# Research Papers — 2025-12 · bundle page 21 of 175 > Full-text markdown of papers #1001–1050 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/21 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/20.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/22.md) ### Role-Based Fault Tolerance System for LLM RL Post-Training Authors: Zhenqian Chen, Baoquan Zhong, Xiang Li, Qing Dai, Xinkui Zhao, Miao Ye, Ren Cheng, Lufei Zhang, Jianwei Yin Published: 2025-12-27 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.22492v1 RL post-training for LLMs has been widely scaled to enhance reasoning and tool-using capabilities. However, RL post-training interleaves training and inference workloads, exposing the system to faults from both sides. Existing fault tolerance frameworks for LLMs target either training or inference, leaving the optimization potential in the asynchronous execution unexplored for RL. Our key insight is role-based fault isolation so the failure in one machine does not affect the others. We treat trainer, rollout, and other management roles in RL training as distinct distributed sub-tasks. Instead of restarting the entire RL task in ByteRobust, we recover only the failed role and reconnect it to living ones, thereby eliminating the full-restart overhead including rollout replay and initialization delay. We present RobustRL, the first comprehensive robust system to handle GPU machine errors for RL post-training Effective Training Time Ratio improvement. (1) \textit{Detect}. We implement role-aware monitoring to distinguish actual failures from role-specific behaviors to avoid the false positive and delayed detection. (2) \textit{Restart}. For trainers, we implement a non-disruptive recovery where rollouts persist state and continue trajectory generation, while the trainer is rapidly restored via rollout warm standbys. For rollout, we perform isolated machine replacement without interrupting the RL task. (3) \textit{Reconnect}. We replace static collective communication with dynamic, UCX-based (Unified Communication X) point-to-point communication, enabling immediate weight synchronization between recovered roles. In an RL training task on a 256-GPU cluster with Qwen3-8B-Math workload under 10\% failure injection frequency, RobustRL can achieve an ETTR of over 80\% compared with the 60\% in ByteRobust and achieves 8.4\%-17.4\% faster in end-to-end training time. --- ### ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text Representation Authors: Suhua Wang, Zifan Wang, Xiaoxin Sun, D. J. Wang, Zhanbo Liu, Xin Li Published: 2025-12-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.22491v1 As an endangered language, Manchu presents unique challenges for speech synthesis, including severe data scarcity and strong phonological agglutination. This paper proposes ManchuTTS(Manchu Text to Speech), a novel approach tailored to Manchu's linguistic characteristics. To handle agglutination, this method designs a three-tier text representation (phoneme, syllable, prosodic) and a cross-modal hierarchical attention mechanism for multi-granular alignment. The synthesis model integrates deep convolutional networks with a flow-matching Transformer, enabling efficient, non-autoregressive generation. This method further introduce a hierarchical contrastive loss to guide structured acoustic-linguistic correspondence. To address low-resource constraints, This method construct the first Manchu TTS dataset and employ a data augmentation strategy. Experiments demonstrate that ManchuTTS attains a MOS of 4.52 using a 5.2-hour training subset derived from our full 6.24-hour annotated corpus, outperforming all baseline models by a notable margin. Ablations confirm hierarchical guidance improves agglutinative word pronunciation accuracy (AWPA) by 31% and prosodic naturalness by 27%. --- ### Tracking by Predicting 3-D Gaussians Over Time Authors: Tanish Baranwal, Himanshu Gaurav Singh, Jathushan Rajasegaran, Jitendra Malik Published: 2025-12-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22489v2 We propose Video Gaussian Masked Autoencoders (Video-GMAE), a self-supervised approach for representation learning that encodes a sequence of images into a set of Gaussian splats moving over time. Representing a video as a set of Gaussians enforces a reasonable inductive bias: that 2-D videos are often consistent projections of a dynamic 3-D scene. We find that tracking emerges when pretraining a network with this architecture. Mapping the trajectory of the learnt Gaussians onto the image plane gives zero-shot tracking performance comparable to state-of-the-art. With small-scale finetuning, our models achieve 34.6% improvement on Kinetics, and 13.1% on Kubric datasets, surpassing existing self-supervised video approaches. The project page and code are publicly available at https://videogmae.org/ and https://github.com/tekotan/video-gmae. --- ### Toward Real-World IoT Security: Concept Drift-Resilient IoT Botnet Detection via Latent Space Representation Learning and Alignment Authors: Hassan Wasswa, Timothy Lynar Published: 2025-12-27 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.22488v1 Although AI-based models have achieved high accuracy in IoT threat detection, their deployment in enterprise environments is constrained by reliance on stationary datasets that fail to reflect the dynamic nature of real-world IoT NetFlow traffic, which is frequently affected by concept drift. Existing solutions typically rely on periodic classifier retraining, resulting in high computational overhead and the risk of catastrophic forgetting. To address these challenges, this paper proposes a scalable framework for adaptive IoT threat detection that eliminates the need for continuous classifier retraining. The proposed approach trains a classifier once on latent-space representations of historical traffic, while an alignment model maps incoming traffic to the learned historical latent space prior to classification, thereby preserving knowledge of previously observed attacks. To capture inter-instance relationships among attack samples, the low-dimensional latent representations are further transformed into a graph-structured format and classified using a graph neural network. Experimental evaluations on real-world heterogeneous IoT traffic datasets demonstrate that the proposed framework maintains robust detection performance under concept drift. These results highlight the framework's potential for practical deployment in dynamic and large-scale IoT environments. --- ### Constituency Structure over Eojeol in Korean Treebanks Authors: Jungyeul Park, Chulwoo Park Published: 2025-12-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.22487v2 The design of Korean constituency treebanks raises a central representational question concerning the choice of terminal units. Although Korean words are morphologically complex, treating morphemes as constituency terminals can obscure the distinction between word-internal morphology and phrase-level syntactic structure, and can create mismatches with eojeol-based dependency resources. This paper argues for an eojeol-based constituency representation, with morphological segmentation and fine-grained POS information encoded in a separate, non-constituent layer. A comparative analysis shows that, under explicit normalization assumptions, the Sejong, Penn Korean, and KAIST treebanks can be compared over a shared eojeol-based constituency backbone. Building on this result, we outline an eojeol-based annotation scheme that preserves interpretable constituency, supports cross-treebank comparison and constituency-dependency alignment, and provides a surface-form terminal layer for future end-to-end Korean constituency parsing. --- ### JParc: Joint cortical surface parcellation with registration Authors: Jian Li, Karthik Gopinath, Brian L. Edlow, Adrian V. Dalca, Bruce Fischl Published: 2025-12-27 Categories: q-bio.NC, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2512.22485v1 Cortical surface parcellation is a fundamental task in both basic neuroscience research and clinical applications, enabling more accurate mapping of brain regions. Model-based and learning-based approaches for automated parcellation alleviate the need for manual labeling. Despite the advancement in parcellation performance, learning-based methods shift away from registration and atlas propagation without exploring the reason for the improvement compared to traditional methods. In this study, we present JParc, a joint cortical registration and parcellation framework, that outperforms existing state-of-the-art parcellation methods. In rigorous experiments, we demonstrate that the enhanced performance of JParc is primarily attributable to accurate cortical registration and a learned parcellation atlas. By leveraging a shallow subnetwork to fine-tune the propagated atlas labels, JParc achieves a Dice score greater than 90% on the Mindboggle dataset, using only basic geometric features (sulcal depth, curvature) that describe cortical folding patterns. The superior accuracy of JParc can significantly increase the statistical power in brain mapping studies as well as support applications in surgical planning and many other downstream neuroscientific and clinical tasks. --- ### Scalpel-SAM: A Semi-Supervised Paradigm for Adapting SAM to Infrared Small Object Detection Authors: Zihan Liu, Xiangning Ren, Dezhang Kong, Yipeng Zhang, Meng Han Published: 2025-12-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22483v1 Infrared small object detection urgently requires semi-supervised paradigms due to the high cost of annotation. However, existing methods like SAM face significant challenges of domain gaps, inability of encoding physical priors, and inherent architectural complexity. To address this, we designed a Hierarchical MoE Adapter consisting of four white-box neural operators. Building upon this core component, we propose a two-stage paradigm for knowledge distillation and transfer: (1) Prior-Guided Knowledge Distillation, where we use our MoE adapter and 10% of available fully supervised data to distill SAM into an expert teacher (Scalpel-SAM); and (2) Deployment-Oriented Knowledge Transfer, where we use Scalpel-SAM to generate pseudo labels for training lightweight and efficient downstream models. Experiments demonstrate that with minimal annotations, our paradigm enables downstream models to achieve performance comparable to, or even surpassing, their fully supervised counterparts. To our knowledge, this is the first semi-supervised paradigm that systematically addresses the data scarcity issue in IR-SOT using SAM as the teacher model. --- ### SPECTRE: Spectral Pre-training Embeddings with Cylindrical Temporal Rotary Position Encoding for Fine-Grained sEMG-Based Movement Decoding Authors: Zihan Weng, Chanlin Yi, Pouya Bashivan, Jing Lu, Fali Li, Dezhong Yao, Jingming Hou, Yangsong Zhang, Peng Xu Published: 2025-12-27 Categories: cs.HC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.22481v1 Decoding fine-grained movement from non-invasive surface Electromyography (sEMG) is a challenge for prosthetic control due to signal non-stationarity and low signal-to-noise ratios. Generic self-supervised learning (SSL) frameworks often yield suboptimal results on sEMG as they attempt to reconstruct noisy raw signals and lack the inductive bias to model the cylindrical topology of electrode arrays. To overcome these limitations, we introduce SPECTRE, a domain-specific SSL framework. SPECTRE features two primary contributions: a physiologically-grounded pre-training task and a novel positional encoding. The pre-training involves masked prediction of discrete pseudo-labels from clustered Short-Time Fourier Transform (STFT) representations, compelling the model to learn robust, physiologically relevant frequency patterns. Additionally, our Cylindrical Rotary Position Embedding (CyRoPE) factorizes embeddings along linear temporal and annular spatial dimensions, explicitly modeling the forearm sensor topology to capture muscle synergies. Evaluations on multiple datasets, including challenging data from individuals with amputation, demonstrate that SPECTRE establishes a new state-of-the-art for movement decoding, significantly outperforming both supervised baselines and generic SSL approaches. Ablation studies validate the critical roles of both spectral pre-training and CyRoPE. SPECTRE provides a robust foundation for practical myoelectric interfaces capable of handling real-world sEMG complexities. --- ### Collaborative Optimization of Multiclass Imbalanced Learning: Density-Aware and Region-Guided Boosting Authors: Chuantao Li, Zhi Li, Jiahao Xu, Jie Li, Sheng Li Published: 2025-12-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22478v2 Numerous studies on Boosting attempt to mitigate classification bias caused by class imbalance. However, existing studies have yet to explore the collaborative optimization of imbalanced learning and model training. This constraint hinders further performance improvements. To bridge this gap, this study proposes a collaborative optimization Boosting model of multiclass imbalanced learning. By integrating the density factor and the confidence factor, this model implements a noise-resistant weight update mechanism alongside a dynamic sampling strategy. Rather than functioning as independent components, these modules are tightly integrated to orchestrate weight updates, sample region partitioning, and region-guided sampling. Thus, this study proposes the collaborative optimization of imbalanced learning and model training. Extensive experiments on 40 public imbalanced datasets demonstrate that the proposed model significantly outperforms seven state-of-the-art baselines. The code and datasets for this paper are available at: https://github.com/ChuantaoLi/DARG. --- ### Event-based high temporal resolution measurement of shock wave motion field Authors: Taihang Lei, Banglei Guan, Minzu Liang, Pengju Sun, Jing Tao, Yang Shang, Qifeng Yu Published: 2025-12-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22474v1 Accurate measurement of shock wave motion parameters with high spatiotemporal resolution is essential for applications such as power field testing and damage assessment. However, significant challenges are posed by the fast, uneven propagation of shock waves and unstable testing conditions. To address these challenges, a novel framework is proposed that utilizes multiple event cameras to estimate the asymmetry of shock waves, leveraging its high-speed and high-dynamic range capabilities. Initially, a polar coordinate system is established, which encodes events to reveal shock wave propagation patterns, with adaptive region-of-interest (ROI) extraction through event offset calculations. Subsequently, shock wave front events are extracted using iterative slope analysis, exploiting the continuity of velocity changes. Finally, the geometric model of events and shock wave motion parameters is derived according to event-based optical imaging model, along with the 3D reconstruction model. Through the above process, multi-angle shock wave measurement, motion field reconstruction, and explosive equivalence inversion are achieved. The results of the speed measurement are compared with those of the pressure sensors and the empirical formula, revealing a maximum error of 5.20% and a minimum error of 0.06%. The experimental results demonstrate that our method achieves high-precision measurement of the shock wave motion field with both high spatial and temporal resolution, representing significant progress. --- ### Gradient Dynamics of Attention: How Cross-Entropy Sculpts Bayesian Manifolds Authors: Naman Agarwal, Siddhartha R. Dalal, Vishal Misra Published: 2025-12-27 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.22473v5 Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale language models, yet the mechanisms by which gradient-based learning creates the required internal geometry remain opaque. We provide a complete first-order analysis of how cross-entropy training reshapes attention scores and value vectors in a transformer attention head. Our core result is an \emph{advantage-based routing law} for attention scores, \( \frac{\partial L}{\partial s_{ij}} = α_{ij}\bigl(b_{ij}-\mathbb{E}_{α_i}(b)\bigr), \qquad b_{ij} := u_i^\top v_j, \) coupled with a \emph{responsibility-weighted update} for values, \( Δv_j = -η\sum_i α_{ij} u_i, \) where $u_i$ is the upstream gradient at position $i$ and $α_{ij}$ are attention weights. These equations induce a positive feedback loop in which routing and content specialize together: queries route more strongly to values that are above-average for their error signal, and those values are pulled toward the queries that use them. We show that this coupled specialization behaves like a two-timescale EM procedure: attention weights implement an E-step (soft responsibilities), while values implement an M-step (responsibility-weighted prototype updates), with queries and keys adjusting the hypothesis frame. Through controlled simulations, including a sticky Markov-chain task where we compare a closed-form EM-style update to standard SGD, we demonstrate that the same gradient dynamics that minimize cross-entropy also sculpt the low-dimensional manifolds identified in our companion work as implementing Bayesian inference. This yields a unified picture in which optimization (gradient flow) gives rise to geometry (Bayesian manifolds), which in turn supports function (in-context probabilistic reasoning). --- ### The Bayesian Geometry of Transformer Attention Authors: Naman Agarwal, Siddhartha R. Dalal, Vishal Misra Published: 2025-12-27 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2512.22471v5 Transformers often appear to perform Bayesian reasoning in context, but verifying this rigorously has been impossible: natural data lack analytic posteriors, and large models conflate reasoning with memorization. We address this by constructing \emph{Bayesian wind tunnels} -- controlled environments where the true posterior is known in closed form and memorization is provably impossible. In these settings, small transformers reproduce Bayesian posteriors with $10^{-3}$-$10^{-4}$ bit accuracy, while capacity-matched MLPs fail by orders of magnitude, establishing a clear architectural separation. Across two tasks -- bijection elimination and Hidden Markov Model (HMM) state tracking -- we find that transformers implement Bayesian inference through a consistent geometric mechanism: residual streams serve as the belief substrate, feed-forward networks perform the posterior update, and attention provides content-addressable routing. Geometric diagnostics reveal orthogonal key bases, progressive query-key alignment, and a low-dimensional value manifold parameterized by posterior entropy. During training this manifold unfurls while attention patterns remain stable, a \emph{frame-precision dissociation} predicted by recent gradient analyses. Taken together, these results demonstrate that hierarchical attention realizes Bayesian inference by geometric design, explaining both the necessity of attention and the failure of flat architectures. Bayesian wind tunnels provide a foundation for mechanistically connecting small, verifiable systems to reasoning phenomena observed in large language models. --- ### DarkPatterns-LLM: A Multi-Layer Benchmark for Detecting Manipulative and Harmful AI Behavior Authors: Sadia Asif, Israel Antonio Rosales Laguan, Haris Khan, Shumaila Asif, Muneeb Asif Published: 2025-12-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.22470v1 The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary labels and fail to capture the nuanced psychological and social mechanisms constituting manipulation. We introduce \textbf{DarkPatterns-LLM}, a comprehensive benchmark dataset and diagnostic framework for fine-grained assessment of manipulative content in LLM outputs across seven harm categories: Legal/Power, Psychological, Emotional, Physical, Autonomy, Economic, and Societal Harm. Our framework implements a four-layer analytical pipeline comprising Multi-Granular Detection (MGD), Multi-Scale Intent Analysis (MSIAN), Threat Harmonization Protocol (THP), and Deep Contextual Risk Alignment (DCRA). The dataset contains 401 meticulously curated examples with instruction-response pairs and expert annotations. Through evaluation of state-of-the-art models including GPT-4, Claude 3.5, and LLaMA-3-70B, we observe significant performance disparities (65.2\%--89.7\%) and consistent weaknesses in detecting autonomy-undermining patterns. DarkPatterns-LLM establishes the first standardized, multi-dimensional benchmark for manipulation detection in LLMs, offering actionable diagnostics toward more trustworthy AI systems. --- ### GLUE: Gradient-free Learning to Unify Experts Authors: Jong-Ik Park, Shreyas Chaudhari, Srinivasa Pranav, Carlee Joe-Wong, José M. F. Moura Published: 2025-12-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22467v2 In many deployed systems (multilingual ASR, cross-hospital imaging, region-specific perception), multiple pretrained specialist models coexist. Yet, new target domains often require domain expansion: a generalized model that performs well beyond any single specialist's domain. Given a new target domain, existing methods obtain a single strong initialization prior for the model parameters by blending expert models to initialize a target model. However, heuristic blending -- using mixing coefficients based on data size or proxy metrics -- often yields lower target-domain test accuracy, and learning these coefficients on the target domain's loss function typically requires computationally-expensive full backpropagation through a neural network. We propose GLUE, Gradient-free Learning to Unify Experts, which initializes the target model as a convex combination of fixed experts and learns the mixture coefficients of this combination via gradient-free two-point SPSA (simultaneous perturbation stochastic approximation) updates, requiring only two forward passes per step. Across experiments on three datasets and three network architectures, GLUE produces model parameter priors that can be fine-tuned to outperform baselines. GLUE improves test accuracy by up to 8.5% over data-size weighting and by up to 9.1% over proxy-metric selection. GLUE either outperforms backpropagation-based full-gradient mixing or matches its performance within 1.4%. --- ### AMBIT: Augmenting Mobility Baselines with Interpretable Trees Authors: Qizhi Wang Published: 2025-12-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.22466v1 Origin-destination (OD) flow prediction remains a core task in GIS and urban analytics, yet practical deployments face two conflicting needs: high accuracy and clear interpretability. This paper develops AMBIT, a gray-box framework that augments physical mobility baselines with interpretable tree models. We begin with a comprehensive audit of classical spatial interaction models on a year-long, hourly NYC taxi OD dataset. The audit shows that most physical models are fragile at this temporal resolution; PPML gravity is the strongest physical baseline, while constrained variants improve when calibrated on full OD margins but remain notably weaker. We then build residual learners on top of physical baselines using gradient-boosted trees and SHAP analysis, demonstrating that (i) physics-grounded residuals approach the accuracy of a strong tree-based predictor while retaining interpretable structure, and (ii) POI-anchored residuals are consistently competitive and most robust under spatial generalization. We provide a reproducible pipeline, rich diagnostics, and spatial error analysis designed for urban decision-making. --- ### Pose-Guided Residual Refinement for Interpretable Text-to-Motion Generation and Editing Authors: Sukhyun Jeong, Yong-Hoon Choi Published: 2025-12-27 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.22464v1 Text-based 3D motion generation aims to automatically synthesize diverse motions from natural-language descriptions to extend user creativity, whereas motion editing modifies an existing motion sequence in response to text while preserving its overall structure. Pose-code-based frameworks such as CoMo map quantifiable pose attributes into discrete pose codes that support interpretable motion control, but their frame-wise representation struggles to capture subtle temporal dynamics and high-frequency details, often degrading reconstruction fidelity and local controllability. To address this limitation, we introduce pose-guided residual refinement for motion (PGR$^2$M), a hybrid representation that augments interpretable pose codes with residual codes learned via residual vector quantization (RVQ). A pose-guided RVQ tokenizer decomposes motion into pose latents that encode coarse global structure and residual latents that model fine-grained temporal variations. Residual dropout further discourages over-reliance on residuals, preserving the semantic alignment and editability of the pose codes. On top of this tokenizer, a base Transformer autoregressively predicts pose codes from text, and a refine Transformer predicts residual codes conditioned on text, pose codes, and quantization stage. Experiments on HumanML3D and KIT-ML show that PGR$^2$M improves Fréchet inception distance and reconstruction metrics for both generation and editing compared with CoMo and recent diffusion- and tokenization-based baselines, while user studies confirm that it enables intuitive, structure-preserving motion edits. --- ### MEGA-PCC: A Mamba-based Efficient Approach for Joint Geometry and Attribute Point Cloud Compression Authors: Kai-Hsiang Hsieh, Monyneath Yim, Wen-Hsiao Peng, Jui-Chiu Chiang Published: 2025-12-27 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2512.22463v1 Joint compression of point cloud geometry and attributes is essential for efficient 3D data representation. Existing methods often rely on post-hoc recoloring procedures and manually tuned bitrate allocation between geometry and attribute bitstreams in inference, which hinders end-to-end optimization and increases system complexity. To overcome these limitations, we propose MEGA-PCC, a fully end-to-end, learning-based framework featuring two specialized models for joint compression. The main compression model employs a shared encoder that encodes both geometry and attribute information into a unified latent representation, followed by dual decoders that sequentially reconstruct geometry and then attributes. Complementing this, the Mamba-based Entropy Model (MEM) enhances entropy coding by capturing spatial and channel-wise correlations to improve probability estimation. Both models are built on the Mamba architecture to effectively model long-range dependencies and rich contextual features. By eliminating the need for recoloring and heuristic bitrate tuning, MEGA-PCC enables data-driven bitrate allocation during training and simplifies the overall pipeline. Extensive experiments demonstrate that MEGA-PCC achieves superior rate-distortion performance and runtime efficiency compared to both traditional and learning-based baselines, offering a powerful solution for AI-driven point cloud compression. --- ### AFA-LoRA: Enabling Non-Linear Adaptations in LoRA with Activation Function Annealing Authors: Jiacheng Li, Jianchao Tan, Zhidong Yang, Feiye Huo, Yerui Sun, Yuchen Xie, Xunliang Cai Published: 2025-12-27 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.22455v2 Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method. However, its linear adaptation process limits its expressive power. This means there is a gap between the expressive power of linear training and non-linear training. To bridge this gap, we propose AFA-LoRA, a novel training strategy that brings non-linear expressivity to LoRA while maintaining its seamless mergeability. Our key innovation is an annealed activation function that transitions from a non-linear to a linear transformation during training, allowing the adapter to initially adopt stronger representational capabilities before converging to a mergeable linear form. We implement our method on supervised fine-tuning, reinforcement learning, and speculative decoding. The results show that AFA-LoRA reduces the performance gap between LoRA and full-parameter training. This work enables a more powerful and practical paradigm of parameter-efficient adaptation. --- ### Comparing Object Detection Models for Electrical Substation Component Mapping Authors: Namish Bansal, Haley Mody, Dennies Kiprono Bor, Dante Groccia, Edward J. Oughton Published: 2025-12-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22454v2 Electrical substations are a significant component of an electrical grid. Indeed, the assets at these substations (e.g., transformers) are vulnerable to hazards such as hurricanes, flooding, earthquakes, and geomagnetically induced currents (GICs). Because failures can have significant economic and public safety implications, identifying key substation components is essential for quantifying vulnerability. Unfortunately, traditional manual mapping of substation infrastructure is time-consuming and labor-intensive. Therefore, an autonomous solution utilizing computer vision models is preferable, as it offers greater convenience and efficiency. In this study, we train and compare 16 models on a manually labeled dataset of US substation images. These models include 12 You Only Look Once (YOLO) models, 2 Roboflow Detection Transformer (RF-DETR) models, and 2 Cascade R-CNN models. RF-DETR-large achieved the highest overall detection performance with mAP@50 and mAP@50:95 scores of 0.881 and 0.632, respectively. Across all models, alternate energy systems were detected most accurately, while transformers and reactors were more difficult to identify due to their smaller size and greater visual variability. Applying our best-performing model to nationwide imagery yielded approximately 22,591 component detections across 11,083 unique substations within the United States. These detections were broken down by state and Federal Energy Regulatory Commission (FERC) regions, with Florida (2,478 detections) and Midcontinent Independent System Operator (MISO; 4,329 detections) having the largest number of detections in their respective categories. --- ### SAM 3D for 3D Object Reconstruction from Remote Sensing Images Authors: Junsheng Yao, Lichao Mou, Qingyu Li Published: 2025-12-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22452v1 Monocular 3D building reconstruction from remote sensing imagery is essential for scalable urban modeling, yet existing methods often require task-specific architectures and intensive supervision. This paper presents the first systematic evaluation of SAM 3D, a general-purpose image-to-3D foundation model, for monocular remote sensing building reconstruction. We benchmark SAM 3D against TRELLIS on samples from the NYC Urban Dataset, employing Frechet Inception Distance (FID) and CLIP-based Maximum Mean Discrepancy (CMMD) as evaluation metrics. Experimental results demonstrate that SAM 3D produces more coherent roof geometry and sharper boundaries compared to TRELLIS. We further extend SAM 3D to urban scene reconstruction through a segment-reconstruct-compose pipeline, demonstrating its potential for urban scene modeling. We also analyze practical limitations and discuss future research directions. These findings provide practical guidance for deploying foundation models in urban 3D reconstruction and motivate future integration of scene-level structural priors. --- ### SonoVision: A Computer Vision Approach for Helping Visually Challenged Individuals Locate Objects with the Help of Sound Cues Authors: Md Abu Obaida Zishan, Annajiat Alim Rasel Published: 2025-12-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22449v1 Locating objects for the visually impaired is a significant challenge and is something no one can get used to over time. However, this hinders their independence and could push them towards risky and dangerous scenarios. Hence, in the spirit of making the visually challenged more self-sufficient, we present SonoVision, a smart-phone application that helps them find everyday objects using sound cues through earphones/headphones. This simply means, if an object is on the right or left side of a user, the app makes a sinusoidal sound in a user's respective ear through ear/headphones. However, to indicate objects located directly in front, both the left and right earphones are rung simultaneously. These sound cues could easily help a visually impaired individual locate objects with the help of their smartphones and reduce the reliance on people in their surroundings, consequently making them more independent. This application is made with the flutter development platform and uses the Efficientdet-D2 model for object detection in the backend. We believe the app will significantly assist the visually impaired in a safe and user-friendly manner with its capacity to work completely offline. Our application can be accessed here https://github.com/MohammedZ666/SonoVision.git. --- ### Towards Robust Optical-SAR Object Detection under Missing Modalities: A Dynamic Quality-Aware Fusion Framework Authors: Zhicheng Zhao, Yuancheng Xu, Andong Lu, Chenglong Li, Jin Tang Published: 2025-12-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.22447v1 Optical and Synthetic Aperture Radar (SAR) fusion-based object detection has attracted significant research interest in remote sensing, as these modalities provide complementary information for all-weather monitoring. However, practical deployment is severely limited by inherent challenges. Due to distinct imaging mechanisms, temporal asynchrony, and registration difficulties, obtaining well-aligned optical-SAR image pairs remains extremely difficult, frequently resulting in missing or degraded modality data. Although recent approaches have attempted to address this issue, they still suffer from limited robustness to random missing modalities and lack effective mechanisms to ensure consistent performance improvement in fusion-based detection. To address these limitations, we propose a novel Quality-Aware Dynamic Fusion Network (QDFNet) for robust optical-SAR object detection. Our proposed method leverages learnable reference tokens to dynamically assess feature reliability and guide adaptive fusion in the presence of missing modalities. In particular, we design a Dynamic Modality Quality Assessment (DMQA) module that employs learnable reference tokens to iteratively refine feature reliability assessment, enabling precise identification of degraded regions and providing quality guidance for subsequent fusion. Moreover, we develop an Orthogonal Constraint Normalization Fusion (OCNF) module that employs orthogonal constraints to preserve modality independence while dynamically adjusting fusion weights based on reliability scores, effectively suppressing unreliable feature propagation. Extensive experiments on the SpaceNet6-OTD and OGSOD-2.0 datasets demonstrate the superiority and effectiveness of QDFNet compared to state-of-the-art methods, particularly under partial modality corruption or missing data scenarios. --- ### Accounting Reasoning in Large Language Models: Concepts, Evaluation, and Empirical Analysis Authors: Jie Zhou, Xin Chen, Jie Zhang, Zhe Li Published: 2025-12-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.22443v2 Large language models (LLMs) are increasingly reshaping learning paradigms, cognitive processes, and research methodologies across diverse domains. As their adoption expands, effectively integrating LLMs into professional fields and clarifying their role in domain-specific applications has become a key challenge for enterprise digital transformation and broader societal development. In the accounting domain, successful integration requires a systematic understanding of LLMs' domain-specific reasoning capabilities. In this study, we introduce the concept of accounting reasoning and propose a set of evaluation criteria grounded in an analysis of the training data characteristics of representative GLM-series models. These criteria establish a foundation for studying accounting-oriented reasoning paradigms and provide benchmarks for assessing and improving model performance. Building on this framework, we evaluate several representative LLMs, including GLM-6B, GLM-130B, GLM-4, and GPT-4, across a range of accounting reasoning tasks. Our experimental results show that prompt engineering strategies can yield varying degrees of performance improvement across models, with GPT-4 demonstrating the strongest overall accounting reasoning capability. Nevertheless, the results indicate that current LLMs remain insufficient for real-world accounting applications. In particular, further optimization is required for deployment in enterprise-level accounting scenarios to fully realize the potential value of LLMs in this domain. --- ### HiFi-RAG: Hierarchical Content Filtering and Two-Pass Generation for Open-Domain RAG Authors: Cattalyya Nuengsigkapian Published: 2025-12-27 Categories: cs.CL, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2512.22442v1 Retrieval-Augmented Generation (RAG) in open-domain settings faces significant challenges regarding irrelevant information in retrieved documents and the alignment of generated answers with user intent. We present HiFi-RAG (Hierarchical Filtering RAG), the winning closed-source system in the Text-to-Text static evaluation of the MMU-RAGent NeurIPS 2025 Competition. Our approach moves beyond standard embedding-based retrieval via a multi-stage pipeline. We leverage the speed and cost-efficiency of Gemini 2.5 Flash (4-6x cheaper than Pro) for query formulation, hierarchical content filtering, and citation attribution, while reserving the reasoning capabilities of Gemini 2.5 Pro for final answer generation. On the MMU-RAGent validation set, our system outperformed the baseline, improving ROUGE-L to 0.274 (+19.6%) and DeBERTaScore to 0.677 (+6.2%). On Test2025, our custom dataset evaluating questions that require post-cutoff knowledge (post January 2025), HiFi-RAG outperforms the parametric baseline by 57.4% in ROUGE-L and 14.9% in DeBERTaScore. --- ### LECalib: Line-Based Event Camera Calibration Authors: Zibin Liu, Banglei Guan, Yang Shang, Zhenbao Yu, Yifei Bian, Qifeng Yu Published: 2025-12-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22441v1 Camera calibration is an essential prerequisite for event-based vision applications. Current event camera calibration methods typically involve using flashing patterns, reconstructing intensity images, and utilizing the features extracted from events. Existing methods are generally time-consuming and require manually placed calibration objects, which cannot meet the needs of rapidly changing scenarios. In this paper, we propose a line-based event camera calibration framework exploiting the geometric lines of commonly-encountered objects in man-made environments, e.g., doors, windows, boxes, etc. Different from previous methods, our method detects lines directly from event streams and leverages an event-line calibration model to generate the initial guess of camera parameters, which is suitable for both planar and non-planar lines. Then, a non-linear optimization is adopted to refine camera parameters. Both simulation and real-world experiments have demonstrated the feasibility and accuracy of our method, with validation performed on monocular and stereo event cameras. The source code is released at https://github.com/Zibin6/line_based_event_camera_calib. --- ### SuperiorGAT: Graph Attention Networks for Sparse LiDAR Point Cloud Reconstruction in Autonomous Systems Authors: Khalfalla Awedat, Mohamed Abidalrekab, Gurcan Comert, Mustafa Ayad Published: 2025-12-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.22439v3 LiDAR-based perception in autonomous systems is constrained by fixed vertical beam resolution and further compromised by beam dropout resulting from environmental occlusions. This paper introduces SuperiorGAT, a graph attention-based framework designed to reconstruct missing elevation information in sparse LiDAR point clouds. By modeling LiDAR scans as beam-aware graphs and incorporating gated residual fusion with feed-forward refinement, SuperiorGAT enables accurate reconstruction without increasing network depth. To evaluate performance, structured beam dropout is simulated by removing every fourth vertical scanning beam. Extensive experiments across diverse KITTI environments, including Person, Road, Campus, and City sequences, demonstrate that SuperiorGAT consistently achieves lower reconstruction error and improved geometric consistency compared to PointNet-based models and deeper GAT baselines. Qualitative X-Z projections further confirm the model's ability to preserve structural integrity with minimal vertical distortion. These results suggest that architectural refinement offers a computationally efficient method for improving LiDAR resolution without requiring additional sensor hardware. --- ### EmoCtrl: Controllable Emotional Image Content Generation Authors: Jingyuan Yang, Weibin Luo, Hui Huang Published: 2025-12-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22437v2 An image conveys meaning through both its visual content and emotional tone, jointly shaping human perception. We introduce Controllable Emotional Image Content Generation (C-EICG), which aims to generate images that remain faithful to a given content description while expressing a target emotion. Existing text-to-image models ensure content consistency but lack emotional awareness, whereas emotion-driven models generate affective results at the cost of content distortion. To address this gap, we propose EmoCtrl, supported by a dataset annotated with content, emotion, and affective prompts, bridging abstract emotions to visual cues. EmoCtrl incorporates textual and visual emotion enhancement modules that enrich affective expression via descriptive semantics and perceptual cues. To align with human preference, we further introduce an emotion-driven preference optimization with specifically designed emotion reward. Comprehensive experiments demonstrate that EmoCtrl achieves faithful content and expressive emotion control, outperforming existing methods. User studies confirm EmoCtrl's strong alignment with human preference. Moreover, EmoCtrl generalizes well to creative applications, further demonstrating the robustness and adaptability of the learned emotion tokens. --- ### AnalogSAGE: Self-evolving Analog Design Multi-Agents with Stratified Memory and Grounded Experience Authors: Zining Wang, Jian Gao, Weimin Fu, Xiaolong Guo, Xuan Zhang Published: 2025-12-27 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2512.22435v1 Analog circuit design remains a knowledge- and experience-intensive process that relies heavily on human intuition for topology generation and device parameter tuning. Existing LLM-based approaches typically depend on prompt-driven netlist generation or predefined topology templates, limiting their ability to satisfy complex specification requirements. We propose AnalogSAGE, an open-source self-evolving multi-agent framework that coordinates three-stage agent explorations through four stratified memory layers, enabling iterative refinement with simulation-grounded feedback. To support reproducibility and generality, we release the source code. Our benchmark spans ten specification-driven operational amplifier design problems of varying difficulty, enabling quantitative and cross-task comparison under identical conditions. Evaluated under the open-source SKY130 PDK with ngspice, AnalogSAGE achieves a 10$\times$ overall pass rate, a 48$\times$ Pass@1, and a 4$\times$ reduction in parameter search space compared with existing frameworks, demonstrating that stratified memory and grounded reasoning substantially enhance the reliability and autonomy of analog design automation in practice. --- ### Monadic Context Engineering Authors: Yifan Zhang, Yang Yuan, Mengdi Wang, Andrew Chi-Chih Yao Published: 2025-12-27 Categories: cs.AI, cs.CL, cs.FL arXiv: https://arxiv.org/abs/2512.22431v6 The proliferation of Large Language Models (LLMs) has catalyzed a shift towards autonomous agents capable of complex reasoning and tool use. However, current agent architectures are frequently constructed using imperative, ad hoc patterns. This results in brittle systems plagued by difficulties in state management, error handling, and concurrency. This paper introduces Monadic Context Engineering (MCE), a novel architectural paradigm leveraging the algebraic structures of Functors, Applicative Functors, and Monads to provide a formal foundation for agent design. MCE treats agent workflows as computational contexts where cross-cutting concerns, such as state propagation, short-circuiting error handling, and asynchronous execution, are managed intrinsically by the algebraic properties of the abstraction. We demonstrate how Monads enable robust sequential composition, how Applicatives provide a principled structure for parallel execution, and crucially, how Monad Transformers allow for the systematic composition of these capabilities. This layered approach enables developers to construct complex, resilient, and efficient AI agents from simple, independently verifiable components. We further extend this framework to describe Meta-Agents, which leverage MCE for generative orchestration, dynamically creating and managing sub-agent workflows through metaprogramming. --- ### Causality-Inspired Safe Residual Correction for Multivariate Time Series Authors: Jianxiang Xie, Yuncheng Hua, Mingyue Cheng, Flora Salim, Hao Xue Published: 2025-12-27 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.22428v2 While modern multivariate forecasters such as Transformers and GNNs achieve strong benchmark performance, they often suffer from systematic errors at specific variables or horizons and, critically, lack guarantees against performance degradation in deployment. Existing post-hoc residual correction methods attempt to fix these errors, but are inherently greedy: although they may improve average accuracy, they can also "help in the wrong way" by overcorrecting reliable predictions and causing local failures in unseen scenarios. To address this critical "safety gap," we propose CRC (Causality-inspired Safe Residual Correction), a plug-and-play framework explicitly designed to ensure non-degradation. CRC follows a divide-and-conquer philosophy: it employs a causality-inspired encoder to expose direction-aware structure by decoupling self- and cross-variable dynamics, and a hybrid corrector to model residual errors. Crucially, the correction process is governed by a strict four-fold safety mechanism that prevents harmful updates. Experiments across multiple datasets and forecasting backbones show that CRC consistently improves accuracy, while an in-depth ablation study confirms that its core safety mechanisms ensure exceptionally high non-degradation rates (NDR), making CRC a correction framework suited for safe and reliable deployment. --- ### Uncertainty-Aware Flow Field Reconstruction Using SVGP Kolmogorov-Arnold Networks Authors: Y. Sungtaek Ju Published: 2025-12-27 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2512.22426v1 Reconstructing time-resolved flow fields from temporally sparse velocimetry measurements is critical for characterizing many complex thermal-fluid systems. We introduce a machine learning framework for uncertainty-aware flow reconstruction using sparse variational Gaussian processes in the Kolmogorov-Arnold network topology (SVGP-KAN). This approach extends the classical foundations of Linear Stochastic Estimation (LSE) and Spectral Analysis Modal Methods (SAMM) while enabling principled epistemic uncertainty quantification. We perform a systematic comparison of our framework with the classical reconstruction methods as well as Kalman filtering. Using synthetic data from pulsed impingement jet flows, we assess performance across fractional PIV sampling rates ranging from 0.5% to 10%. Evaluation metrics include reconstruction error, generalization gap, structure preservation, and uncertainty calibration. Our SVGP-KAN methods achieve reconstruction accuracy comparable to established methods, while also providing well-calibrated uncertainty estimates that reliably indicate when and where predictions degrade. The results demonstrate a robust, data-driven framework for flow field reconstruction with meaningful uncertainty quantification and offer practical guidance for experimental design in periodic flows. --- ### FluenceFormer: Transformer-Driven Multi-Beam Fluence Map Regression for Radiotherapy Planning Authors: Ujunwa Mgboh, Rafi Ibn Sultan, Joshua Kim, Kundan Thind, Dongxiao Zhu Published: 2025-12-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.22425v2 Fluence map prediction is central to automated radiotherapy planning but remains an ill-posed inverse problem due to the complex relationship between volumetric anatomy and beam-intensity modulation. Convolutional methods in prior work often struggle to capture long-range dependencies, which can lead to structurally inconsistent or physically unrealizable plans. We introduce \textbf{FluenceFormer}, a backbone-agnostic transformer framework for direct, geometry-aware fluence regression. The model uses a unified two-stage design: Stage~1 predicts a global dose prior from anatomical inputs, and Stage~2 conditions this prior on explicit beam geometry to regress physically calibrated fluence maps. Central to the approach is the \textbf{Fluence-Aware Regression (FAR)} loss, a physics-informed objective that integrates voxel-level fidelity, gradient smoothness, structural consistency, and beam-wise energy conservation. We evaluate the generality of the framework across multiple transformer backbones, including Swin UNETR, UNETR, nnFormer, and MedFormer, using a prostate IMRT dataset. FluenceFormer with Swin UNETR achieves the strongest performance among the evaluated models and improves over existing benchmark CNN and single-stage methods, reducing Energy Error to $\mathbf{4.5\%}$ and yielding statistically significant gains in structural fidelity ($p < 0.05$). --- ### Bright 4B: Scaling Hyperspherical Learning for Segmentation in 3D Brightfield Microscopy Authors: Amil Khan, Matheus Palhares Viana, Suraj Mishra, B. S. Manjunath Published: 2025-12-27 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.22423v1 Label-free 3D brightfield microscopy offers a fast and noninvasive way to visualize cellular morphology, yet robust volumetric segmentation still typically depends on fluorescence or heavy post-processing. We address this gap by introducing Bright-4B, a 4 billion parameter foundation model that learns on the unit hypersphere to segment subcellular structures directly from 3D brightfield volumes. Bright-4B combines a hardware-aligned Native Sparse Attention mechanism (capturing local, coarse, and selected global context), depth-width residual HyperConnections that stabilize representation flow, and a soft Mixture-of-Experts for adaptive capacity. A plug-and-play anisotropic patch embed further respects confocal point-spread and axial thinning, enabling geometry-faithful 3D tokenization. The resulting model produces morphology-accurate segmentations of nuclei, mitochondria, and other organelles from brightfield stacks alone--without fluorescence, auxiliary channels, or handcrafted post-processing. Across multiple confocal datasets, Bright-4B preserves fine structural detail across depth and cell types, outperforming contemporary CNN and Transformer baselines. All code, pretrained weights, and models for downstream finetuning will be released to advance large-scale, label-free 3D cell mapping. --- ### Differentiable Inverse Modeling with Physics-Constrained Latent Diffusion for Heterogeneous Subsurface Parameter Fields Authors: Zihan Lin, QiZhi He Published: 2025-12-27 Categories: math.NA, cs.LG, physics.geo-ph arXiv: https://arxiv.org/abs/2512.22421v1 We present a latent diffusion-based differentiable inversion method (LD-DIM) for PDE-constrained inverse problems involving high-dimensional spatially distributed coefficients. LD-DIM couples a pretrained latent diffusion prior with an end-to-end differentiable numerical solver to reconstruct unknown heterogeneous parameter fields in a low-dimensional nonlinear manifold, improving numerical conditioning and enabling stable gradient-based optimization under sparse observations. The proposed framework integrates a latent diffusion model (LDM), trained in a compact latent space, with a differentiable finite-volume discretization of the forward PDE. Sensitivities are propagated through the discretization using adjoint-based gradients combined with reverse-mode automatic differentiation. Inversion is performed directly in latent space, which implicitly suppresses ill-conditioned degrees of freedom while preserving dominant structural modes, including sharp material interfaces. The effectiveness of LD-DIM is demonstrated using a representative inverse problem for flow in porous media, where heterogeneous conductivity fields are reconstructed from spatially sparse hydraulic head measurements. Numerical experiments assess convergence behavior and reconstruction quality for both Gaussian random fields and bimaterial coefficient distributions. The results show that LD-DIM achieves consistently improved numerical stability and reconstruction accuracy of both parameter fields and corresponding PDE solutions compared with physics-informed neural networks (PINNs) and physics-embedded variational autoencoder (VAE) baselines, while maintaining sharp discontinuities and reducing sensitivity to initialization. --- ### Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving Authors: Rui Li, Zhaoning Zhang, Libo Zhang, Huaimin Wang, Xiang Fu, Zhiquan Lai Published: 2025-12-27 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2512.22420v5 Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, memory-bound systems but degrades performance in high-load, compute-bound environments due to verification overhead. Existing speculative decoding methods use fixed lengths and cannot adapt to workload changes or decide when to stop speculation. The cost of restarting speculative inference also remains unquantified. Under high load, the benefit of speculation diminishes, while retaining the draft model reduces KV cache capacity, limiting batch size and degrading throughput. To overcome this, we propose Nightjar, a resource-aware adaptive speculative framework. It first adjusts to the request load by dynamically selecting the optimal speculative length for different batch sizes. Crucially, Nightjar proactively disables speculative decoding when the MAB planner determines that speculation is no longer beneficial, and during the disabled phase, offloads the draft model to the CPU only under GPU memory pressure. This reclaims memory for the KV cache, thereby facilitating larger batch sizes and maximizing overall system throughput. Experiments show that Nightjar achieves up to 14.76% higher throughput than standard speculative decoding and up to 20.18% lower latency in the main benchmark suite under dynamic request arrival rates for real-time LLM serving scenarios. --- ### Hallucination Detection and Evaluation of Large Language Model Authors: Chenggong Zhang, Haopeng Wang, Hexi Meng Published: 2025-12-27 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2512.22416v2 Hallucinations in Large Language Models (LLMs) pose a significant challenge, generating misleading or unverifiable content that undermines trust and reliability. Existing evaluation methods, such as KnowHalu, employ multi-stage verification but suffer from high computational costs. To address this, we integrate the Hughes Hallucination Evaluation Model (HHEM), a lightweight classification-based framework that operates independently of LLM-based judgments, significantly improving efficiency while maintaining high detection accuracy. We conduct a comparative analysis of hallucination detection methods across various LLMs, evaluating True Positive Rate (TPR), True Negative Rate (TNR), and Accuracy on question-answering (QA) and summarization tasks. Our results show that HHEM reduces evaluation time from 8 hours to 10 minutes, while HHEM with non-fabrication checking achieves the highest accuracy \(82.2\%\) and TPR \(78.9\%\). However, HHEM struggles with localized hallucinations in summarization tasks. To address this, we introduce segment-based retrieval, improving detection by verifying smaller text components. Additionally, our cumulative distribution function (CDF) analysis indicates that larger models (7B-9B parameters) generally exhibit fewer hallucinations, while intermediate-sized models show higher instability. These findings highlight the need for structured evaluation frameworks that balance computational efficiency with robust factual validation, enhancing the reliability of LLM-generated content. --- ### Emergence of Human to Robot Transfer in Vision-Language-Action Models Authors: Simar Kareer, Karl Pertsch, James Darpinian, Judy Hoffman, Danfei Xu, Sergey Levine, Chelsea Finn, Suraj Nair Published: 2025-12-27 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.22414v1 Vision-language-action (VLA) models can enable broad open world generalization, but require large and diverse datasets. It is appealing to consider whether some of this data can come from human videos, which cover diverse real-world situations and are easy to obtain. However, it is difficult to train VLAs with human videos alone, and establishing a mapping between humans and robots requires manual engineering and presents a major research challenge. Drawing inspiration from advances in large language models, where the ability to learn from diverse supervision emerges with scale, we ask whether a similar phenomenon holds for VLAs that incorporate human video data. We introduce a simple co-training recipe, and find that human-to-robot transfer emerges once the VLA is pre-trained on sufficient scenes, tasks, and embodiments. Our analysis suggests that this emergent capability arises because diverse pretraining produces embodiment-agnostic representations for human and robot data. We validate these findings through a series of experiments probing human to robot skill transfer and find that with sufficiently diverse robot pre-training our method can nearly double the performance on generalization settings seen only in human data. --- ### Measuring Stability Beyond Accuracy in Small Open-Source Medical Large Language Models for Pediatric Endocrinology Authors: Vanessa D'Amario, Randy Daniel, Alessandro Zanetti, Dhruv Edamadaka, Nitya Alaparthy, Joshua Tarkoff Published: 2025-12-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.11567v1 Small open-source medical large language models (LLMs) offer promising opportunities for low-resource deployment and broader accessibility. However, their evaluation is often limited to accuracy on medical multiple choice question (MCQ) benchmarks, and lacks evaluation of consistency, robustness, or reasoning behavior. We use MCQ coupled to human evaluation and clinical review to assess six small open-source medical LLMs (HuatuoGPT-o1 (Chen 2024), Diabetica-7B, Diabetica-o1 (Wei 2024), Meditron3-8B (Sallinen2025), MedFound-7B (Liu 2025), and ClinicaGPT-base-zh (Wang 2023)) in pediatric endocrinology. In deterministic settings, we examine the effect of prompt variation on models' output and self-assessment bias. In stochastic settings, we evaluate output variability and investigate the relationship between consistency and correctness. HuatuoGPT-o1-8B achieved the highest performance. The results show that high consistency across the model response is not an indicator of correctness, although HuatuoGPT-o1-8B showed the highest consistency rate. When tasked with selecting correct reasoning, both HuatuoGPT-o1-8B and Diabetica-o1 exhibit self-assessment bias and dependency on the order of the candidate explanations. Expert review of incorrect reasoning rationales identified a mix of clinically acceptable responses and clinical oversight. We further show that system-level perturbations, such as differences in CUDA builds, can yield statistically significant shifts in model output despite stable accuracy. This work demonstrates that small, semantically negligible prompt perturbations lead to divergent outputs, raising concerns about reproducibility of LLM-based evaluations and highlights the output variability under different stochastic regimes, emphasizing the need of a broader diagnostic framework to understand potential pitfalls in real-world clinical decision support scenarios. --- ### Safety boundary maintenance in consumer AI systems responding to pediatric health queries: a cross-platform benchmark evaluation under naturalistic and adversarially pressured conditions Authors: Vahideh Zolfaghari, Leila Mashhadi, Mitra Ahadi, Farzaneh Sedaghatkar, MohammadReza Kargozari Published: 2025-12-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.09721v2 Consumer artificial intelligence chatbots are now accessed by hundreds of millions of users seeking health information, yet systematic evaluation of their safety boundary maintenance under real-world caregiver pressure remains scarce. We evaluated PediatricSafetyBench-v2, a benchmark of 600 pediatrics health queries comprising 300 authentic caregiver queries sourced from the HealthCareMagic-100k-en physician consultation corpus and 300 matched adversarial variants incorporating six operationalized caregiver pressure patterns, across four consumer AI systems (GPT-4o-mini, Gemini-2.0-Flash, Claude-3.5-Haiku, and Llama-3.1-8B). Safety boundary maintenance was assessed using a validated five-component Safety Composite Score (maximum 15 points; safety-appropriate threshold of 10 or above), validated against independent human raters prior to full-corpus application (mean weighted kappa 0.76; Pearson r = 0.88). The overall safety-appropriate rate was 95.5%. Safety-oriented system prompt deployment improved safety-appropriate rates by 5.9 percentage points across all four models. Counter-intuitively, adversarial caregiver pressure was associated with higher rather than lower Safety Composite Score values for all four models across all ten topic categories and severity levels. False expertise claims were the most vulnerability-inducing pressure pattern, whereas emotional escalation was associated with the highest scores. Consumer AI systems maintain safety boundaries in the large majority of pediatrics health interactions. PediatricSafetyBench-v2 is publicly released for longitudinal safety monitoring. --- ### Uncertainty-Aware Dynamic Knowledge Graphs for Reliable Question Answering Authors: Yu Takahashi, Shun Takeuchi, Kexuan Xin, Guillaume Pelat, Yoshiaki Ikai, Junya Saito, Jonathan Vitale, Shlomo Berkovsky, Amin Beheshti Published: 2025-12-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.09720v1 Question answering (QA) systems are increasingly deployed across domains. However, their reliability is undermined when retrieved evidence is incomplete, noisy, or uncertain. Existing knowledge graph (KG) based QA frameworks typically represent facts as static and deterministic, failing to capture the evolving nature of information and the uncertainty inherent in reasoning. We present a demonstration of uncertainty-aware dynamic KGs, a framework that combines (i) dynamic construction of evolving KGs, (ii) confidence scoring and uncertainty-aware retrieval, and (iii) an interactive interface for reliable and interpretable QA. Our system highlights how uncertainty modeling can make QA more robust and transparent by enabling users to explore dynamic graphs, inspect confidence-annotated triples, and compare baseline versus confidence-aware answers. The target users of this demo are clinical data scientists and clinicians, and we instantiate the framework in healthcare: constructing personalized KGs from electronic health records, visualizing uncertainty across patient visits, and evaluating its impact on a mortality prediction task. This use case demonstrates the broader promise of uncertainty-aware dynamic KGs for enhancing QA reliability in high-stakes applications. --- ### Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models Authors: Hoyoon Byun, Youngjun Choi, Taero Kim, Sungrae Park, Kyungwoo Song Published: 2025-12-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.09719v3 Pre-Layer Normalization (Pre-LN) is the de facto choice for large language models (LLMs) and is crucial for stable pretraining and effective transfer learning. However, Pre-LN incurs repeated statistical-computation overhead and remains vulnerable to the curse of depth, where hidden-state magnitudes and variances grow as the number of layers increases, destabilizing training. Efficiency-oriented normalization-free methods such as Dynamic Tanh (DyT) improve throughput but remain fragile at depth. To jointly address stability and efficiency, we propose Bounded Hyperbolic Tanh (BHyT), a drop-in replacement for Pre-LN. BHyT combines a tanh nonlinearity with explicit, data-driven input bounding to keep activations within a non-saturating range. It prevents depth-wise growth in activation magnitude and variance and provides a theoretical stability guarantee. For efficiency, BHyT computes exact statistics once per block and replaces a second normalization with a lightweight variance approximation. Empirically, BHyT demonstrates improved stability and efficiency during pretraining, achieving an average of 1.6\% faster training and an average of 1.77\% higher token generation throughput compared to RMSNorm, while maintaining strong pretraining-only and post-SFT performance across language understanding and reasoning benchmarks\footnote{Code is available at: https://github.com/MLAI-Yonsei/BHyT}. --- ### StatLLaMA: Multi-Stage training for domain-optimized statistical large language models Authors: Jing-Yi Zeng, Guan-Hua Huang Published: 2025-12-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.09718v2 This study investigates how to efficiently build a domain-specialized large language model (LLM) for statistics using the lightweight LLaMA-3.2-3B family as the foundation model (FM). We systematically compare three multi-stage training pipelines--starting from a base FM with no instruction-following capability, a base FM augmented with post-hoc instruction tuning, and an instruction-tuned FM with strong general reasoning abilities--across continual pretraining, supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF) preference alignment, and downstream task fine-tuning (DTFT). Results show that pipelines beginning with a base FM fail to develop meaningful statistical reasoning, even after extensive instruction tuning, SFT, or RLHF alignment. In contrast, starting from LLaMA-3.2-3B-Instruct enables effective domain specialization. A comprehensive evaluation of SFT variants reveals clear trade-offs between domain expertise and general reasoning ability. We further demonstrate that direct preference optimization provides stable and effective RLHF preference alignment. Finally, we show that DTFT must be performed with extremely low intensity to avoid catastrophic forgetting in highly optimized models. The final model, StatLLaMA, achieves strong and balanced performance on benchmarks of mathematical reasoning, common-sense reasoning, and statistical expertise, offering a practical blueprint for developing resource-efficient statistical LLMs. The code is available at https://github.com/HuangDLab/StatLLaMA. --- ### NewsScope: Schema-Grounded Cross-Domain News Claim Extraction with Open Models Authors: Nidhi Pandya Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.08852v1 Automated news verification requires structured claim extraction, but existing approaches either lack schema compliance or generalize poorly across domains. This paper presents NewsScope, a cross-domain dataset, benchmark, and fine-tuned model for schema-grounded news claim extraction. The dataset contains 455 articles across politics, health, science/environment, and business, consisting of 395 in-domain articles and 60 out-of-source articles for generalization testing. LLaMA 3.1 8B was fine-tuned using LoRA on 315 training examples and evaluated on held-out in-domain (80 articles) and out-of-source (60 articles) test sets. Human evaluation on 400 claims shows NewsScope achieves 89.4% human-evaluated accuracy compared to GPT-4o-mini's 93.7% (p=0.07). NewsScope outperforms GPT-4o-mini on political claims (94.3% vs. 87.8%). A numeric grounding filter further improves accuracy to 91.6%, narrowing the gap to 2.1 percentage points. Inter-annotator agreement studies (160 claims) confirm labeling reliability (94.6% positive agreement on SUPPORTED judgments). The open-weight model enables offline deployment at approximately $15 on-demand compute (or $0 on free tiers). Code and benchmark are publicly released. --- ### Socio-technical aspects of Agentic AI Authors: Praveen Kumar Donta, Alaa Saleh, Ying Li, Shubham Vaishnav, Kai Fang, Hailin Feng, Yuchao Xia, Thippa Reddy Gadekallu, Qiyang Zhang, Xiaodan Shi, Ali Beikmohammadi, Sindri Magnússon et al. Published: 2025-12-26 Categories: cs.CY, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2601.06064v1 Agentic Artificial Intelligence (AI) represents a fundamental shift in the design of intelligent systems, characterized by interconnected components that collectively enable autonomous perception, reasoning, planning, action, and learning. Recent research on agentic AI has largely focused on technical foundations, including system architectures, reasoning and planning mechanisms, coordination strategies, and application-level performance across domains. However, the societal, ethical, economic, environmental, and governance implications of agentic AI remain weakly integrated into these technical treatments. This paper addresses this gap by presenting a socio-technical analysis of agentic AI that explicitly connects core technical components with societal context. We examine how architectural choices in perception, cognition, planning, execution, and memory introduce dependencies related to data governance, accountability, transparency, safety, and sustainability. To structure this analysis, we adopt the MAD-BAD-SAD construct as an analytical lens, capturing motivations, applications, and moral dilemmas (MAD); biases, accountability, and dangers (BAD); and societal impact, adoption, and design considerations (SAD). Using this lens, we analyze ethical considerations, implications, and challenges arising from contemporary agentic AI systems and assess their manifestation across emerging applications, including healthcare, education, industry, smart and sustainable cities, social services, communications and networking, and earth observation and satellite communications. The paper further identifies open challenges and suggests future research directions, framing agentic AI as an integrated socio-technical system whose behavior and impact are co-produced by algorithms, data, organizational practices, regulatory frameworks, and social norms. --- ### Beyond Interaction Effects: Two Logics for Studying Population Inequalities Authors: Adel Daoud Published: 2025-12-26 Categories: cs.CY, cs.AI, cs.LG, econ.GN, stat.ME arXiv: https://arxiv.org/abs/2601.04223v1 When sociologists and other social scientist ask whether the return to college differs by race and gender, they face a choice between two fundamentally different modes of inquiry. Traditional interaction models follow deductive logic: the researcher specifies which variables moderate effects and tests these hypotheses. Machine learning methods follow inductive logic: algorithms search across vast combinatorial spaces to discover patterns of heterogeneity. This article develops a framework for navigating between these approaches. We show that the choice between deduction and induction reflects a tradeoff between interpretability and flexibility, and we demonstrate through simulation when each approach excels. Our framework is particularly relevant for inequality research, where understanding how treatment effects vary across intersecting social subpopulation is substantively central. --- ### Pediatric Pneumonia Detection from Chest X-Rays:A Comparative Study of Transfer Learning and Custom CNNs Authors: Agniv Roy Choudhury Published: 2025-12-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.00837v1 Pneumonia is a leading cause of mortality in children under five, with over 700,000 deaths annually. Accurate diagnosis from chest X-rays is limited by radiologist availability and variability. Objective: This study compares custom CNNs trained from scratch with transfer learning (ResNet50, DenseNet121, EfficientNet-B0) for pediatric pneumonia detection, evaluating frozen-backbone and fine-tuning regimes. Methods: A dataset of 5,216 pediatric chest X-rays was split 80/10/10 for training, validation, and testing. Seven models were trained and assessed using accuracy, F1-score, and AUC. Grad-CAM visualizations provided explainability. Results: Fine-tuned ResNet50 achieved the best performance: 99.43\% accuracy, 99.61\% F1-score, and 99.93\% AUC, with only 3 misclassifications. Fine-tuning outperformed frozen-backbone models by 5.5 percentage points on average. Grad-CAM confirmed clinically relevant lung regions guided predictions. Conclusions: Transfer learning with fine-tuning substantially outperforms CNNs trained from scratch for pediatric pneumonia detection, showing near-perfect accuracy. This system has strong potential as a screening tool in resource-limited settings. Future work should validate these findings on multi-center and adult datasets. Keywords: Pneumonia detection, deep learning, transfer learning, CNN, chest X-ray, pediatric diagnosis, ResNet, DenseNet, EfficientNet, Grad-CAM. --- ### Intrinsic-Metric Physics-Informed Neural Networks (IM-PINN) for Reaction-Diffusion Dynamics on Complex Riemannian Manifolds Authors: Julian Evan Chrisnanto, Salsabila Rahma Alia, Nurfauzi Fadillah, Yulison Herry Chrisnanto Published: 2025-12-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.00834v3 Simulating nonlinear reaction-diffusion dynamics on complex, non-Euclidean manifolds remains a fundamental challenge in computational morphogenesis, constrained by high-fidelity mesh generation costs and symplectic drift in discrete time-stepping schemes. This study introduces the Intrinsic-Metric Physics-Informed Neural Network (IM-PINN), a mesh-free geometric deep learning framework that solves partial differential equations directly in the continuous parametric domain. By embedding the Riemannian metric tensor into the automatic differentiation graph, our architecture analytically reconstructs the Laplace-Beltrami operator, decoupling solution complexity from geometric discretization. We validate the framework on a "Stochastic Cloth" manifold with extreme Gaussian curvature fluctuations ($K \in (-2489, 3580)$), where traditional adaptive refinement fails to resolve anisotropic Turing instabilities. Using a dual-stream architecture with Fourier feature embeddings to mitigate spectral bias, the IM-PINN recovers the "splitting spot" and "labyrinthine" regimes of the Gray-Scott model. Benchmarking against the Surface Finite Element Method (SFEM) reveals superior physical rigor: the IM-PINN achieves global mass conservation error of $\mathcal{E}_{mass} \approx 0.157$ versus SFEM's $0.258$, acting as a thermodynamically consistent global solver that eliminates mass drift inherent in semi-implicit integration. The framework offers a memory-efficient, resolution-independent paradigm for simulating biological pattern formation on evolving surfaces, bridging differential geometry and physics-informed machine learning. --- ### Quantitative Rule-Based Strategy modeling in Classic Indian Rummy: A Metric Optimization Approach Authors: Purushottam Saha, Avirup Chakraborty, Sourish Sarkar, Subhamoy Maitra, Diganta Mukherjee, Tridib Mukherjee Published: 2025-12-26 Categories: cs.AI, cs.GT arXiv: https://arxiv.org/abs/2601.00024v1 The 13-card variant of Classic Indian Rummy is a sequential game of incomplete information that requires probabilistic reasoning and combinatorial decision-making. This paper proposes a rule-based framework for strategic play, driven by a new hand-evaluation metric termed MinDist. The metric modifies the MinScore metric by quantifying the edit distance between a hand and the nearest valid configuration, thereby capturing structural proximity to completion. We design a computationally efficient algorithm derived from the MinScore algorithm, leveraging dynamic pruning and pattern caching to exactly calculate this metric during play. Opponent hand-modeling is also incorporated within a two-player zero-sum simulation framework, and the resulting strategies are evaluated using statistical hypothesis testing. Empirical results show significant improvement in win rates for MinDist-based agents over traditional heuristics, providing a formal and interpretable step toward algorithmic Rummy strategy design. --- ### Coordinate Matrix Machine: A Human-level Concept Learning to Classify Very Similar Documents Authors: Amin Sadri, M Maruf Hossain Published: 2025-12-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.23749v2 Human-level concept learning argues that humans typically learn new concepts from a single example, whereas machine learning algorithms typically require hundreds of samples to learn a single concept. Our brain subconsciously identifies important features and learns more effectively. Contribution: In this paper, we present the Coordinate Matrix Machine (CM$^2$). This purpose-built small model augments human intelligence by learning document structures and using this information to classify documents. While modern "Red AI" trends rely on massive pre-training and energy-intensive GPU infrastructure, CM$^2$ is designed as a Green AI solution. It achieves human-level concept learning by identifying only the structural "important features" a human would consider, allowing it to classify very similar documents using only one sample per class. Advantage: Our algorithm outperforms traditional vectorizers and complex deep learning models that require larger datasets and significant compute. By focusing on structural coordinates rather than exhaustive semantic vectors, CM$^2$ offers: 1. High accuracy with minimal data (one-shot learning) 2. Geometric and structural intelligence 3. Green AI and environmental sustainability 4. Optimized for CPU-only environments 5. Inherent explainability (glass-box model) 6. Faster computation and low latency 7. Robustness against unbalanced classes 8. Economic viability 9. Generic, expandable, and extendable --- ### A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios Authors: Haley Rosso, Talea Mayo Published: 2025-12-26 Categories: cs.LG, math.PR, stat.ML arXiv: https://arxiv.org/abs/2512.23748v2 For complex simulation problems, inferring parameters often precludes the use of classical likelihood-based techniques due to intractable likelihoods. Simulation-based inference (SBI) methods offer a likelihood-free approach to directly learn posterior distributions $p(\bftheta \mid \xobs)$ from simulator outputs. Recently, diffusion models have emerged as promising tools for SBI, addressing limitations of earlier neural methods such as neural likelihood/posterior estimation and normalizing flows. This review examines diffusion-based SBI from first principles to applications, emphasizing robustness in three non-ideal data scenarios common to scientific computing: model misspecification (simulator-reality mismatch), unstructured or infinite-dimensional observations, and missing data. We synthesize mathematical foundations and survey eight methods addressing these challenges, such as conditional diffusion for irregular data, guided diffusion for prior adaptation, sequential and factorized approaches for efficiency, and consistency models for fast sampling. Throughout, we maintain consistent notation and emphasize conditions required for accurate posteriors. We conclude with open problems and applications to geophysical uncertainty quantification, where these challenges are acute. ---