing both reliability and interpretability. In addition, a principal component network is designed to forecast the dominant eigenvectors of future flow covariance, enabling the model to capture spatiotemporal uncertainty correlations. This design allows for accurate and efficient uncertainty estimation while also improving point prediction performance. Experimental results on real-world datasets show that our approach outperforms existing probabilistic forecasting methods. --- ### SlideChain: Semantic Provenance for Lecture Understanding via Blockchain Registration Authors: Md Motaleb Hossen Manik, Md Zabirul Islam, Ge Wang Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21684v2 Modern vision--language models (VLMs) are increasingly used to interpret and generate educational content, yet their semantic outputs remain challenging to verify, reproduce, and audit over time. Inconsistencies across model families, inference settings, and computing environments undermine the reliability of AI-generated instructional material, particularly in high-stakes and quantitative STEM domains. This work introduces SlideChain, a blockchain-backed provenance framework designed to provide verifiable integrity for multimodal semantic extraction at scale. Using the SlideChain Slides Dataset-a curated corpus of 1,117 medical imaging lecture slides from a university course-we extract concepts and relational triples from four state-of-the-art VLMs and construct structured provenance records for every slide. SlideChain anchors cryptographic hashes of these records on a local EVM (Ethereum Virtual Machine)-compatible blockchain, providing tamper-evident auditability and persistent semantic baselines. Through the first systematic analysis of semantic disagreement, cross-model similarity, and lecture-level variability in multimodal educational content, we reveal pronounced cross-model discrepancies, including low concept overlap and near-zero agreement in relational triples on many slides. We further evaluate gas usage, throughput, and scalability under simulated deployment conditions, and demonstrate perfect tamper detection along with deterministic reproducibility across independent extraction runs. Together, these results show that SlideChain provides a practical and scalable step toward trustworthy, verifiable multimodal educational pipelines, supporting long-term auditability, reproducibility, and integrity for AI-assisted instructional systems. --- ### Contrastive Graph Modeling for Cross-Domain Few-Shot Medical Image Segmentation Authors: Yuntian Bo, Tao Zhou, Zechao Li, Haofeng Zhang, Ling Shao Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21683v1 Cross-domain few-shot medical image segmentation (CD-FSMIS) offers a promising and data-efficient solution for medical applications where annotations are severely scarce and multimodal analysis is required. However, existing methods typically filter out domain-specific information to improve generalization, which inadvertently limits cross-domain performance and degrades source-domain accuracy. To address this, we present Contrastive Graph Modeling (C-Graph), a framework that leverages the structural consistency of medical images as a reliable domain-transferable prior. We represent image features as graphs, with pixels as nodes and semantic affinities as edges. A Structural Prior Graph (SPG) layer is proposed to capture and transfer target-category node dependencies and enable global structure modeling through explicit node interactions. Building upon SPG layers, we introduce a Subgraph Matching Decoding (SMD) mechanism that exploits semantic relations among nodes to guide prediction. Furthermore, we design a Confusion-minimizing Node Contrast (CNC) loss to mitigate node ambiguity and subgraph heterogeneity by contrastively enhancing node discriminability in the graph space. Our method significantly outperforms prior CD-FSMIS approaches across multiple cross-domain benchmarks, achieving state-of-the-art performance while simultaneously preserving strong segmentation accuracy on the source domain. --- ### Dictionary-Transform Generative Adversarial Networks Authors: Angshul Majumdar Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21677v1 Generative adversarial networks (GANs) are widely used for distribution learning, yet their classical formulations remain theoretically fragile, with ill-posed objectives, unstable training dynamics, and limited interpretability. In this work, we introduce \emph{Dictionary-Transform Generative Adversarial Networks} (DT-GAN), a fully model-based adversarial framework in which the generator is a sparse synthesis dictionary and the discriminator is an analysis transform acting as an energy model. By restricting both players to linear operators with explicit constraints, DT-GAN departs fundamentally from neural GAN architectures and admits rigorous theoretical analysis. We show that the DT-GAN adversarial game is well posed and admits at least one Nash equilibrium. Under a sparse generative model, equilibrium solutions are provably identifiable up to standard permutation and sign ambiguities and exhibit a precise geometric alignment between synthesis and analysis operators. We further establish finite-sample stability and consistency of empirical equilibria, demonstrating that DT-GAN training converges reliably under standard sampling assumptions and remains robust in heavy-tailed regimes. Experiments on mixture-structured synthetic data validate the theoretical predictions, showing that DT-GAN consistently recovers underlying structure and exhibits stable behavior under identical optimization budgets where a standard GAN degrades. DT-GAN is not proposed as a universal replacement for neural GANs, but as a principled adversarial alternative for data distributions that admit sparse synthesis structure. The results demonstrate that adversarial learning can be made interpretable, stable, and provably correct when grounded in classical sparse modeling. --- ### UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture Authors: Shuo Cao, Jiayang Li, Xiaohui Li, Yuandong Pu, Kaiwen Zhu, Yuanting Gao, Siqi Luo, Yi Xin, Qi Qin, Yu Zhou, Xiangyu Chen, Wenlong Zhang et al. Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21675v1 Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks such as visual grounding, segmentation, and captioning. However, their ability to perceive perceptual-level image features remains limited. In this work, we present UniPercept-Bench, a unified framework for perceptual-level image understanding across three key domains: Aesthetics, Quality, Structure and Texture. We establish a hierarchical definition system and construct large-scale datasets to evaluate perceptual-level image understanding. Based on this foundation, we develop a strong baseline UniPercept trained via Domain-Adaptive Pre-Training and Task-Aligned RL, enabling robust generalization across both Visual Rating (VR) and Visual Question Answering (VQA) tasks. UniPercept outperforms existing MLLMs on perceptual-level image understanding and can serve as a plug-and-play reward model for text-to-image generation. This work defines Perceptual-Level Image Understanding in the era of MLLMs and, through the introduction of a comprehensive benchmark together with a strong baseline, provides a solid foundation for advancing perceptual-level multimodal image understanding. --- ### Comparative Analysis of Deep Learning Models for Perception in Autonomous Vehicles Authors: Jalal Khan Published: 2025-12-25 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.21673v1 Recently, a plethora of machine learning (ML) and deep learning (DL) algorithms have been proposed to achieve the efficiency, safety, and reliability of autonomous vehicles (AVs). The AVs use a perception system to detect, localize, and identify other vehicles, pedestrians, and road signs to perform safe navigation and decision-making. In this paper, we compare the performance of DL models, including YOLO-NAS and YOLOv8, for a detection-based perception task. We capture a custom dataset and experiment with both DL models using our custom dataset. Our analysis reveals that the YOLOv8s model saves 75% of training time compared to the YOLO-NAS model. In addition, the YOLOv8s model (83%) outperforms the YOLO-NAS model (81%) when the target is to achieve the highest object detection accuracy. These comparative analyses of these new emerging DL models will allow the relevant research community to understand the models' performance under real-world use case scenarios. --- ### The Deepfake Detective: Interpreting Neural Forensics Through Sparse Features and Manifolds Authors: Subramanyam Sahoo, Jared Junkin Published: 2025-12-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.21670v1 Deepfake detection models have achieved high accuracy in identifying synthetic media, but their decision processes remain largely opaque. In this paper we present a mechanistic interpretability framework for deepfake detection applied to a vision-language model. Our approach combines a sparse autoencoder (SAE) analysis of internal network representations with a novel forensic manifold analysis that probes how the model's features respond to controlled forensic artifact manipulations. We demonstrate that only a small fraction of latent features are actively used in each layer, and that the geometric properties of the model's feature manifold, including intrinsic dimensionality, curvature, and feature selectivity, vary systematically with different types of deepfake artifacts. These insights provide a first step toward opening the "black box" of deepfake detectors, allowing us to identify which learned features correspond to specific forensic artifacts and to guide the development of more interpretable and robust models. --- ### Near-Optimal Coalition Structures in Polynomial Time Authors: Angshul Majumdar Published: 2025-12-25 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2512.21657v1 We study the classical coalition structure generation (CSG) problem and compare the anytime behavior of three algorithmic paradigms: dynamic programming (DP), MILP branch-and-bound, and sparse relaxations based on greedy or $l_1$-type methods. Under a simple random "sparse synergy" model for coalition values, we prove that sparse relaxations recover coalition structures whose welfare is arbitrarily close to optimal in polynomial time with high probability. In contrast, broad classes of DP and MILP algorithms require exponential time before attaining comparable solution quality. This establishes a rigorous probabilistic anytime separation in favor of sparse relaxations, even though exact methods remain ultimately optimal. --- ### Structural Induced Exploration for Balanced and Scalable Multi-Robot Path Planning Authors: Zikun Guo, Adeyinka P. Adedigba, Rammohan Mallipeddi, Heoncheol Lee Published: 2025-12-25 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.21654v1 Multi-robot path planning is a fundamental yet challenging problem due to its combinatorial complexity and the need to balance global efficiency with fair task allocation among robots. Traditional swarm intelligence methods, although effective on small instances, often converge prematurely and struggle to scale to complex environments. In this work, we present a structure-induced exploration framework that integrates structural priors into the search process of the ant colony optimization (ACO). The approach leverages the spatial distribution of the task to induce a structural prior at initialization, thereby constraining the search space. The pheromone update rule is then designed to emphasize structurally meaningful connections and incorporates a load-aware objective to reconcile the total travel distance with individual robot workload. An explicit overlap suppression strategy further ensures that tasks remain distinct and balanced across the team. The proposed framework was validated on diverse benchmark scenarios covering a wide range of instance sizes and robot team configurations. The results demonstrate consistent improvements in route compactness, stability, and workload distribution compared to representative metaheuristic baselines. Beyond performance gains, the method also provides a scalable and interpretable framework that can be readily applied to logistics, surveillance, and search-and-rescue applications where reliable large-scale coordination is essential. --- ### Decoder-Side Semantic Conditioning for Low-Bitrate Neural Speech Compression Authors: Liuyang Bai, Weiyi Lu, Li Guo Published: 2025-12-25 Categories: cs.SD, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.21653v2 Speech codecs are usually optimized for waveform fidelity, allocating bits to acoustic detail that can be inferred from linguistic structure. This leads to inefficient compression and degraded recognition performance. We propose SemDAC, a semantic-aware neural speech codec that adds hierarchical semantic conditioning to residual vector quantization (RVQ). The first RVQ quantizer is distilled from HuBERT features to produce semantic tokens capturing phonetic content, while later quantizers encode residual acoustics. The decoder is conditioned on semantic tokens via feature-wise linear modulation (FiLM), steering reconstruction toward information not explained by semantic abstraction. At 0.95 kbps, SemDAC matches or surpasses a 2.5 kbps DAC baseline on PESQ, STOI, SI-SNR, and Whisper WER, with comparable ViSQOL, and achieves higher subjective MOS than higher-bitrate DAC baselines. Results show that explicit semantic conditioning, rather than token disentanglement or increased model size alone, improves compression efficiency and recognition robustness. --- ### Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with A Generalist Foundation Model and Multimodal Database Authors: Zi Wang, Mingkai Huang, Zhang Shi, Hongjie Hu, Lan Lan, Hui Zhang, Yan Li, Xi Hu, Qing Lu, Zongming Zhu, Qiong Yao, Yuxiang Dai et al. Published: 2025-12-25 Categories: eess.IV, cs.AI, physics.med-ph arXiv: https://arxiv.org/abs/2512.21652v2 Multimodal cardiovascular magnetic resonance (CMR) imaging provides comprehensive and non-invasive insights into cardiovascular disease (CVD) diagnosis and underlying mechanisms. Despite decades of advancements, its widespread clinical adoption remains constrained by prolonged scan times, inconsistent image quality, and heterogeneity across medical environments. This underscores the urgent need for a generalist reconstruction foundation model for ultra-fast CMR imaging, one formulated for physics-constrained inverse problems in the sensor (k-space) domain, capable of adapting across diverse imaging scenarios and serving as the essential substrate for all downstream analyses. To enable this goal, we curate MMCMR-427K, the largest and most comprehensive multimodal CMR k-space database to date, comprising 427,465 multi-coil k-space data paired with structured metadata across 13 international centers, 12 CMR modalities, 15 scanners spanning four field strengths, and 17 CVD categories in populations across three continents. Building on this unprecedented resource, we introduce CardioMM, a generalist reconstruction foundation model capable of dynamically adapting to heterogeneous fast CMR imaging scenarios. CardioMM unifies semantic contextual understanding with physics-informed data consistency to deliver robust reconstructions across varied scanners, protocols, and patient presentations. Comprehensive evaluations demonstrate that CardioMM achieves state-of-the-art performance across internal centers and exhibits strong zero-shot generalization to unseen external settings. Importantly, CardioMM supports acceleration up to 24x, providing the first evidence that such extreme acquisition speed can preserve key cardiac phenotypes, quantitative myocardial biomarkers, and diagnostic image quality without compromising clinical integrity. --- ### Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models Authors: Dung Anh Hoang, Cuong Pham, Cuong Nguyen, Trung le, Jianfei Cai, Thanh-Toan Do Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21651v3 Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but their massive sizes hinder deployment on resource-constrained devices. To reduce their computational and memory burden, various compression techniques have been proposed, including quantization, pruning, and knowledge distillation. Among these, post-training quantization (PTQ) is widely adopted for its efficiency, as it requires no retraining and only a small dataset for calibration, enabling low-cost deployment. Recent advances for post-training quantization have demonstrated that even near 4-bit methods can maintain most of the original model performance. However, 1-bit quantization remains particularly challenging. A common strategy in 1-bit quantization is to determine binary weights by matching full-precision parameters, following a weight-driven criterion. However, this objective is not directly aligned with the quantized model's objective, which is to preserve the model's output behavior under the impact of quantization. A natural alternative is to adopt output-driven criteria that minimize discrepancies in model outputs using calibration data. Surprisingly, naive output-driven approaches often perform even worse in the 1-bit regime. In this paper, we show that this failure arises from two fundamental issues: error accumulation across layers and, more critically, \emph{anisotropic distortion} of the representation space. Based on these insights, we propose a novel PTQ method for 1-bit LLMs that explicitly addresses these issues while maintaining computational efficiency. Extensive experiments demonstrate that our approach consistently outperforms existing 1-bit PTQ methods. --- ### Physic-HM: Restoring Physical Generative Logic in Multimodal Anomaly Detection via Hierarchical Modulation Authors: Xiao Liu, Junchen Jin, Yanjie Zhao, Zhixuan Xing Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21650v2 Multimodal Unsupervised Anomaly Detection (UAD) is critical for quality assurance in smart manufacturing, particularly in complex processes like robotic welding. However, existing methods often suffer from process-logic blindness, treating process modalities (e.g., real-time video, audio, and sensors) and result modalities (e.g., post-weld images) as symmetric feature sources, thereby ignoring the inherent unidirectional physical generative logic. Furthermore, the heterogeneity gap between high-dimensional visual data and low-dimensional sensor signals frequently leads to critical process context being drowned out. In this paper, we propose Physic-HM, a multimodal UAD framework that explicitly incorporates physical inductive bias to model the process-to-result dependency. Specifically, our framework incorporates two key innovations: a Sensor-Guided PHM Modulation mechanism that utilizes low-dimensional sensor signals as context to guide high-dimensional audio-visual feature extraction, and a Physic-Hierarchical architecture that enforces a unidirectional generative mapping to identify anomalies that violate physical consistency. Extensive experiments on Weld-4M benchmark demonstrate that Physic-HM achieves a SOTA I-AUROC of 90.7%. The source code of Physic-HM will be released after the paper is accepted. --- ### Variance-Aware Prior-Based Tree Policies for Monte Carlo Tree Search Authors: Maximilian Weichart Published: 2025-12-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.21648v3 Monte Carlo Tree Search (MCTS) has profoundly influenced reinforcement learning (RL) by integrating planning and learning in tasks requiring long-horizon reasoning, exemplified by the AlphaZero family of algorithms. Central to MCTS is the search strategy, governed by a tree policy based on an upper confidence bound (UCB) applied to trees (UCT). A key factor in the success of AlphaZero is the introduction of a prior term in the UCB1-based tree policy PUCT, which improves exploration efficiency and thus accelerates training. While many alternative UCBs with stronger theoretical guarantees than UCB1 exist, extending them to prior-based UCTs has been challenging, since PUCT was derived empirically rather than from first principles. Recent work retrospectively justified PUCT by framing MCTS as a regularized policy optimization (RPO) problem. Building on this perspective, we introduce Inverse-RPO, a general methodology that systematically derives prior-based UCTs from a broad class of prior-free UCBs. Applying this method to the variance-aware UCB-V, we obtain two new prior-based tree policies that incorporate variance estimates into the search. Experiments indicate that these variance-aware prior-based UCTs outperform PUCT across multiple benchmarks without incurring additional computational cost. We also provide an extension of the mctx library supporting variance-aware UCTs, showing that the required code changes are minimal and intended to facilitate further research on principled prior-based UCTs. Code: github.com/Max-We/inverse-rpo. --- ### Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation Authors: Zhiwang Zhou, Yuandong Pu, Xuming He, Yidi Liu, Yixin Chen, Junchao Gong, Xiang Zhuang, Wanghan Xu, Qinglong Cao, Shixiang Tang, Yihao Liu, Wenlong Zhang et al. Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21643v3 Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To address this gap, we present Omni-Weather, the first multimodal foundation model that unifies weather generation and understanding within a single architecture. Omni-Weather integrates a radar encoder for weather generation tasks, followed by unified processing using a shared self-attention mechanism. Moreover, we construct a Chain-of-Thought dataset for causal reasoning in weather generation, enabling interpretable outputs and improved perceptual quality. Extensive experiments show Omni-Weather achieves state-of-the-art performance in both weather generation and understanding. Our findings further indicate that generative and understanding tasks in the weather domain can mutually enhance each other. Omni-Weather also demonstrates the feasibility and value of unifying weather generation and understanding. --- ### TrackTeller: Temporal Multimodal 3D Grounding for Behavior-Dependent Object References Authors: Jiahong Yu, Ziqi Wang, Hailiang Zhao, Wei Zhai, Xueqiang Yan, Shuiguang Deng Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21641v1 Understanding natural-language references to objects in dynamic 3D driving scenes is essential for interactive autonomous systems. In practice, many referring expressions describe targets through recent motion or short-term interactions, which cannot be resolved from static appearance or geometry alone. We study temporal language-based 3D grounding, where the objective is to identify the referred object in the current frame by leveraging multi-frame observations. We propose TrackTeller, a temporal multimodal grounding framework that integrates LiDAR-image fusion, language-conditioned decoding, and temporal reasoning in a unified architecture. TrackTeller constructs a shared UniScene representation aligned with textual semantics, generates language-aware 3D proposals, and refines grounding decisions using motion history and short-term dynamics. Experiments on the NuPrompt benchmark demonstrate that TrackTeller consistently improves language-grounded tracking performance, outperforming strong baselines with a 70% relative improvement in Average Multi-Object Tracking Accuracy and a 3.15-3.4 times reduction in False Alarm Frequency. --- ### Mechanical Strength Prediction of Steel-Polypropylene Fiber-based High-Performance Concrete Using Hybrid Machine Learning Algorithms Authors: Jagaran Chakma, Zhiguang Zhou, Badhan Chakma Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21638v1 This research develops and evaluates machine learning models to predict the mechanical properties of steel-polypropylene fiber-reinforced high-performance concrete (HPC). Three model families were investigated: Extra Trees with XGBoost (ET-XGB), Random Forest with LightGBM (RF-LGBM), and Transformer with XGBoost (Transformer-XGB). The target properties included compressive strength (CS), flexural strength (FS), and tensile strength (TS), based on an extensive dataset compiled from published experimental studies. Model training involved k-fold cross-validation, hyperparameter optimization, Shapley additive explanations (SHAP), and uncertainty analysis to ensure both robustness and interpretability. Among the tested approaches, the ET-XGB model achieved the highest overall accuracy, with testing R^2 values of 0.994 for CS, 0.944 for FS, and 0.978 for TS and exhibited lowest uncertainty for CS and TS (approximately 13-16% and 30.4%, respectively). The RF-LGBM model provided the most stable and reliable predictions for FS (R^2 0.977), yielding the lowest uncertainty for FS (approximately 5-33%). The Transformer-XGB model demonstrated strong predictive capability (R^2 0.978 for TS and 0.967 for FS) but consistently showed the highest uncertainty, indicating reduced generalization reliability. SHAP analysis further indicated that fiber aspect ratios (AR1 and AR2), silica fume (Sfu), and steel fiber content (SF) were the most influential predictors of strength, whereas water content (W) and the water-binder ratio (w/b) consistently had negative effects. The findings confirm that machine learning models can provide accurate, interpretable, and generalizable predictions of HPC mechanical properties. These models offer valuable tools for optimizing concrete mix design and enhancing structural performance evaluation in engineering applications. --- ### Training-Free Disentangled Text-Guided Image Editing via Sparse Latent Constraints Authors: Mutiara Shabrina, Nova Kurnia Putri, Jefri Satria Ferdiansyah, Sabita Khansa Dewi, Novanto Yudistira Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21637v1 Text-driven image manipulation often suffers from attribute entanglement, where modifying a target attribute (e.g., adding bangs) unintentionally alters other semantic properties such as identity or appearance. The Predict, Prevent, and Evaluate (PPE) framework addresses this issue by leveraging pre-trained vision-language models for disentangled editing. In this work, we analyze the PPE framework, focusing on its architectural components, including BERT-based attribute prediction and StyleGAN2-based image generation on the CelebA-HQ dataset. Through empirical analysis, we identify a limitation in the original regularization strategy, where latent updates remain dense and prone to semantic leakage. To mitigate this issue, we introduce a sparsity-based constraint using L1 regularization on latent space manipulation. Experimental results demonstrate that the proposed approach enforces more focused and controlled edits, effectively reducing unintended changes in non-target attributes while preserving facial identity. --- ### Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations Authors: Chengxu Yang, Jingling Yuan, Siqi Cai, Jiawei Jiang, Chuang Hu Published: 2025-12-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21635v2 Hallucinations in large language models (LLMs) are commonly regarded as errors to be minimized. However, recent perspectives suggest that some hallucinations may encode creative or epistemically valuable content, a dimension that remains underquantified in current literature. Existing hallucination detection methods primarily focus on factual consistency, struggling to handle heterogeneous scientific tasks and balance creativity with accuracy. To address these challenges, we propose HIC-Bench, a novel evaluation framework that categorizes hallucinations into Intelligent Hallucinations (IH) and Defective Hallucinations (DH), enabling systematic investigation of their interplay in LLM creativity. HIC-Bench features three core characteristics: (1) Structured IH/DH Assessment. using a multi-dimensional metric matrix integrating Torrance Tests of Creative Thinking (TTCT) metrics (Originality, Feasibility, Value) with hallucination-specific dimensions (scientific plausibility, factual deviation); (2) Cross-Domain Applicability. spanning ten scientific domains with open-ended innovation tasks; and (3) Dynamic Prompt Optimization. leveraging the Dynamic Hallucination Prompt (DHP) to guide models toward creative and reliable outputs. The evaluation process employs multiple LLM judges, averaging scores to mitigate bias, with human annotators verifying IH/DH classifications. Experimental results reveal a nonlinear relationship between IH and DH, demonstrating that creativity and correctness can be jointly optimized. These insights position IH as a catalyst for creativity and reveal the ability of LLM hallucinations to drive scientific innovation.Additionally, the HIC-Bench offers a valuable platform for advancing research into the creative intelligence of LLM hallucinations. --- ### MAD-NG: Meta-Auto-Decoder Neural Galerkin Method for Solving Parametric Partial Differential Equations Authors: Qiuqi Li, Yiting Liu, Jin Zhao, Wencan Zhu Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21633v1 Parametric partial differential equations (PDEs) are fundamental for modeling a wide range of physical and engineering systems influenced by uncertain or varying parameters. Traditional neural network-based solvers, such as Physics-Informed Neural Networks (PINNs) and Deep Galerkin Methods, often face challenges in generalization and long-time prediction efficiency due to their dependence on full space-time approximations. To address these issues, we propose a novel and scalable framework that significantly enhances the Neural Galerkin Method (NGM) by incorporating the Meta-Auto-Decoder (MAD) paradigm. Our approach leverages space-time decoupling to enable more stable and efficient time integration, while meta-learning-driven adaptation allows rapid generalization to unseen parameter configurations with minimal retraining. Furthermore, randomized sparse updates effectively reduce computational costs without compromising accuracy. Together, these advancements enable our method to achieve physically consistent, long-horizon predictions for complex parameterized evolution equations with significantly lower computational overhead. Numerical experiments on benchmark problems demonstrate that our methods performs comparatively well in terms of accuracy, robustness, and adaptability. --- ### Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing Authors: Hong Xie, Haoran Gu, Yanying Huang, Tao Tan, Defu Lian Published: 2025-12-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.21626v1 This paper proposes a variant of multiple-play stochastic bandits tailored to resource allocation problems arising from LLM applications, edge intelligence, etc. The model is composed of $M$ arms and $K$ plays. Each arm has a stochastic number of capacities, and each unit of capacity is associated with a reward function. Each play is associated with a priority weight. When multiple plays compete for the arm capacity, the arm capacity is allocated in a larger priority weight first manner. Instance independent and instance dependent regret lower bounds of $Ω( α_1 σ\sqrt{KM T} )$ and $Ω(α_1 σ^2 \frac{M}Δ \ln T)$ are proved, where $α_1$ is the largest priority weight and $σ$ characterizes the reward tail. When model parameters are given, we design an algorithm named \texttt{MSB-PRS-OffOpt} to locate the optimal play allocation policy with a computational complexity of $O(MK^3)$. Utilizing \texttt{MSB-PRS-OffOpt} as a subroutine, an approximate upper confidence bound (UCB) based algorithm is designed, which has instance independent and instance dependent regret upper bounds matching the corresponding lower bound up to factors of $ \sqrt{K \ln KT }$ and $α_1 K^2$ respectively. To this end, we address nontrivial technical challenges arising from optimizing and learning under a special nonlinear combinatorial utility function induced by the prioritized resource sharing mechanism. --- ### Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards Authors: Xinyu Tang, Yuliang Zhan, Zhixun Li, Wayne Xin Zhao, Zhenduo Zhang, Zujie Wen, Zhiqiang Zhang, Jun Zhou Published: 2025-12-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21625v1 Large reasoning models (LRMs) are typically trained using reinforcement learning with verifiable reward (RLVR) to enhance their reasoning abilities. In this paradigm, policies are updated using both positive and negative self-generated rollouts, which correspond to distinct sample polarities. In this paper, we provide a systematic investigation into how these sample polarities affect RLVR training dynamics and behaviors. We find that positive samples sharpen existing correct reasoning patterns, while negative samples encourage exploration of new reasoning paths. We further explore how adjusting the advantage values of positive and negative samples at both the sample level and the token level affects RLVR training. Based on these insights, we propose an Adaptive and Asymmetric token-level Advantage shaping method for Policy Optimization, namely A3PO, that more precisely allocates advantage signals to key tokens across different polarities. Experiments across five reasoning benchmarks demonstrate the effectiveness of our approach. --- ### Democratizing Drug Discovery with an Orchestrated, Knowledge-Driven Multi-Agent Team for User-Guided Therapeutic Design Authors: Takahide Suzuki, Kazuki Nakanishi, Takashi Fujiwara, Hideyuki Shimizu Published: 2025-12-25 Categories: cs.AI, cs.MA, q-bio.QM arXiv: https://arxiv.org/abs/2512.21623v1 Therapeutic discovery remains a formidable challenge, impeded by the fragmentation of specialized domains and the execution gap between computational design and physiological validation. Although generative AI offers promise, current models often function as passive assistants rather than as autonomous executors. Here, we introduce OrchestRA, a human-in-the-loop multi-agent platform that unifies biology, chemistry, and pharmacology into an autonomous discovery engine. Unlike static code generators, our agents actively execute simulations and reason the results to drive iterative optimization. Governed by an Orchestrator, a Biologist Agent leverages deep reasoning over a massive knowledge graph (>10 million associations) to pinpoint high-confidence targets; a Chemist Agent autonomously detects structural pockets for de novo design or drug repositioning; and a Pharmacologist Agent evaluates candidates via rigorous physiologically based pharmacokinetic (PBPK) simulations. This architecture establishes a dynamic feedback loop where pharmacokinetic and toxicity profiles directly trigger structural reoptimization. By seamlessly integrating autonomous execution with human guidance, OrchestRA democratizes therapeutic design, transforming drug discovery from a stochastic search to a programmable evidence-based engineering discipline. --- ### SymDrive: Realistic and Controllable Driving Simulator via Symmetric Auto-regressive Online Restoration Authors: Zhiyuan Liu, Daocheng Fu, Pinlong Cai, Lening Wang, Ying Liu, Yilong Ren, Botian Shi, Jianqiang Wang Published: 2025-12-25 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.21618v1 High-fidelity and controllable 3D simulation is essential for addressing the long-tail data scarcity in Autonomous Driving (AD), yet existing methods struggle to simultaneously achieve photorealistic rendering and interactive traffic editing. Current approaches often falter in large-angle novel view synthesis and suffer from geometric or lighting artifacts during asset manipulation. To address these challenges, we propose SymDrive, a unified diffusion-based framework capable of joint high-quality rendering and scene editing. We introduce a Symmetric Auto-regressive Online Restoration paradigm, which constructs paired symmetric views to recover fine-grained details via a ground-truth-guided dual-view formulation and utilizes an auto-regressive strategy for consistent lateral view generation. Furthermore, we leverage this restoration capability to enable a training-free harmonization mechanism, treating vehicle insertion as context-aware inpainting to ensure seamless lighting and shadow consistency. Extensive experiments demonstrate that SymDrive achieves state-of-the-art performance in both novel-view enhancement and realistic 3D vehicle insertion. --- ### CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspective Authors: Zhiwen Yang, Jinglin Xu, Yuxin Pen Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21617v1 Few-shot fine-grained visual categorization (FS-FGVC) focuses on identifying various subcategories within a common superclass given just one or few support examples. Most existing methods aim to boost classification accuracy by enriching the extracted features with discriminative part-level details. However, they often overlook the fact that the set of support samples acts as a confounding variable, which hampers the FS-FGVC performance by introducing biased data distribution and misguiding the extraction of discriminative features. To address this issue, we propose a new causal FS-FGVC (CausalFSFG) approach inspired by causal inference for addressing biased data distributions through causal intervention. Specifically, based on the structural causal model (SCM), we argue that FS-FGVC infers the subcategories (i.e., effect) from the inputs (i.e., cause), whereas both the few-shot condition disturbance and the inherent fine-grained nature (i.e., large intra-class variance and small inter-class variance) lead to unobservable variables that bring spurious correlations, compromising the final classification performance. To further eliminate the spurious correlations, our CausalFSFG approach incorporates two key components: (1) Interventional multi-scale encoder (IMSE) conducts sample-level interventions, (2) Interventional masked feature reconstruction (IMFR) conducts feature-level interventions, which together reveal real causalities from inputs to subcategories. Extensive experiments and thorough analyses on the widely-used public datasets, including CUB-200-2011, Stanford Dogs, and Stanford Cars, demonstrate that our CausalFSFG achieves new state-of-the-art performance. The code is available at https://github.com/PKU-ICST-MIPL/CausalFSFG_TMM. --- ### TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistant Authors: Rongpei Hong, Jian Lang, Ting Zhong, Yong Wang, Fan Zhou Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21616v1 Multimodal Large Language Model (MLLM) Personalization is a critical research problem that facilitates personalized dialogues with MLLMs targeting specific entities (known as personalized concepts). However, existing methods and benchmarks focus on the simple, context-agnostic visual identification and textual replacement of the personalized concept (e.g., "A yellow puppy" -> "Your puppy Mochi"), overlooking the ability to support long-context conversations. An ideal personalized MLLM assistant is capable of engaging in long-context dialogues with humans and continually improving its experience quality by learning from past dialogue histories. To bridge this gap, we propose LCMP, the first Long-Context MLLM Personalization evaluation benchmark. LCMP assesses the capability of MLLMs in perceiving variations of personalized concepts and generating contextually appropriate personalized responses that reflect these variations. As a strong baseline for LCMP, we introduce a novel training-free and state-aware framework TAME. TAME endows MLLMs with double memories to manage the temporal and persistent variations of each personalized concept in a differentiated manner. In addition, TAME incorporates a new training-free Retrieve-then-Align Augmented Generation (RA2G) paradigm. RA2G introduces an alignment step to extract the contextually fitted information from the multi-memory retrieved knowledge to the current questions, enabling better interactions for complex real-world user queries. Experiments on LCMP demonstrate that TAME achieves the best performance, showcasing remarkable and evolving interaction experiences in long-context scenarios. --- ### AMS-IO-Bench and AMS-IO-Agent: Benchmarking and Structured Reasoning for Analog and Mixed-Signal Integrated Circuit Input/Output Design Authors: Zhishuai Zhang, Xintian Li, Shilong Liu, Aodong Zhang, Lu Jie, Nan Sun Published: 2025-12-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.21613v1 In this paper, we propose AMS-IO-Agent, a domain-specialized LLM-based agent for structure-aware input/output (I/O) subsystem generation in analog and mixed-signal (AMS) integrated circuits (ICs). The central contribution of this work is a framework that connects natural language design intent with industrial-level AMS IC design deliverables. AMS-IO-Agent integrates two key capabilities: (1) a structured domain knowledge base that captures reusable constraints and design conventions; (2) design intent structuring, which converts ambiguous user intent into verifiable logic steps using JSON and Python as intermediate formats. We further introduce AMS-IO-Bench, a benchmark for wirebond-packaged AMS I/O ring automation. On this benchmark, AMS-IO-Agent achieves over 70\% DRC+LVS pass rate and reduces design turnaround time from hours to minutes, outperforming the baseline LLM. Furthermore, an agent-generated I/O ring was fabricated and validated in a 28 nm CMOS tape-out, demonstrating the practical effectiveness of the approach in real AMS IC design flows. To our knowledge, this is the first reported human-agent collaborative AMS IC design in which an LLM-based agent completes a nontrivial subtask with outputs directly used in silicon. --- ### A Data-Driven Multi-Objective Approach for Predicting Mechanical Performance, Flowability, and Porosity in Ultra-High-Performance Concrete (UHPC) Authors: Jagaran Chakma, Zhiguang Zhou, Jyoti Chakma, Cao YuSen Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21610v1 This study presents a data-driven, multi-objective approach to predict the mechanical performance, flow ability, and porosity of Ultra-High-Performance Concrete (UHPC). Out of 21 machine learning algorithms tested, five high-performing models are selected, with XGBoost showing the best accuracy after hyperparameter tuning using Random Search and K-Fold Cross-Validation. The framework follows a two-stage process: the initial XGBoost model is built using raw data, and once selected as the final model, the dataset is cleaned by (1) removing multicollinear features, (2) identifying outliers with Isolation Forest, and (3) selecting important features using SHAP analysis. The refined dataset as model 2 is then used to retrain XGBoost, which achieves high prediction accuracy across all outputs. A graphical user interface (GUI) is also developed to support material designers. Overall, the proposed framework significantly improves the prediction accuracy and minimizes the need for extensive experimental testing in UHPC mix design. --- ### An Empirical Study of Machine Learning Robustness and Scalability for Imbalanced Tabular Clinical Data in Emergency and Critical Care Authors: Yusuf Brima, Marcellin Atemkeng Published: 2025-12-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.21602v3 Every year, millions of patients pass through emergency departments and intensive care units, where clinicians must make high-stakes decisions under time pressure and uncertainty. Machine learning could support prediction of deterioration, triage, and rare critical outcomes, but clinical data are often severely imbalanced, biasing models toward majority classes and reducing predictive performance. Developing robust and efficient models for imbalanced clinical tabular data therefore remains an important challenge. We evaluated six model families on imbalanced tabular data from the MIMIC-IV-ED and eICU databases: Decision Tree, Random Forest, XGBoost, TabNet, TabICL, and TabPFN v2.6. Trainable models were optimized using Bayesian hyperparameter tuning, while foundation models were evaluated in their pretrained inference regime without task-specific reweighting. Models were assessed using Macro F1-score, robustness to increasing imbalance, and computational scalability across seven clinical prediction tasks. Results differed across datasets. On MIMIC-IV-ED, TabPFN v2.6 and TabICL achieved the strongest average Macro F1 ranks, with XGBoost remaining competitive. On eICU, XGBoost consistently performed best, followed by other tree-based methods, while foundation models achieved intermediate performance. Across both datasets, TabNet showed the largest degradation under increasing imbalance and the highest computational cost. Training-time analysis showed that tree-based methods scaled most favorably with dataset size, while foundation models offered low per-task adaptation cost. These findings suggest that no single model family dominates across all clinical settings. However, tabular foundation models are narrowing the performance gap with strong classical baselines while offering a distinct efficiency-performance trade-off that may benefit resource-constrained clinical environments. --- ### Resolving compositional and conformational heterogeneity in cryo-EM with deformable 3D Gaussian representations Authors: Bintao He, Yiran Cheng, Hongjia Li, Xiang Gao, Xin Gao, Fa Zhang, Renmin Han Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21599v2 Understanding protein flexibility and its dynamic interactions with other molecules is essential for studying protein function. Although cryogenic electron microscopy(cryo-EM) provides an opportunity to observe macromolecular dynamics directly, computational analysis of datasets mixing continuous and discrete structural states remains a formidable challenge. Here we introduce GaussianEM, a Gaussian-based pseudo-atomic framework that simultaneously resolves compositional and conformational heterogeneity from cryo-EM images. GaussianEM employs a dual-encoder-single-decoder architecture to decompose images into learnable Gaussian components, with variability encoded through modulated parameters. This explicit parameterization yields a continuous, intuitive representation of conformational dynamics that inherently preserves local structural integrity. By modeling displacements in Gaussian space, we capture atomic-scale conformational landscapes, bridging density maps and all-atom models. In comprehensive experiments, GaussianEM successfully reconstructs complex compositional and conformational variability,and resolves previously unobserved details in public datasets. Quantitative evaluations further confirm its ability to capture broader conformational diversity without sacrificing structural fidelity. --- ### From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection via LMM Agent Self-Improvement Authors: Jian Lang, Rongpei Hong, Ting Zhong, Leiting Chen, Qiang Gao, Fan Zhou Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21598v1 The proliferation of harmful memes on online media poses significant risks to public health and stability. Existing detection methods heavily rely on large-scale labeled data for training, which necessitates substantial manual annotation efforts and limits their adaptability to the continually evolving nature of harmful content. To address these challenges, we present ALARM, the first lAbeL-free hARmful Meme detection framework powered by Large Multimodal Model (LMM) agent self-improvement. The core innovation of ALARM lies in exploiting the expressive information from "shallow" memes to iteratively enhance its ability to tackle more complex and subtle ones. ALARM consists of a novel Confidence-based Explicit Meme Identification mechanism that isolates the explicit memes from the original dataset and assigns them pseudo-labels. Besides, a new Pairwise Learning Guided Agent Self-Improvement paradigm is introduced, where the explicit memes are reorganized into contrastive pairs (positive vs. negative) to refine a learner LMM agent. This agent autonomously derives high-level detection cues from these pairs, which in turn empower the agent itself to handle complex and challenging memes effectively. Experiments on three diverse datasets demonstrate the superior performance and strong adaptability of ALARM to newly evolved memes. Notably, our method even outperforms label-driven methods. These results highlight the potential of label-free frameworks as a scalable and promising solution for adapting to novel forms and topics of harmful memes in dynamic online environments. --- ### Quantitative Verification of Omega-regular Properties in Probabilistic Programming Authors: Peixin Wang, Jianhao Bai, Min Zhang, C. -H. Luke Ong Published: 2025-12-25 Categories: cs.PL, cs.FL, cs.LG, cs.LO, cs.SC arXiv: https://arxiv.org/abs/2512.21596v1 Probabilistic programming provides a high-level framework for specifying statistical models as executable programs with built-in randomness and conditioning. Existing inference techniques, however, typically compute posterior distributions over program states at fixed time points, most often at termination, thereby failing to capture the temporal evolution of probabilistic behaviors. We introduce temporal posterior inference (TPI), a new framework that unifies probabilistic programming with temporal logic by computing posterior distributions over execution traces that satisfy omega-regular specifications, conditioned on possibly temporal observations. To obtain rigorous quantitative guarantees, we develop a new method for computing upper and lower bounds on the satisfaction probabilities of omega-regular properties. Our approach decomposes Rabin acceptance conditions into persistence and recurrence components and constructs stochastic barrier certificates that soundly bound each component. We implement our approach in a prototype tool, TPInfer, and evaluate it on a suite of benchmarks, demonstrating effective and efficient inference over rich temporal properties in probabilistic models. --- ### LLM-I2I: Boost Your Small Item2Item Recommendation Model with Large Language Model Authors: Yinfu Feng, Yanjing Wu, Rong Xiao, Xiaoyi Zen Published: 2025-12-25 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.21595v1 Item-to-Item (I2I) recommendation models are widely used in real-world systems due to their scalability, real-time capabilities, and high recommendation quality. Research to enhance I2I performance focuses on two directions: 1) model-centric approaches, which adopt deeper architectures but risk increased computational costs and deployment complexity, and 2) data-centric methods, which refine training data without altering models, offering cost-effectiveness but struggling with data sparsity and noise. To address these challenges, we propose LLM-I2I, a data-centric framework leveraging Large Language Models (LLMs) to mitigate data quality issues. LLM-I2I includes (1) an LLM-based generator that synthesizes user-item interactions for long-tail items, alleviating data sparsity, and (2) an LLM-based discriminator that filters noisy interactions from real and synthetic data. The refined data is then fused to train I2I models. Evaluated on industry (AEDS) and academic (ARD) datasets, LLM-I2I consistently improves recommendation accuracy, particularly for long-tail items. Deployed on a large-scale cross-border e-commerce platform, it boosts recall number (RN) by 6.02% and gross merchandise value (GMV) by 1.22% over existing I2I models. This work highlights the potential of LLMs in enhancing data-centric recommendation systems without modifying model architectures. --- ### Residual Prior Diffusion: A Probabilistic Framework Integrating Coarse Latent Priors with Diffusion Models Authors: Takuro Kutsuna Published: 2025-12-25 Categories: stat.ML, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.21593v1 Diffusion models have become a central tool in deep generative modeling, but standard formulations rely on a single network and a single diffusion schedule to transform a simple prior, typically a standard normal distribution, into the target data distribution. As a result, the model must simultaneously represent the global structure of the distribution and its fine-scale local variations, which becomes difficult when these scales are strongly mismatched. This issue arises both in natural images, where coarse manifold-level structure and fine textures coexist, and in low-dimensional distributions with highly concentrated local structure. To address this issue, we propose Residual Prior Diffusion (RPD), a two-stage framework in which a coarse prior model first captures the large-scale structure of the data distribution, and a diffusion model is then trained to represent the residual between the prior and the target data distribution. We formulate RPD as an explicit probabilistic model with a tractable evidence lower bound, whose optimization reduces to the familiar objectives of noise prediction or velocity prediction. We further introduce auxiliary variables that leverage information from the prior model and theoretically analyze how they reduce the difficulty of the prediction problem in RPD. Experiments on synthetic datasets with fine-grained local structure show that standard diffusion models fail to capture local details, whereas RPD accurately captures fine-scale detail while preserving the large-scale structure of the distribution. On natural image generation tasks, RPD achieved generation quality that matched or exceeded that of representative diffusion-based baselines and it maintained strong performance even with a small number of inference steps. --- ### Incorporating rank-free coupling and external field via an incoherent modulated spatial photonic Ising machine Authors: Ze Zheng, Yuegang Li, Hang Xu, Jingzheng Huang, Tailong Xiao, Guihua Zeng Published: 2025-12-25 Categories: physics.optics, cond-mat.dis-nn, cs.LG, math-ph, physics.app-ph arXiv: https://arxiv.org/abs/2512.21587v2 Spatial photonic Ising machines offer a novel optical platform for optimization and spin-model simulation, but existing diffraction-based schemes rely on auxiliary spins or multiplexing to encode high-rank couplings and external fields, reducing either speed or spin count. We demonstrate an amplitude-only, rank-free spatial photonic Ising machine in which arbitrary Ising Hamiltonians are encoded as Hadamard products on aligned amplitude and binary spatial modulators and read out by a single-pixel intensity measurement. The machine directly programs fully connected 797-spin Ising models with external fields at nearly 9-bit precision and operates at a constant iteration rate of ~200 Hz. By removing zero-valued product terms, the same architecture scales to sparse problems and experimentally solves a Max-Cut instance on a 424,108-vertex Mobius ladder graph. We also observe the phase transition of the Sherrington-Kirkpatrick model, demonstrating programmable optical simulation beyond low-rank couplings. These results establish amplitude modulation as a scalable route to programmable photonic Ising machines. --- ### Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations Authors: Xin Liu, Haoran Li, Dongbin Zhao Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21586v1 Humans can efficiently extract knowledge and learn skills from the videos within only a few trials and errors. However, it poses a big challenge to replicate this learning process for autonomous agents, due to the complexity of visual input, the absence of action or reward signals, and the limitations of interaction steps. In this paper, we propose a novel, unsupervised, and sample-efficient framework to achieve imitation learning from videos (ILV), named Behavior Cloning from Videos via Latent Representations (BCV-LR). BCV-LR extracts action-related latent features from high-dimensional video inputs through self-supervised tasks, and then leverages a dynamics-based unsupervised objective to predict latent actions between consecutive frames. The pre-trained latent actions are fine-tuned and efficiently aligned to the real action space online (with collected interactions) for policy behavior cloning. The cloned policy in turn enriches the agent experience for further latent action finetuning, resulting in an iterative policy improvement that is highly sample-efficient. We conduct extensive experiments on a set of challenging visual tasks, including both discrete control and continuous control. BCV-LR enables effective (even expert-level on some tasks) policy performance with only a few interactions, surpassing state-of-the-art ILV baselines and reinforcement learning methods (provided with environmental rewards) in terms of sample efficiency across 24/28 tasks. To the best of our knowledge, this work for the first time demonstrates that videos can support extremely sample-efficient visual policy learning, without the need to access any other expert supervision. --- ### UltraLBM-UNet: Ultralight Bidirectional Mamba-based Model for Skin Lesion Segmentation Authors: Linxuan Fan, Juntao Jiang, Weixuan Liu, Zhucun Xue, Jiajun Lv, Jiangning Zhang, Yong Liu Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21584v1 Skin lesion segmentation is a crucial step in dermatology for guiding clinical decision-making. However, existing methods for accurate, robust, and resource-efficient lesion analysis have limitations, including low performance and high computational complexity. To address these limitations, we propose UltraLBM-UNet, a lightweight U-Net variant that integrates a bidirectional Mamba-based global modeling mechanism with multi-branch local feature perception. The proposed architecture integrates efficient local feature injection with bidirectional state-space modeling, enabling richer contextual interaction across spatial dimensions while maintaining computational compactness suitable for point-of-care deployment. Extensive experiments on the ISIC 2017, ISIC 2018, and PH2 datasets demonstrate that our model consistently achieves state-of-the-art segmentation accuracy, outperforming existing lightweight and Mamba counterparts with only 0.034M parameters and 0.060 GFLOPs. In addition, we introduce a hybrid knowledge distillation strategy to train an ultra-compact student model, where the distilled variant UltraLBM-UNet-T, with only 0.011M parameters and 0.019 GFLOPs, achieves competitive segmentation performance. These results highlight the suitability of UltraLBM-UNet for point-of-care deployment, where accurate and robust lesion analyses are essential. The source code is publicly available at https://github.com/LinLinLin-X/UltraLBM-UNet. --- ### A Medical Multimodal Diagnostic Framework Integrating Vision-Language Models and Logic Tree Reasoning Authors: Zelin Zang, Wenyi Gu, Siqi Ma, Dan Yang, Yue Shen, Zhu Zhang, Guohui Fan, Wing-Kuen Ling, Fuji Yang Published: 2025-12-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.21583v1 With the rapid growth of large language models (LLMs) and vision-language models (VLMs) in medicine, simply integrating clinical text and medical imaging does not guarantee reliable reasoning. Existing multimodal models often produce hallucinations or inconsistent chains of thought, limiting clinical trust. We propose a diagnostic framework built upon LLaVA that combines vision-language alignment with logic-regularized reasoning. The system includes an input encoder for text and images, a projection module for cross-modal alignment, a reasoning controller that decomposes diagnostic tasks into steps, and a logic tree generator that assembles stepwise premises into verifiable conclusions. Evaluations on MedXpertQA and other benchmarks show that our method improves diagnostic accuracy and yields more interpretable reasoning traces on multimodal tasks, while remaining competitive on text-only settings. These results suggest a promising step toward trustworthy multimodal medical AI. --- ### LLM-Free Image Captioning Evaluation in Reference-Flexible Settings Authors: Shinnosuke Hirano, Yuiga Wada, Kazuki Matsuda, Seitaro Otsuki, Komei Sugiura Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21582v1 We focus on the automatic evaluation of image captions in both reference-based and reference-free settings. Existing metrics based on large language models (LLMs) favor their own generations; therefore, the neutrality is in question. Most LLM-free metrics do not suffer from such an issue, whereas they do not always demonstrate high performance. To address these issues, we propose Pearl, an LLM-free supervised metric for image captioning, which is applicable to both reference-based and reference-free settings. We introduce a novel mechanism that learns the representations of image--caption and caption--caption similarities. Furthermore, we construct a human-annotated dataset for image captioning metrics, that comprises approximately 333k human judgments collected from 2,360 annotators across over 75k images. Pearl outperformed other existing LLM-free metrics on the Composite, Flickr8K-Expert, Flickr8K-CF, Nebula, and FOIL datasets in both reference-based and reference-free settings. Our project page is available at https://pearl.kinsta.page/. --- ### Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLM Authors: Alexander Podolskiy, Semen Molokov, Timofey Gerasin, Maksim Titov, Alexey Rukhovich, Artem Khrapov, Kirill Morozov, Evgeny Tetin, Constantine Korikov, Pavel Efimov, Polina Lazukova, Yuliya Skripkar et al. Published: 2025-12-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21580v2 We present Gamayun, a 1.5B-parameter multilingual language model trained entirely from scratch on 2.5T tokens. Designed for efficiency and deployment in resource-constrained environments, Gamayun addresses the lack of research on small non-English-centric LLMs by adopting a novel two-stage pre-training strategy: balanced multilingual training for cross-lingual alignment, followed by high-quality English enrichment to transfer performance gains across languages. Our model supports 12 languages, with special focus on Russian. Despite a significantly smaller training budget than comparable models, Gamayun outperforms LLaMA3.2-1B (9T tokens) on all considered benchmarks, and surpasses Qwen2.5-1.5B (18T tokens) on a wide range of English and multilingual tasks. It matches or exceeds Qwen3 (36T tokens) on most tasks outside advanced STEM, achieving state-of-the-art results in Russian, including the MERA benchmark, among the models of comparable size (1-2B parameters). --- ### NEMO-4-PAYPAL: Leveraging NVIDIA's Nemo Framework for empowering PayPal's Commerce Agent Authors: Sudhanshu Garg, Andrew Wang, Chaitanya Kulkarni, Ali Sahami, Farhad Farahani, Sean Yun-Shiuan Chuang, Jian Wan, Srinivasan Manoharan, Uma Kona, Nitin Sharma, Linsey Pang, Prakhar Mehrotra et al. Published: 2025-12-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.21578v3 We present the development and optimization of PayPal's Commerce Agent, powered by NEMO-4-PAYPAL, a multi-agent system designed to revolutionize agentic commerce on the PayPal platform. Through our strategic partnership with NVIDIA, we leveraged the NeMo Framework for LLM model fine-tuning to enhance agent performance. Specifically, we optimized the Search and Discovery agent by replacing our base model with a fine-tuned Nemotron small language model (SLM). We conducted comprehensive experiments using the llama3.1-nemotron-nano-8B-v1 architecture, training LoRA-based models through systematic hyperparameter sweeps across learning rates, optimizers (Adam, AdamW), cosine annealing schedules, and LoRA ranks. Our contributions include: (1) the first application of NVIDIA's NeMo Framework to commerce-specific agent optimization, (2) LLM powered fine-tuning strategy for retrieval-focused commerce tasks, (3) demonstration of significant improvements in latency and cost while maintaining agent quality, and (4) a scalable framework for multi-agent system optimization in production e-commerce environments. Our results demonstrate that the fine-tuned Nemotron SLM effectively resolves the key performance issue in the retrieval component, which represents over 50\% of total agent response time, while maintaining or enhancing overall system performance. --- ### A Unified Definition of Hallucination: It's The World Model, Stupid! Authors: Emmy Liu, Varun Gangal, Chelsea Zou, Michael Yu, Xiaoqi Huang, Alex Chang, Zhuofu Tao, Karan Singh, Sachin Kumar, Steven Y. Feng Published: 2025-12-25 Categories: cs.CL, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.21577v3 Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. We argue that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we also connect our framework to HalluWorld, a complementary benchmark that instantiates fully specified reference world models for stress-testing model hallucinations. --- ### Towards Long-window Anchoring in Vision-Language Model Distillation Authors: Haoyi Zhou, Shuo Li, Tianyu Chen, Qi Song, Chonghan Gao, Jianxin Li Published: 2025-12-25 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.21576v1 While large vision-language models (VLMs) demonstrate strong long-context understanding, their prevalent small branches fail on linguistics-photography alignment for a limited window size. We discover that knowledge distillation improves students' capability as a complement to Rotary Position Embeddings (RoPE) on window sizes (anchored from large models). Building on this insight, we propose LAid, which directly aims at the transfer of long-range attention mechanisms through two complementary components: (1) a progressive distance-weighted attention matching that dynamically emphasizes longer position differences during training, and (2) a learnable RoPE response gain modulation that selectively amplifies position sensitivity where needed. Extensive experiments across multiple model families demonstrate that LAid-distilled models achieve up to 3.2 times longer effective context windows compared to baseline small models, while maintaining or improving performance on standard VL benchmarks. Spectral analysis also suggests that LAid successfully preserves crucial low-frequency attention components that conventional methods fail to transfer. Our work not only provides practical techniques for building more efficient long-context VLMs but also offers theoretical insights into how positional understanding emerges and transfers during distillation. --- ### RefineBridge: Generative Bridge Models Improve Financial Forecasting by Foundation Models Authors: Anthony Bolton, Wuyang Zhou, Zehua Chen, Giorgos Iacovides, Danilo Mandic Published: 2025-12-25 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2512.21572v2 Financial time series forecasting is particularly challenging for transformer-based time series foundation models (TSFMs) due to non-stationarity, heavy-tailed distributions, and high-frequency noise present in data. Low-rank adaptation (LoRA) has become a popular parameter-efficient method for adapting pre-trained TSFMs to downstream data domains. However, it still underperforms in financial data, as it preserves the network architecture and training objective of TSFMs rather than complementing the foundation model. To further enhance TSFMs, we propose a novel refinement module, RefineBridge, built upon a tractable Schrödinger Bridge (SB) generative framework. Given the forecasts of TSFM as generative prior and the observed ground truths as targets, RefineBridge learns context-conditioned stochastic transport maps to improve TSFM predictions, iteratively approaching the ground-truth target from even a low-quality prior. Simulations on multiple financial benchmarks demonstrate that RefineBridge consistently improves the performance of state-of-the-art TSFMs across different prediction horizons. ---