# Research Papers — 2025-12 · bundle page 120 of 175 > Full-text markdown of papers #5951–6000 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/120 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/119.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/121.md) ### Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations Authors: Yuchi Zhang, Churui Sun, Shiqi Liang, Diyuan Liu, Chao Ji, Wei-Nan Zhang, Ting Liu Published: 2025-12-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.08548v1 Recent end-to-end robotic manipulation research increasingly adopts architectures inspired by large language models to enable robust manipulation. However, a critical challenge arises from severe distribution shifts between robotic action data, primarily due to substantial numerical variations in action commands across diverse robotic platforms and tasks, hindering the effective transfer of pretrained knowledge. To address this limitation, we propose a semantically grounded linguistic representation to normalize actions for efficient pretraining. Unlike conventional discretized action representations that are sensitive to numerical scales, the motion representation specifically disregards numeric scale effects, emphasizing directionality instead. This abstraction mitigates distribution shifts, yielding a more generalizable pretraining representation. Moreover, using the motion representation narrows the feature distance between action tokens and standard vocabulary tokens, mitigating modality gaps. Multi-task experiments on two benchmarks demonstrate that the proposed method significantly improves generalization performance and transferability in robotic manipulation tasks. --- ### An Iteration-Free Fixed-Point Estimator for Diffusion Inversion Authors: Yifei Chen, Kaiyu Song, Yan Pan, Jianxing Yu, Jian Yin, Hanjiang Lai Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08547v1 Diffusion inversion aims to recover the initial noise corresponding to a given image such that this noise can reconstruct the original image through the denoising diffusion process. The key component of diffusion inversion is to minimize errors at each inversion step, thereby mitigating cumulative inaccuracies. Recently, fixed-point iteration has emerged as a widely adopted approach to minimize reconstruction errors at each inversion step. However, it suffers from high computational costs due to its iterative nature and the complexity of hyperparameter selection. To address these issues, we propose an iteration-free fixed-point estimator for diffusion inversion. First, we derive an explicit expression of the fixed point from an ideal inversion step. Unfortunately, it inherently contains an unknown data prediction error. Building upon this, we introduce the error approximation, which uses the calculable error from the previous inversion step to approximate the unknown error at the current inversion step. This yields a calculable, approximate expression for the fixed point, which is an unbiased estimator characterized by low variance, as shown by our theoretical analysis. We evaluate reconstruction performance on two text-image datasets, NOCAPS and MS-COCO. Compared to DDIM inversion and other inversion methods based on the fixed-point iteration, our method achieves consistent and superior performance in reconstruction tasks without additional iterations or training. --- ### Curriculum Guided Massive Multi Agent System Solving For Robust Long Horizon Tasks Authors: Indrajit Kar, Kalathur Chenchu Kishore Kumar Published: 2025-12-09 Categories: cs.CL, cs.AI, cs.CV, cs.MA arXiv: https://arxiv.org/abs/2512.08545v1 Large Language Models and multi-agent systems have shown promise in decomposing complex tasks, yet they struggle with long-horizon reasoning tasks and escalating computation cost. This work introduces a hierarchical multi-agent architecture that distributes reasoning across a 64*64 grid of lightweight agents, supported by a selective oracle. A spatial curriculum progressively expands the operational region of the grid, ensuring that agents master easier central tasks before tackling harder peripheral ones. To improve reliability, the system integrates Negative Log-Likelihood as a measure of confidence, allowing the curriculum to prioritize regions where agents are both accurate and well calibrated. A Thompson Sampling curriculum manager adaptively chooses training zones based on competence and NLL-driven reward signals. We evaluate the approach on a spatially grounded Tower of Hanoi benchmark, which mirrors the long-horizon structure of many robotic manipulation and planning tasks. Results demonstrate improved stability, reduced oracle usage, and stronger long-range reasoning from distributed agent cooperation. --- ### A Novel Wasserstein Quaternion Generative Adversarial Network for Color Image Generation Authors: Zhigang Jia, Duan Wang, Hengkai Wang, Yajun Xie, Meixiang Zhao, Xiaoyu Zhao Published: 2025-12-09 Categories: cs.CV, cs.AI, math.NA arXiv: https://arxiv.org/abs/2512.08542v1 Color image generation has a wide range of applications, but the existing generation models ignore the correlation among color channels, which may lead to chromatic aberration problems. In addition, the data distribution problem of color images has not been systematically elaborated and explained, so that there is still the lack of the theory about measuring different color images datasets. In this paper, we define a new quaternion Wasserstein distance and develop its dual theory. To deal with the quaternion linear programming problem, we derive the strong duality form with helps of quaternion convex set separation theorem and quaternion Farkas lemma. With using quaternion Wasserstein distance, we propose a novel Wasserstein quaternion generative adversarial network. Experiments demonstrate that this novel model surpasses both the (quaternion) generative adversarial networks and the Wasserstein generative adversarial network in terms of generation efficiency and image quality. --- ### Fast-ARDiff: An Entropy-informed Acceleration Framework for Continuous Space Autoregressive Generation Authors: Zhen Zou, Xiaoxiao Ma, Jie Huang, Zichao Yu, Feng Zhao Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08537v1 Autoregressive(AR)-diffusion hybrid paradigms combine AR's structured modeling with diffusion's photorealistic synthesis, yet suffer from high latency due to sequential AR generation and iterative denoising. In this work, we tackle this bottleneck and propose a unified AR-diffusion framework Fast-ARDiff that jointly optimizes both components, accelerating AR speculative decoding while simultaneously facilitating faster diffusion decoding. Specifically: (1) The entropy-informed speculative strategy encourages draft model to produce higher-entropy representations aligned with target model's entropy characteristics, mitigating entropy mismatch and high rejection rates caused by draft overconfidence. (2) For diffusion decoding, rather than treating it as an independent module, we integrate it into the same end-to-end framework using a dynamic scheduler that prioritizes AR optimization to guide the diffusion part in further steps. The diffusion part is optimized through a joint distillation framework combining trajectory and distribution matching, ensuring stable training and high-quality synthesis with extremely few steps. During inference, shallow feature entropy from AR module is used to pre-filter low-entropy drafts, avoiding redundant computation and improving latency. Fast-ARDiff achieves state-of-the-art acceleration across diverse models: on ImageNet 256$\times$256, TransDiff attains 4.3$\times$ lossless speedup, and NextStep-1 achieves 3$\times$ acceleration on text-conditioned generation. Code will be available at https://github.com/aSleepyTree/Fast-ARDiff. --- ### Principles2Plan: LLM-Guided System for Operationalising Ethical Principles into Plans Authors: Tammy Zhong, Yang Song, Maurice Pagnucco Published: 2025-12-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.08536v1 Ethical awareness is critical for robots operating in human environments, yet existing automated planning tools provide little support. Manually specifying ethical rules is labour-intensive and highly context-specific. We present Principles2Plan, an interactive research prototype demonstrating how a human and a Large Language Model (LLM) can collaborate to produce context-sensitive ethical rules and guide automated planning. A domain expert provides the planning domain, problem details, and relevant high-level principles such as beneficence and privacy. The system generates operationalisable ethical rules consistent with these principles, which the user can review, prioritise, and supply to a planner to produce ethically-informed plans. To our knowledge, no prior system supports users in generating principle-grounded rules for classical planning contexts. Principles2Plan showcases the potential of human-LLM collaboration for making ethical automated planning more practical and feasible. --- ### Photo3D: Advancing Photorealistic 3D Generation through Structure-Aligned Detail Enhancement Authors: Xinyue Liang, Zhinyuan Ma, Lingchen Sun, Yanjun Guo, Lei Zhang Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08535v3 Although recent 3D-native generators have made great progress in synthesizing reliable geometry, they still fall short in achieving realistic appearances. A key obstacle lies in the lack of diverse and high-quality real-world 3D assets with rich texture details, since capturing such data is intrinsically difficult due to the diverse scales of scenes, non-rigid motions of objects, and the limited precision of 3D scanners. We introduce Photo3D, a framework for advancing photorealistic 3D generation, which is driven by the image data generated by the GPT-4o-Image model. Considering that the generated images can distort 3D structures due to their lack of multi-view consistency, we design a structure-aligned multi-view synthesis pipeline and construct a detail-enhanced multi-view dataset paired with 3D geometry. Building on it, we present a realistic detail enhancement scheme that leverages perceptual feature adaptation and semantic structure matching to enforce appearance consistency with realistic details while preserving the structural consistency with the 3D-native geometry. Our scheme is general to different 3D-native generators, and we present dedicated training strategies to facilitate the optimization of geometry-texture coupled and decoupled 3D-native generation paradigms. Experiments demonstrate that Photo3D generalizes well across diverse 3D-native generation paradigms and achieves state-of-the-art photorealistic 3D generation performance. --- ### PaintFlow: A Unified Framework for Interactive Oil Paintings Editing and Generation Authors: Zhangli Hu, Ye Chen, Jiajun Yao, Bingbing Ni Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08534v1 Oil painting, as a high-level medium that blends human abstract thinking with artistic expression, poses substantial challenges for digital generation and editing due to its intricate brushstroke dynamics and stylized characteristics. Existing generation and editing techniques are often constrained by the distribution of training data and primarily focus on modifying real photographs. In this work, we introduce a unified multimodal framework for oil painting generation and editing. The proposed system allows users to incorporate reference images for precise semantic control, hand-drawn sketches for spatial structure alignment, and natural language prompts for high-level semantic guidance, while consistently maintaining a unified painting style across all outputs. Our method achieves interactive oil painting creation through three crucial technical advancements. First, we enhance the training stage with spatial alignment and semantic enhancement conditioning strategy, which map masks and sketches into spatial constraints, and encode contextual embedding from reference images and text into feature constraints, enabling object-level semantic alignment. Second, to overcome data scarcity, we propose a self-supervised style transfer pipeline based on Stroke-Based Rendering (SBR), which simulates the inpainting dynamics of oil painting restoration, converting real images into stylized oil paintings with preserved brushstroke textures to construct a large-scale paired training dataset. Finally, during inference, we integrate features using the AdaIN operator to ensure stylistic consistency. Extensive experiments demonstrate that our interactive system enables fine-grained editing while preserving the artistic qualities of oil paintings, achieving an unprecedented level of imagination realization in stylized oil paintings generation and editing. --- ### MVP: Multiple View Prediction Improves GUI Grounding Authors: Yunzhu Zhang, Zeyu Pan, Zhengwen Zeng, Shuheng Shen, Changhua Meng, Linchao Zhu Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08529v1 GUI grounding, which translates natural language instructions into precise pixel coordinates, is essential for developing practical GUI agents. However, we observe that existing grounding models exhibit significant coordinate prediction instability, minor visual perturbations (e.g. cropping a few pixels) can drastically alter predictions, flipping results between correct and incorrect. This instability severely undermines model performance, especially for samples with high-resolution and small UI elements. To address this issue, we propose Multi-View Prediction (MVP), a training-free framework that enhances grounding performance through multi-view inference. Our key insight is that while single-view predictions may be unstable, aggregating predictions from multiple carefully cropped views can effectively distinguish correct coordinates from outliers. MVP comprises two components: (1) Attention-Guided View Proposal, which derives diverse views guided by instruction-to-image attention scores, and (2) Multi-Coordinates Clustering, which ensembles predictions by selecting the centroid of the densest spatial cluster. Extensive experiments demonstrate MVP's effectiveness across various models and benchmarks. Notably, on ScreenSpot-Pro, MVP boosts UI-TARS-1.5-7B to 56.1%, GTA1-7B to 61.7%, Qwen3VL-8B-Instruct to 65.3%, and Qwen3VL-32B-Instruct to 74.0%. The code is available at https://github.com/ZJUSCL/MVP. --- ### Beyond Real Weights: Hypercomplex Representations for Stable Quantization Authors: Jawad Ibn Ahad, Maisha Rahman, Amrijit Biswas, Muhammad Rafsan Kabir, Robin Krambroeckers, Sifat Momen, Nabeel Mohammed, Shafin Rahman Published: 2025-12-09 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2512.08524v1 Multimodal language models (MLLMs) require large parameter capacity to align high-dimensional visual features with linguistic representations, making them computationally heavy and difficult to deploy efficiently. We introduce a progressive reparameterization strategy that compresses these models by gradually replacing dense feed-forward network blocks with compact Parameterized Hypercomplex Multiplication (PHM) layers. A residual interpolation schedule, together with lightweight reconstruction and knowledge distillation losses, ensures that the PHM modules inherit the functional behavior of their dense counterparts during training. This transition yields substantial parameter and FLOP reductions while preserving strong multimodal alignment, enabling faster inference without degrading output quality. We evaluate the approach on multiple vision-language models (VLMs). Our method maintains performance comparable to the base models while delivering significant reductions in model size and inference latency. Progressive PHM substitution thus offers an architecture-compatible path toward more efficient multimodal reasoning and complements existing low-bit quantization techniques. --- ### SensHRPS: Sensing Comfortable Human-Robot Proxemics and Personal Space With Eye-Tracking Authors: Nadezhda Kushina, Ko Watanabe, Aarthi Kannan, Ashita Ashok, Andreas Dengel, Karsten Berns Published: 2025-12-09 Categories: cs.RO, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2512.08518v2 Social robots must adjust to human proxemic norms to ensure user comfort and engagement. While prior research demonstrates that eye-tracking features reliably estimate comfort in human-human interactions, their applicability to interactions with humanoid robots remains unexplored. In this study, we investigate user comfort with the robot "Ameca" across four experimentally controlled distances (0.5 m to 2.0 m) using mobile eye-tracking and subjective reporting (N=19). We evaluate multiple machine learning and deep learning models to estimate comfort based on gaze features. Contrary to previous human-human studies where Transformer models excelled, a Decision Tree classifier achieved the highest performance (F1-score = 0.73), with minimum pupil diameter identified as the most critical predictor. These findings suggest that physiological comfort thresholds in human-robot interaction differ from human-human dynamics and can be effectively modeled using interpretable logic. --- ### Minimax and Bayes Optimal Adaptive Experimental Design for Treatment Choice Authors: Masahiro Kato Published: 2025-12-09 Categories: econ.EM, cs.LG, math.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.08513v1 We consider an adaptive experiment for treatment choice and design a minimax and Bayes optimal adaptive experiment with respect to regret. Given binary treatments, the experimenter's goal is to choose the treatment with the highest expected outcome through an adaptive experiment, in order to maximize welfare. We consider adaptive experiments that consist of two phases, the treatment allocation phase and the treatment choice phase. The experiment starts with the treatment allocation phase, where the experimenter allocates treatments to experimental subjects to gather observations. During this phase, the experimenter can adaptively update the allocation probabilities using the observations obtained in the experiment. After the allocation phase, the experimenter proceeds to the treatment choice phase, where one of the treatments is selected as the best. For this adaptive experimental procedure, we propose an adaptive experiment that splits the treatment allocation phase into two stages, where we first estimate the standard deviations and then allocate each treatment proportionally to its standard deviation. We show that this experiment, often referred to as Neyman allocation, is minimax and Bayes optimal in the sense that its regret upper bounds exactly match the lower bounds that we derive. To show this optimality, we derive minimax and Bayes lower bounds for the regret using change-of-measure arguments. Then, we evaluate the corresponding upper bounds using the central limit theorem and large deviation bounds. --- ### A Lightweight Transfer Learning-Based State-of-Health Monitoring with Application to Lithium-ion Batteries in Autonomous Air Vehicles Authors: Jiang Liu, Yan Qin, Wei Dai, Chau Yuen Published: 2025-12-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.08512v2 Accurate and rapid state-of-health (SOH) monitoring plays an important role in indicating energy information for lithium-ion battery-powered portable mobile devices. To confront their variable working conditions, transfer learning (TL) emerges as a promising technique for leveraging knowledge from data-rich source working conditions, significantly reducing the training data required for SOH monitoring from target working conditions. However, traditional TL-based SOH monitoring is infeasible when applied in portable mobile devices since substantial computational resources are consumed during the TL stage and unexpectedly reduce the working endurance. To address these challenges, this paper proposes a lightweight TL-based SOH monitoring approach with constructive incremental transfer learning (CITL). First, taking advantage of the unlabeled data in the target domain, a semi-supervised TL mechanism is proposed to minimize the monitoring residual in a constructive way, through iteratively adding network nodes in the CITL. Second, the cross-domain learning ability of node parameters for CITL is comprehensively guaranteed through structural risk minimization, transfer mismatching minimization, and manifold consistency maximization. Moreover, the convergence analysis of the CITL is given, theoretically guaranteeing the efficacy of TL performance and network compactness. Finally, the proposed approach is verified through extensive experiments with a realistic autonomous air vehicles (AAV) battery dataset collected from dozens of flight missions. Specifically, the CITL outperforms SS-TCA, MMD-LSTM-DA, DDAN, BO-CNN-TL, and AS$^3$LSTM, in SOH estimation by 83.73%, 61.15%, 28.24%, 87.70%, and 57.34%, respectively, as evaluated using the index root mean square error. --- ### Thinking with Images via Self-Calling Agent Authors: Wenxi Yang, Yuzhong Zhao, Fang Wan, Qixiang Ye Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08511v2 Thinking-with-images paradigms have showcased remarkable visual reasoning capability by integrating visual information as dynamic elements into the Chain-of-Thought (CoT). However, optimizing interleaved multimodal CoT (iMCoT) through reinforcement learning remains challenging, as it relies on scarce high-quality reasoning data. In this study, we propose Self-Calling Chain-of-Thought (sCoT), a novel visual reasoning paradigm that reformulates iMCoT as a language-only CoT with self-calling. Specifically, a main agent decomposes the complex visual reasoning task to atomic subtasks and invokes its virtual replicas, i.e. parameter-sharing subagents, to solve them in isolated context. sCoT enjoys substantial training effectiveness and efficiency, as it requires no explicit interleaving between modalities. sCoT employs group-relative policy optimization to reinforce effective reasoning behavior to enhance optimization. Experiments on HR-Bench 4K show that sCoT improves the overall reasoning performance by up to $1.9\%$ with $\sim 75\%$ fewer GPU hours compared to strong baseline approaches. Code is available at https://github.com/YWenxi/think-with-images-through-self-calling. --- ### Data-Efficient Learning of Anomalous Diffusion with Wavelet Representations: Enabling Direct Learning from Experimental Trajectories Authors: Gongyi Wang, Yu Zhang, Zihan Huang Published: 2025-12-09 Categories: physics.bio-ph, cond-mat.soft, cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2512.08510v1 Machine learning (ML) has become a versatile tool for analyzing anomalous diffusion trajectories, yet most existing pipelines are trained on large collections of simulated data. In contrast, experimental trajectories, such as those from single-particle tracking (SPT), are typically scarce and may differ substantially from the idealized models used for simulation, leading to degradation or even breakdown of performance when ML methods are applied to real data. To address this mismatch, we introduce a wavelet-based representation of anomalous diffusion that enables data-efficient learning directly from experimental recordings. This representation is constructed by applying six complementary wavelet families to each trajectory and combining the resulting wavelet modulus scalograms. We first evaluate the wavelet representation on simulated trajectories from the andi-datasets benchmark, where it clearly outperforms both feature-based and trajectory-based methods with as few as 1000 training trajectories and still retains an advantage on large training sets. We then use this representation to learn directly from experimental SPT trajectories of fluorescent beads diffusing in F-actin networks, where the wavelet representation remains superior to existing alternatives for both diffusion-exponent regression and mesh-size classification. In particular, when predicting the diffusion exponents of experimental trajectories, a model trained on 1200 experimental tracks using the wavelet representation achieves significantly lower errors than state-of-the-art deep learning models trained purely on $10^6$ simulated trajectories. We associate this data efficiency with the emergence of distinct scale fingerprints disentangling underlying diffusion mechanisms in the wavelet spectra. --- ### Multi-Alignment Contrastive Learning for Enzyme--Reaction Retrieval Authors: Gengmo Zhou, Feng Yu, Wenda Wang, Zhifeng Gao, Guolin Ke, Zhewei Wei, Zhen Wang Published: 2025-12-09 Categories: q-bio.BM, cs.LG arXiv: https://arxiv.org/abs/2512.08508v2 Identifying enzymes that catalyze target biochemical reactions is a key step in computational enzyme discovery and biocatalyst design. Recent representation-learning methods formulate this problem as enzyme--reaction matching, where paired enzymes and reactions are embedded into a shared space. However, most existing approaches primarily rely on pairwise enzyme--reaction supervision and make limited use of the relationships within reaction sets or enzyme families. This work introduces a multi-alignment contrastive learning framework for biochemical retrieval. The framework jointly models cross-domain compatibility between enzymes and reactions and within-domain relationships induced by functional annotations. In addition, a Gromov--Wasserstein-inspired regularization objective encourages geometric consistency between the learned enzyme and reaction representation spaces. By combining pairwise catalytic supervision with higher-order relational alignment, the model captures both direct enzyme--reaction associations and broader functional organization. We evaluate the approach on enzyme virtual screening and bidirectional enzyme--reaction retrieval tasks. Experiments on EnzymeMap show improved early-recognition performance under BEDROC and enrichment-factor metrics compared with strong contrastive baselines. On ReactZyme, the method achieves consistent gains across time-based, enzyme-similarity, and reaction-similarity splits, demonstrating robustness to unseen enzymes and unseen reactions. Ablation studies further indicate that within-domain alignment, functional supervision, and the geometric regularization term each contribute to the observed improvements. These results suggest that modeling multiple forms of alignment can improve contrastive retrieval models for enzyme discovery, reaction annotation, and related computational biology applications. --- ### OCCDiff: Occupancy Diffusion Model for High-Fidelity 3D Building Reconstruction from Noisy Point Clouds Authors: Jialu Sui, Rui Liu, Hongsheng Zhang Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08506v1 A major challenge in reconstructing buildings from LiDAR point clouds lies in accurately capturing building surfaces under varying point densities and noise interference. To flexibly gather high-quality 3D profiles of the building in diverse resolution, we propose OCCDiff applying latent diffusion in the occupancy function space. Our OCCDiff combines a latent diffusion process with a function autoencoder architecture to generate continuous occupancy functions evaluable at arbitrary locations. Moreover, a point encoder is proposed to provide condition features to diffusion learning, constraint the final occupancy prediction for occupancy decoder, and insert multi-modal features for latent generation to latent encoder. To further enhance the model performance, a multi-task training strategy is employed, ensuring that the point encoder learns diverse and robust feature representations. Empirical results show that our method generates physically consistent samples with high fidelity to the target distribution and exhibits robustness to noisy data. --- ### Early Estimation of Language to Latent Alignment in Diffusion Models Authors: Vasco Ramos, Regev Cohen, Idan Szpektor, Joao Magalhaes Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08505v2 Conditional diffusion models frequently suffer from language-image misalignments. Due to the ambiguity of intermediate noise corrupted latents, assessing prompt adherence currently requires completing the entire sampling trajectory. This late-stage evaluation incurs even higher computational costs during test-time scaling strategies, such as Best-of-N (BoN) sampling, as all misaligned trajectories must finish generation before being discarded. To tackle this, we propose NoisyCLIP, a noise-aware twin-tower model that enables early language-to-latent alignment estimation. By learning a vision encoder on noise-corrupted latents, we allow the model to "see" through the ambiguity of intermediate diffusion steps. To facilitate this training, we investigate noise-data augmentation sampling strategies and introduce two new benchmark datasets: Noisy-Conceptual-Captions and Noisy-GenAI-Bench. When applied as an early-stopping criterion for BoN, NoisyCLIP at half cost matches or beats frozen CLIP at full cost. Ultimately, this transforms alignment assessment from an expensive final check into a continuous monitoring tool, drastically reducing compute costs without sacrificing semantic fidelity. --- ### Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models Authors: Jiaming Zhang, Che Wang, Yang Cao, Longtao Huang, Wei Yang Bryan Lim Published: 2025-12-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.08503v2 Multi-modal large reasoning models (MLRMs) pose significant privacy risks by inferring precise geographic locations from personal images through hierarchical chain-of-thought reasoning. Existing privacy protection techniques, primarily designed for perception-based models, prove ineffective against MLRMs' sophisticated multi-step reasoning processes that analyze environmental cues. We introduce \textbf{ReasonBreak}, a novel adversarial framework specifically designed to disrupt hierarchical reasoning in MLRMs through concept-aware perturbations. Our approach is founded on the key insight that effective disruption of geographic reasoning requires perturbations aligned with conceptual hierarchies rather than uniform noise. ReasonBreak strategically targets critical conceptual dependencies within reasoning chains, generating perturbations that invalidate specific inference steps and cascade through subsequent reasoning stages. To facilitate this approach, we contribute \textbf{GeoPrivacy-6K}, a comprehensive dataset comprising 6,341 ultra-high-resolution images ($\geq$2K) with hierarchical concept annotations. Extensive evaluation across seven state-of-the-art MLRMs (including GPT-o3, GPT-5, Gemini 2.5 Pro) demonstrates ReasonBreak's superior effectiveness, achieving a 14.4\% improvement in tract-level protection (33.8\% vs 19.4\%) and nearly doubling block-level protection (33.5\% vs 16.8\%). This work establishes a new paradigm for privacy protection against reasoning-based threats. --- ### Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D Motions Authors: Jianan Li, Xiao Chen, Tao Huang, Tien-Tsin Wong Published: 2025-12-09 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2512.08500v1 Video data is more cost-effective than motion capture data for learning 3D character motion controllers, yet synthesizing realistic and diverse behaviors directly from videos remains challenging. Previous approaches typically rely on off-the-shelf motion reconstruction techniques to obtain 3D trajectories for physics-based imitation. These reconstruction methods struggle with generalizability, as they either require 3D training data (potentially scarce) or fail to produce physically plausible poses, hindering their application to challenging scenarios like human-object interaction (HOI) or non-human characters. We tackle this challenge by introducing Mimic2DM, a novel motion imitation framework that learns the control policy directly and solely from widely available 2D keypoint trajectories extracted from videos. By minimizing the reprojection error, we train a general single-view 2D motion tracking policy capable of following arbitrary 2D reference motions in physics simulation, using only 2D motion data. The policy, when trained on diverse 2D motions captured from different or slightly different viewpoints, can further acquire 3D motion tracking capabilities by aggregating multiple views. Moreover, we develop a transformer-based autoregressive 2D motion generator and integrate it into a hierarchical control framework, where the generator produces high-quality 2D reference trajectories to guide the tracking policy. We show that the proposed approach is versatile and can effectively learn to synthesize physically plausible and diverse motions across a range of domains, including dancing, soccer dribbling, and animal movements, without any reliance on explicit 3D motion data. Project Website: https://jiann-li.github.io/mimic2dm/ --- ### Developing Distance-Aware Physics-Constrained Probabilistic Frameworks for Industrial Prognostics Authors: Waleed Razzaq, Yun-Bo Zhao Published: 2025-12-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.08499v3 Development of reliable and physically interpretable probabilistic frameworks for industrial prognostics remain nascent, and existing literature is often insensitive as inputs move away from the training manifold. In this paper, we develop two sampling-free, distance-aware physics-constrained probabilistic frameworks: (i) PC-SNGP and (ii) PC-SNER. Both apply spectral normalization to hidden layer weights, enforcing bi-Lipschitz distance-preserving representation from the input to the latent space. PC-SNGP replaces the dense output with Gaussian process whose posterior variance increases with input distance from the training manifold. PC-SNER modifies the output layer to predict Normal-Inverse-Gamma~(NIG) parameters for distance preserving estimation. To maintain balance between data fidelity and physical consistency during training, we introduce a dynamic weighting strategy for the physics-constrained loss. We also introduce a distance-aware-coefficient~(DAC) metric to quantify sensitivity to distributional shifts. Empirically, we validate both frameworks on rolling-element-bearings (REBs) prognostics using the PRONOSTIA, XJTU-SY, and HUST benchmark datasets. Experimental results demonstrate improved prediction accuracy and well-calibrated uncertainty estimates relative to competing baselines, while maintaining auditable performance in cross-validation and robustness under extreme adversarial perturbations. --- ### On-the-fly Large-scale 3D Reconstruction from Multi-Camera Rigs Authors: Yijia Guo, Tong Hu, Zhiwei Li, Liwen Hu, Keming Qian, Xitong Lin, Shengbo Chen, Tiejun Huang, Lei Ma Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08498v1 Recent advances in 3D Gaussian Splatting (3DGS) have enabled efficient free-viewpoint rendering and photorealistic scene reconstruction. While on-the-fly extensions of 3DGS have shown promise for real-time reconstruction from monocular RGB streams, they often fail to achieve complete 3D coverage due to the limited field of view (FOV). Employing a multi-camera rig fundamentally addresses this limitation. In this paper, we present the first on-the-fly 3D reconstruction framework for multi-camera rigs. Our method incrementally fuses dense RGB streams from multiple overlapping cameras into a unified Gaussian representation, achieving drift-free trajectory estimation and efficient online reconstruction. We propose a hierarchical camera initialization scheme that enables coarse inter-camera alignment without calibration, followed by a lightweight multi-camera bundle adjustment that stabilizes trajectories while maintaining real-time performance. Furthermore, we introduce a redundancy-free Gaussian sampling strategy and a frequency-aware optimization scheduler to reduce the number of Gaussian primitives and the required optimization iterations, thereby maintaining both efficiency and reconstruction fidelity. Our method reconstructs hundreds of meters of 3D scenes within just 2 minutes using only raw multi-camera video streams, demonstrating unprecedented speed, robustness, and Fidelity for on-the-fly 3D scene reconstruction. --- ### LLM-based Vulnerable Code Augmentation: Generate or Refactor? Authors: Dyna Soumhane Ouchebara, Stéphane Dupont Published: 2025-12-09 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.08493v2 Vulnerability code-bases often suffer from severe imbalance, limiting the effectiveness of Deep Learning-based vulnerability classifiers. Data Augmentation could help solve this by mitigating the scarcity of under-represented vulnerability types. In this context, we investigate LLM-based augmentation for vulnerable functions, comparing controlled generation of new vulnerable samples with semantics-preserving refactoring of existing ones. Using Qwen2.5-Coder to produce augmented data and CodeBERT as a classifier on the SVEN dataset, we find that our approaches are indeed effective in enriching vulnerable code-bases through a simple process and with reasonable quality, and that a hybrid strategy best boosts vulnerability classifiers' performance. Code repository is available here : https://github.com/DynaSoumhaneOuchebara/LLM-based-code-augmentation-Generate-or-Refactor- --- ### Autonomous Issue Resolver: Towards Zero-Touch Code Maintenance Authors: Aliaksei Kaliutau Published: 2025-12-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.08492v3 Recent advances in Large Language Models have revolutionized function-level code generation; however, repository-scale Automated Program Repair (APR) remains a significant challenge. Current approaches typically employ a control-centric paradigm, forcing agents to navigate complex directory structures and irrelevant control logic. In this paper, we propose a paradigm shift from the standard Code Property Graphs (CPGs) to the concept of Data Transformation Graph (DTG) that inverts the topology by modeling data states as nodes and functions as edges, enabling agents to trace logic defects through data lineage rather than control flow. We introduce a multi-agent framework that reconciles data integrity navigation with control flow logic. Our theoretical analysis and case studies demonstrate that this approach resolves the "Semantic Trap" inherent in standard RAG systems in modern coding agents. We provide a comprehensive implementation in the form of Autonomous Issue Resolver (AIR), a self-improvement system for zero-touch code maintenance that utilizes neuro-symbolic reasoning and uses the DTG structure for scalable logic repair. Our approach has demonstrated good results on several SWE benchmarks, reaching a resolution rate of 87.1% on SWE-Verified benchmark. Our approach directly addresses the core limitations of current AI code-assistant tools and tackles the critical need for a more robust foundation for our increasingly software-dependent world. --- ### Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions Authors: Ada Gorgun, Fawaz Sammani, Nikos Deligiannis, Bernt Schiele, Jonas Fischer Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08486v2 Diffusion models are usually evaluated by their final outputs, gradually denoising random noise into meaningful images. Yet, generation unfolds along a trajectory, and analyzing this dynamic process is crucial for understanding how controllable, reliable, and predictable these models are in terms of their success/failure modes. In this work, we ask the question: when does noise turn into a specific concept (e.g., age) and lock in the denoising trajectory? We propose PCI (Prompt-Conditioned Intervention) to study this question. PCI is a training-free and model-agnostic framework for analyzing concept dynamics through diffusion time. The central idea is the analysis of Concept Insertion Success (CIS), defined as the probability that a concept inserted at a given timestep is preserved and reflected in the final image, offering a way to characterize the temporal dynamics of concept formation. Applied to several state-of-the-art text-to-image diffusion models and a broad taxonomy of concepts, PCI reveals diverse temporal behaviors across diffusion models, in which certain phases of the trajectory are more favorable to specific concepts even within the same concept type. These findings also provide actionable insights for text-driven image editing, highlighting when interventions are most effective without requiring access to model internals or training, and yielding quantitatively stronger edits that achieve a balance of semantic accuracy and content preservation than strong baselines. Code is available at: https://adagorgun.github.io/PCI-Project/ --- ### Optimal Perturbation Budget Allocation for Data Poisoning in Offline Reinforcement Learning Authors: Junnan Qiu, Yuanjie Zhao, Jie Li Published: 2025-12-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.08485v2 Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to data poisoning attacks. Existing attack strategies typically rely on locally uniform perturbations, which treat all samples indiscriminately. This approach is inefficient, as it wastes the perturbation budget on low-impact samples, and lacks stealthiness due to significant statistical deviations. In this paper, we propose a novel Global Budget Allocation attack strategy. Leveraging the theoretical insight that a sample's influence on value function convergence is proportional to its Temporal Difference (TD) error, we formulate the attack as a global resource allocation problem. We derive a closed-form solution where perturbation magnitudes are assigned proportional to the TD-error sensitivity under a global L2 constraint. Empirical results on D4RL benchmarks demonstrate that our method significantly outperforms baseline strategies, achieving up to 80% performance degradation with minimal perturbations that evade detection by state-of-the-art statistical and spectral defenses. --- ### Soft Inductive Bias Approach via Explicit Reasoning Perspectives in Inappropriate Utterance Detection Using Large Language Models Authors: Ju-Young Kim, Ji-Hong Park, Se-Yeon Lee, Sujin Park, Gun-Woo Kim Published: 2025-12-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.08480v1 Recent incidents in certain online games and communities, where anonymity is guaranteed, show that unchecked inappropriate remarks frequently escalate into verbal abuse and even criminal behavior, raising significant social concerns. Consequently, there is a growing need for research on techniques that can detect inappropriate utterances within conversational texts to help build a safer communication environment. Although large-scale language models trained on Korean corpora and chain-of-thought reasoning have recently gained attention, research applying these approaches to inappropriate utterance detection remains limited. In this study, we propose a soft inductive bias approach that explicitly defines reasoning perspectives to guide the inference process, thereby promoting rational decision-making and preventing errors that may arise during reasoning. We fine-tune a Korean large language model using the proposed method and conduct both quantitative performance comparisons and qualitative evaluations across different training strategies. Experimental results show that the Kanana-1.5 model achieves an average accuracy of 87.0046, improving by approximately 3.89 percent over standard supervised learning. These findings indicate that the proposed method goes beyond simple knowledge imitation by large language models and enables more precise and consistent judgments through constrained reasoning perspectives, demonstrating its effectiveness for inappropriate utterance detection. --- ### Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform Authors: Yuning Gong, Yifei Liu, Yifan Zhan, Muyao Niu, Xueying Li, Yuanjun Liao, Jiaming Chen, Yuanyuan Gao, Jiaqi Chen, Minming Chen, Li Zhou, Yuning Zhang et al. Published: 2025-12-09 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2512.08478v1 Neural rendering, particularly 3D Gaussian Splatting (3DGS), has evolved rapidly and become a key component for building world models. However, existing viewer solutions remain fragmented, heavy, or constrained by legacy pipelines, resulting in high deployment friction and limited support for dynamic content and generative models. In this work, we present Visionary, an open, web-native platform for real-time various Gaussian Splatting and meshes rendering. Built on an efficient WebGPU renderer with per-frame ONNX inference, Visionary enables dynamic neural processing while maintaining a lightweight, "click-to-run" browser experience. It introduces a standardized Gaussian Generator contract, which not only supports standard 3DGS rendering but also allows plug-and-play algorithms to generate or update Gaussians each frame. Such inference also enables us to apply feedforward generative post-processing. The platform further offers a plug in three.js library with a concise TypeScript API for seamless integration into existing web applications. Experiments show that, under identical 3DGS assets, Visionary achieves superior rendering efficiency compared to current Web viewers due to GPU-based primitive sorting. It already supports multiple variants, including MLP-based 3DGS, 4DGS, neural avatars, and style transformation or enhancement networks. By unifying inference and rendering directly in the browser, Visionary significantly lowers the barrier to reproduction, comparison, and deployment of 3DGS-family methods, serving as a unified World Model Carrier for both reconstructive and generative paradigms. --- ### ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention Authors: Huiguo He, Pengyu Yan, Ziqi Yi, Weizhi Zhong, Zheng Liu, Yejun Tang, Huan Yang, Guanbin Li, Lianwen Jin Published: 2025-12-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.08477v2 Drag-based image editing enables intuitive visual manipulation through point-based drag operations. Existing methods mainly rely on diffusion inversion or pixel-space warping with inpainting. However, inversion inherently introduces approximation errors that degrade texture fidelity, whereas rigid pixel-space operations discard semantic context and produce unnatural deformations. To address these issues, we introduce ContextDrag, to our knowledge the first framework that brings drag-based manipulation into the in-context image editing paradigm. By leveraging the in-context capabilities of editing models (e.g., FLUX-Kontext), ContextDrag enables precise drag editing without inversion or fine-tuning. Specifically, we first propose Context-preserving Token Injection (CTI), which injects VAE-encoded reference features into attention layers at spatially aligned target positions, guided by latent-space correspondences estimated directly from user-specified control points. By operating on clean, directly encoded features rather than noisy inversion outputs, CTI preserves rich texture details and enables precise drag control. Second, we propose Position-Aligned Attention (PAA) to eliminate interference caused by spatial displacement of reference features. PAA re-encodes positional embeddings of displaced reference tokens to match their target locations, and masks overlapping regions between source and destination to prevent conflicting features from degrading visual consistency. Experiments on DragBench-SR and DragBench-DR demonstrate that ContextDrag achieves SOTA editing accuracy and overall quality, and comprehensive ablations validate the effectiveness of each proposed component. Code will be publicly available. --- ### Solving Oversmoothing in GNNs via Nonlocal Message Passing: Algebraic Smoothing and Depth Scalability Authors: Weiqi Guan, Junlin He Published: 2025-12-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.08475v2 The relationship between Layer Normalization (LN) placement and the oversmoothing phenomenon remains underexplored. We identify a critical dilemma: Pre-LN architectures avoid oversmoothing but suffer from the curse of depth, while Post-LN architectures bypass the curse of depth but experience oversmoothing. To resolve this, we propose a new method based on Post-LN that induces algebraic smoothing, preventing oversmoothing without the curse of depth. Empirical results across five benchmarks demonstrate that our approach supports deeper networks (up to 256 layers) and improves performance, requiring no additional parameters. Key contributions: Theoretical Characterization: Analysis of LN dynamics and their impact on oversmoothing and the curse of depth. A Principled Solution: A parameter-efficient method that induces algebraic smoothing and avoids oversmoothing and the curse of depth. Empirical Validation: Extensive experiments showing the effectiveness of the method in deeper GNNs. --- ### Team-Aware Football Player Tracking with SAM: An Appearance-Based Approach to Occlusion Recovery Authors: Chamath Ranasinghe, Uthayasanker Thayasivam Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08467v1 Football player tracking is challenged by frequent occlusions, similar appearances, and rapid motion in crowded scenes. This paper presents a lightweight SAM-based tracking method combining the Segment Anything Model (SAM) with CSRT trackers and jersey color-based appearance models. We propose a team-aware tracking system that uses SAM for precise initialization and HSV histogram-based re-identification to improve occlusion recovery. Our evaluation measures three dimensions: processing speed (FPS and memory), tracking accuracy (success rate and box stability), and robustness (occlusion recovery and identity consistency). Experiments on football video sequences show that the approach achieves 7.6-7.7 FPS with stable memory usage (~1880 MB), maintaining 100 percent tracking success in light occlusions and 90 percent in crowded penalty-box scenarios with 5 or more players. Appearance-based re-identification recovers 50 percent of heavy occlusions, demonstrating the value of domain-specific cues. Analysis reveals key trade-offs: the SAM + CSRT combination provides consistent performance across crowd densities but struggles with long-term occlusions where players leave the frame, achieving only 8.66 percent re-acquisition success. These results offer practical guidelines for deploying football tracking systems under resource constraints, showing that classical tracker-based methods work well with continuous visibility but require stronger re-identification mechanisms for extended absences. --- ### Privileged observations enable rapid and reliable policy discovery directly in the physical world Authors: Antonio Terpin, Raffaello D'Andrea Published: 2025-12-09 Categories: cs.AI, cs.LG, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2512.08463v2 We study how privileged information about a physical system affects the discovery of high-performing policies when training a reinforcement learning agent directly in the physical world. We let the agent control a cylinder in a tabletop water channel to maximize or minimize drag. The flow is chaotic and difficult to model or simulate accurately and good strategies are not obvious beforehand. Decades-old experimental studies provide recipes for simple, high-performance, periodic open-loop policies that increase drag by 26.6% +/- 0.7% and reduce it by 29.7% +/- 1.3%. With dense observations of the cylinder wake, the agent learns within tens of minutes policies that increase drag by 25.5% +/- 0.9% and reduce it by 32.4% +/- 1.6%. We record action trajectories during online policy execution and replay them open loop as fixed sequences; these replays increase drag by 23.2% +/- 2.2% and reduce it by 32.1% +/- 3.0%. However, when we withhold flow observations during training, the agent still learns to decrease drag by 31.4% +/- 2.1%, but no run learns to increase it (1.8% +/- 4.3% drag increase). Our physical experiments demonstrate an extreme case: privileged observations can be decisive for policy discovery even when the resulting actions can be replayed in open loop. --- ### Transformers for Multimodal Brain State Decoding: Integrating Functional Magnetic Resonance Imaging Data and Medical Metadata Authors: Danial Jafarzadeh Jazi, Maryam Hajiesmaeili Published: 2025-12-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.08462v2 Decoding brain states from functional magnetic resonance imaging (fMRI) data is vital for advancing neuroscience and clinical applications. While traditional machine learning and deep learning approaches have made strides in leveraging the high-dimensional and complex nature of fMRI data, they often fail to utilize the contextual richness provided by Digital Imaging and Communications in Medicine (DICOM) metadata. This paper presents a novel framework integrating transformer-based architectures with multimodal inputs, including fMRI data and DICOM metadata. By employing attention mechanisms, the proposed method captures intricate spatial-temporal patterns and contextual relationships, enhancing model accuracy, interpretability, and robustness. The potential of this framework spans applications in clinical diagnostics, cognitive neuroscience, and personalized medicine. Limitations, such as metadata variability and computational demands, are addressed, and future directions for optimizing scalability and generalizability are discussed. --- ### Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models III: Implementing the Bacterial Biothreat Benchmark (B3) Dataset Authors: Gary Ackerman, Theodore Wilson, Zachary Kallenborn, Olivia Shoemaker, Anna Wetzel, Hayley Peterson, Abigail Danfora, Jenna LaTourette, Brandon Behlendorf, Douglas Clifford Published: 2025-12-09 Categories: cs.LG, cs.AI, cs.CY, cs.ET arXiv: https://arxiv.org/abs/2512.08459v1 The potential for rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons has generated significant policy, academic, and public concern. Both model developers and policymakers seek to quantify and mitigate any risk, with an important element of such efforts being the development of model benchmarks that can assess the biosecurity risk posed by a particular model. This paper discusses the pilot implementation of the Bacterial Biothreat Benchmark (B3) dataset. It is the third in a series of three papers describing an overall Biothreat Benchmark Generation (BBG) framework, with previous papers detailing the development of the B3 dataset. The pilot involved running the benchmarks through a sample frontier AI model, followed by human evaluation of model responses, and an applied risk analysis of the results along several dimensions. Overall, the pilot demonstrated that the B3 dataset offers a viable, nuanced method for rapidly assessing the biosecurity risk posed by a LLM, identifying the key sources of that risk and providing guidance for priority areas of mitigation priority. --- ### Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models II: Benchmark Generation Process Authors: Gary Ackerman, Zachary Kallenborn, Anna Wetzel, Hayley Peterson, Jenna LaTourette, Olivia Shoemaker, Brandon Behlendorf, Sheriff Almakki, Doug Clifford, Noah Sheinbaum Published: 2025-12-09 Categories: cs.LG, cs.AI, cs.CY, cs.ET arXiv: https://arxiv.org/abs/2512.08451v1 The potential for rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons has generated significant policy, academic, and public concern. Both model developers and policymakers seek to quantify and mitigate any risk, with an important element of such efforts being the development of model benchmarks that can assess the biosecurity risk posed by a particular model. This paper, the second in a series of three, describes the second component of a novel Biothreat Benchmark Generation (BBG) framework: the generation of the Bacterial Biothreat Benchmark (B3) dataset. The development process involved three complementary approaches: 1) web-based prompt generation, 2) red teaming, and 3) mining existing benchmark corpora, to generate over 7,000 potential benchmarks linked to the Task-Query Architecture that was developed during the first component of the project. A process of de-duplication, followed by an assessment of uplift diagnosticity, and general quality control measures, reduced the candidates to a set of 1,010 final benchmarks. This procedure ensured that these benchmarks are a) diagnostic in terms of providing uplift; b) directly relevant to biosecurity threats; and c) are aligned with a larger biosecurity architecture permitting nuanced analysis at different levels of analysis. --- ### From Accuracy to Impact: The Impact-Driven AI Framework (IDAIF) for Aligning Engineering Architecture with Theory of Change Authors: Yong-Woon Kim Published: 2025-12-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.08449v1 This paper introduces the Impact-Driven AI Framework (IDAIF), a novel architectural methodology that integrates Theory of Change (ToC) principles with modern artificial intelligence system design. As AI systems increasingly influence high-stakes domains including healthcare, finance, and public policy, the alignment problem--ensuring AI behavior corresponds with human values and intentions--has become critical. Current approaches predominantly optimize technical performance metrics while neglecting the sociotechnical dimensions of AI deployment. IDAIF addresses this gap by establishing a systematic mapping between ToC's five-stage model (Inputs-Activities-Outputs-Outcomes-Impact) and corresponding AI architectural layers (Data Layer-Pipeline Layer-Inference Layer-Agentic Layer-Normative Layer). Each layer incorporates rigorous theoretical foundations: multi-objective Pareto optimization for value alignment, hierarchical multi-agent orchestration for outcome achievement, causal directed acyclic graphs (DAGs) for hallucination mitigation, and adversarial debiasing with Reinforcement Learning from Human Feedback (RLHF) for fairness assurance. We provide formal mathematical formulations for each component and introduce an Assurance Layer that manages assumption failures through guardian architectures. Three case studies demonstrate IDAIF application across healthcare, cybersecurity, and software engineering domains. This framework represents a paradigm shift from model-centric to impact-centric AI development, providing engineers with concrete architectural patterns for building ethical, trustworthy, and socially beneficial AI systems. --- ### Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts Authors: Madhav Gupta, Vishak Prasad C, Ganesh Ramakrishnan Published: 2025-12-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.08445v2 Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in in-distribution (ID) settings, their behavior under out-of-distribution (OOD) conditions remains poorly understood. Through extensive experiments across multiple ID-OOD sets, we find that reliability of the existing subset based methods degrades markedly, yielding redundant, unstable, and uncertainty-sensitive explanations. To address these shortcomings, we introduce a framework that combines submodular subset selection with layer-wise, gradient-based uncertainty estimation to improve robustness and fidelity without requiring additional training or auxiliary models. Our approach estimates uncertainty via adaptive weight perturbations and uses these estimates to guide submodular optimization, ensuring diverse and informative subset selection. Empirical evaluations show that, beyond mitigating the weaknesses of existing methods under OOD scenarios, our framework also yields improvements in ID settings. These findings highlight limitations of current subset-based approaches and demonstrate how uncertainty-driven optimization can enhance attribution and object-level interpretability, paving the way for more transparent and trustworthy AI in real-world vision applications. --- ### Learned iterative networks: An operator learning perspective Authors: Andreas Hauptmann, Ozan Öktem Published: 2025-12-09 Categories: eess.IV, cs.LG, math.FA, math.NA, math.OC arXiv: https://arxiv.org/abs/2512.08444v2 Learned image reconstruction has become a pillar in computational imaging and inverse problems. Among the most successful approaches are learned iterative networks, which are formulated by unrolling classical iterative optimisation algorithms for solving variational problems. While the underlying algorithm is usually formulated in the functional analytic setting, learned approaches are often viewed as purely discrete. In this survey we present a unified operator view for learned iterative networks. Specifically, we formulate a learned reconstruction operator, defining how to compute, and separately the learning problem, which defines what to compute. In this setting we present common approaches and show that many approaches are closely related in their core. We review linear as well as non-linear inverse problems in this framework and present a short numerical study to conclude. --- ### Fully Decentralized Certified Unlearning Authors: Hithem Lamri, Michail Maniatakos Published: 2025-12-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.08443v1 Machine unlearning (MU) seeks to remove the influence of specified data from a trained model in response to privacy requests or data poisoning. While certified unlearning has been analyzed in centralized and server-orchestrated federated settings (via guarantees analogous to differential privacy, DP), the decentralized setting -- where peers communicate without a coordinator remains underexplored. We study certified unlearning in decentralized networks with fixed topologies and propose RR-DU, a random-walk procedure that performs one projected gradient ascent step on the forget set at the unlearning client and a geometrically distributed number of projected descent steps on the retained data elsewhere, combined with subsampled Gaussian noise and projection onto a trust region around the original model. We provide (i) convergence guarantees in the convex case and stationarity guarantees in the nonconvex case, (ii) $(\varepsilon,δ)$ network-unlearning certificates on client views via subsampled Gaussian Rényi DP (RDP) with segment-level subsampling, and (iii) deletion-capacity bounds that scale with the forget-to-local data ratio and quantify the effect of decentralization (network mixing and randomized subsampling) on the privacy-utility trade-off. Empirically, on image benchmarks (MNIST, CIFAR-10), RR-DU matches a given $(\varepsilon,δ)$ while achieving higher test accuracy than decentralized DP baselines and reducing forget accuracy to random guessing ($\approx 10\%$). --- ### Leveraging Multispectral Sensors for Color Correction in Mobile Cameras Authors: Luca Cogo, Marco Buzzelli, Simone Bianco, Javier Vazquez-Corral, Raimondo Schettini Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08441v2 Recent advances in snapshot multispectral (MS) imaging have enabled compact, low-cost spectral sensors for consumer and mobile devices. By capturing richer spectral information than conventional RGB sensors, these systems can enhance key imaging tasks, including color correction. However, most existing methods treat the color correction pipeline in separate stages, often discarding MS data early in the process. We propose a unified, learning-based framework that performs end-to-end color correction and jointly leverages data from a high-resolution RGB sensor and an auxiliary low-resolution MS sensor. Our approach integrates the full pipeline within a single model, producing coherent and color-accurate outputs. We demonstrate the flexibility and generality of our framework by refactoring two different state-of-the-art image-to-image architectures. To support training and evaluation, we construct a dedicated dataset by aggregating and repurposing publicly available spectral datasets, rendering under multiple RGB camera sensitivities. Extensive experiments show that our approach improves color accuracy and stability, reducing error by up to 50% compared to RGB-only and MS-driven baselines. Code, models and dataset available at: https://lucacogo.github.io/Mobile-Spectral-CC/. --- ### What Triggers my Model? Contrastive Explanations Inform Gender Choices by Translation Models Authors: Janiça Hackenbuchner, Arda Tezcan, Joke Daems Published: 2025-12-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.08440v2 Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs). Yet, research in this area has been limited in relation to a manifested problem in these models: gender bias. In this work, we aim to move away from simply measuring bias to exploring its origins. Working with gender-ambiguous natural source data, this exploratory study examines which context, in the form of input tokens in the source sentence (EN), influences (or triggers) the NMT model's choice of a certain gender inflection in the target languages (DE/ES). To analyse this, we compute saliency attribution based on contrastive translations. We first address the challenge of the lack of a scoring threshold and specifically examine different attribution levels of source words on the model's gender decisions in the translation. We compare salient source words with human perceptions of gender and demonstrate a noticeable overlap between human perceptions and model attribution. Additionally, we provide a linguistic analysis of salient words. Our work showcases the relevance of understanding model translation decisions in terms of gender, how this compares to human decisions and that this information should be leveraged to mitigate gender bias. --- ### LapFM: A Laparoscopic Segmentation Foundation Model via Hierarchical Concept Evolving Pre-training Authors: Qing Xu, Kun Yuan, Yuxiang Luo, Yuhao Zhai, Wenting Duan, Nassir Navab, Zhen Chen Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08439v1 Surgical segmentation is pivotal for scene understanding yet remains hindered by annotation scarcity and semantic inconsistency across diverse procedures. Existing approaches typically fine-tune natural foundation models (e.g., SAM) with limited supervision, functioning merely as domain adapters rather than surgical foundation models. Consequently, they struggle to generalize across the vast variability of surgical targets. To bridge this gap, we present LapFM, a foundation model designed to evolve robust segmentation capabilities from massive unlabeled surgical images. Distinct from medical foundation models relying on inefficient self-supervised proxy tasks, LapFM leverages a Hierarchical Concept Evolving Pre-training paradigm. First, we establish a Laparoscopic Concept Hierarchy (LCH) via a hierarchical mask decoder with parent-child query embeddings, unifying diverse entities (i.e., Anatomy, Tissue, and Instrument) into a scalable knowledge structure with cross-granularity semantic consistency. Second, we propose a Confidence-driven Evolving Labeling that iteratively generates and filters pseudo-labels based on hierarchical consistency, progressively incorporating reliable samples from unlabeled images into training. This process yields LapBench-114K, a large-scale benchmark comprising 114K image-mask pairs. Extensive experiments demonstrate that LapFM significantly outperforms state-of-the-art methods, establishing new standards for granularity-adaptive generalization in universal laparoscopic segmentation. The source code is available at https://github.com/xq141839/LapFM. --- ### Beyond Wave Variables: A Data-Driven Ensemble Approach for Enhanced Teleoperation Transparency and Stability Authors: Nour Mitiche, Farid Ferguene, Mourad Oussalah Published: 2025-12-09 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2512.08436v1 Time delays in communication channels present significant challenges for bilateral teleoperation systems, affecting both transparency and stability. Although traditional wave variable-based methods for a four-channel architecture ensure stability via passivity, they remain vulnerable to wave reflections and disturbances like variable delays and environmental noise. This article presents a data-driven hybrid framework that replaces the conventional wave-variable transform with an ensemble of three advanced sequence models, each optimized separately via the state-of-the-art Optuna optimizer, and combined through a stacking meta-learner. The base predictors include an LSTM augmented with Prophet for trend correction, an LSTM-based feature extractor paired with clustering and a random forest for improved regression, and a CNN-LSTM model for localized and long-term dynamics. Experimental validation was performed in Python using data generated from the baseline system implemented in MATLAB/Simulink. The results show that our optimized ensemble achieves a transparency comparable to the baseline wave-variable system under varying delays and noise, while ensuring stability through passivity constraints. --- ### SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking Authors: Nico Leuze, Maximilian Hoh, Samed Doğan, Nicolas R. -Peña, Alfred Schoettl Published: 2025-12-09 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.08430v1 Accurately recovering 6D poses in densely packed industrial bin-picking environments remain a serious challenge, owing to occlusions, reflections, and textureless parts. We introduce a holistic depth-only 6D pose estimation approach that fuses multi-view depth maps into either a fine-grained 3D point cloud in its vanilla version, or a sparse Truncated Signed Distance Field (TSDF). At the core of our framework lies a staged heatmap mechanism that yields scene-adaptive attention priors across different resolutions, steering computation toward foreground regions, thus keeping memory requirements at high resolutions feasible. Along, we propose a density-aware sparse transformer block that dynamically attends to (self-) occlusions and the non-uniform distribution of 3D data. While sparse 3D approaches has proven effective for long-range perception, its potential in close-range robotic applications remains underexplored. Our framework operates fully sparse, enabling high-resolution volumetric representations to capture fine geometric details crucial for accurate pose estimation in clutter. Our method processes the entire scene integrally, predicting the 6D pose via a novel per-voxel voting strategy, allowing simultaneous pose predictions for an arbitrary number of target objects. We validate our method on the recently published IPD and MV-YCB multi-view datasets, demonstrating competitive performance in heavily cluttered industrial and household bin picking scenarios. --- ### Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems Authors: Mingwei Li, Xiaoyuan Zhang, Chengwei Yang, Zilong Zheng, Yaodong Yang Published: 2025-12-09 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2512.08411v2 Model-based planning in robotic domains is challenged by the hybrid nature of physical dynamics, where continuous motion is punctuated by discrete events such as contacts and impacts. Conventional latent world models typically employ monolithic neural networks that enforce global continuity, which over-smooths distinct dynamic modes (e.g., sticking vs. sliding, flight vs. stance). For a planner, this smoothing results in compounding errors during long-horizon lookaheads, rendering the search process unreliable at physical boundaries. To address this, we introduce the Prismatic World Model (PRISM-WM), a structured architecture designed to decompose complex hybrid dynamics into composable primitives. PRISM-WM uses a context-aware Mixture-of-Experts (MoE) framework where a gating mechanism implicitly identifies the current physical mode, and specialized experts predict the associated transition dynamics. We further introduce a latent orthogonalization objective to ensure expert diversity, preventing mode collapse. By modeling the mode transitions in system dynamics, PRISM-WM reduces rollout drift. Experiments on continuous control benchmarks, including high-dimensional humanoids and multi-task settings, demonstrate that PRISM-WM provides a high-fidelity substrate for trajectory optimization algorithms (e.g., TD-MPC), indicating its potential as a foundational model for model-based agents. --- ### Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval Authors: Tao Chen, Shaobo Ju, Qiong Wu, Chenxin Fang, Kun Zhang, Jun Peng, Hui Li, Yiyi Zhou, Rongrong Ji Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08410v2 Due to excessive memory overhead, most Multimodal Large Language Models (MLLMs) can only process videos of limited frames. In this paper, we propose an effective and efficient paradigm to remedy this shortcoming, termed One-shot video-Clip based Retrieval-Augmented Generation (OneClip-RAG). Compared with existing video RAG methods, OneClip-RAG makes full use of the merits of video clips for augmented video understanding in terms of both knowledge integrity and semantic coherence. Besides, it is also equipped with a novel query-guided video chunking algorithm that can unify clip chunking and cross-modal retrieval in one processing step, avoiding redundant computations. To improve instruction following, we further propose a new dataset called SynLongVideo and design a progressive training regime for OneClip-RAG. OneClip-RAG is plugged into three recent MLLMs and validated on a set of long-video benchmarks. Experimental results not only show the obvious performance gains by OneClip-RAG over MLLMs, e.g., boosting Qwen3-VL 8B to the level of GPT-5 on MLVU, but also show its superior efficiency in handling long videos. e.g., enabling LLaVA-Video understand up to an hour of videos in less than 1.2 minutes on a single 4090 GPU. --- ### SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos Authors: Mingqi Gao, Yunqi Miao, Jungong Han Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08406v1 Human Mesh Recovery (HMR) aims to reconstruct 3D human pose and shape from 2D observations and is fundamental to human-centric understanding in real-world scenarios. While recent image-based HMR methods such as SAM 3D Body achieve strong robustness on in-the-wild images, they rely on per-frame inference when applied to videos, leading to temporal inconsistency and degraded performance under occlusions. We address these issues without extra training by leveraging the inherent human continuity in videos. We propose SAM-Body4D, a training-free framework for temporally consistent and occlusion-robust HMR from videos. We first generate identity-consistent masklets using a promptable video segmentation model, then refine them with an Occlusion-Aware module to recover missing regions. The refined masklets guide SAM 3D Body to produce consistent full-body mesh trajectories, while a padding-based parallel strategy enables efficient multi-human inference. Experimental results demonstrate that SAM-Body4D achieves improved temporal stability and robustness in challenging in-the-wild videos, without any retraining. Our code and demo are available at: https://github.com/gaomingqi/sam-body4d. --- ### Are generative AI text annotations systematically biased? Authors: Sjoerd B. Stolwijk, Mark Boukes, Damian Trilling Published: 2025-12-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.08404v1 This paper investigates bias in GLLM annotations by conceptually replicating manual annotations of Boukes (2024). Using various GLLMs (Llama3.1:8b, Llama3.3:70b, GPT4o, Qwen2.5:72b) in combination with five different prompts for five concepts (political content, interactivity, rationality, incivility, and ideology). We find GLLMs perform adequate in terms of F1 scores, but differ from manual annotations in terms of prevalence, yield substantively different downstream results, and display systematic bias in that they overlap more with each other than with manual annotations. Differences in F1 scores fail to account for the degree of bias. --- ### Towards Visual Re-Identification of Fish using Fine-Grained Classification for Electronic Monitoring in Fisheries Authors: Samitha Nuwan Thilakarathna, Ercan Avsar, Martin Mathias Nielsen, Malte Pedersen Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08400v2 Accurate fisheries data are crucial for effective and sustainable marine resource management. With the recent adoption of Electronic Monitoring (EM) systems, more video data is now being collected than can be feasibly reviewed manually. This paper addresses this challenge by developing an optimized deep learning pipeline for automated fish re-identification (Re-ID) using the novel AutoFish dataset, which simulates EM systems with conveyor belts with six similarly looking fish species. We demonstrate that key Re-ID metrics (R1 and mAP@k) are substantially improved by using hard triplet mining in conjunction with a custom image transformation pipeline that includes dataset-specific normalization. By employing these strategies, we demonstrate that the Vision Transformer-based Swin-T architecture consistently outperforms the Convolutional Neural Network-based ResNet-50, achieving peak performance of 41.65% mAP@k and 90.43% Rank-1 accuracy. An in-depth analysis reveals that the primary challenge is distinguishing visually similar individuals of the same species (Intra-species errors), where viewpoint inconsistency proves significantly more detrimental than partial occlusion. The source code and documentation are available at: https://github.com/msamdk/Fish_Re_Identification.git --- ### Ontology-Based Knowledge Graph Framework for Industrial Standard Documents via Hierarchical and Propositional Structuring Authors: Jiin Park, Hyuna Jeon, Yoonseo Lee, Jisu Hong, Misuk Kim Published: 2025-12-09 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2512.08398v2 Ontology-based knowledge graph (KG) construction is a core technology that enables multidimensional understanding and advanced reasoning over domain knowledge. Industrial standards, in particular, contain extensive technical information and complex rules presented in highly structured formats that combine tables, scopes of application, constraints, exceptions, and numerical calculations, making KG construction especially challenging. In this study, we propose a method that organizes such documents into a hierarchical semantic structure, decomposes sentences and tables into atomic propositions derived from conditional and numerical rules, and integrates them into an ontology-knowledge graph through LLM-based triple extraction. Our approach captures both the hierarchical and logical structures of documents, effectively representing domain-specific semantics that conventional methods fail to reflect. To verify its effectiveness, we constructed rule, table, and multi-hop QA datasets, as well as a toxic clause detection dataset, from industrial standards, and implemented an ontology-aware KG-RAG framework for comparative evaluation. Experimental results show that our method achieves significant performance improvements across all QA types compared to existing KG-RAG approaches. This study demonstrates that reliable and scalable knowledge representation is feasible even for industrial documents with intertwined conditions, constraints, and scopes, contributing to future domain-specific RAG development and intelligent document management. ---