# Research Papers — 2025-12 · bundle page 165 of 175 > Full-text markdown of papers #8201–8250 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/165 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/164.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/166.md) ### Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaboration Authors: Yuxiang He, Jian Zhao, Yuchen Yuan, Tianle Zhang, Wei Cai, Haojie Cheng, Ziyan Shi, Ming Zhu, Haichuan Tang, Chi Zhang, Xuelong Li Published: 2025-12-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.02530v2 The exponential growth of digital content presents significant challenges for content safety. Current moderation systems, often based on single models or fixed pipelines, exhibit limitations in identifying implicit risks and providing interpretable judgment processes. To address these issues, we propose Aetheria, a multimodal interpretable content safety framework based on multi-agent debate and collaboration.Employing a collaborative architecture of five core agents, Aetheria conducts in-depth analysis and adjudication of multimodal content through a dynamic, mutually persuasive debate mechanism, which is grounded by RAG-based knowledge retrieval.Comprehensive experiments on our proposed benchmark (AIR-Bench) validate that Aetheria not only generates detailed and traceable audit reports but also demonstrates significant advantages over baselines in overall content safety accuracy, especially in the identification of implicit risks. This framework establishes a transparent and interpretable paradigm, significantly advancing the field of trustworthy AI content moderation. --- ### A Concise Review of Hallucinations in LLMs and their Mitigation Authors: Parth Pulkundwar, Vivek Dhanawade, Rohit Yadav, Minal Sonkar, Medha Asurlekar, Sarita Rathod Published: 2025-12-02 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.02527v1 Traditional language models face a challenge from hallucinations. Their very presence casts a large, dangerous shadow over the promising realm of natural language processing. It becomes crucial to understand the various kinds of hallucinations that occur nowadays, their origins, and ways of reducing them. This document provides a concise and straightforward summary of that. It serves as a one-stop resource for a general understanding of hallucinations and how to mitigate them. --- ### Generative Multi-modal Feedback for Singing Voice Synthesis Evaluation Authors: Xueyan Li, Yuxin Wang, Mengjie Jiang, Qingzi Zhu, Jiang Zhang, Zoey Kim, Yazhe Niu Published: 2025-12-02 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2512.02523v1 Singing voice synthesis (SVS) has advanced significantly, enabling models to generate vocals with accurate pitch and consistent style. As these capabilities improve, the need for reliable evaluation and optimization becomes increasingly critical. However, current methods like reward systems often rely on single numerical scores, struggle to capture various dimensions such as phrasing or expressiveness, and require costly annotations, limiting interpretability and generalization. To address these issues, we propose a generative feedback (i.e., reward model) framework that provides multi-dimensional language and audio feedback for SVS assessment. Our approach leverages an audio-language model to generate text and audio critiques-covering aspects such as melody, content, and auditory quality. The model is fine-tuned on a hybrid dataset combining human music reactions and synthetic critiques from a MLLMs, enhancing diversity and linguistic richness. Quantitative experiments validate the effectiveness of the proposed dataset and training strategy, demonstrating that the framework produces musically accurate and interpretable evaluations suitable for guiding generative model improvement. The code is at (https://github.com/opendilab/VocalCritic)(https://github.com/opendilab/VocalCritic) --- ### On the Problem of Consistent Anomalies in Zero-Shot Anomaly Detection Authors: Tai Le-Gia Published: 2025-12-02 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2512.02520v1 Zero-shot anomaly classification and segmentation (AC/AS) aim to detect anomalous samples and regions without any training data, a capability increasingly crucial in industrial inspection and medical imaging. This dissertation aims to investigate the core challenges of zero-shot AC/AS and presents principled solutions rooted in theory and algorithmic design. We first formalize the problem of consistent anomalies, a failure mode in which recurring similar anomalies systematically bias distance-based methods. By analyzing the statistical and geometric behavior of patch representations from pre-trained Vision Transformers, we identify two key phenomena - similarity scaling and neighbor-burnout - that describe how relationships among normal patches change with and without consistent anomalies in settings characterized by highly similar objects. We then introduce CoDeGraph, a graph-based framework for filtering consistent anomalies built on the similarity scaling and neighbor-burnout phenomena. Through multi-stage graph construction, community detection, and structured refinement, CoDeGraph effectively suppresses the influence of consistent anomalies. Next, we extend this framework to 3D medical imaging by proposing a training-free, computationally efficient volumetric tokenization strategy for MRI data. This enables a genuinely zero-shot 3D anomaly detection pipeline and shows that volumetric anomaly segmentation is achievable without any 3D training samples. Finally, we bridge batch-based and text-based zero-shot methods by demonstrating that CoDeGraph-derived pseudo-masks can supervise prompt-driven vision-language models. Together, this dissertation provides theoretical understanding and practical solutions for the zero-shot AC/AS problem. --- ### SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts Authors: Jiaqi Liu, Ronghao Fu, Lang Sun, Haoran Liu, Xiao Yang, Weipeng Zhang, Xu Na, Zhuoran Duan, Bo Yang Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02517v1 The emergence of large vision-language models (VLMs) has significantly enhanced the efficiency and flexibility of geospatial interpretation. However, general-purpose VLMs remain suboptimal for remote sensing (RS) tasks. Existing geospatial VLMs typically adopt a unified modeling strategy and struggle to differentiate between task types and interpretation granularities, limiting their ability to balance local detail perception and global contextual understanding. In this paper, we present SkyMoE, a Mixture-of-Experts (MoE) vision-language model tailored for multimodal, multi-task RS interpretation. SkyMoE employs an adaptive router that generates task- and granularity-aware routing instructions, enabling specialized large language model experts to handle diverse sub-tasks. To further promote expert decoupling and granularity sensitivity, we introduce a context-disentangled augmentation strategy that creates contrastive pairs between local and global features, guiding experts toward level-specific representation learning. We also construct MGRS-Bench, a comprehensive benchmark covering multiple RS interpretation tasks and granularity levels, to evaluate generalization in complex scenarios. Extensive experiments on 21 public datasets demonstrate that SkyMoE achieves state-of-the-art performance across tasks, validating its adaptability, scalability, and superior multi-granularity understanding in remote sensing. --- ### Decentralized Fairness Aware Multi Task Federated Learning for VR Network Authors: Krishnendu S. Tharakan, Carlo Fischione Published: 2025-12-02 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2512.02513v2 Wireless connectivity promises to unshackle virtual reality (VR) experiences, allowing users to engage from anywhere, anytime. However, delivering seamless, high-quality, real-time VR video wirelessly is challenging due to the stringent quality of experience requirements, low latency constraints, and limited VR device capabilities. This paper addresses these challenges by introducing a novel decentralized multi task fair federated learning (DMTFL) based caching that caches and prefetches each VR user's field of view (FOV) at base stations (BSs) based on the caching strategies tailored to each BS. In federated learning (FL) in its naive form, often biases toward certain users, and a single global model fails to capture the statistical heterogeneity across users and BSs. In contrast, the proposed DMTFL algorithm personalizes content delivery by learning individual caching models at each BS. These models are further optimized to perform well under any target distribution, while providing theoretical guarantees via Rademacher complexity and a probably approximately correct (PAC) bound on the loss. Using a realistic VR head-tracking dataset, our simulations demonstrate the superiority of our proposed DMTFL algorithm compared to baseline algorithms. --- ### Two-Stage Vision Transformer for Image Restoration: Colorization Pretraining + Residual Upsampling Authors: Aditya Chaudhary, Prachet Dev Singh, Ankit Jha Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02512v2 In computer vision, Single Image Super-Resolution (SISR) is still a difficult problem. We present ViT-SR, a new technique to improve the performance of a Vision Transformer (ViT) employing a two-stage training strategy. In our method, the model learns rich, generalizable visual representations from the data itself through a self-supervised pretraining phase on a colourization task. The pre-trained model is then adjusted for 4x super-resolution. By predicting the addition of a high-frequency residual image to an initial bicubic interpolation, this design simplifies residual learning. ViT-SR, trained and evaluated on the DIV2K benchmark dataset, achieves an impressive SSIM of 0.712 and PSNR of 22.90 dB. These results demonstrate the efficacy of our two-stage approach and highlight the potential of self-supervised pre-training for complex image restoration tasks. Further improvements may be possible with larger ViT architectures or alternative pretext tasks. --- ### Water Quality Estimation Through Machine Learning Multivariate Analysis Authors: Marco Cardia, Stefano Chessa, Alessio Micheli, Antonella Giuliana Luminare, Francesca Gambineri Published: 2025-12-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.02508v1 The quality of water is key for the quality of agrifood sector. Water is used in agriculture for fertigation, for animal husbandry, and in the agrifood processing industry. In the context of the progressive digitalization of this sector, the automatic assessment of the quality of water is thus becoming an important asset. In this work, we present the integration of Ultraviolet-Visible (UV-Vis) spectroscopy with Machine Learning in the context of water quality assessment aiming at ensuring water safety and the compliance of water regulation. Furthermore, we emphasize the importance of model interpretability by employing SHapley Additive exPlanations (SHAP) to understand the contribution of absorbance at different wavelengths to the predictions. Our approach demonstrates the potential for rapid, accurate, and interpretable assessment of key water quality parameters. --- ### GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding Authors: Jiaqi Liu, Ronghao Fu, Haoran Liu, Lang Sun, Bo Yang Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02505v2 Autoregressive models are structurally misaligned with the inherently parallel nature of geospatial understanding, forcing a rigid sequential narrative onto scenes and fundamentally hindering the generation of structured and coherent outputs. We challenge this paradigm by reframing geospatial generation as a parallel refinement process, enabling a holistic, coarse-to-fine synthesis that resolves all semantic elements simultaneously. To operationalize this, we introduce GeoDiT, the first diffusion-based vision-language model tailored for the geospatial domain. Extensive experiments demonstrate that GeoDiT establishes a new state-of-the-art on benchmarks requiring structured, object-centric outputs. It achieves significant gains in image captioning, visual grounding, and multi-object detection, precisely the tasks where autoregressive models falter. Our work validates that aligning the generative process with the data's intrinsic structure is key to unlocking superior performance in complex geospatial analysis. --- ### AskNearby: An LLM-Based Application for Neighborhood Information Retrieval and Personalized Cognitive-Map Recommendations Authors: Luyao Niu, Zhicheng Deng, Boyang Li, Nuoxian Huang, Ruiqi Liu, Wenjia Zhang Published: 2025-12-02 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.02502v1 The "15-minute city" envisions neighborhoods where residents can meet daily needs via a short walk or bike ride. Realizing this vision requires not only physical proximity but also efficient and reliable access to information about nearby places, services, and events. Existing location-based systems, however, focus mainly on city-level tasks and neglect the spatial, temporal, and cognitive factors that shape localized decision-making. We conceptualize this gap as the Local Life Information Accessibility (LLIA) problem and introduce AskNearby, an AI-driven community application that unifies retrieval and recommendation within the 15-minute life circle. AskNearby integrates (i) a three-layer Retrieval-Augmented Generation (RAG) pipeline that synergizes graph-based, semantic-vector, and geographic retrieval with (ii) a cognitive-map model that encodes each user's neighborhood familiarity and preferences. Experiments on real-world community datasets demonstrate that AskNearby significantly outperforms LLM-based and map-based baselines in retrieval accuracy and recommendation quality, achieving robust performance in spatiotemporal grounding and cognitive-aware ranking. Real-world deployments further validate its effectiveness. By addressing the LLIA challenge, AskNearby empowers residents to more effectively discover local resources, plan daily activities, and engage in community life. --- ### COPE: Chain-Of-Thought Prediction Engine for Open-Source Large Language Model Based Stroke Outcome Prediction from Clinical Notes Authors: Yongkai Liu, Helena Feng, Bin Jiang, Yixin Wang, Max Wintermark, David S. Liebeskind, Michael Moseley, Maarten Lansberg, Gregory Albers, Jeremy Heit, Greg Zaharchuk Published: 2025-12-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.02499v1 Predicting outcomes in acute ischemic stroke (AIS) guides clinical decision-making, patient counseling, and resource allocation. Clinical notes contain rich contextual information, but their unstructured nature limits their use in traditional predictive models. We developed and evaluated the Chain-of-Thought (CoT) Outcome Prediction Engine (COPE), a reasoning-enhanced large language model framework, for predicting 90-day functional outcomes after AIS from unstructured clinical notes. This study included 464 AIS patients with discharge summaries and 90-day modified Rankin Scale (mRS) scores. COPE uses a two-step CoT framework based on sequential open-source LLaMA-3-8B models: the first generates clinical reasoning, and the second outputs an mRS prediction. We compared COPE with GPT-4.1, ClinicalBERT, a structured variable-based machine learning model (Clinical ML), and a single-step LLM without CoT. Performance was evaluated using mean absolute error (MAE), accuracy within +/-1 mRS point, and exact accuracy. COPE achieved an MAE of 1.01 (95% CI 0.92-1.11), +/-1 accuracy of 74.4% (69.9, 78.8%), and exact accuracy of 32.8% (28.0, 37.6%), comparable to GPT-4.1 and superior to ClinicalBERT (MAE 1.24 (1.13-1.36)), Clinical ML (1.28 (1.18-1.39)), and the single-step LLM (1.20 (1.09-1.33)). Subgroup analyses showed consistent performance across sex and age, with slightly higher error among older patients, those undergoing thrombectomy, and those with longer summaries. These findings demonstrate that COPE, a lightweight, interpretable, and privacy-preserving open-source framework, provides an accurate and practical solution for outcome prediction from unstructured clinical text. --- ### dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model Authors: Yumeng Li, Guang Yang, Hao Liu, Bowen Wang, Colin Zhang Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02498v4 Document Layout Parsing serves as a critical gateway for Artificial Intelligence (AI) to access and interpret the world's vast stores of structured knowledge. This process,which encompasses layout detection, text recognition, and relational understanding, is particularly crucial for empowering next-generation Vision-Language Models. Current methods, however, rely on fragmented, multi-stage pipelines that suffer from error propagation and fail to leverage the synergies of joint training. In this paper, we introduce dots_ocr, a single Vision-Language Model that, for the first time, demonstrates the advantages of jointly learning three core tasks within a unified, end-to-end framework. This is made possible by a highly scalable data engine that synthesizes a vast multilingual corpus, empowering the model to deliver robust performance across a wide array of tasks, encompassing diverse languages, layouts, and domains. The efficacy of our unified paradigm is validated by state-of-the-art performance on the comprehensive OmniDocBench. Furthermore, to catalyze research in global document intelligence, we introduce XDocParse, a challenging new benchmark spanning 126 languages. On this benchmark, dots_ocr achieves state-of-the-art performance, delivering an approximately 10% relative improvement and demonstrating strong multilingual capability. --- ### A Large Scale Benchmark for Test Time Adaptation Methods in Medical Image Segmentation Authors: Wenjing Yu, Shuo Jiang, Yifei Chen, Shuo Chang, Yuanhan Wang, Beining Wu, Jie Dong, Mingxuan Liu, Shenghao Zhu, Feiwei Qin, Changmiao Wang, Qiyuan Tian Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02497v1 Test time Adaptation is a promising approach for mitigating domain shift in medical image segmentation; however, current evaluations remain limited in terms of modality coverage, task diversity, and methodological consistency. We present MedSeg-TTA, a comprehensive benchmark that examines twenty representative adaptation methods across seven imaging modalities, including MRI, CT, ultrasound, pathology, dermoscopy, OCT, and chest X-ray, under fully unified data preprocessing, backbone configuration, and test time protocols. The benchmark encompasses four significant adaptation paradigms: Input-level Transformation, Feature-level Alignment, Output-level Regularization, and Prior Estimation, enabling the first systematic cross-modality comparison of their reliability and applicability. The results show that no single paradigm performs best in all conditions. Input-level methods are more stable under mild appearance shifts. Feature-level and Output-level methods offer greater advantages in boundary-related metrics, whereas prior-based methods exhibit strong modality dependence. Several methods degrade significantly under large inter-center and inter-device shifts, which highlights the importance of principled method selection for clinical deployment. MedSeg-TTA provides standardized datasets, validated implementations, and a public leaderboard, establishing a rigorous foundation for future research on robust, clinically reliable test-time adaptation. All source codes and open-source datasets are available at https://github.com/wenjing-gg/MedSeg-TTA. --- ### Attention-guided reference point shifting for Gaussian-mixture-based partial point set registration Authors: Mizuki Kikkawa, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki Published: 2025-12-02 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2512.02496v2 This study investigates the impact of the invariance of feature vectors for partial-to-partial point set registration under translation and rotation of input point sets, particularly in the realm of techniques based on deep learning and Gaussian mixture models (GMMs). We reveal both theoretical and practical problems associated with such deep-learning-based registration methods using GMMs, with a particular focus on the limitations of DeepGMR, a pioneering study in this line, to the partial-to-partial point set registration. Our primary goal is to uncover the causes behind such methods and propose a comprehensible solution for that. To address this, we introduce an attention-based reference point shifting (ARPS) layer, which robustly identifies a common reference point of two partial point sets, thereby acquiring transformation-invariant features. The ARPS layer employs a well-studied attention module to find a common reference point rather than the overlap region. Owing to this, it significantly enhances the performance of DeepGMR and its recent variant, UGMMReg. Furthermore, these extension models outperform even prior deep learning methods using attention blocks and Transformer to extract the overlap region or common reference points. We believe these findings provide deeper insights into registration methods using deep learning and GMMs. --- ### Bayesian Physics-Informed Neural Networks for Inverse Problems (BPINN-IP): Application in Infrared Image Processing Authors: Ali Mohammad-Djafari, Ning Chu, Li Wang Published: 2025-12-02 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.02495v1 Inverse problems arise across scientific and engineering domains, where the goal is to infer hidden parameters or physical fields from indirect and noisy observations. Classical approaches, such as variational regularization and Bayesian inference, provide well established theoretical foundations for handling ill posedness. However, these methods often become computationally restrictive in high dimensional settings or when the forward model is governed by complex physics. Physics Informed Neural Networks (PINNs) have recently emerged as a promising framework for solving inverse problems by embedding physical laws directly into the training process of neural networks. In this paper, we introduce a new perspective on the Bayesian Physics Informed Neural Network (BPINN) framework, extending classical PINNs by explicitly incorporating training data generation, modeling and measurement uncertainties through Bayesian prior modeling and doing inference with the posterior laws. Also, as we focus on the inverse problems, we call this method BPINN-IP, and we show that the standard PINN formulation naturally appears as its special case corresponding to the Maximum A Posteriori (MAP) estimate. This unified formulation allows simultaneous exploitation of physical constraints, prior knowledge, and data-driven inference, while enabling uncertainty quantification through posterior distributions. To demonstrate the effectiveness of the proposed framework, we consider inverse problems arising in infrared image processing, including deconvolution and super-resolution, and present results on both simulated and real industrial data. --- ### A Fully First-Order Layer for Differentiable Optimization Authors: Zihao Zhao, Kai-Chia Mo, Shing-Hei Ho, Brandon Amos, Kai Wang Published: 2025-12-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.02494v2 Differentiable optimization layers enable learning systems to make decisions by solving embedded optimization problems. However, computing gradients via implicit differentiation requires solving a linear system with Hessian terms, which is both compute- and memory-intensive. To address this challenge, we propose a novel algorithm that computes the gradient using only first-order information. The key insight is to rewrite the differentiable optimization as a bilevel optimization problem and leverage recent advances in bilevel methods. Specifically, we introduce an active-set Lagrangian hypergradient oracle that avoids Hessian evaluations and provides finite-time, non-asymptotic approximation guarantees. We show that an approximate hypergradient can be computed using only first-order information in $\tilde{O}(1)$ time, leading to an overall complexity of $\tilde{O}(δ^{-1}ε^{-3})$ for constrained bilevel optimization, which matches the best known rate for non-smooth non-convex optimization. Furthermore, we release an open-source Python library that can be easily adapted from existing solvers. The source code is available at https://github.com/guaguakai/FFOLayer. --- ### YingVideo-MV: Music-Driven Multi-Stage Video Generation Authors: Jiahui Chen, Weida Wang, Runhua Shi, Huan Yang, Chaofan Ding, Zihao Chen Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02492v1 While diffusion model for audio-driven avatar video generation have achieved notable process in synthesizing long sequences with natural audio-visual synchronization and identity consistency, the generation of music-performance videos with camera motions remains largely unexplored. We present YingVideo-MV, the first cascaded framework for music-driven long-video generation. Our approach integrates audio semantic analysis, an interpretable shot planning module (MV-Director), temporal-aware diffusion Transformer architectures, and long-sequence consistency modeling to enable automatic synthesis of high-quality music performance videos from audio signals. We construct a large-scale Music-in-the-Wild Dataset by collecting web data to support the achievement of diverse, high-quality results. Observing that existing long-video generation methods lack explicit camera motion control, we introduce a camera adapter module that embeds camera poses into latent noise. To enhance continulity between clips during long-sequence inference, we further propose a time-aware dynamic window range strategy that adaptively adjust denoising ranges based on audio embedding. Comprehensive benchmark tests demonstrate that YingVideo-MV achieves outstanding performance in generating coherent and expressive music videos, and enables precise music-motion-camera synchronization. More videos are available in our project page: https://giantailab.github.io/YingVideo-MV/ . --- ### Stress-Testing Causal Claims via Cardinality Repairs Authors: Yarden Gabbay, Haoquan Guan, Shaull Almagor, El Kindi Rezig, Brit Youngmann, Babak Salimi Published: 2025-12-02 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2512.02491v2 Causal analyses derived from observational data underpin high-stakes decisions in domains such as healthcare, public policy, and economics. Yet such conclusions can be surprisingly fragile: even minor data errors - duplicate records, or entry mistakes - may drastically alter causal relationships. This raises a fundamental question: how robust is a causal claim to small, targeted modifications in the data? Addressing this question is essential for ensuring the reliability, interpretability, and reproducibility of empirical findings. We introduce SubCure, a framework for robustness auditing via cardinality repairs. Given a causal query and a user-specified target range for the estimated effect, SubCure identifies a small set of tuples or subpopulations whose removal shifts the estimate into the desired range. This process not only quantifies the sensitivity of causal conclusions but also pinpoints the specific regions of the data that drive those conclusions. We formalize this problem under both tuple- and pattern-level deletion settings and show both are NP-complete. To scale to large datasets, we develop efficient algorithms that incorporate machine unlearning techniques to incrementally update causal estimates without retraining from scratch. We evaluate SubCure across four real-world datasets covering diverse application domains. In each case, it uncovers compact, high-impact subsets whose removal significantly shifts the causal conclusions, revealing vulnerabilities that traditional methods fail to detect. Our results demonstrate that cardinality repair is a powerful and general-purpose tool for stress-testing causal analyses and guarding against misleading claims rooted in ordinary data imperfections. --- ### Hybrid(Penalized Regression and MLP) Models for Outcome Prediction in HDLSS Health Data Authors: Mithra D K Published: 2025-12-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.02489v1 I present an application of established machine learning techniques to NHANES health survey data for predicting diabetes status. I compare baseline models (logistic regression, random forest, XGBoost) with a hybrid approach that uses an XGBoost feature encoder and a lightweight multilayer perceptron (MLP) head. Experiments show the hybrid model attains improved AUC and balanced accuracy compared to baselines on the processed NHANES subset. I release code and reproducible scripts to encourage replication. --- ### Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding Authors: Yerim Jeon, Miso Lee, WonJun Moon, Jae-Pil Heo Published: 2025-12-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.02487v2 Recent advances in 3D scene-language understanding have leveraged Large Language Models (LLMs) for 3D reasoning by transferring their general reasoning ability to 3D multi-modal contexts. However, existing methods typically adopt standard decoders from language modeling, which rely on a causal attention mask. This design introduces two fundamental conflicts in 3D scene understanding: sequential bias among order-agnostic 3D objects and restricted object-instruction attention, hindering task-specific reasoning. To overcome these limitations, we propose 3D Spatial Language Instruction Mask (3D-SLIM), an effective masking strategy that replaces the causal mask with an adaptive attention mask tailored to the spatial structure of 3D scenes. Our 3D-SLIM introduces two key components: a Geometry-adaptive Mask that constrains attention based on spatial density rather than token order, and an Instruction-aware Mask that enables object tokens to directly access instruction context. This design allows the model to process objects based on their spatial relationships while being guided by the user's task. 3D-SLIM is simple, requires no architectural modifications, and adds no extra parameters, yet it yields substantial performance improvements across diverse 3D scene-language tasks. Extensive experiments across multiple benchmarks and LLM baselines validate its effectiveness and underscore the critical role of decoder design in 3D multi-modal reasoning. --- ### Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts Authors: Zhongjian Qiao, Rui Yang, Jiafei Lyu, Xiu Li, Zhongxiang Dai, Zhuoran Yang, Siyang Gao, Shuang Qiu Published: 2025-12-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.02486v2 Single-domain offline reinforcement learning (RL) often suffers from limited data coverage, while cross-domain offline RL handles this issue by leveraging additional data from other domains with dynamics shifts. However, existing studies primarily focus on train-time robustness (handling dynamics shifts from training data), neglecting the test-time robustness against dynamics perturbations when deployed in practical scenarios. In this paper, we investigate dual (both train-time and test-time) robustness against dynamics shifts in cross-domain offline RL. We first empirically show that the policy trained with cross-domain offline RL exhibits fragility under dynamics perturbations during evaluation, particularly when target domain data is limited. To address this, we introduce a novel robust cross-domain Bellman (RCB) operator, which enhances test-time robustness against dynamics perturbations while staying conservative to the out-of-distribution dynamics transitions, thus guaranteeing the train-time robustness. To further counteract potential value overestimation or underestimation caused by the RCB operator, we introduce two techniques, the dynamic value penalty and the Huber loss, into our framework, resulting in the practical \textbf{D}ual-\textbf{RO}bust \textbf{C}ross-domain \textbf{O}ffline RL (DROCO) algorithm. Extensive empirical results across various dynamics shift scenarios show that DROCO outperforms strong baselines and exhibits enhanced robustness to dynamics perturbations. --- ### UCAgents: Unidirectional Convergence for Visual Evidence Anchored Multi-Agent Medical Decision-Making Authors: Qianhan Feng, Zhongzhen Huang, Yakun Zhu, Xiaofan Zhang, Qi Dou Published: 2025-12-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.02485v1 Vision-Language Models (VLMs) show promise in medical diagnosis, yet suffer from reasoning detachment, where linguistically fluent explanations drift from verifiable image evidence, undermining clinical trust. Recent multi-agent frameworks simulate Multidisciplinary Team (MDT) debates to mitigate single-model bias, but open-ended discussions amplify textual noise and computational cost while failing to anchor reasoning to visual evidence, the cornerstone of medical decision-making. We propose UCAgents, a hierarchical multi-agent framework enforcing unidirectional convergence through structured evidence auditing. Inspired by clinical workflows, UCAgents forbids position changes and limits agent interactions to targeted evidence verification, suppressing rhetorical drift while amplifying visual signal extraction. In UCAgents, a one-round inquiry discussion is introduced to uncover potential risks of visual-textual misalignment. This design jointly constrains visual ambiguity and textual noise, a dual-noise bottleneck that we formalize via information theory. Extensive experiments on four medical VQA benchmarks show UCAgents achieves superior accuracy (71.3% on PathVQA, +6.0% over state-of-the-art) with 87.7% lower token cost, the evaluation results further confirm that UCAgents strikes a balance between uncovering more visual evidence and avoiding confusing textual interference. These results demonstrate that UCAgents exhibits both diagnostic reliability and computational efficiency critical for real-world clinical deployment. Code is available at https://github.com/fqhank/UCAgents. --- ### G-SHARP: Gaussian Surgical Hardware Accelerated Real-time Pipeline Authors: Vishwesh Nath, Javier G. Tejero, Aravind S. Kumar, Ruilong Li, Filippo Filicori, Mahdi Azizian, Sean D. Huver Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02482v2 We propose G-SHARP, a commercially compatible, real-time surgical scene reconstruction framework designed for minimally invasive procedures that require fast and accurate 3D modeling of deformable tissue. While recent Gaussian splatting approaches have advanced real-time endoscopic reconstruction, existing implementations often depend on non-commercial derivatives, limiting deployability. G-SHARP overcomes these constraints by being the first surgical pipeline built natively on the GSplat (Apache-2.0) differentiable Gaussian rasterizer, enabling principled deformation modeling, robust occlusion handling, and high-fidelity reconstructions on the EndoNeRF pulling benchmark. Our results demonstrate state-of-the-art reconstruction quality with strong speed-accuracy trade-offs suitable for intra-operative use. Finally, we provide a Holoscan SDK application that deploys G-SHARP on NVIDIA IGX Orin and Thor edge hardware, enabling real-time surgical visualization in practical operating-room settings. --- ### Q-BERT4Rec: Quantized Semantic-ID Representation Learning for Multimodal Recommendation Authors: Haofeng Huang, Ling Gai Published: 2025-12-02 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.02474v2 Sequential recommendation plays a critical role in modern online platforms such as e-commerce, advertising, and content streaming, where accurately predicting users' next interactions is essential for personalization. Recent Transformer-based methods like BERT4Rec have shown strong modeling capability, yet they still rely on discrete item IDs that lack semantic meaning and ignore rich multimodal information (e.g., text and image). This leads to weak generalization and limited interpretability. To address these challenges, we propose Q-Bert4Rec, a multimodal sequential recommendation framework that unifies semantic representation and quantized modeling. Specifically, Q-Bert4Rec consists of three stages: (1) cross-modal semantic injection, which enriches randomly initialized ID embeddings through a dynamic transformer that fuses textual, visual, and structural features; (2) semantic quantization, which discretizes fused representations into meaningful tokens via residual vector quantization; and (3) multi-mask pretraining and fine-tuning, which leverage diverse masking strategies -- span, tail, and multi-region -- to improve sequential understanding. We validate our model on public Amazon benchmarks and demonstrate that Q-Bert4Rec significantly outperforms many strong existing methods, confirming the effectiveness of semantic tokenization for multimodal sequential recommendation. Our source code will be publicly available on GitHub after publishing. --- ### WorldPack: Dynamic Frame Compression for Long-context Video World Modeling Authors: Yuta Oshima, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta Published: 2025-12-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.02473v3 Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation actions. However, achieving temporally and spatially consistent generation over long horizons remains an open challenge: existing approaches either compress past frames without explicitly accounting for 3D viewpoint geometry or retrieve only a handful of spatially relevant frames without increasing the total amount of retained history. In this paper, we propose WorldPack, a video world model that introduces spatially-aware compressed memory to address both limitations simultaneously. The key insight is that compression rates should not be uniform or temporally determined, but should instead be dynamically allocated based on 3D spatial relevance to the current viewpoint. WorldPack achieves this through two tightly coupled mechanisms: trajectory packing, which fits substantially more historical frames into a fixed-length context through hierarchical frame compression, and geometric selection, which leverages camera pose information and field-of-view overlap to assign lower compression to spatially important frames and higher compression to less relevant ones. Together, these mechanisms expand the effective context from 4 to 22 frames with moderate computational overhead: trajectory packing increases diffusion-model inference time by 16%, while FoV-based geometric selection introduces an additional cost. We evaluate WorldPack on LoopNav, a Minecraft benchmark for long-horizon spatial consistency, and conduct comprehensive experiments on the RECON, real-world navigation dataset, across multiple metrics. WorldPack outperforms strong baselines, including Oasis, Mineworld, DIAMOND, and NWM, with pronounced gains on spatial reasoning tasks that require recall of distant observations. --- ### Guided Self-Evolving LLMs with Minimal Human Supervision Authors: Wenhao Yu, Zhenwen Liang, Chengsong Huang, Kishan Panaganti, Tianqing Fang, Haitao Mi, Dong Yu Published: 2025-12-02 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.02472v1 AI self-evolution has long been envisioned as a path toward superintelligence, where models autonomously acquire, refine, and internalize knowledge from their own learning experiences. Yet in practice, unguided self-evolving systems often plateau quickly or even degrade as training progresses. These failures arise from issues such as concept drift, diversity collapse, and mis-evolution, as models reinforce their own biases and converge toward low-entropy behaviors. To enable models to self-evolve in a stable and controllable manner while minimizing reliance on human supervision, we introduce R-Few, a guided Self-Play Challenger-Solver framework that incorporates lightweight human oversight through in-context grounding and mixed training. At each iteration, the Challenger samples a small set of human-labeled examples to guide synthetic question generation, while the Solver jointly trains on human and synthetic examples under an online, difficulty-based curriculum. Across math and general reasoning benchmarks, R-Few achieves consistent and iterative improvements. For example, Qwen3-8B-Base improves by +3.0 points over R-Zero on math tasks and achieves performance on par with General-Reasoner, despite the latter being trained on 20 times more human data. Ablation studies confirm the complementary contributions of grounded challenger training and curriculum-based solver training, and further analysis shows that R-Few mitigates drift, yielding more stable and controllable co-evolutionary dynamics. --- ### scCluBench: Comprehensive Benchmarking of Clustering Algorithms for Single-Cell RNA Sequencing Authors: Ping Xu, Zaitian Wang, Zhirui Wang, Pengjiang Li, Jiajia Wang, Ran Zhang, Pengfei Wang, Yuanchun Zhou Published: 2025-12-02 Categories: q-bio.GN, cs.AI arXiv: https://arxiv.org/abs/2512.02471v1 Cell clustering is crucial for uncovering cellular heterogeneity in single-cell RNA sequencing (scRNA-seq) data by identifying cell types and marker genes. Despite its importance, benchmarks for scRNA-seq clustering methods remain fragmented, often lacking standardized protocols and failing to incorporate recent advances in artificial intelligence. To fill these gaps, we present scCluBench, a comprehensive benchmark of clustering algorithms for scRNA-seq data. First, scCluBench provides 36 scRNA-seq datasets collected from diverse public sources, covering multiple tissues, which are uniformly processed and standardized to ensure consistency for systematic evaluation and downstream analyses. To evaluate performance, we collect and reproduce a range of scRNA-seq clustering methods, including traditional, deep learning-based, graph-based, and biological foundation models. We comprehensively evaluate each method both quantitatively and qualitatively, using core performance metrics as well as visualization analyses. Furthermore, we construct representative downstream biological tasks, such as marker gene identification and cell type annotation, to further assess the practical utility. scCluBench then investigates the performance differences and applicability boundaries of various clustering models across diverse analytical tasks, systematically assessing their robustness and scalability in real-world scenarios. Overall, scCluBench offers a standardized and user-friendly benchmark for scRNA-seq clustering, with curated datasets, unified evaluation protocols, and transparent analyses, facilitating informed method selection and providing valuable insights into model generalizability and application scope. --- ### TGDD: Trajectory Guided Dataset Distillation with Balanced Distribution Authors: Fengli Ran, Xiao Pu, Bo Liu, Xiuli Bi, Bin Xiao Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02469v1 Dataset distillation compresses large datasets into compact synthetic ones to reduce storage and computational costs. Among various approaches, distribution matching (DM)-based methods have attracted attention for their high efficiency. However, they often overlook the evolution of feature representations during training, which limits the expressiveness of synthetic data and weakens downstream performance. To address this issue, we propose Trajectory Guided Dataset Distillation (TGDD), which reformulates distribution matching as a dynamic alignment process along the model's training trajectory. At each training stage, TGDD captures evolving semantics by aligning the feature distribution between the synthetic and original dataset. Meanwhile, it introduces a distribution constraint regularization to reduce class overlap. This design helps synthetic data preserve both semantic diversity and representativeness, improving performance in downstream tasks. Without additional optimization overhead, TGDD achieves a favorable balance between performance and efficiency. Experiments on ten datasets demonstrate that TGDD achieves state-of-the-art performance, notably a 5.0% accuracy gain on high-resolution benchmarks. --- ### TabGRU: An Enhanced Design for Urban Rainfall Intensity Estimation Using Commercial Microwave Links Authors: Xingwang Li, Mengyun Chen, Jiamou Liu, Sijie Wang, Shuanggen Jin, Jafet C. M. Andersson, Jonas Olsson, Remco, van de Beek, Hai Victor Habi, Congzheng Han Published: 2025-12-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.02465v1 In the face of accelerating global urbanization and the increasing frequency of extreme weather events, highresolution urban rainfall monitoring is crucial for building resilient smart cities. Commercial Microwave Links (CMLs) are an emerging data source with great potential for this task.While traditional rainfall retrieval from CMLs relies on physicsbased models, these often struggle with real-world complexities like signal noise and nonlinear attenuation. To address these limitations, this paper proposes a novel hybrid deep learning architecture based on the Transformer and a Bidirectional Gated Recurrent Unit (BiGRU), which we name TabGRU. This design synergistically captures both long-term dependencies and local sequential features in the CML signal data. The model is further enhanced by a learnable positional embedding and an attention pooling mechanism to improve its dynamic feature extraction and generalization capabilities. The model was validated on a public benchmark dataset from Gothenburg, Sweden (June-September 2015). The evaluation used 12 sub-links from two rain gauges (Torp and Barl) over a test period (August 22-31) covering approximately 10 distinct rainfall events. The proposed TabGRU model demonstrated consistent advantages, outperforming deep learning baselines and achieving high coefficients of determination (R2) at both the Torp site (0.91) and the Barl site (0.96). Furthermore, compared to the physics-based approach, TabGRU maintained higher accuracy and was particularly effective in mitigating the significant overestimation problem observed in the PL model during peak rainfall events. This evaluation confirms that the TabGRU model can effectively overcome the limitations of traditional methods, providing a robust and accurate solution for CML-based urban rainfall monitoring under the tested conditions. --- ### Neural Architecture Search of Time-to-First-Spike-Coded Spiking Neural Networks for Efficient Eye-based Emotion Recognition Authors: Qianhui Liu, Jing Yang, Miao Yu, Trevor E. Carlson, Gang Pan, Haizhou Li, Zhumin Chen Published: 2025-12-02 Categories: cs.NE arXiv: https://arxiv.org/abs/2512.02459v2 Eye-based emotion recognition enables eyewear devices to perceive users' emotional states and support emotion-aware interaction. However, deploying such functionality on their resource-limited embedded hardware remains challenging. Time-to-first-spike (TTFS)-coded spiking neural networks (SNNs) offer a promising solution due to their extremely sparse and energy-efficient computation, where each neuron emits at most one binary spike. While prior works have primarily focused on improving TTFS SNN training algorithms, the role of network architecture has been largely overlooked. This is particularly critical, as spike timing in TTFS SNNs is tightly coupled with architectural design, and eye-based emotion recognition requires compact yet highly efficient networks. In this paper, we propose TNAS-ER, the first neural architecture search (NAS) framework tailored to TTFS SNNs for eye-based emotion recognition. TNAS-ER presents a novel ANN-assisted search strategy that leverages a ReLU-based ANN counterpart to guide architecture optimization and stabilize training of the TTFS SNN. TNAS-ER employs an evolutionary algorithm, with weighted and unweighted average recall jointly defined as fitness objectives for emotion recognition. Extensive experiments demonstrate that TNAS-ER achieves high recognition performance with significantly improved efficiency. Furthermore, we evaluate TNAS-ER on a neuromorphic hardware, confirming its superior energy efficiency and strong potential for real-world applications. --- ### Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration Authors: Zhongyi Cai, Yi Du, Chen Wang, Yu Kong Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02458v2 Embodied agents are expected to assist humans by actively exploring unknown environments and reasoning about spatial contexts. When deployed in real life, agents often face sequential tasks where each new task follows the completion of the previous one and may include infeasible objectives, such as searching for non-existent objects. However, most existing research focuses on isolated goals, overlooking the core challenge of sequential tasks: the ability to reuse spatial knowledge accumulated from previous explorations to guide subsequent reasoning and exploration. In this work, we investigate this underexplored yet practically significant embodied AI challenge. Specifically, we propose 3DSPMR, a 3D SPatial Memory Reasoning framework that utilizes Field-of-View (FoV) coverage as an explicit geometric prior. By integrating FoV-based constraints, 3DSPMR significantly enhances an agent's memory, reasoning, and exploration capabilities across sequential tasks. To facilitate research in this area, we further introduce SEER-Bench, a novel Sequential Embodied Exploration and Reasoning Benchmark that spans two foundational tasks: Embodied Question Answering (EQA) and Embodied Multi-modal Navigation (EMN). SEER-Bench uniquely incorporates both feasible and infeasible tasks to provide a rigorous and comprehensive evaluation of agent performance. Extensive experiments verify that 3DSPMR achieves substantial performance gains on both sequential EQA and EMN tasks. --- ### Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation Authors: Jianzong Wu, Hao Lian, Dachao Hao, Ye Tian, Qingyu Shi, Biaolong Chen, Hao Jiang, Yunhai Tong Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02457v2 Recent audio-video generative systems suggest that coupling modalities benefits not only audio-video synchrony but also the video modality itself. We pose a fundamental question: Does audio-video joint denoising training improve video generation, even when we only care about video quality? To study this, we introduce a parameter-efficient Audio-Video Full DiT (AVFullDiT) architecture that leverages pre-trained text-to-video (T2V) and text-to-audio (T2A) modules for joint denoising. We train (i) a T2AV model with AVFullDiT and (ii) a T2V-only counterpart under identical settings. Our results provide the first systematic evidence that audio-video joint denoising can deliver more than synchrony. We observe consistent improvements on challenging subsets featuring large and object contact motions. We hypothesize that predicting audio acts as a privileged signal, encouraging the model to internalize causal relationships between visual events and their acoustic consequences (e.g., collision $\times$ impact sound), which in turn regularizes video dynamics. Our findings suggest that cross-modal co-training is a promising approach to developing stronger, more physically grounded world models. Code and dataset will be made publicly available. --- ### See, Think, Learn: A Self-Taught Multimodal Reasoner Authors: Sourabh Sharma, Sonam Gupta, Sadbhawna Published: 2025-12-02 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2512.02456v2 Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effective multimodal reasoning requires both accurate perception and robust reasoning, and weakness in either limits the performance of VLMs. Prior efforts to enhance reasoning often depend on high-quality chain-of-thought (CoT) data, obtained via labor-intensive human annotations, costly proprietary models, or self-training methods that overlook perception. To address these limitations, we propose a simple yet effective self-training framework called See-Think-Learn (STL). At its core, STL introduces a structured reasoning template that encourages the model to see before thinking, first extracting visual attributes in textual form, then using them to guide reasoning. The framework jointly improves perception and reasoning by having the model generate and learn from its own structured rationales in a self-training loop. Furthermore, we augment the training data with negative rationales, i.e. explanations that justify why certain answer choices are incorrect, to enhance the model's ability to distinguish between correct and misleading responses. This fosters more discriminative and robust learning. Experiments across diverse domains show that STL consistently outperforms baselines trained directly only on answers or self-generated reasoning, while qualitative analysis confirms the high quality of its rationales. STL thus provides a cost-effective solution to enhance multimodal reasoning ability of VLMs. --- ### ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation Authors: Kerui Chen, Jianrong Zhang, Ming Li, Zhonglong Zheng, Hehe Fan Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02453v2 Existing stylized motion generation models have shown their remarkable ability to understand specific style information from the style motion, and insert it into the content motion. However, capturing intra-style diversity, where a single style should correspond to diverse motion variations, remains a significant challenge. In this paper, we propose a clustering-based framework, ClusterStyle, to address this limitation. Instead of learning an unstructured embedding from each style motion, we leverage a set of prototypes to effectively model diverse style patterns across motions belonging to the same style category. We consider two types of style diversity: global-level diversity among style motions of the same category, and local-level diversity within the temporal dynamics of motion sequences. These components jointly shape two structured style embedding spaces, i.e., global and local, optimized via alignment with non-learnable prototype anchors. Furthermore, we augment the pretrained text-to-motion generation model with the Stylistic Modulation Adapter (SMA) to integrate the style features. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art models in stylized motion generation and motion style transfer. --- ### HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild Authors: Valentin Bieri, Marie-Julie Rakotosaona, Keisuke Tateno, Francis Engelmann, Leonidas Guibas Published: 2025-12-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.02450v1 Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively handle large multi floor buildings and require scenes to be split into individual floors before processing, which removes global spatial context that is essential for reasoning about structures such as staircases that connect multiple levels. In this work, we introduce HouseLayout3D, a real world benchmark designed to support progress toward full building scale layout estimation, including multiple floors and architecturally intricate spaces. We also present MultiFloor3D, a simple training free baseline that leverages recent scene understanding methods and already outperforms existing 3D layout estimation models on both our benchmark and prior datasets, highlighting the need for further research in this direction. Data and code are available at: https://houselayout3d.github.io. --- ### nuScenes Revisited: Progress and Challenges in Autonomous Driving Authors: Whye Kit Fong, Venice Erin Liong, Kok Seang Tan, Holger Caesar Published: 2025-12-02 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.02448v2 Autonomous Vehicles (AV) and Advanced Driver Assistance Systems (ADAS) have been revolutionized by Deep Learning. As a data-driven approach, Deep Learning relies on vast amounts of driving data, typically labeled in great detail. As a result, datasets, alongside hardware and algorithms, are foundational building blocks for the development of AVs. In this work we revisit one of the most widely used autonomous driving datasets: the nuScenes dataset. nuScenes exemplifies key trends in AV development, being the first dataset to include radar data, to feature diverse urban driving scenes from two continents, and to be collected using a fully autonomous vehicle operating on public roads, while also promoting multi-modal sensor fusion, standardized benchmarks, and a broad range of tasks including perception, localization & mapping, prediction and planning. We provide an unprecedented look into the creation of nuScenes, as well as its extensions nuImages and Panoptic nuScenes, summarizing many technical details that have hitherto not been revealed in academic publications. Furthermore, we trace how the influence of nuScenes impacted a large number of other datasets that were released later and how it defined numerous standards that are used by the community to this day. Finally, we present an overview of both official and unofficial tasks using the nuScenes dataset and review major methodological developments, thereby offering a comprehensive survey of the autonomous driving literature, with a particular focus on nuScenes. --- ### Temporal Dynamics Enhancer for Directly Trained Spiking Object Detectors Authors: Fan Luo, Zeyu Gao, Xinhao Luo, Kai Zhao, Yanfeng Lu Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02447v1 Spiking Neural Networks (SNNs), with their brain-inspired spatiotemporal dynamics and spike-driven computation, have emerged as promising energy-efficient alternatives to Artificial Neural Networks (ANNs). However, existing SNNs typically replicate inputs directly or aggregate them into frames at fixed intervals. Such strategies lead to neurons receiving nearly identical stimuli across time steps, severely limiting the model's expressive power, particularly in complex tasks like object detection. In this work, we propose the Temporal Dynamics Enhancer (TDE) to strengthen SNNs' capacity for temporal information modeling. TDE consists of two modules: a Spiking Encoder (SE) that generates diverse input stimuli across time steps, and an Attention Gating Module (AGM) that guides the SE generation based on inter-temporal dependencies. Moreover, to eliminate the high-energy multiplication operations introduced by the AGM, we propose a Spike-Driven Attention (SDA) to reduce attention-related energy consumption. Extensive experiments demonstrate that TDE can be seamlessly integrated into existing SNN-based detectors and consistently outperforms state-of-the-art methods, achieving mAP50-95 scores of 57.7% on the static PASCAL VOC dataset and 47.6% on the neuromorphic EvDET200K dataset. In terms of energy consumption, the SDA consumes only 0.240 times the energy of conventional attention modules. --- ### When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents Authors: Tsimur Hadeliya, Mohammad Ali Jauhar, Nidhi Sakpal, Diogo Cruz Published: 2025-12-02 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.02445v1 Solving complex or long-horizon problems often requires large language models (LLMs) to use external tools and operate over a significantly longer context window. New LLMs enable longer context windows and support tool calling capabilities. Prior works have focused mainly on evaluation of LLMs on long-context prompts, leaving agentic setup relatively unexplored, both from capability and safety perspectives. Our work addresses this gap. We find that LLM agents could be sensitive to length, type, and placement of the context, exhibiting unexpected and inconsistent shifts in task performance and in refusals to execute harmful requests. Models with 1M-2M token context windows show severe degradation already at 100K tokens, with performance drops exceeding 50\% for both benign and harmful tasks. Refusal rates shift unpredictably: GPT-4.1-nano increases from $\sim$5\% to $\sim$40\% while Grok 4 Fast decreases from $\sim$80\% to $\sim$10\% at 200K tokens. Our work shows potential safety issues with agents operating on longer context and opens additional questions on the current metrics and paradigm for evaluating LLM agent safety on long multi-step tasks. In particular, our results on LLM agents reveal a notable divergence in both capability and safety performance compared to prior evaluations of LLMs on similar criteria. --- ### MetaJoin: Adaptive Join Selections for Heterogeneous Tables Authors: Ning Wang, Sainyam Galhotra Published: 2025-12-02 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2512.02444v2 Joining heterogeneous tables requires different forms of correspondence, including exact agreement, syntactic transformation, semantic similarity, and entity-level matching. The appropriate join method is often unknown in advance, while running every candidate method incurs unnecessary cost. We introduce MetaJoin, a label-free framework for adaptive join selection. MetaJoin uses input evidence to choose an initial specialist, then uses specialist-specific output evidence to determine whether that result should be retained, compared with an alternative, escalated, or repaired. This allows join selection to adapt after execution rather than committing to a one-shot routing decision. We also introduce MNN Join, a transformation specialist that searches for string transformations by maximizing mutual-nearest-neighbor coverage between two unaligned columns and uses the same reciprocal structure to validate its output. We evaluate MetaJoin on 670 datasets from six benchmarks. It achieves 0.817 macro row-F1, slightly exceeding a benchmark-level oracle that is given the best standalone specialist for each benchmark (0.812), and outperforms label-free selection policies built from the same specialist portfolio by more than 0.13. Across the 609 datasets in the four transformation-dominant benchmarks, MNN Join outperforms every evaluated transformation baseline. Finally, MetaJoin's accuracy varies by only 0.015 as the controller backbone ranges from 3B to 14B parameters, showing that output validation and repair substantially reduce dependence on the initial routing decision. --- ### Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation Authors: Junghwan Park, Woojin Cho, Junhyuk Heo, Darongsae Kwon, Kookjin Lee Published: 2025-12-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.02441v1 Adapting large pre-trained models to unseen tasks under tight data and compute budgets remains challenging. Meta-learning approaches explicitly learn good initializations, but they require an additional meta-training phase over many tasks, incur high training cost, and can be unstable. At the same time, the number of task-specific pre-trained models continues to grow, yet the question of how to transfer them to new tasks with minimal additional training remains relatively underexplored. We propose BOLT (Basis-Oriented Low-rank Transfer), a framework that reuses existing fine-tuned models not by merging weights, but instead by extracting an orthogonal, task-informed spectral basis and adapting within that subspace. In the offline phase, BOLT collects dominant singular directions from multiple task vectors and orthogonalizes them per layer to form reusable bases. In the online phase, we freeze these bases and train only a small set of diagonal coefficients per layer for the new task, yielding a rank-controlled update with very few trainable parameters. This design provides (i) a strong, training-free initialization for unseen tasks, obtained by pooling source-task coefficients, along with a lightweight rescaling step while leveraging the shared orthogonal bases, and (ii) a parameter-efficient fine-tuning (PEFT) path that, in our experiments, achieves robust performance compared to common PEFT baselines as well as a representative meta-learned initialization. Our results show that constraining adaptation to a task-informed orthogonal subspace provides an effective alternative for unseen-task transfer. --- ### Boosting Medical Vision-Language Pretraining via Momentum Self-Distillation under Limited Computing Resources Authors: Phuc Pham, Nhu Pham, Ngoc Quoc Ly Published: 2025-12-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.02438v1 In medical healthcare, obtaining detailed annotations is challenging, highlighting the need for robust Vision-Language Models (VLMs). Pretrained VLMs enable fine-tuning on small datasets or zero-shot inference, achieving performance comparable to task-specific models. Contrastive learning (CL) is a key paradigm for training VLMs but inherently requires large batch sizes for effective learning, making it computationally demanding and often limited to well-resourced institutions. Moreover, with limited data in healthcare, it is important to prioritize knowledge extraction from both data and models during training to improve performance. Therefore, we focus on leveraging the momentum method combined with distillation to simultaneously address computational efficiency and knowledge exploitation. Our contributions can be summarized as follows: (1) leveraging momentum self-distillation to enhance multimodal learning, and (2) integrating momentum mechanisms with gradient accumulation to enlarge the effective batch size without increasing resource consumption. Our method attains competitive performance with state-of-the-art (SOTA) approaches in zero-shot classification, while providing a substantial boost in the few-shot adaption, achieving over 90% AUC-ROC and improving retrieval tasks by 2-3%. Importantly, our method achieves high training efficiency with a single GPU while maintaining reasonable training time. Our approach aims to advance efficient multimodal learning by reducing resource requirements while improving performance over SOTA methods. The implementation of our method is available at https://github.com/phphuc612/MSD . --- ### LightHCG: a Lightweight yet powerful HSIC Disentanglement based Causal Glaucoma Detection Model framework Authors: Daeyoung Kim Published: 2025-12-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.02437v1 As a representative optic degenerative condition, glaucoma has been a threat to millions due to its irreversibility and severe impact on human vision fields. Mainly characterized by dimmed and blurred visions, or peripheral vision loss, glaucoma is well known to occur due to damages in the optic nerve from increased intraocular pressure (IOP) or neovascularization within the retina. Traditionally, most glaucoma related works and clinical diagnosis focused on detecting these damages in the optic nerve by using patient data from perimetry tests, optic papilla inspections and tonometer-based IOP measurements. Recently, with advancements in computer vision AI models, such as VGG16 or Vision Transformers (ViT), AI-automatized glaucoma detection and optic cup segmentation based on retinal fundus images or OCT recently exhibited significant performance in aiding conventional diagnosis with high performance. However, current AI-driven glaucoma detection approaches still have significant room for improvement in terms of reliability, excessive parameter usage, possibility of spurious correlation within detection, and limitations in applications to intervention analysis or clinical simulations. Thus, this research introduced a novel causal representation driven glaucoma detection model: LightHCG, an extremely lightweight Convolutional VAE-based latent glaucoma representation model that can consider the true causality among glaucoma-related physical factors within the optic nerve region. Using HSIC-based latent space disentanglement and Graph Autoencoder based unsupervised causal representation learning, LightHCG not only exhibits higher performance in classifying glaucoma with 93~99% less weights, but also enhances the possibility of AI-driven intervention analysis, compared to existing advanced vision models such as InceptionV3, MobileNetV2 or VGG16. --- ### Agentic AI for Clustering, Relationship Discovery, and Semantic Trading in Prediction Markets Authors: Agostino Capponi, Alfio Gliozzo, Brian Zhu Published: 2025-12-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.02436v3 Prediction markets allow users to trade on outcomes of real-world events, but are prone to fragmentation with overlapping questions, implicit equivalences, and hidden contradictions across markets. We present an agentic AI (AAI) pipeline that autonomously recovers cross-market structure from contract text before prices enter the analysis. The workflow first clusters markets into coherent topical groups using natural-language understanding over contract text and metadata, and then identifies contracts within each cluster, but from different event markets, that exhibit strong dependence or leader--follower relationships. We evaluate this system, along with a natural language inference (NLI) benchmark, on a large prediction market dataset from early 2026. Using resolved outcomes to evaluate identified relations, we find that AAI-identified relations are 62.8\% consistent with exchange-recorded settlements, whereas the NLI benchmark only achieves 40.6\% accuracy. Within clusters, the AAI output is sparse and also remarkably compatible as a signed graph with a frustration rate of 0.324\%. As an application, we show how discovered relations inform semantics-based trading strategies on prediction markets. One such strategy yields 14.12\% net ROI after fees in a two-month period in 2026. Overall, we demonstrate the potential for agentic AI as a structural discovery layer for prediction markets. --- ### Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filtering Authors: Zhongjian Qiao, Rui Yang, Jiafei Lyu, Chenjia Bai, Xiu Li, Siyang Gao, Shuang Qiu Published: 2025-12-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.02435v4 Cross-domain offline reinforcement learning (RL) aims to train a well-performing agent in the target environment, leveraging both a limited target domain dataset and a source domain dataset with (possibly) sufficient data coverage. Due to the underlying dynamics misalignment between source and target domains, naively merging the two datasets may incur inferior performance. Recent advances address this issue by selectively leveraging source domain samples whose dynamics align well with the target domain. However, our work demonstrates that dynamics alignment alone is insufficient, by examining the limitations of prior frameworks and deriving a new target domain sub-optimality bound for the policy learned on the source domain. More importantly, our theory underscores an additional need for \textit{value alignment}, i.e., selecting high-quality, high-value samples from the source domain, a critical dimension overlooked by existing works. Motivated by such theoretical insight, we propose \textbf{\underline{D}}ynamics- and \textbf{\underline{V}}alue-aligned \textbf{\underline{D}}ata \textbf{\underline{F}}iltering (DVDF) method, a novel unified cross-domain RL framework that selectively incorporates source domain samples exhibiting strong alignment in \textit{both dynamics and values}. We empirically study a range of dynamics shift scenarios, including kinematic and morphology shifts, and evaluate DVDF on various tasks and datasets, even in the challenging setting where the target domain dataset contains an extremely limited amount of data. Extensive experiments demonstrate that DVDF consistently outperforms strong baselines with significant improvements. --- ### WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning Authors: Woongyeong Yeo, Kangsan Kim, Jaehong Yoon, Sung Ju Hwang Published: 2025-12-02 Categories: cs.CV, cs.AI, cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2512.02425v2 Recent advances in video large language models have demonstrated strong capabilities in understanding short clips. However, scaling them to hours- or days-long videos remains highly challenging due to limited context capacity and the loss of critical visual details during abstraction. Existing memory-augmented methods mitigate this by leveraging textual summaries of video segments, yet they heavily rely on text and fail to utilize visual evidence when reasoning over complex scenes. Moreover, retrieving from fixed temporal scales further limits their flexibility in capturing events that span variable durations. To address this, we introduce WorldMM, a novel multimodal memory agent that constructs and retrieves from multiple complementary memories, encompassing both textual and visual representations. WorldMM comprises three types of memory: episodic memory indexes factual events across multiple temporal scales, semantic memory continuously updates high-level conceptual knowledge, and visual memory preserves detailed information about scenes. During inference, an adaptive retrieval agent iteratively selects the most relevant memory source and leverages multiple temporal granularities based on the query, continuing until it determines that sufficient information has been gathered. WorldMM significantly outperforms existing baselines across five long video question-answering benchmarks, achieving an average 8.4% performance gain over previous state-of-the-art methods, showing its effectiveness on long video reasoning. --- ### GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning Authors: Haolong Yan, Yeqing Shen, Xin Huang, Jia Wang, Kaijun Tan, Zhixuan Liang, Hongxin Li, Zheng Ge, Osamu Yoshie, Si Li, Xiangyu Zhang, Daxin Jiang Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02423v1 With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC software and mobile Apps, are often complex and proprietary, making it difficult to obtain the comprehensive environment information needed for agent training and evaluation. This limitation hinders systematic investigation and benchmarking of agent navigation capabilities. To address this limitation, we introduce GUI Exploration Lab, a simulation environment engine for GUI agent navigation research that enables flexible definition and composition of screens, icons, and navigation graphs, while providing full access to environment information for comprehensive agent training and evaluation. Through extensive experiments, we find that supervised fine-tuning enables effective memorization of fundamental knowledge, serving as a crucial foundation for subsequent training. Building on this, single-turn reinforcement learning further enhances generalization to unseen scenarios. Finally, multi-turn reinforcement learning encourages the development of exploration strategies through interactive trial and error, leading to further improvements in screen navigation performance. We validate our methods on both static and interactive benchmarks, demonstrating that our findings generalize effectively to real-world scenarios. These findings demonstrate the advantages of reinforcement learning approaches in GUI navigation and offer practical guidance for building more capable and generalizable GUI agents. --- ### Quantum feature encoding optimization Authors: Tommaso Fioravanti, Brian Quanz, Gabriele Agliardi, Edgar Andres Ruiz Guzman, Ginés Carrascal, Jae-Eun Park Published: 2025-12-02 Categories: quant-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.02422v1 Quantum Machine Learning (QML) holds the promise of enhancing machine learning modeling in terms of both complexity and accuracy. A key challenge in this domain is the encoding of input data, which plays a pivotal role in determining the performance of QML models. In this work, we tackle a largely unaddressed aspect of encoding that is unique to QML modeling -- rather than adjusting the ansatz used for encoding, we consider adjusting how data is conveyed to the ansatz. We specifically implement QML pipelines that leverage classical data manipulation (i.e., ordering, selecting, and weighting features) as a preprocessing step, and evaluate if these aspects of encoding can have a significant impact on QML model performance, and if they can be effectively optimized to improve performance. Our experimental results, applied across a wide variety of data sets, ansatz, and circuit sizes, with a representative QML approach, demonstrate that by optimizing how features are encoded in an ansatz we can substantially and consistently improve the performance of QML models, making a compelling case for integrating these techniques in future QML applications. Finally we demonstrate the practical feasibility of this approach by running it using real quantum hardware with 100 qubit circuits and successfully achieving improved QML modeling performance in this case as well. --- ### Generalizing Vision-Language Models with Dedicated Prompt Guidance Authors: Xinyao Li, Yinjie Min, Hongbo Chen, Zhekai Du, Fengling Li, Jingjing Li Published: 2025-12-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.02421v2 Fine-tuning large pretrained vision-language models (VLMs) has emerged as a prevalent paradigm for downstream adaptation, yet it faces a critical trade-off between domain specificity and domain generalization (DG) ability. Current methods typically fine-tune a universal model on the entire dataset, which potentially compromises the ability to generalize to unseen domains. To fill this gap, we provide a theoretical understanding of the generalization ability for VLM fine-tuning, which reveals that training multiple parameter-efficient expert models on partitioned source domains leads to better generalization than fine-tuning a universal model. Inspired by this finding, we propose a two-step domain-expert-Guided DG (GuiDG) framework. GuiDG first employs prompt tuning to obtain source domain experts, then introduces a Cross-Modal Attention module to guide the fine-tuning of the vision encoder via adaptive expert integration. To better evaluate few-shot DG, we construct ImageNet-DG from ImageNet and its variants. Extensive experiments on standard DG benchmarks and ImageNet-DG demonstrate that GuiDG improves upon state-of-the-art fine-tuning methods while maintaining efficiency. --- ### The brain-AI convergence: Predictive and generative world models for general-purpose computation Authors: Shogo Ohmae, Keiko Ohmae Published: 2025-12-02 Categories: q-bio.NC, cs.AI, cs.CL, cs.NE arXiv: https://arxiv.org/abs/2512.02419v1 Recent advances in general-purpose AI systems with attention-based transformers offer a potential window into how the neocortex and cerebellum, despite their relatively uniform circuit architectures, give rise to diverse functions and, ultimately, to human intelligence. This Perspective provides a cross-domain comparison between the brain and AI that goes beyond the traditional focus on visual processing, adopting the emerging perspecive of world-model-based computation. Here, we identify shared computational mechanisms in the attention-based neocortex and the non-attentional cerebellum: both predict future world events from past inputs and construct internal world models through prediction-error learning. These predictive world models are repurposed for seemingly distinct functions -- understanding in sensory processing and generation in motor processing -- enabling the brain to achieve multi-domain capabilities and human-like adaptive intelligence. Notably, attention-based AI has independently converged on a similar learning paradigm and world-model-based computation. We conclude that these shared mechanisms in both biological and artificial systems constitute a core computational foundation for realizing diverse functions including high-level intelligence, despite their relatively uniform circuit structures. Our theoretical insights bridge neuroscience and AI, advancing our understanding of the computational essence of intelligence. --- ### Leveraging Large Language Models to Bridge Cross-Domain Transparency in Stablecoins Authors: Yuexin Xiang, Yuchen Lei, Yuanzhe Zhang, Qin Wang, Tsz Hon Yuen, Andreas Deppeler, Jiangshan Yu Published: 2025-12-02 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.02418v3 Stablecoins such as USDT and USDC aspire to peg stability by coupling issuance controls with reserve attestations. In practice, however, transparency remains fragmented across heterogeneous data sources, with key evidence about circulation, reserves, and disclosure dispersed across records that are difficult to connect and interpret jointly. We introduce a large language model (LLM)-based automated framework for bridging cross-domain transparency in stablecoins by aligning issuer disclosures with observable circulation evidence. First, we propose an integrative framework using LLMs to parse documents, extract salient financial indicators, and semantically align reported statements with corresponding market and issuance metrics. Second, we integrate multi-chain issuance records and disclosure documents within a model context protocol (MCP) framework that standardizes LLM access to both quantitative market data and qualitative disclosure narratives. This framework enables unified retrieval and contextual alignment across heterogeneous stablecoin information sources and facilitates consistent analysis. Third, we demonstrate the capability of LLMs to operate across heterogeneous data domains in blockchain analytics, quantifying discrepancies between reported and observed circulation and examining their implications for transparency and price dynamics. Our findings reveal systematic gaps between disclosed and verifiable data, showing that LLM-assisted analysis enhances cross-domain transparency and supports automated, data-driven auditing in decentralized finance (DeFi). ---