# Research Papers — 2025-12 · bundle page 45 of 175 > Full-text markdown of papers #2201–2250 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/45 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/44.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/46.md) ### R-GenIMA: Integrating Neuroimaging and Genetics with Interpretable Multimodal AI for Alzheimer's Disease Progression Authors: Kun Zhao, Siyuan Dai, Yingying Zhang, Guodong Liu, Pengfei Gu, Chenghua Lin, Paul M. Thompson, Alex Leow, Heng Huang, Lifang He, Liang Zhan, Haoteng Tang Published: 2025-12-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.18986v1 Early detection of Alzheimer's disease (AD) requires models capable of integrating macro-scale neuroanatomical alterations with micro-scale genetic susceptibility, yet existing multimodal approaches struggle to align these heterogeneous signals. We introduce R-GenIMA, an interpretable multimodal large language model that couples a novel ROI-wise vision transformer with genetic prompting to jointly model structural MRI and single nucleotide polymorphisms (SNPs) variations. By representing each anatomically parcellated brain region as a visual token and encoding SNP profiles as structured text, the framework enables cross-modal attention that links regional atrophy patterns to underlying genetic factors. Applied to the ADNI cohort, R-GenIMA achieves state-of-the-art performance in four-way classification across normal cognition (NC), subjective memory concerns (SMC), mild cognitive impairment (MCI), and AD. Beyond predictive accuracy, the model yields biologically meaningful explanations by identifying stage-specific brain regions and gene signatures, as well as coherent ROI-Gene association patterns across the disease continuum. Attention-based attribution revealed genes consistently enriched for established GWAS-supported AD risk loci, including APOE, BIN1, CLU, and RBFOX1. Stage-resolved neuroanatomical signatures identified shared vulnerability hubs across disease stages alongside stage-specific patterns: striatal involvement in subjective decline, frontotemporal engagement during prodromal impairment, and consolidated multimodal network disruption in AD. These results demonstrate that interpretable multimodal AI can synthesize imaging and genetics to reveal mechanistic insights, providing a foundation for clinically deployable tools that enable earlier risk stratification and inform precision therapeutic strategies in Alzheimer's disease. --- ### OPBO: Order-Preserving Bayesian Optimization Authors: Wei Peng, Jianchen Hu, Kang Liu, Qiaozhu Zhai Published: 2025-12-22 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2512.18980v1 Bayesian optimization is an effective method for solving expensive black-box optimization problems. Most existing methods use Gaussian processes (GP) as the surrogate model for approximating the black-box objective function, it is well-known that it can fail in high-dimensional space (e.g., dimension over 500). We argue that the reliance of GP on precise numerical fitting is fundamentally ill-suited in high-dimensional space, where it leads to prohibitive computational complexity. In order to address this, we propose a simple order-preserving Bayesian optimization (OPBO) method, where the surrogate model preserves the order, instead of the value, of the black-box objective function. Then we can use a simple but effective OP neural network (NN) to replace GP as the surrogate model. Moreover, instead of searching for the best solution from the acquisition model, we select good-enough solutions in the ordinal set to reduce computational cost. The experimental results show that for high-dimensional (over 500) black-box optimization problems, the proposed OPBO significantly outperforms traditional BO methods based on regression NN and GP. The source code is available at https://github.com/pengwei222/OPBO. --- ### Outlier detection in mixed-attribute data: a semi-supervised approach with fuzzy approximations and relative entropy Authors: Baiyang Chen, Zhong Yuan, Zheng Liu, Dezhong Peng, Yongxiang Li, Chang Liu, Guiduo Duan Published: 2025-12-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18978v1 Outlier detection is a critical task in data mining, aimed at identifying objects that significantly deviate from the norm. Semi-supervised methods improve detection performance by leveraging partially labeled data but typically overlook the uncertainty and heterogeneity of real-world mixed-attribute data. This paper introduces a semi-supervised outlier detection method, namely fuzzy rough sets-based outlier detection (FROD), to effectively handle these challenges. Specifically, we first utilize a small subset of labeled data to construct fuzzy decision systems, through which we introduce the attribute classification accuracy based on fuzzy approximations to evaluate the contribution of attribute sets in outlier detection. Unlabeled data is then used to compute fuzzy relative entropy, which provides a characterization of outliers from the perspective of uncertainty. Finally, we develop the detection algorithm by combining attribute classification accuracy with fuzzy relative entropy. Experimental results on 16 public datasets show that FROD is comparable with or better than leading detection algorithms. All datasets and source codes are accessible at https://github.com/ChenBaiyang/FROD. This manuscript is the accepted author version of a paper published by Elsevier. The final published version is available at https://doi.org/10.1016/j.ijar.2025.109373 --- ### Consistency-guided semi-supervised outlier detection in heterogeneous data using fuzzy rough sets Authors: Baiyang Chen, Zhong Yuan, Dezhong Peng, Xiaoliang Chen, Hongmei Chen Published: 2025-12-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18977v1 Outlier detection aims to find samples that behave differently from the majority of the data. Semi-supervised detection methods can utilize the supervision of partial labels, thus reducing false positive rates. However, most of the current semi-supervised methods focus on numerical data and neglect the heterogeneity of data information. In this paper, we propose a consistency-guided outlier detection algorithm (COD) for heterogeneous data with the fuzzy rough set theory in a semi-supervised manner. First, a few labeled outliers are leveraged to construct label-informed fuzzy similarity relations. Next, the consistency of the fuzzy decision system is introduced to evaluate attributes' contributions to knowledge classification. Subsequently, we define the outlier factor based on the fuzzy similarity class and predict outliers by integrating the classification consistency and the outlier factor. The proposed algorithm is extensively evaluated on 15 freshly proposed datasets. Experimental results demonstrate that COD is better than or comparable with the leading outlier detectors. This manuscript is the accepted author version of a paper published by Elsevier. The final published version is available at https://doi.org/10.1016/j.asoc.2024.112070 --- ### On Conditional Stochastic Interpolation for Generative Nonlinear Sufficient Dimension Reduction Authors: Shuntuo Xu, Zhou Yu, Jian Huang Published: 2025-12-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.18971v1 Identifying low-dimensional sufficient structures in nonlinear sufficient dimension reduction (SDR) has long been a fundamental yet challenging problem. Most existing methods lack theoretical guarantees of exhaustiveness in identifying lower dimensional structures, either at the population level or at the sample level. We tackle this issue by proposing a new method, generative sufficient dimension reduction (GenSDR), which leverages modern generative models. We show that GenSDR is able to fully recover the information contained in the central $σ$-field at both the population and sample levels. In particular, at the sample level, we establish a consistency property for the GenSDR estimator from the perspective of conditional distributions, capitalizing on the distributional learning capabilities of deep generative models. Moreover, by incorporating an ensemble technique, we extend GenSDR to accommodate scenarios with non-Euclidean responses, thereby substantially broadening its applicability. Extensive numerical results demonstrate the outstanding empirical performance of GenSDR and highlight its strong potential for addressing a wide range of complex, real-world tasks. --- ### Self-Attention with State-Object Weighted Combination for Compositional Zero Shot Learning Authors: Cheng-Hong Chang, Pei-Hsuan Tsai Published: 2025-12-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.18969v1 Object recognition has become prevalent across various industries. However, most existing applications are limited to identifying objects alone, without considering their associated states. The ability to recognize both the state and object simultaneously remains less common. One approach to address this is by treating state and object as a single category during training. However, this approach poses challenges in data collection and training since it requires comprehensive data for all possible combinations. Compositional Zero-shot Learning (CZSL) emerges as a viable solution by treating the state and object as distinct categories during training. CZSL facilitates the identification of novel compositions even in the absence of data for every conceivable combination. The current state-of-the-art method, KG-SP, addresses this issue by training distinct classifiers for states and objects, while leveraging a semantic model to evaluate the plausibility of composed compositions. However, KG-SP's accuracy in state and object recognition can be further improved, and it fails to consider the weighting of states and objects during composition. In this study, we propose SASOW, an enhancement of KG-SP that considers the weighting of states and objects while improving composition recognition accuracy. First, we introduce self-attention mechanisms into the classifiers for states and objects, leading to enhanced accuracy in recognizing both. Additionally, we incorporate the weighting of states and objects during composition to generate more reasonable and accurate compositions. Our validation process involves testing SASOW on three established benchmark datasets. Experimental outcomes affirm when compared against OW-CZSL approach, KG-SP, SASOW showcases improvements of 2.1%, 1.7%, and 0.4% in terms of accuracy for unseen compositions across the MIT-States, UT Zappos, and C-GQA datasets, respectively. --- ### Total Normal Curvature Regularization and its Minimization for Surface and Image Smoothing Authors: Tianle Lu, Ke Chen, Yuping Duan Published: 2025-12-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18968v2 We introduce a novel formulation for curvature regularization by penalizing normal curvatures from multiple directions. This total normal curvature regularization is capable of producing solutions with sharp edges and precise isotropic properties. To tackle the resulting high-order nonlinear optimization problem, we reformulate it as the task of finding the steady-state solution of a time-dependent partial differential equation (PDE) system. Time discretization is achieved through operator splitting, where each subproblem at the fractional steps either has a closed-form solution or can be efficiently solved using advanced algorithms. Our method circumvents the need for complex parameter tuning and demonstrates robustness to parameter choices. The efficiency and effectiveness of our approach have been rigorously validated in the context of surface and image smoothing problems. --- ### Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling Authors: Sutashu Tomonaga, Kenji Doya, Noboru Murata Published: 2025-12-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18965v2 Structured State Space Models (SSMs), which are at the heart of the recently popular Mamba architecture, are powerful tools for sequence modeling. However, their theoretical foundation relies on a complex, multistage process of continuous-time modeling and subsequent discretization, which can obscure intuition. We introduce a direct, first-principles framework for constructing discrete-time SSMs that is both flexible and modular. Our approach is based on a novel lag operator, which geometrically derives the discrete-time recurrence by measuring how the system's basis functions undergo what we call a domain expansion from one timestep to the next. The resulting state matrices are computed via a single inner product involving this operator, enabling a modular design space for creating novel SSMs by flexibly combining different basis functions and time-warping schemes. To validate our framework, we demonstrate that a specific instance exactly recovers the recurrence of the influential HiPPO model. Numerical simulations confirm our derivation, providing new theoretical tools for designing flexible and robust sequence models. --- ### DVI: Disentangling Semantic and Visual Identity for Training-Free Personalized Generation Authors: Guandong Li, Yijun Ding Published: 2025-12-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18964v1 Recent tuning-free identity customization methods achieve high facial fidelity but often overlook visual context, such as lighting, skin texture, and environmental tone. This limitation leads to ``Semantic-Visual Dissonance,'' where accurate facial geometry clashes with the input's unique atmosphere, causing an unnatural ``sticker-like'' effect. We propose **DVI (Disentangled Visual-Identity)**, a zero-shot framework that orthogonally disentangles identity into fine-grained semantic and coarse-grained visual streams. Unlike methods relying solely on semantic vectors, DVI exploits the inherent statistical properties of the VAE latent space, utilizing mean and variance as lightweight descriptors for global visual atmosphere. We introduce a **Parameter-Free Feature Modulation** mechanism that adaptively modulates semantic embeddings with these visual statistics, effectively injecting the reference's ``visual soul'' without training. Furthermore, a **Dynamic Temporal Granularity Scheduler** aligns with the diffusion process, prioritizing visual atmosphere in early denoising stages while refining semantic details later. Extensive experiments demonstrate that DVI significantly enhances visual consistency and atmospheric fidelity without parameter fine-tuning, maintaining robust identity preservation and outperforming state-of-the-art methods in IBench evaluations. --- ### Online Robust Reinforcement Learning with General Function Approximation Authors: Debamita Ghosh, George K. Atia, Yue Wang Published: 2025-12-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18957v3 In many real-world settings, reinforcement learning systems suffer performance degradation when the environment encountered at deployment differs from that observed during training. Distributionally robust reinforcement learning (DR-RL) mitigates this issue by seeking policies that maximize performance under the most adverse transition dynamics within a prescribed uncertainty set. Most existing DR-RL approaches, however, rely on strong data availability assumptions, such as access to a generative model or large offline datasets, and are largely restricted to tabular settings. In this work, we propose a fully online DR-RL algorithm with general function approximation that learns robust policies solely through interaction, without requiring prior knowledge or pre-collected data. Our approach is based on a dual-driven fitted robust Bellman procedure that simultaneously estimates the value function and the corresponding worst-case backup operator. We establish regret guarantees for online DR-RL characterized by an intrinsic complexity notion, the robust Bellman-Eluder dimension, covering a broad class of phi-divergence uncertainty sets. The resulting regret bounds are sublinear, do not scale with the size of the state or action spaces, and specialize to tight rates in structured problem classes, demonstrating the practicality and scalability of our framework. --- ### Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection Authors: Yizhi Wang, Linan Yue, Min-Ling Zhang Published: 2025-12-22 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.18956v2 Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks through long Chain-of-Thought (CoT) reasoning. Extending these successes to multimodal reasoning remains challenging due to the increased complexity of integrating diverse input modalities and the scarcity of high-quality long CoT training data. Existing multimodal datasets and CoT synthesis methods still suffer from limited reasoning depth, modality conversion errors, and rigid generation pipelines, hindering model performance and stability. To this end, in this paper, we propose SynSelect, a novel three-stage Synthesis-Selection framework for generating high-quality long CoT data tailored to multimodal reasoning tasks. Specifically, SynSelect first leverages multiple heterogeneous multimodal LRMs to produce diverse candidate CoTs, and then applies both instance and batch level selection to filter high-quality CoTs that can effectively enhance the model's reasoning capabilities. Extensive experiments on multiple multimodal benchmarks demonstrate that models supervised fine-tuned on SynSelect-generated data significantly outperform baselines and achieve further improvements after reinforcement learning post-training. Our results validate SynSelect as an effective approach for advancing multimodal LRMs reasoning capabilities. --- ### VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion Authors: Zaidao Han, Risa Higashita, Jiang Liu Published: 2025-12-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18954v6 Camera-based 3D Semantic Scene Completion (SSC) is a critical task for autonomous driving and robotic scene understanding. It aims to infer a complete 3D volumetric representation of both semantics and geometry from a single image. Existing methods typically focus on end-to-end 2D-to-3D feature lifting and voxel completion. However, they often overlook the interference between high-confidence visible-region perception and low-confidence occluded-region reasoning caused by single-image input, which can lead to feature dilution and error propagation. To address these challenges, we introduce an offline Visible Region Label Extraction (VRLE) strategy that explicitly separates and extracts voxel-level supervision for visible regions from dense 3D ground truth. This strategy purifies the supervisory space for two complementary sub-tasks: visible-region perception and occluded-region reasoning. Building on this idea, we propose the Visible-Occluded Interactive Completion Network (VOIC), a novel dual-decoder framework that explicitly decouples SSC into visible-region semantic perception and occluded-region scene completion. VOIC first constructs a base 3D voxel representation by fusing image features with depth-derived occupancy. The visible decoder focuses on generating high-fidelity geometric and semantic priors, while the occlusion decoder leverages these priors together with cross-modal interaction to perform coherent global scene reasoning. Extensive experiments on the SemanticKITTI and SSCBench-KITTI360 benchmarks demonstrate that VOIC outperforms existing monocular SSC methods in both geometric completion and semantic segmentation accuracy, achieving state-of-the-art performance. --- ### Symmetry Matters: Auditing and Symmetrizing 3D Generative Models Authors: Nicolas Caytuiro, Ivan Sipiran Published: 2025-12-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18953v3 Symmetry is a strong prior present in many object categories, yet standard benchmarks for 3D generative models rarely report whether this prior is preserved. We study symmetry preservation in unconditional point cloud generation. We first audit the symmetry of generated shapes by several 3D generative models and compute a normalized symmetry score based on the Chamfer Distance (CD). We show that although current 3D generative models achieve competitive results under standard evaluation, they reveal a persistent symmetry gap when a symmetry-aware evaluation protocol is applied. To test whether this gap is merely inherited from the training data, we evaluate these models over a mirrored-objects dataset derived from ShapeNet and analyze symmetry dynamics during training. Mechanism-inspired diagnostic tests were conducted at the sampling and latent-representation levels to further show that reflection symmetry is not reliably encoded in the learned generative process. Finally, to address this gap, we propose a data-centric symmetry-based intervention: training generative models on a half-objects dataset and reconstructing full objects by reflection during sampling. Across multiple backbones, this intervention substantially improves geometric consistency and visual plausibility while remaining competitive under standard metrics. These findings suggest that symmetry-aware evaluation is needed alongside standard benchmarks, and future 3D generative models should incorporate this prior explicitly, either during training or sampling. --- ### Benchmarking Attribute Discrimination in Infant-Scale Vision-Language Models Authors: Patrick Batsell, Satoshi Tsutsui, Bihan Wen Published: 2025-12-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18951v3 Infants learn not only object categories but also fine-grained visual attributes such as color, size, and texture from limited experience. Prior infant-scale vision--language models have mainly been evaluated on object recognition, leaving open whether they support within-class attribute discrimination. We introduce a controlled benchmark that varies color, size, and texture across 67 everyday object classes using synthetic rendering to decouple attribute values from object identity. We evaluate infant-trained models (CVCL and an infant-trained DINO baseline) against web-scale and ImageNet models (CLIP, SigLIP, ResNeXt) under two complementary settings: an image-only prototype test and a text--vision test with attribute--object prompts. We find a dissociation between visual and linguistic attribute information: infant-trained models form strong visual representations for size and discriminate texture comparably to other models, but perform poorly on visual color discrimination, and in the text--vision setting they struggle to ground color and show only modest size grounding. In contrast, web-trained vision--language models strongly ground color from text while exhibiting weaker visual size discrimination. --- ### Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement Authors: Saman Forouzandeh, Wei Peng, Parham Moradi, Xinghuo Yu, Mahdi Jalili Published: 2025-12-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.18950v1 We present MACLA, a framework that decouples reasoning from learning by maintaining a frozen large language model while performing all adaptation in an external hierarchical procedural memory. MACLA extracts reusable procedures from trajectories, tracks reliability via Bayesian posteriors, selects actions through expected-utility scoring, and refines procedures by contrasting successes and failures. Across four benchmarks (ALFWorld, WebShop, TravelPlanner, InterCodeSQL), MACLA achieves 78.1 percent average performance, outperforming all baselines. On ALFWorld unseen tasks, MACLA reaches 90.3 percent with 3.1 percent positive generalization. The system constructs memory in 56 seconds, 2800 times faster than the state-of-the-art LLM parameter-training baseline, compressing 2851 trajectories into 187 procedures. Experimental results demonstrate that structured external memory with Bayesian selection and contrastive refinement enables sample-efficient, interpretable, and continually improving agents without LLM parameter updates. --- ### Clustering-based Transfer Learning for Dynamic Multimodal MultiObjective Evolutionary Algorithm Authors: Li Yan, Bolun Liu, Chao Li, Jing Liang, Kunjie Yu, Caitong Yue, Xuzhao Chai, Boyang Qu Published: 2025-12-22 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2512.18947v1 Dynamic multimodal multiobjective optimization presents the dual challenge of simultaneously tracking multiple equivalent pareto optimal sets and maintaining population diversity in time-varying environments. However, existing dynamic multiobjective evolutionary algorithms often neglect solution modality, whereas static multimodal multiobjective evolutionary algorithms lack adaptability to dynamic changes. To address above challenge, this paper makes two primary contributions. First, we introduce a new benchmark suite of dynamic multimodal multiobjective test functions constructed by fusing the properties of both dynamic and multimodal optimization to establish a rigorous evaluation platform. Second, we propose a novel algorithm centered on a Clustering-based Autoencoder prediction dynamic response mechanism, which utilizes an autoencoder model to process matched clusters to generate a highly diverse initial population. Furthermore, to balance the algorithm's convergence and diversity, we integrate an adaptive niching strategy into the static optimizer. Empirical analysis on 12 instances of dynamic multimodal multiobjective test functions reveals that, compared with several state-of-the-art dynamic multiobjective evolutionary algorithms and multimodal multiobjective evolutionary algorithms, our algorithm not only preserves population diversity more effectively in the decision space but also achieves superior convergence in the objective space. --- ### FASTRIC: Prompt Specification Language for Verifiable LLM Interactions Authors: Wen-Long Jin Published: 2025-12-22 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2512.18940v1 Large Language Models (LLMs) execute complex multi-turn interaction protocols but lack formal specifications to verify execution against designer intent. We introduce FASTRIC, a Prompt Specification Language that makes implicit Finite State Machines (FSMs) explicit in natural language prompts, enabling conformance verification through execution trace analysis. The LLM serves as intelligent execution agent: interpreting designer-encoded FSMs to execute specified behavioral roles. Unlike symbolic specification languages requiring parsers and compilers, FASTRIC leverages LLMs as unified infrastructure-simultaneously parser, interpreter, runtime environment, and development assistant. FASTRIC guides designers to articulate seven FSM elements (Final States, Agents, States, Triggers, Roles, Initial State, Constraints) structuring multi-turn interactions. Specification formality-ranging from implicit descriptions that frontier models infer to explicit step-by-step instructions for weaker models-serves as a design parameter. We introduce procedural conformance as verification metric measuring execution adherence to FSM specifications. Testing a 3-state kindergarten tutoring FSM across four formality levels and three model scales (14.7B, 685B, 1T+ parameters) reveals optimal specification formality is a function of model capacity. DeepSeek-V3.2 (685B) achieves perfect conformance (1.00) at L2-L4; ChatGPT-5 (~1T) peaks at L3 (0.90) before collapsing at L4 (0.39); Phi4 (14.7B) shows no stable optimum with high variance (SD=0.16-0.36). These findings reveal model-specific formality ranges-"Goldilocks zones"-where specifications provide sufficient structure without over-constraint, establishing Prompt Specification Engineering for creating verifiable interaction protocols, transforming multi-turn interaction design from heuristic art to systematic engineering with measurable procedural guarantees. --- ### When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models Authors: Michael S. Zhang, Rishi A. Ruia, Arnav Kewalram, Saathvik Dharmapuram, Utkarsh Sharma, Kevin Zhu Published: 2025-12-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.18934v2 Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency. We systematically investigate the interplay between quantization precision (FP16, INT8, INT4) and replay buffer strategies in large language models, revealing unexpected dynamics. While FP16 achieves superior initial task performance (74.44% on NLU), we observe a striking inversion on subsequent tasks: quantized models outperform FP16 by 8-15% on final task forward accuracy, with INT4 achieving nearly double FP16's performance on Code generation (40% vs 20%). Critically, even minimal replay buffers (0.1%) dramatically improve retention - increasing NLU retention after Math training from 45% to 65% across all precision levels - with INT8 consistently achieving the optimal balance between learning plasticity and knowledge retention. We hypothesize that quantization-induced noise acts as implicit regularization, preventing the overfitting to new task gradients that plagues high-precision models. These findings challenge the conventional wisdom that higher precision is always preferable, suggesting instead that INT8 quantization offers both computational efficiency and superior continual learning dynamics. Our results provide practical guidelines for deploying compressed models in continual learning scenarios: small replay buffers (1-2%) suffice for NLU tasks, while Math and Code benefit from moderate buffers (5-10%), with quantized models requiring less replay than FP16 to achieve comparable retention. Code is available at https://github.com/Festyve/LessIsMore. --- ### When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models Authors: Michael S. Zhang, Rishi A. Ruia, Arnav Kewalram, Saathvik Dharmapuram, Utkarsh Sharma, Kevin Zhu Published: 2025-12-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.18934v1 Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency. We systematically investigate the interplay between quantization precision (FP16, INT8, INT4) and replay buffer strategies in large language models, revealing unexpected dynamics. While FP16 achieves superior initial task performance (74.44% on NLU), we observe a striking inversion on subsequent tasks: quantized models outperform FP16 by 8-15% on final task forward accuracy, with INT4 achieving nearly double FP16's performance on Code generation (40% vs 20%). Critically, even minimal replay buffers (0.1%) dramatically improve retention - increasing NLU retention after Math training from 45% to 65% across all precision levels - with INT8 consistently achieving the optimal balance between learning plasticity and knowledge retention. We hypothesize that quantization-induced noise acts as implicit regularization, preventing the overfitting to new task gradients that plagues high-precision models. These findings challenge the conventional wisdom that higher precision is always preferable, suggesting instead that INT8 quantization offers both computational efficiency and superior continual learning dynamics. Our results provide practical guidelines for deploying compressed models in continual learning scenarios: small replay buffers (1-2%) suffice for NLU tasks, while Math and Code benefit from moderate buffers (5-10%), with quantized models requiring less replay than FP16 to achieve comparable retention. Code is available at https://github.com/Festyve/LessIsMore. --- ### Point What You Mean: Visually Grounded Instruction Policy Authors: Hang Yu, Juntu Zhao, Yufeng Liu, Kaiyu Li, Cheng Ma, Di Zhang, Yingdong Hu, Guang Chen, Junyuan Xie, Junliang Guo, Junqiao Zhao, Yang Gao Published: 2025-12-22 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.18933v2 Vision-Language-Action (VLA) models align vision and language with embodied control, but their object referring ability remains limited when relying solely on text prompt, especially in cluttered or out-of-distribution (OOD) scenes. In this study, we introduce the Point-VLA, a plug-and-play policy that augments language instructions with explicit visual cues (e.g., bounding boxes) to resolve referential ambiguity and enable precise object-level grounding. To efficiently scale visually grounded datasets, we further develop an automatic data annotation pipeline requiring minimal human effort. We evaluate Point-VLA on diverse real-world referring tasks and observe consistently stronger performance than text-only instruction VLAs, particularly in cluttered or unseen-object scenarios, with robust generalization. These results demonstrate that Point-VLA effectively resolves object referring ambiguity through pixel-level visual grounding, achieving more generalizable embodied control. --- ### Point What You Mean: Visually Grounded Instruction Policy Authors: Hang Yu, Juntu Zhao, Yufeng Liu, Kaiyu Li, Cheng Ma, Di Zhang, Yingdong Hu, Guang Chen, Junyuan Xie, Junliang Guo, Junqiao Zhao, Yang Gao Published: 2025-12-22 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.18933v1 Vision-Language-Action (VLA) models align vision and language with embodied control, but their object referring ability remains limited when relying solely on text prompt, especially in cluttered or out-of-distribution (OOD) scenes. In this study, we introduce the Point-VLA, a plug-and-play policy that augments language instructions with explicit visual cues (e.g., bounding boxes) to resolve referential ambiguity and enable precise object-level grounding. To efficiently scale visually grounded datasets, we further develop an automatic data annotation pipeline requiring minimal human effort. We evaluate Point-VLA on diverse real-world referring tasks and observe consistently stronger performance than text-only instruction VLAs, particularly in cluttered or unseen-object scenarios, with robust generalization. These results demonstrate that Point-VLA effectively resolves object referring ambiguity through pixel-level visual grounding, achieving more generalizable embodied control. --- ### DPSR: Differentially Private Sparse Reconstruction via Multi-Stage Denoising for Recommender Systems Authors: Sarwan Ali Published: 2025-12-22 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2512.18932v1 Differential privacy (DP) has emerged as the gold standard for protecting user data in recommender systems, but existing privacy-preserving mechanisms face a fundamental challenge: the privacy-utility tradeoff inevitably degrades recommendation quality as privacy budgets tighten. We introduce DPSR (Differentially Private Sparse Reconstruction), a novel three-stage denoising framework that fundamentally addresses this limitation by exploiting the inherent structure of rating matrices -- sparsity, low-rank properties, and collaborative patterns. DPSR consists of three synergistic stages: (1) \textit{information-theoretic noise calibration} that adaptively reduces noise for high-information ratings, (2) \textit{collaborative filtering-based denoising} that leverages item-item similarities to remove privacy noise, and (3) \textit{low-rank matrix completion} that exploits latent structure for signal recovery. Critically, all denoising operations occur \textit{after} noise injection, preserving differential privacy through the post-processing immunity theorem while removing both privacy-induced and inherent data noise. Through extensive experiments on synthetic datasets with controlled ground truth, we demonstrate that DPSR achieves 5.57\% to 9.23\% RMSE improvement over state-of-the-art Laplace and Gaussian mechanisms across privacy budgets ranging from $\varepsilon=0.1$ to $\varepsilon=10.0$ (all improvements statistically significant with $p < 0.05$, most $p < 0.001$). Remarkably, at $\varepsilon=1.0$, DPSR achieves RMSE of 0.9823, \textit{outperforming even the non-private baseline} (1.0983), demonstrating that our denoising pipeline acts as an effective regularizer that removes data noise in addition to privacy noise. --- ### LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer Authors: Raina Panda, Daniel Fein, Arpita Singhal, Mark Fiore, Maneesh Agrawala, Matyas Bohacek Published: 2025-12-22 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2512.18930v1 Artistic style transfer in generative models remains a significant challenge, as existing methods often introduce style only via model fine-tuning, additional adapters, or prompt engineering, all of which can be computationally expensive and may still entangle style with subject matter. In this paper, we introduce a training- and inference-light, interpretable method for representing and transferring artistic style. Our approach leverages an art-specific Sparse Autoencoder (SAE) on top of latent embeddings of generative image models. Trained on artistic data, our SAE learns an emergent, largely disentangled set of stylistic and compositional concepts, corresponding to style-related elements pertaining brushwork, texture, and color palette, as well as semantic and structural concepts. We call it LouvreSAE and use it to construct style profiles: compact, decomposable steering vectors that enable style transfer without any model updates or optimization. Unlike prior concept-based style transfer methods, our method requires no fine-tuning, no LoRA training, and no additional inference passes, enabling direct steering of artistic styles from only a few reference images. We validate our method on ArtBench10, achieving or surpassing existing methods on style evaluations (VGG Style Loss and CLIP Score Style) while being 1.7-20x faster and, critically, interpretable. --- ### The Ensemble Schr{ö}dinger Bridge filter for Nonlinear Data Assimilation Authors: Hui Sun Published: 2025-12-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18928v4 This work introduces a novel nonlinear optimal filtering method, termed the Ensemble Schr{ö}dinger Bridge nonlinear filter. The proposed filter combines the standard prediction step with a diffusion-generative-modeling-based analysis step, thereby completing one full filtering update. The resulting approach introduces no structural model error, and is derivative-free, training-free, and highly parallelizable. Numerical experiments demonstrate that the proposed algorithm performs effectively for highly nonlinear dynamics and nonlinear observation processes, including chaotic systems with dimension up to 40 and beyond. The results also show that the method outperforms classical approaches such as the ensemble Kalman filter and particle filter across a range of tests with varying degrees of nonlinearity. Future work will focus on extending the proposed method to practical meteorological applications and developing a rigorous convergence theory. --- ### The Ensemble Schr{ö}dinger Bridge filter for Nonlinear Data Assimilation Authors: Feng Bao, Hui Sun Published: 2025-12-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18928v1 This work puts forward a novel nonlinear optimal filter namely the Ensemble Schr{ö}dinger Bridge nonlinear filter. The proposed filter finds marriage of the standard prediction procedure and the diffusion generative modeling for the analysis procedure to realize one filtering step. The designed approach finds no structural model error, and it is derivative free, training free and highly parallizable. Experimental results show that the designed algorithm performs well given highly nonlinear dynamics in (mildly) high dimension up to 40 or above under a chaotic environment. It also shows better performance than classical methods such as the ensemble Kalman filter and the Particle filter in numerous tests given different level of nonlinearity. Future work will focus on extending the proposed approach to practical meteorological applications and establishing a rigorous convergence analysis. --- ### Reason to Contrast: A Cascaded Multimodal Retrieval Framework Authors: Xuanming Cui, Hong-You Chen, Hao Yu, Hao Yuan, Zihao Wang, Shlok Kumar Mishra, Hanchao Yu, Yonghuan Yang, Jun Xiao, Ser-Nam Lim, Jianpeng Cheng, Qi Guo et al. Published: 2025-12-21 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.23369v1 Traditional multimodal retrieval systems rely primarily on bi-encoder architectures, where performance is closely tied to embedding dimensionality. Recent work, Think-Then-Embed (TTE), shows that incorporating multimodal reasoning to elicit additional informative tokens before embedding can further improve retrieval. In this paper, we extend this paradigm with TTE-v2, a hybrid multimodal retrieval framework that introduces reasoning-driven performance scaling based on additional input token budget rather than model or embedding size. Our approach augments the initial multimodal retrieval with additional reasoning steps for reranking, enabling more expressive query-candidate interactions at test time. The reranking stage further provides fine-grained supervision for hard negative mining and false negative filtering, creating a feedback loop that effectively strengthens the upstream retriever. This cascaded design delivers substantial test-time improvements based on intermediate reasoning token scaling. Experiments on the MMEB-V2 benchmark demonstrate that TTE-v2-7B achieves a new state-of-the-art accuracy of 75.7%, and that TTE-v2-2B matches or surpasses leading 7B models trained with significantly larger external data. Our results highlight the promise of token-wise scaling as an alternative scaling paradigm for multimodal retrieval. --- ### Elsewise: Authoring Open-ended Interactive Narrative with Possibility Space Visualization Authors: Yi Wang, John Joon Young Chung, Melissa Roemmele, Yuqian Sun, Tiffany Wang, Shm Garanganao Almeda, Brett A. Halperin, Yuwen Lu, Max Kreminski Published: 2025-12-21 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.15295v2 Interactive narrative (IN) authors craft spaces of divergent narrative possibilities for players to explore, with the player's input determining which narrative possibilities they actually experience. Generative AI can enable new forms of IN by improvisationally expanding on pre-authored content in response to open-ended player input. However, this extrapolation risks widening the gap between author-envisioned and player-experienced stories, potentially limiting the strength of plot progression and the communication of the author's narrative intent. To bridge the gap, we introduce Elsewise: an authoring tool for LLM-based INs that implements a novel Bundled Storyline concept to enhance author's perception and understanding of the narrative possibility space, allowing authors to explore similarities and differences between possible playthroughs of their IN in terms of open-ended, user-configurable narrative dimensions. A user study (n=12) shows that our approach improves author anticipation of player-experienced narrative, leading to more effective control and exploration of the narrative possibility spaces. --- ### No Universal Hyperbola: A Formal Disproof of the Epistemic Trade-Off Between Certainty and Scope in Symbolic and Generative AI Authors: Generoso Immediato Published: 2025-12-21 Categories: cs.CY, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2601.08845v2 In direct response to requests for a logico-mathematical test of the conjecture, we formally disprove a recently conjectured artificial intelligence trade-off between epistemic certainty and scope in its published universal hyperbolic product form, as introduced in Philosophy and Technology. Certainty is defined as the worst-case correctness probability over the input space, and scope as the sum of the Kolmogorov complexities of the input and output sets. Using standard facts from coding theory and algorithmic information theory, we show, first, that when the conjecture is instantiated with prefix (self-delimiting, prefix-free) Kolmogorov complexity, it leads to an internal inconsistency, and second, that when it is instantiated with plain Kolmogorov complexity, it is refuted by a constructive counterexample. These results establish a main theorem: contrary to the conjecture's claim, no universal "certainty-scope" hyperbola holds as a general bound under the published definitions. We further show that a subsequent "entropy-based" revision, replacing the Kolmogorov scope with Shannon joint entropy and redefining the epistemic certainty level accordingly, cannot restore universality either. --- ### Emissions and Performance Trade-off Between Small and Large Language Models Authors: Anandita Garg, Uma Gaba, Deepan Muthirayan, Anish Roy Chowdhury Published: 2025-12-21 Categories: cs.CL, cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2601.08844v1 The advent of Large Language Models (LLMs) has raised concerns about their enormous carbon footprint, starting with energy-intensive training and continuing through repeated inference. This study investigates the potential of using fine-tuned Small Language Models (SLMs) as a sustainable alternative for predefined tasks. Here, we present a comparative analysis of the performance-emissions trade-off between LLMs and fine-tuned SLMs across selected tasks under Natural Language Processing, Reasoning and Programming. Our results show that in four out of the six selected tasks, SLMs maintained comparable performances for a significant reduction in carbon emissions during inference. Our findings demonstrate the viability of smaller models in mitigating the environmental impact of resource-heavy LLMs, thus advancing towards sustainable, green AI. --- ### Rubric-Conditioned LLM Grading: Alignment, Uncertainty, and Robustness Authors: Haotian Deng, Chris Farber, Jiyoon Lee, David Tang Published: 2025-12-21 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.08843v1 Automated short-answer grading (ASAG) remains a challenging task due to the linguistic variability of student responses and the need for nuanced, rubric-aligned partial credit. While Large Language Models (LLMs) offer a promising solution, their reliability as automated judges in rubric-based settings requires rigorous assessment. In this paper, we systematically evaluate the performance of LLM-judges for rubric-based short-answer grading. We investigate three key aspects: the alignment of LLM grading with expert judgment across varying rubric complexities, the trade-off between uncertainty and accuracy facilitated by a consensus-based deferral mechanism, and the model's robustness under random input perturbations and adversarial attacks. Using the SciEntsBank benchmark and Qwen 2.5-72B, we find that alignment is strong for binary tasks but degrades with increased rubric granularity. Our "Trust Curve" analysis demonstrates a clear trade-off where filtering low-confidence predictions improves accuracy on the remaining subset. Additionally, robustness experiments reveal that while the model is resilient to prompt injection, it is sensitive to synonym substitutions. Our work provides critical insights into the capabilities and limitations of rubric-conditioned LLM judges, highlighting the importance of uncertainty estimation and robustness testing for reliable deployment. --- ### The Artificial Intelligence Value Chain: A Critical Appraisal. (Spanish Version) Authors: Pompeu Casanovas Published: 2025-12-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.04218v1 The artificial intelligence value chain is one of the main concepts underpinning the European legislation on the subject, especially the Artificial Intelligence Act. It is an economic concept that has become a legal one. i.e., a concept of legal governance, due to its continued use in policy documents and legal texts. This article (i) analyses its significance and function within the framework of the regulatory strategy established by recent EU programs (the Compass for Competitiveness, the Action Plan, Apply AI Strategy, and the Digital Omnibus on AI), (ii) identifies its limitations, and (iii) advances the theoretical construction of value chains that capture intangible dimensions that are not directly monetizable (such as language, culture, and, especially, ethical and legal values) but have a significant impact on the social environment. It also briefly compares three different legal frameworks for the regulation of AI (EU, Commonwealth and USA). It proposes at the end a specific framework for the analysis of the ethical and legal AI value chain to preserve democratic values and foster the digital implementation of the rule of law. --- ### A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM Interaction Authors: Tobias Heimig-Elschner, Changyu Du, Anna Scheuvens, André Borrmann, Jakob Beetz Published: 2025-12-21 Categories: cs.OH, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2601.00809v2 Agentic workflows driven by large language models (LLMs) are increasingly applied to Building Information Modelling (BIM), enabling natural-language retrieval, modification and generation of IFC models. Recent work has begun adopting the emerging Model Context Protocol (MCP) as a uniform tool-calling interface for LLMs, simplifying the agent side of BIM interaction. While MCP standardises how LLMs invoke tools, current BIM-side implementations are still authoring tool-specific and ad hoc, limiting reuse, evaluation, and workflow portability across environments. This paper addresses this gap by introducing a modular reference architecture for MCP servers that enables API-agnostic, isolated and reproducible agentic BIM interactions. From a systematic analysis of recurring capabilities in recent literature, we derive a core set of requirements. These inform a microservice architecture centred on an explicit adapter contract that decouples the MCP interface from specific BIM-APIs. A prototype implementation using IfcOpenShell demonstrates feasibility across common modification and generation tasks. Evaluation across representative scenarios shows that the architecture enables reliable workflows, reduces coupling, and provides a reusable foundation for systematic research. --- ### When in Doubt, Consult: Expert Debate for Sexism Detection via Confidence-Based Routing Authors: Anwar Alajmi, Gabriele Pergola Published: 2025-12-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.23732v3 Online sexism increasingly appears in subtle, context-dependent forms that evade traditional detection methods. Its interpretation often depends on overlapping linguistic, psychological, legal, and cultural dimensions, which produce mixed and sometimes contradictory signals in annotated datasets. These inconsistencies, combined with label scarcity and class imbalance, result in unstable decision boundaries and cause fine-tuned models to overlook subtler, underrepresented forms of harm. To address these challenges, we propose a two-stage framework that unifies (i) targeted training procedures to better regularize supervision to scarce and noisy data with (ii) selective, reasoning-based inference to handle ambiguous or borderline cases. First, we stabilize the training combining class-balanced focal loss, class-aware batching, and post-hoc threshold calibration, strategies for the firs time adapted for this domain to mitigate label imbalance and noisy supervision. Second, we bridge the gap between efficiency and reasoning with a a dynamic routing mechanism that distinguishes between unambiguous instances and complex cases requiring a deliberative process. This reasoning process results in the novel Collaborative Expert Judgment (CEJ) module which prompts multiple personas and consolidates their reasoning through a judge model. Our approach outperforms existing approaches across several public benchmarks, with F1 gains of +4.48% and +1.30% on EDOS Tasks A and B, respectively, and a +2.79% improvement in ICM on EXIST 2025 Task 1.1. --- ### CosineGate: Semantic Dynamic Routing via Cosine Incompatibility in Residual Networks Authors: Yogeswar Reddy Thota Published: 2025-12-21 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.22206v1 Modern deep residual networks perform substantial redundant computation by evaluating all residual blocks for every input, even when identity mappings suffice. We introduce CosineGate, an end-to-end differentiable architecture for dynamic routing in residual networks that uses cosine incompatibility between identity and residual feature representations as a self-supervised skip signal. CosineGate measures semantic redundancy through the Cosine Incompatibility Ratio (CIR), defined as 1 - cos(x, F(x)), and uses Gumbel-Softmax relaxation to enable per-sample, per-block gating during training. A progressive FLOPs regularization term controls average compute usage without destabilizing optimization. On CIFAR-10, CosineGate spans the accuracy-efficiency Pareto frontier: an aggressive configuration achieves 89.9 percent accuracy with 24.1 percent FLOPs savings, a balanced configuration achieves 91.3 percent accuracy with 28.5 percent savings at epoch 160, and a conservative configuration reaches a peak of 93.2 percent accuracy with minimal compute reduction. These results match or exceed ResNet-20 (91.3 percent) while reducing computation, without auxiliary supervision, distillation, or task-specific heuristics. Our results demonstrate that simple geometric measures of feature incompatibility provide a principled and effective signal for dynamic residual routing. --- ### A CNN-Based Malaria Diagnosis from Blood Cell Images with SHAP and LIME Explainability Authors: Md. Ismiel Hossen Abir, Awolad Hossain Published: 2025-12-21 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2512.22205v1 Malaria remains a prevalent health concern in regions with tropical and subtropical climates. The cause of malaria is the Plasmodium parasite, which is transmitted through the bites of infected female Anopheles mosquitoes. Traditional diagnostic methods, such as microscopic blood smear analysis, are low in sensitivity, depend on expert judgment, and require resources that may not be available in remote settings. To overcome these limitations, this study proposes a deep learning-based approach utilizing a custom Convolutional Neural Network (CNN) to automatically classify blood cell images as parasitized or uninfected. The model achieves an accuracy of 96%, with precision and recall scores exceeding 0.95 for both classes. This study also compares the custom CNN with established deep learning architectures, including ResNet50, VGG16, MobileNetV2, and DenseNet121. To enhance model interpretability, Explainable AI techniques such as SHAP, LIME, and Saliency Maps are applied. The proposed system shows how deep learning can provide quick, accurate and understandable malaria diagnosis, especially in areas with limited resources. --- ### TCFormer: A 5M-Parameter Transformer with Density-Guided Aggregation for Weakly-Supervised Crowd Counting Authors: Qiang Guo, Rubo Zhang, Bingbing Zhang, Junjie Liu, Jianqing Liu Published: 2025-12-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.22203v1 Crowd counting typically relies on labor-intensive point-level annotations and computationally intensive backbones, restricting its scalability and deployment in resource-constrained environments. To address these challenges, this paper proposes the TCFormer, a tiny, ultra-lightweight, weakly-supervised transformer-based crowd counting framework with only 5 million parameters that achieves competitive performance. Firstly, a powerful yet efficient vision transformer is adopted as the feature extractor, the global context-aware capabilities of which provides semantic meaningful crowd features with a minimal memory footprint. Secondly, to compensate for the lack of spatial supervision, we design a feature aggregation mechanism termed the Learnable Density-Weighted Averaging module. This module dynamically re-weights local tokens according to predicted density scores, enabling the network to adaptively modulate regional features based on their specific density characteristics without the need for additional annotations. Furthermore, this paper introduces a density-level classification loss, which discretizes crowd density into distinct grades, thereby regularizing the training process and enhancing the model's classification power across varying levels of crowd density. Therefore, although TCformer is trained under a weakly-supervised paradigm utilizing only image-level global counts, the joint optimization of count and density-level losses enables the framework to achieve high estimation accuracy. Extensive experiments on four benchmarks including ShanghaiTech A/B, UCF-QNRF, and NWPU datasets demonstrate that our approach strikes a superior trade-off between parameter efficiency and counting accuracy and can be a good solution for crowd counting tasks in edge devices. --- ### Complex Swin Transformer for Accelerating Enhanced SMWI Reconstruction Authors: Muhammad Usman, Sung-Min Gho Published: 2025-12-21 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2512.22202v1 Susceptibility Map Weighted Imaging (SMWI) is an advanced magnetic resonance imaging technique used to detect nigral hyperintensity in Parkinsons disease. However, full resolution SMWI acquisition is limited by long scan times. Efficient reconstruction methods are therefore required to generate high quality SMWI from reduced k space data while preserving diagnostic relevance. In this work, we propose a complex valued Swin Transformer based network for super resolution reconstruction of multi echo MRI data. The proposed method reconstructs high quality SMWI images from low resolution k space inputs. Experimental results demonstrate that the method achieves a structural similarity index of 0.9116 and a mean squared error of 0.076 when reconstructing SMWI from 256 by 256 k space data, while maintaining critical diagnostic features. This approach enables high quality SMWI reconstruction from reduced k space sampling, leading to shorter scan times without compromising diagnostic detail. The proposed method has the potential to improve the clinical applicability of SMWI for Parkinsons disease and support faster and more efficient neuroimaging workflows. --- ### Multi-Agent LLM Committees for Autonomous Software Beta Testing Authors: Sumanth Bharadwaj Hachalli Karanam, Dhiwahar Adhithya Kennady Published: 2025-12-21 Categories: cs.SE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.21352v1 Manual software beta testing is costly and time-consuming, while single-agent large language model (LLM) approaches suffer from hallucinations and inconsistent behavior. We propose a multi-agent committee framework in which diverse vision-enabled LLMs collaborate through a three-round voting protocol to reach consensus on testing actions. The framework combines model diversity, persona-driven behavioral variation, and visual user interface understanding to systematically explore web applications. Across 84 experimental runs with 9 testing personas and 4 scenarios, multi-agent committees achieve an 89.5 percent overall task success rate. Configurations with 2 to 4 agents reach 91.7 to 100 percent success, compared to 78.0 percent for single-agent baselines, yielding improvements of 13.7 to 22.0 percentage points. At the action level, the system attains a 93.1 percent success rate with a median per-action latency of 0.71 seconds, enabling real-time and continuous integration testing. Vision-enabled agents successfully identify user interface elements, with navigation and reporting achieving 100 percent success and form filling achieving 99.2 percent success. We evaluate the framework on WebShop and OWASP benchmarks, achieving 74.7 percent success on WebShop compared to a 50.1 percent published GPT-3 baseline, and 82.0 percent success on OWASP Juice Shop security testing with coverage of 8 of the 10 OWASP Top 10 vulnerability categories. Across 20 injected regressions, the committee achieves an F1 score of 0.91 for bug detection, compared to 0.78 for single-agent baselines. The open-source implementation enables reproducible research and practical deployment of LLM-based software testing in CI/CD pipelines. --- ### Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models Authors: Zhang Wei, Hanxuan Chen, Peilu Hu, Zhenyuan Wei, Chenwei Liang, Jiayi Gu, Wenqian Weng, Jacqueline Pang, Hao Yan, Li Mei, Shengning Lang, Kuan Lu et al. Published: 2025-12-21 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2512.20677v6 Red-teaming is becoming a central part of large language model (LLM) safety evaluation, yet current practice still relies heavily on expert-written prompts or fixed benchmark suites. This creates a gap between what is easy to test and what deployed models can actually do: failures may be rare, context-sensitive, and distributed across many threat categories. We study automated red-teaming as a constrained adversarial search problem and introduce a learning-driven framework that couples category-aware attack generation with hierarchical vulnerability detection. The method starts from curated safety seeds, expands them through meta-prompt-guided and evolutionary search, and scores the resulting prompt--response pairs with lexical, semantic, and behavioral detectors. Across six threat categories on GPT-OSS-20B, the framework discovers 47 validated vulnerabilities, including 21 high-severity cases and 12 novel attack patterns. Under matched query budgets, it achieves a 3.9$\times$ higher discovery rate than manual expert red-teaming while maintaining 89\% detection accuracy and full category coverage. Ablations show that the gains do not come from more prompts alone: diversity constraints prevent template collapse, coverage constraints prevent category blind spots, and semantic detection recovers failures missed by lexical rules. These results suggest that red-teaming can be made more scalable and reproducible when treated as adaptive search rather than as a static checklist. --- ### Learning to Design City-scale Transit Routes Authors: Bibek Poudel, Weizi Li Published: 2025-12-21 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2512.19767v1 Designing efficient transit route networks is an NP-hard problem with exponentially large solution spaces that traditionally relies on manual planning processes. We present an end-to-end reinforcement learning (RL) framework based on graph attention networks for sequential transit network construction. To address the long-horizon credit assignment challenge, we introduce a two-level reward structure combining incremental topological feedback with simulation-based terminal rewards. We evaluate our approach on a new real-world dataset from Bloomington, Indiana with topologically accurate road networks, census-derived demand, and existing transit routes. Our learned policies substantially outperform existing designs and traditional heuristics across two initialization schemes and two modal-split scenarios. Under high transit adoption with transit center initialization, our approach achieves 25.6% higher service rates, 30.9\% shorter wait times, and 21.0% better bus utilization compared to the real-world network. Under mixed-mode conditions with random initialization, it delivers 68.8% higher route efficiency than demand coverage heuristics and 5.9% lower travel times than shortest path construction. These results demonstrate that end-to-end RL can design transit networks that substantially outperform both human-designed systems and hand-crafted heuristics on realistic city-scale benchmarks. --- ### How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts Authors: Sumin Park, Noseong Park Published: 2025-12-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.19765v1 Finding the optimal configuration of Sparse Mixture-ofExperts (SMoE) that maximizes semantic differentiation among experts is essential for exploiting the full potential of MoE architectures. However, existing SMoE frameworks either heavily rely on hyperparameter tuning or overlook the importance of diversifying semantic roles across experts when adapting the expert pool size. We propose Mixture-of-Experts for Adaptive Semantic Specialization (MASS), a semanticaware MoE framework for adaptive expert expansion and dynamic routing. MASS introduces two key advancements: (i) a gradient-based semantic drift detector that prompts targeted expert expansion when the existing expert pool lacks capacity to capture the full semantic diversity of the data, and (ii) an integration of adaptive routing strategy that dynamically adjusts expert usage based on token-level routing confidence mass. We first demonstrate that MASS reliably converges to the point of optimal balance between cost-performance trade-off with notably improved sematic specialization in a highly controlled synthetic setup. Further empirical results on real-world datasets across language and vision domains show that MASS consistently outperforms a range of strong MoE baselines, demonstrating its domain robustness and enhanced expert specialization. --- ### Beyond the Prompt: An Empirical Study of Cursor Rules Authors: Shaokang Jiang, Daye Nam Published: 2025-12-21 Categories: cs.SE, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2512.18925v3 While Large Language Models (LLMs) have demonstrated remarkable capabilities, research shows that their effectiveness depends not only on explicit prompts but also on the broader context provided. This requirement is especially pronounced in software engineering, where the goals, architecture, and collaborative conventions of an existing project play critical roles in response quality. To support this, many AI coding assistants have introduced ways for developers to author persistent, machine-readable directives that encode a project's unique constraints. Although this practice is growing, the content of these directives remains unstudied. This paper presents a large-scale empirical study to characterize this emerging form of developer-provided context. Through a qualitative analysis of 401 open-source repositories containing cursor rules, we developed a comprehensive taxonomy of project context that developers consider essential, organized into five high-level themes: Conventions, Guidelines, Project Information, LLM Directives, and Examples. Our study also explores how this context varies across different project types and programming languages, offering implications for the next generation of context-aware AI developer tools. --- ### Testing for latent structure via the Wilcoxon--Wigner random matrix of normalized rank statistics Authors: Jonquil Z. Liao, Joshua Cape Published: 2025-12-21 Categories: stat.ME, math.PR, math.ST, stat.ML arXiv: https://arxiv.org/abs/2512.18924v1 This paper considers the problem of testing for latent structure in large symmetric data matrices. The goal here is to develop statistically principled methodology that is flexible in its applicability, computationally efficient, and insensitive to extreme data variation, thereby overcoming limitations facing existing approaches. To do so, we introduce and systematically study certain symmetric matrices, called Wilcoxon--Wigner random matrices, whose entries are normalized rank statistics derived from an underlying independent and identically distributed sample of absolutely continuous random variables. These matrices naturally arise as the matricization of one-sample problems in statistics and conceptually lie at the interface of nonparametrics, multivariate analysis, and data reduction. Among our results, we establish that the leading eigenvalue and corresponding eigenvector of Wilcoxon--Wigner random matrices admit asymptotically Gaussian fluctuations with explicit centering and scaling terms. These asymptotic results enable rigorous parameter-free and distribution-free spectral methodology for addressing two hypothesis testing problems, namely community detection and principal submatrix detection. Numerical examples illustrate the performance of the proposed approach. Throughout, our findings are juxtaposed with existing results based on the spectral properties of independent entry symmetric random matrices in signal-plus-noise data settings. --- ### Concurrent training methods for Kolmogorov-Arnold networks: Disjoint datasets and FPGA implementation Authors: Andrew Polar, Michael Poluektov Published: 2025-12-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18921v5 The present paper introduces concurrency-driven enhancements to the training algorithm for the Kolmogorov-Arnold networks (KANs) that is based on the Newton-Kaczmarz (NK) method. Prior research shows that KANs trained using the NK-based approach outperform classical neural networks (multilayer perceptrons - MLPs) both in terms of accuracy and training time. Up to now, the fundamental limitation of the algorithm has been the sequential computation of the updates - each update depends on the results of the previous step, obstructing parallelisation; even though parallelisation of some parts of the algorithm, such as the evaluation of the basis functions, has already been proposed and tested. However, substantial acceleration is achievable. Three complementary concurrency-driven novel strategies are proposed in the present paper: (i) a pre-training procedure tailored to the NK updates' structure, (ii) training on disjoint subsets of data together with models' merging, and (iii) a division-free customisation of the algorithm for field-programmable gate arrays (FPGAs), which is implemented and tested directly on the device. Computational experiments are used to assess the scalability and to compare the authors' KAN implementation with popular MLP packages. All presented experimental results are fully reproducible, with the complete source codes available online. --- ### Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models Authors: Mohamad Zamini, Diksha Shukla Published: 2025-12-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18910v1 Multimodal Large Language Models (MLLMs) combine visual and textual representations to enable rich reasoning capabilities. However, the high computational cost of processing dense visual tokens remains a major bottleneck. A critical component in this pipeline is the visual projector, which bridges the vision encoder and the language model. Standard designs often employ a simple multi-layer perceptron for direct token mapping, but this approach scales poorly with high-resolution inputs, introducing significant redundancy. We present Delta-LLaVA, a token-efficient projector that employs a low-rank DeltaProjection to align multi-level vision features into a compact subspace before further interaction. On top of this base alignment, lightweight Transformer blocks act as specialization layers, capturing both global and local structure under constrained token budgets. Extensive experiments and ablations demonstrate that this base-then-specialize design yields consistent gains across multiple benchmarks with only 144 tokens, highlighting the importance of token formation prior to scaling interaction capacity. With Delta-LLaVA, inference throughput improves by up to 55%, while end-to-end training accelerates by nearly 4-5x in pretraining and over 1.5x in finetuning, highlighting the dual benefits of our design in both efficiency and scalability. --- ### Multimodal Bayesian Network for Robust Assessment of Casualties in Autonomous Triage Authors: Szymon Rusiecki, Cecilia G. Morales, Kimberly Elenberg, Leonard Weiss, Artur Dubrawski Published: 2025-12-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.18908v2 Mass Casualty Incidents can overwhelm emergency medical systems and resulting delays or errors in the assessment of casualties can lead to preventable deaths. We present a decision support framework that fuses outputs from multiple computer vision models, estimating signs of severe hemorrhage, respiratory distress, physical alertness, or visible trauma, into a Bayesian network constructed entirely from expert-defined rules. Unlike traditional data-driven models, our approach does not require training data, supports inference with incomplete information, and is robust to noisy or uncertain observations. We report performance for two missions involving 11 and 9 casualties, respectively, where our Bayesian network model substantially outperformed vision-only baselines during evaluation of our system in the DARPA Triage Challenge (DTC) field scenarios. The accuracy of physiological assessment improved from 15% to 42% in the first scenario and from 19% to 46% in the second, representing nearly threefold increase in performance. More importantly, overall triage accuracy increased from 14% to 53% in all patients, while the diagnostic coverage of the system expanded from 31% to 95% of the cases requiring assessment. These results demonstrate that expert-knowledge-guided probabilistic reasoning can significantly enhance automated triage systems, offering a promising approach to supporting emergency responders in MCIs. This approach enabled Team Chiron to achieve 4th place out of 11 teams during the 1st physical round of the DTC. --- ### Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations Authors: Shaomu Tan, Ryosuke Mitani, Ritvik Choudhary, Qiyu Wu, Toshiyuki Sekiya, Christof Monz Published: 2025-12-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.18906v1 Over the years, automatic MT metrics have hillclimbed benchmarks and presented strong and sometimes human-level agreement with human ratings. Yet they remain black-box, offering little insight into their decision-making and often failing under real-world out-of-distribution (OOD) inputs. We introduce Remedy-R, a reasoning-driven generative MT metric trained with reinforcement learning from pairwise translation preferences, without requiring error-span annotations or distillation from closed LLMs. Remedy-R produces step-by-step analyses of accuracy, fluency, and completeness, followed by a final score, enabling more interpretable assessments. With only 60K training pairs across two language pairs, Remedy-R remains competitive with top scalar metrics and GPT-4-based judges on WMT22-24 meta-evaluation, generalizes to other languages, and exhibits strong robustness on OOD stress tests. Moreover, Remedy-R models generate self-reflective feedback that can be reused for translation improvement. Building on this finding, we introduce Remedy-R Agent, a simple evaluate-revise pipeline that leverages Remedy-R's evaluation analysis to refine translations. This agent consistently improves translation quality across diverse models, including Qwen2.5, ALMA-R, GPT-4o-mini, and Gemini-2.0-Flash, suggesting that Remedy-R's reasoning captures translation-relevant information and is practically useful. --- ### Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models Authors: Gökdeniz Gülmez Published: 2025-12-21 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.18901v3 We present Gabliteration, a novel neural weight modification technique that advances beyond traditional abliteration methods by implementing adaptive multi-directional projections with regularized layer selection. Our approach addresses the fundamental limitation of existing methods that compromise model quality while attempting to modify specific behavioral patterns. Through dynamic layer optimization, regularized projection matrices, and adaptive scaling mechanisms, we achieve theoretically superior weight modification while minimizing quality degradation in unrelated domains. We validate our method through the gabliterated-v1 model series (0.6B to 4B parameters) available on Hugging Face, demonstrating practical applicability across multiple model scales. --- ### Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMs Authors: Dmitry Demidov, Zaigham Zaheer, Zongyan Han, Omkar Thawakar, Rao Anwer Published: 2025-12-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18897v1 Vocabulary-free fine-grained image recognition aims to distinguish visually similar categories within a meta-class without a fixed, human-defined label set. Existing solutions for this problem are limited by either the usage of a large and rigid list of vocabularies or by the dependency on complex pipelines with fragile heuristics where errors propagate across stages. Meanwhile, the ability of recent large multi-modal models (LMMs) equipped with explicit or implicit reasoning to comprehend visual-language data, decompose problems, retrieve latent knowledge, and self-correct suggests a more principled and effective alternative. Building on these capabilities, we propose FiNDR (Fine-grained Name Discovery via Reasoning), the first reasoning-augmented LMM-based framework for vocabulary-free fine-grained recognition. The system operates in three automated steps: (i) a reasoning-enabled LMM generates descriptive candidate labels for each image; (ii) a vision-language model filters and ranks these candidates to form a coherent class set; and (iii) the verified names instantiate a lightweight multi-modal classifier used at inference time. Extensive experiments on popular fine-grained classification benchmarks demonstrate state-of-the-art performance under the vocabulary-free setting, with a significant relative margin of up to 18.8% over previous approaches. Remarkably, the proposed method surpasses zero-shot baselines that exploit pre-defined ground-truth names, challenging the assumption that human-curated vocabularies define an upper bound. Additionally, we show that carefully curated prompts enable open-source LMMs to match proprietary counterparts. These findings establish reasoning-augmented LMMs as an effective foundation for scalable, fully automated, open-world fine-grained visual recognition. The source code is available on github.com/demidovd98/FiNDR. --- ### Structural Reinforcement Learning for Heterogeneous Agent Macroeconomics Authors: Yucheng Yang, Chiyuan Wang, Andreas Schaab, Benjamin Moll Published: 2025-12-21 Categories: econ.TH, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.18892v1 We present a new approach to formulating and solving heterogeneous agent models with aggregate risk. We replace the cross-sectional distribution with low-dimensional prices as state variables and let agents learn equilibrium price dynamics directly from simulated paths. To do so, we introduce a structural reinforcement learning (SRL) method which treats prices via simulation while exploiting agents' structural knowledge of their own individual dynamics. Our SRL method yields a general and highly efficient global solution method for heterogeneous agent models that sidesteps the Master equation and handles problems traditional methods struggle with, in particular nontrivial market-clearing conditions. We illustrate the approach in the Krusell-Smith model, the Huggett model with aggregate shocks, and a HANK model with a forward-looking Phillips curve, all of which we solve globally within minutes. ---