# Research Papers — 2025-12 · bundle page 136 of 175 > Full-text markdown of papers #6751–6800 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/136 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/135.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/137.md) ### Zero Generalization Error Theorem for Random Interpolators via Algebraic Geometry Authors: Naoki Yoshida, Isao Ishikawa, Masaaki Imaizumi Published: 2025-12-06 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.06347v1 We theoretically demonstrate that the generalization error of interpolators for machine learning models under teacher-student settings becomes 0 once the number of training samples exceeds a certain threshold. Understanding the high generalization ability of large-scale models such as deep neural networks (DNNs) remains one of the central open problems in machine learning theory. While recent theoretical studies have attributed this phenomenon to the implicit bias of stochastic gradient descent (SGD) toward well-generalizing solutions, empirical evidences indicate that it primarily stems from properties of the model itself. Specifically, even randomly sampled interpolators, which are parameters that achieve zero training error, have been observed to generalize effectively. In this study, under a teacher-student framework, we prove that the generalization error of randomly sampled interpolators becomes exactly zero once the number of training samples exceeds a threshold determined by the geometric structure of the interpolator set in parameter space. As a proof technique, we leverage tools from algebraic geometry to mathematically characterize this geometric structure. --- ### CLUENet: Cluster Attention Makes Neural Networks Have Eyes Authors: Xiangshuai Song, Jun-Jie Huang, Tianrui Liu, Ke Liang, Chang Tang Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06345v2 Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing challenges for tasks requiring high model transparency. Clustering paradigms offer promising interpretability and flexible semantic modeling, but suffer from limited accuracy, low efficiency, and gradient vanishing during training. To address these issues, we propose CLUster attEntion Network (CLUENet), an transparent deep architecture for visual semantic understanding. We propose three key innovations include (i) a Global Soft Aggregation and Hard Assignment with a Temperature-Scaled Cosin Attention and gated residual connections for enhanced local modeling, (ii) inter-block Hard and Shared Feature Dispatching, and (iii) an improved cluster pooling strategy. These enhancements significantly improve both classification performance and visual interpretability. Experiments on CIFAR-100 and Mini-ImageNet demonstrate that CLUENet outperforms existing clustering methods and mainstream visual models, offering a compelling balance of accuracy, efficiency, and transparency. --- ### SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitrates Authors: Kaile Wang, Lijun He, Haisheng Fu, Haixia Bi, Fan Li Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06344v2 Generative image compression has recently shown impressive perceptual quality, but often suffers from semantic inconsistency at ultra-low bitrates (bpp < 0.05), limiting its reliable deployment in bandwidth-constrained scenarios such as 6G semantic communications. This inconsistency stems from incomplete guidance information, which introduces semantic ambiguity into the generation process and may lead to natural-looking but source-inconsistent content. In this work, we propose a Semantic-Disambiguation-Guided Generative Image Compression (SDGIC) framework to constrain diffusion-based reconstruction at ultra-low bitrates. Specifically, SDGIC compresses the source image into three compact and complementary guidance streams: a concise text caption for global semantics, a highly compressed image (HCI) for dense visual evidence, and Reconstruction-Aware Semantic Residual Tokens (RSRTs) for reconstruction-relevant residual semantics that remain ambiguous under the text caption and HCI conditions. The RSRTs are directly optimized toward the downstream denoising objective, enabling them to provide source-specific semantic constraints for disambiguating diffusion-based reconstruction. To inject these three guidance streams into the generation process effectively, we design a Dual-Path Conditioned Diffusion Decoder (DPCD), which uses cross-attention for semantic conditions and ControlNet residuals for dense visual guidance. Extensive experiments demonstrate that SDGIC improves semantic consistency at ultra-low bitrates while maintaining favorable perceptual quality, with a 23.4% reduction in AFINE on the CLIC2020 dataset. --- ### When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models Authors: Tong Xie, Andrew Bai, Yuanhao Ban, Yunqi Hong, Haoyu Li, Cho-Jui Hsieh Published: 2025-12-06 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.06343v3 Reward models are central to Large Language Model (LLM) alignment within the framework of RLHF. The standard objective used in reward modeling is the Bradley-Terry (BT) loss, which learns from pairwise data consisting of chosen and rejected responses. In this work, we analyze the per-sample gradient of BT-loss and show spurious learning signals due to representation distance. In particular, BT gradient norm scales with two distinct components: (1) prediction error, reflected by the difference in predicted rewards between chosen and rejected responses, and critically, (2) representation distance between the pair measured in the output space of the final layer. While the first term captures the intended training signal, the second term can significantly impact the update magnitude and misalign learning. Specifically, pairs with small representation distance often receive vanishingly weak updates, even when misranked, while pairs with large distance receive disproportionately strong updates. This leads to gradients from large-distance pairs to overshadow those from small-distance pairs, where fine-grained distinctions are especially important. To overcome this limitation, we propose NormBT, an adaptive pair-wise normalization scheme that rescales updates to balance representation-driven effects and focuses learning signals on prediction error. NormBT is a lightweight, drop-in modification to BT loss with negligible overhead. Across various LLM backbones and datasets, NormBT improves reward model performance consistently, with notable gains of over 5% on the Reasoning category of RewardBench, which contains numerous fine-grained pairs. --- ### Interpretive Efficiency: Information-Geometric Foundations of Data Usefulness Authors: Ronald Katende Published: 2025-12-06 Categories: cs.LG, cs.IR, cs.IT arXiv: https://arxiv.org/abs/2512.06341v1 Interpretability is central to trustworthy machine learning, yet existing metrics rarely quantify how effectively data support an interpretive representation. We propose Interpretive Efficiency, a normalized, task-aware functional that measures the fraction of task-relevant information transmitted through an interpretive channel. The definition is grounded in five axioms ensuring boundedness, Blackwell-style monotonicity, data-processing stability, admissible invariance, and asymptotic consistency. We relate the functional to mutual information and derive a local Fisher-geometric expansion, then establish asymptotic and finite-sample estimation guarantees using standard empirical-process tools. Experiments on controlled image and signal tasks demonstrate that the measure recovers theoretical orderings, exposes representational redundancy masked by accuracy, and correlates with robustness, making it a practical, theory-backed diagnostic for representation design. --- ### DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization Authors: Xuan Xie, Xuan Wang, Wenjie Wang, Shuai Chen, Wei Lin Published: 2025-12-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.06337v2 The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift from superficial instruction following to rigorous long-horizon reasoning. While Group Relative Policy Optimization (GRPO) has emerged as a pivotal mechanism for eliciting such post-training reasoning capabilities due to its exceptional performance, it remains plagued by significant training instability and poor sample efficiency. We theoretically identify the root cause of these issues as the lack of distinctiveness within on-policy rollouts: for routine queries, highly homogeneous samples induce destructive gradient conflicts; whereas for hard queries, the scarcity of valid positive samples results in ineffective optimization. To bridge this gap, we propose Distinctiveness-aware Group Relative Policy Optimization (DaGRPO). DaGRPO incorporates two core mechanisms: (1) Sequence-level Gradient Rectification, which utilizes fine-grained scoring to dynamically mask sample pairs with low distinctiveness, thereby eradicating gradient conflicts at the source; and (2) Off-policy Data Augmentation, which introduces high-quality anchors to recover training signals for challenging tasks. Extensive experiments across 9 mathematical reasoning and out-of-distribution (OOD) generalization benchmarks demonstrate that DaGRPO significantly surpasses existing SFT, GRPO, and hybrid baselines, achieving new state-of-the-art performance (e.g., a +4.7% average accuracy gain on math benchmarks). Furthermore, in-depth analysis confirms that DaGRPO effectively mitigates gradient explosion and accelerates the emergence of long-chain reasoning capabilities. --- ### CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworks Authors: Jeffrey Gu, Minkyu Jeon, Ambri Ma, Serena Yeung-Levy, Ellen D. Zhong Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06332v2 Cryo-electron microscopy (cryo-EM) is an indispensable technique for determining the 3D structures of dynamic biomolecular complexes. While typically applied to image a single molecular species, cryo-EM has the potential for structure determination of many targets simultaneously in a high-throughput fashion. However, existing methods typically focus on modeling conformational heterogeneity within a single or a few structures and are not designed to resolve compositional heterogeneity arising from mixtures of many distinct molecular species. To address this challenge, we propose CryoHype, a transformer-based hypernetwork for cryo-EM reconstruction that dynamically adjusts the weights of an implicit neural representation. Using CryoHype, we achieve state-of-the-art results on a challenging benchmark dataset containing 100 structures. We further demonstrate that CryoHype scales to the reconstruction of 1,000 distinct structures from unlabeled cryo-EM images in the fixed-pose setting. --- ### S2WMamba: A Wavelet-Assisted Mamba-Based Dual-Branch Network For Pansharpening Authors: Haoyu Zhang, Junhan Luo, Yugang Cao, Jie Huang, Liangjian-Deng Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06330v3 Pansharpening fuses a high-resolution panchromatic (PAN) image with a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral (HRMS) image. A key difficulty is that jointly processing PAN and MS features often entangles spatial detail enhancement with spectral fidelity. To address this feature entanglement, we propose S2WMamba, a framework that explicitly disentangles modality-specific frequency information for highly controlled crossmodal interaction. Concretely, unlike global frequency transforms, a localized 2D Haar DWT is applied to the PAN image to precisely isolate spatial edges and textures. Concurrently, a novel channel-wise 1D Haar DWT treats each pixel's spectrum as a 1D signal, isolating the shared spectral base from band-specific variations to strictly limit spectral distortion. The resulting Spectral branch injects wavelet-extracted spatial details into MS features, while the Spatial branch refines PAN features using spectra from the DWT1D process. To overcome inadequate frequency fusion, the two branches exchange information via Mambabased cross-modulation, which explicitly models long-range dependencies across these decoupled sub-bands with linear complexity. On WV3, GF2, and QB datasets, S2WMamba matches or surpasses recent strong baselines (FusionMamba, CANNet, U2Net, PanNet), improving PSNR by up to 0.23 dB and reaching an HQNR of 0.956 on full-resolution WV3. Extensive ablations justify the modality-specific DWT placement and the parallel dual-branch architecture. --- ### ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models Authors: Jiahao Li, Yusheng Luo, Yunzhong Lou, Xiangdong Zhou Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06328v1 We present ReCAD, a reinforcement learning (RL) framework that bootstraps pretrained large models (PLMs) to generate precise parametric computer-aided design (CAD) models from multimodal inputs by leveraging their inherent generative capabilities. With just access to simple functional interfaces (e.g., point coordinates), our approach enables the emergence of complex CAD operations (e.g., pattern replication and mirror). This stands in contrast to previous methods, which typically rely on knowledge injected through supervised fine-tuning (SFT), offer limited support for editability, and fail to exploit the strong generative priors of PLMs. Specifically, the ReCAD framework begins by fine-tuning vision-language models (VLMs) to equip them with basic CAD model generation capabilities, where we rewrite CAD scripts into parameterized code that is leveraged to generate accurate textual descriptions for supervision. Then, we propose a novel RL strategy that incorporates parameterized code as guidance to enhance the model's reasoning on challenging questions. Furthermore, we employ a hierarchical primitive learning process to progressively teach structured and compositional skills under a unified reward function that ensures both geometric accuracy and semantic fidelity. ReCAD sets a new state-of-the-art in both text-to-CAD and image-to-CAD tasks, significantly improving geometric accuracy across in-distribution and out-of-distribution settings. In the image-to-CAD task, for instance, it reduces the mean Chamfer Distance from 73.47 to 29.61 (in-distribution) and from 272.06 to 80.23 (out-of-distribution), outperforming existing baselines by a substantial margin. --- ### Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation Authors: Haoxian Zhou, Chuanzhi Xu, Langyi Chen, Pengfei Ye, Haodong Chen, Yuk Ying Chung, Qiang Qu Published: 2025-12-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06306v2 Human pose estimation focuses on predicting body keypoints to analyze human motion. Currently, most pose estimation tasks rely on conventional RGB cameras. In contrast, event cameras provide high temporal resolution and low latency, enabling robust estimation under challenging conditions and opening up new possibilities for pose estimation. However, most existing methods convert event streams into dense event frames, which adds extra computation and sacrifices the high temporal resolution of the event signal. In this work, we aim to exploit the spatiotemporal properties of event streams based on point cloud-based framework, designed to enhance human pose estimation performance while maintaining computational efficiency. We design Event Temporal Slicing Convolution module to capture short-term dependencies across event slices, and combine it with Event Slice Sequencing module for structured temporal modeling. We further propose an edge-enhanced point cloud-based event representation to enhance spatial edge information under sparse event conditions to further improve performance. Experiments on the DHP19 dataset show our proposed method consistently improves performance across three representative point cloud backbones: PointNet, DGCNN, and Point Transformer, with an average MPJPE reduction of 4%. --- ### Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulation Authors: Xining Song, Zhihua Wei, Rui Wang, Haixiao Hu, Yanxiang Chen, Meng Han Published: 2025-12-06 Categories: eess.AS, cs.AI, cs.CR, cs.SD arXiv: https://arxiv.org/abs/2512.06304v1 Identity, accent, style, and emotions are essential components of human speech. Voice conversion (VC) techniques process the speech signals of two input speakers and other modalities of auxiliary information such as prompts and emotion tags. It changes para-linguistic features from one to another, while maintaining linguistic contents. Recently, VC models have made rapid advancements in both generation quality and personalization capabilities. These developments have attracted considerable attention for diverse applications, including privacy preservation, voice-print reproduction for the deceased, and dysarthric speech recovery. However, these models only learn non-robust features due to the clean training data. Subsequently, it results in unsatisfactory performances when dealing with degraded input speech in real-world scenarios, including additional noise, reverberation, adversarial attacks, or even minor perturbation. Hence, it demands robust deployments, especially in real-world settings. Although latest researches attempt to find potential attacks and countermeasures for VC systems, there remains a significant gap in the comprehensive understanding of how robust the VC model is under input manipulation. here also raises many questions: For instance, to what extent do different forms of input degradation attacks alter the expected output of VC models? Is there potential for optimizing these attack and defense strategies? To answer these questions, we classify existing attack and defense methods from the perspective of input manipulation and evaluate the impact of degraded input speech across four dimensions, including intelligibility, naturalness, timbre similarity, and subjective perception. Finally, we outline open issues and future directions. --- ### Multimodal Graph Neural Networks for Prognostic Modeling of Brain Network Reorganization Authors: Preksha Girish, Rachana Mysore, Kiran K. N., Hiranmayee R., Shipra Prashanth, Shrey Kumar Published: 2025-12-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06303v2 Understanding the dynamic reorganization of brain networks is critical for predicting cognitive decline, neurological progression, and individual variability in clinical outcomes. This work proposes a multimodal graph neural network framework that integrates structural MRI, diffusion tensor imaging, and functional MRI to model spatiotemporal brain network reorganization. Brain regions are represented as nodes and structural and functional connectivity as edges, forming longitudinal brain graphs for each subject. Temporal evolution is captured via fractional stochastic differential operators embedded within graph-based recurrent networks, enabling the modeling of long-term dependencies and stochastic fluctuations in network dynamics. Attention mechanisms fuse multimodal information and generate interpretable biomarkers, including network energy entropy, graph curvature, fractional memory indices, and modality-specific attention scores. These biomarkers are combined into a composite prognostic index to quantify individual risk of network instability or cognitive decline. Experiments on longitudinal neuroimaging datasets demonstrate both predictive accuracy and interpretability. The results highlight the potential of mathematically rigorous, multimodal graph-based approaches for deriving clinically meaningful biomarkers from existing imaging data without requiring new data collection. --- ### Chemistry Integrated Language Model using Hierarchical Molecular Representation for Polymer Informatics Authors: Jihun Ahn, Gabriella Pasya Irianti, Vikram Thapar, Su-Mi Hur Published: 2025-12-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.06301v1 Machine learning has transformed material discovery for inorganic compounds and small molecules, yet polymers remain largely inaccessible to these methods. While data scarcity is often cited as the primary bottleneck, we demonstrate that strategic molecular representations can overcome this limitation. We introduce CI-LLM (Chemically Informed Language Model), a framework combining HAPPY (Hierarchically Abstracted rePeat unit of PolYmer), which encodes chemical substructures as tokens, with numerical descriptors within transformer architectures. For property prediction, De$^3$BERTa, our descriptor-enriched encoder, achieves 3.5x faster inference than SMILES-based models with improved accuracy ($R^2$ score gains of 0.9-4.1 percent across four properties), while providing interpretable structure-property insights at the subgroup level. For inverse design, our GPT-based generator produces polymers with targeted properties, achieving 100 percent scaffold retention and successful multi-property optimization for negatively correlated objectives. This comprehensive framework demonstrates both forward prediction and inverse design capabilities, showcasing how strategic molecular representation advances machine learning applications in polymer science. --- ### Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks Authors: Luca Di Carlo, Chase Goddard, David J. Schwab Published: 2025-12-06 Categories: cs.LG, cond-mat.dis-nn, cond-mat.stat-mech, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2512.06297v2 Modern neural networks exhibit a striking property: basins of attraction in the loss landscape are often connected by low-loss paths, yet optimization dynamics generally remain confined to a single convex basin and rarely explore intermediate points. We resolve this paradox by identifying entropic barriers arising from the interplay between curvature variations along these paths and noise in optimization dynamics. Empirically, we find that curvature systematically rises away from minima, producing effective forces that bias noisy dynamics back toward the endpoints - even when the loss remains nearly flat. These barriers persist longer than energetic barriers, shaping the late-time localization of solutions in parameter space. Our results highlight the role of curvature-induced entropic forces in governing both connectivity and confinement in deep learning landscapes. --- ### How Sharp and Bias-Robust is a Model? Dual Evaluation Perspectives on Knowledge Graph Completion Authors: Sooho Moon, Yunyong Ko Published: 2025-12-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.06296v1 Knowledge graph completion (KGC) aims to predict missing facts from the observed KG. While a number of KGC models have been studied, the evaluation of KGC still remain underexplored. In this paper, we observe that existing metrics overlook two key perspectives for KGC evaluation: (A1) predictive sharpness -- the degree of strictness in evaluating an individual prediction, and (A2) popularity-bias robustness -- the ability to predict low-popularity entities. Toward reflecting both perspectives, we propose a novel evaluation framework (PROBE), which consists of a rank transformer (RT) estimating the score of each prediction based on a required level of predictive sharpness and a rank aggregator (RA) aggregating all the scores in a popularity-aware manner. Experiments on real-world KGs reveal that existing metrics tend to over- or under-estimate the accuracy of KGC models, whereas PROBE yields a comprehensive understanding of KGC models and reliable evaluation results. --- ### Interpretable Neural Approximation of Stochastic Reaction Dynamics with Guaranteed Reliability Authors: Quentin Badolle, Arthur Theuer, Zhou Fang, Ankit Gupta, Mustafa Khammash Published: 2025-12-06 Categories: q-bio.MN, cs.LG, math.PR, q-bio.QM, stat.ML arXiv: https://arxiv.org/abs/2512.06294v1 Stochastic Reaction Networks (SRNs) are a fundamental modeling framework for systems ranging from chemical kinetics and epidemiology to ecological and synthetic biological processes. A central computational challenge is the estimation of expected outputs across initial conditions and times, a task that is rarely solvable analytically and becomes computationally prohibitive with current methods such as Finite State Projection or the Stochastic Simulation Algorithm. Existing deep learning approaches offer empirical scalability, but provide neither interpretability nor reliability guarantees, limiting their use in scientific analysis and in applications where model outputs inform real-world decisions. Here we introduce DeepSKA, a neural framework that jointly achieves interpretability, guaranteed reliability, and substantial computational gains. DeepSKA yields mathematically transparent representations that generalise across states, times, and output functions, and it integrates this structure with a small number of stochastic simulations to produce unbiased, provably convergent, and dramatically lower-variance estimates than classical Monte Carlo. We demonstrate these capabilities across nine SRNs, including nonlinear and non-mass-action models with up to ten species, where DeepSKA delivers accurate predictions and orders-of-magnitude efficiency improvements. This interpretable and reliable neural framework offers a principled foundation for developing analogous methods for other Markovian systems, including stochastic differential equations. --- ### Importance-aware Topic Modeling for Discovering Public Transit Risk from Noisy Social Media Authors: Fatima Ashraf, Muhammad Ayub Sabir, Jiaxin Deng, Junbiao Pang, Haitao Yu Published: 2025-12-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06293v1 Urban transit agencies increasingly turn to social media to monitor emerging service risks such as crowding, delays, and safety incidents, yet the signals of concern are sparse, short, and easily drowned by routine chatter. We address this challenge by jointly modeling linguistic interactions and user influence. First, we construct an influence-weighted keyword co-occurrence graph from cleaned posts so that socially impactful posts contributes proportionally to the underlying evidence. The core of our framework is a Poisson Deconvolution Factorization (PDF) that decomposes this graph into a low-rank topical structure and topic-localized residual interactions, producing an interpretable topic--keyword basis together with topic importance scores. A decorrelation regularizer \emph{promotes} distinct topics, and a lightweight optimization procedure ensures stable convergence under nonnegativity and normalization constraints. Finally, the number of topics is selected through a coherence-driven sweep that evaluates the quality and distinctness of the learned topics. On large-scale social streams, the proposed model achieves state-of-the-art topic coherence and strong diversity compared with leading baselines. The code and dataset are publicly available at https://github.com/pangjunbiao/Topic-Modeling_ITS.git --- ### StrokeNet: Unveiling How to Learn Fine-Grained Interactions in Online Handwritten Stroke Classification Authors: Yiheng Huang, Shuang She, Zewei Wei, Jianmin Lin, Ming Yang, Wenyin Liu Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06290v1 Stroke classification remains challenging due to variations in writing style, ambiguous content, and dynamic writing positions. The core challenge in stroke classification is modeling the semantic relationships between strokes. Our observations indicate that stroke interactions are typically localized, making it difficult for existing deep learning methods to capture such fine-grained relationships. Although viewing strokes from a point-level perspective can address this issue, it introduces redundancy. However, by selecting reference points and using their sequential order to represent strokes in a fine-grained manner, this problem can be effectively solved. This insight inspired StrokeNet, a novel network architecture encoding strokes as reference pair representations (points + feature vectors), where reference points enable spatial queries and features mediate interaction modeling. Specifically, we dynamically select reference points for each stroke and sequence them, employing an Inline Sequence Attention (ISA) module to construct contextual features. To capture spatial feature interactions, we devised a Cross-Ellipse Query (CEQ) mechanism that clusters reference points and extracts features across varying spatial scales. Finally, a joint optimization framework simultaneously predicts stroke categories via reference points regression and adjacent stroke semantic transition modeling through an Auxiliary Branch (Aux-Branch). Experimental results show that our method achieves state-of-the-art performance on multiple public online handwritten datasets. Notably, on the CASIA-onDo dataset, the accuracy improves from 93.81$\%$ to 95.54$\%$, demonstrating the effectiveness and robustness of our approach. --- ### Theoretical Compression Bounds for Wide Multilayer Perceptrons Authors: Houssam El Cheairi, David Gamarnik, Rahul Mazumder Published: 2025-12-06 Categories: cs.LG, math.ST arXiv: https://arxiv.org/abs/2512.06288v1 Pruning and quantization techniques have been broadly successful in reducing the number of parameters needed for large neural networks, yet theoretical justification for their empirical success falls short. We consider a randomized greedy compression algorithm for pruning and quantization post-training and use it to rigorously show the existence of pruned/quantized subnetworks of multilayer perceptrons (MLPs) with competitive performance. We further extend our results to structured pruning of MLPs and convolutional neural networks (CNNs), thus providing a unified analysis of pruning in wide networks. Our results are free of data assumptions, and showcase a tradeoff between compressibility and network width. The algorithm we consider bears some similarities with Optimal Brain Damage (OBD) and can be viewed as a post-training randomized version of it. The theoretical results we derive bridge the gap between theory and application for pruning/quantization, and provide a justification for the empirical success of compression in wide multilayer perceptrons. --- ### A Sleep Monitoring System Based on Audio, Video and Depth Information Authors: Lyn Chao-ling Chen, Kuan-Wen Chen, Yi-Ping Hung Published: 2025-12-06 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2512.06282v1 For quantitative evaluation of sleep disturbances, a noninvasive monitoring system is developed by introducing an event-based method. We observe sleeping in home context and classify the sleep disturbances into three types of events: motion events, light-on/off events and noise events. A device with an infrared depth sensor, a RGB camera, and a four-microphone array is used in sleep monitoring in an environment with barely light sources. One background model is established in depth signals for measuring magnitude of movements. Because depth signals cannot observe lighting changes, another background model is established in color images for measuring magnitude of lighting effects. An event detection algorithm is used to detect occurrences of events from the processed data of the three types of sensors. The system was tested in sleep condition and the experiment result validates the system reliability. --- ### Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models Authors: Hengzhuang Li, Xinsong Zhang, Qiming Peng, Bin Luo, Han Hu, Dengyang Jiang, Han-Jia Ye, Teng Zhang, Hai Jin Published: 2025-12-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06281v1 Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in multimodal tasks. Despite their impressive performance, MLLMs suffer from the modality imbalance issue, where visual information is often underutilized compared to textual representations in deeper layers, leading to degraded visual performance or hallucinations. This issue stems from the predominant reliance on next-text-token-prediction during training, which fails to provide direct visual supervisory signals, resulting in progressive homogenization of visual representations throughout the layers. To this end, we propose Latent Visual Reconstruction (LaVer), a novel training framework that facilitates MLLMs in learning more discriminative visual representations via masked image modeling in the joint latent semantic space of LLM. Our method offers direct visual activation to MLLMs, which exhibit increased visual attention allocation, indicating enhanced utilization of visual information. Extensive experiments across diverse benchmarks prove the superiority of our approach in various scenarios, especially those requiring dense visual capabilities. Code of LaVer is available at https://github.com/Fir-lat/LaVer. --- ### RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Authors: Tianyi Gao, Hao Li, Han Fang, Xin Wei, Xiaodong Dong, Hongbo Sun, Ye Yuan, Zhongjiang He, Jinglin Xu, Jingmin Xin, Hao Sun Published: 2025-12-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06276v3 Referring Expression Comprehension (REC) is a vision-language task that localizes a specific image region based on a textual description. Existing REC benchmarks primarily evaluate perceptual capabilities and lack interpretable scoring mechanisms, which cannot reveal the grounding capability of Multi-modal Large Language Model (MLLM) across different cognitive abilities. To address this limitation, we introduce RefBench-PRO, a comprehensive REC benchmark, which decomposes referring expressions into two core dimensions, i.e., perception and reasoning, and further subdivides them into six progressively challenging tasks, such as attribute, position, interaction, commonsense, relation and reject. We also develop a fully automated data-generation pipeline that produces diverse referring expressions across these six sub-dimensions. Furthermore, We propose Ref-R1, an RL-based learning scheme, which incorporates Dynamic IoU-based GRPO to improve localization accuracy under increasingly complex reasoning conditions, establishing a stronger baseline for REC. Extensive experiments demonstrate that our RefBench-PRO enables interpretable evaluation of MLLM on referring expression comprehension, presenting greater challenges in both perception and reasoning. --- ### FacePhys: State of the Heart Learning Authors: Kegang Wang, Jiankai Tang, Yuntao Wang, Xin Liu, Yuxuan Fan, Jiatong Ji, Yuanchun Shi, Daniel McDuff Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06275v1 Vital sign measurement using cameras presents opportunities for comfortable, ubiquitous health monitoring. Remote photoplethysmography (rPPG), a foundational technology, enables cardiac measurement through minute changes in light reflected from the skin. However, practical deployment is limited by the computational constraints of performing analysis on front-end devices and the accuracy degradation of transmitting data through compressive channels that reduce signal quality. We propose a memory efficient rPPG algorithm - \emph{FacePhys} - built on temporal-spatial state space duality, which resolves the trilemma of model scalability, cross-dataset generalization, and real-time operation. Leveraging a transferable heart state, FacePhys captures subtle periodic variations across video frames while maintaining a minimal computational overhead, enabling training on extended video sequences and supporting low-latency inference. FacePhys establishes a new state-of-the-art, with a substantial 49\% reduction in error. Our solution enables real-time inference with a memory footprint of 3.6 MB and per-frame latency of 9.46 ms -- surpassing existing methods by 83\% to 99\%. These results translate into reliable real-time performance in practical deployments, and a live demo is available at https://www.facephys.com/. --- ### Networked Restless Multi-Arm Bandits with Reinforcement Learning Authors: Hanmo Zhang, Zenghui Sun, Kai Wang Published: 2025-12-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.06274v1 Restless Multi-Armed Bandits (RMABs) are a powerful framework for sequential decision-making, widely applied in resource allocation and intervention optimization challenges in public health. However, traditional RMABs assume independence among arms, limiting their ability to account for interactions between individuals that can be common and significant in a real-world environment. This paper introduces Networked RMAB, a novel framework that integrates the RMAB model with the independent cascade model to capture interactions between arms in networked environments. We define the Bellman equation for networked RMAB and present its computational challenge due to exponentially large action and state spaces. To resolve the computational challenge, we establish the submodularity of Bellman equation and apply the hill-climbing algorithm to achieve a $1-\frac{1}{e}$ approximation guarantee in Bellman updates. Lastly, we prove that the approximate Bellman updates are guaranteed to converge by a modified contraction analysis. We experimentally verify these results by developing an efficient Q-learning algorithm tailored to the networked setting. Experimental results on real-world graph data demonstrate that our Q-learning approach outperforms both $k$-step look-ahead and network-blind approaches, highlighting the importance of capturing and leveraging network effects where they exist. --- ### Contextual Strongly Convex Simulation Optimization: Optimize then Predict with Inexact Solutions Authors: Nifei Lin, Heng Luo, L. Jeff Hong Published: 2025-12-06 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.06270v2 In this work, we study contextual strongly convex simulation optimization and adopt an "optimize then predict" (OTP) approach for real-time decision making. In the offline stage, simulation optimization is conducted across a set of covariates to approximate the optimal-solution function; in the online stage, decisions are obtained by evaluating this approximation at the observed covariate. The central theoretical challenge is to understand how the inexactness of solutions generated by simulation-optimization algorithms affects the optimality gap, which is overlooked in existing studies. To address this, we develop a unified analysis framework that explicitly accounts for both solution bias and variance. Using Polyak-Ruppert averaging SGD as an illustrative simulation-optimization algorithm, we analyze the optimality gap of OTP under four representative smoothing techniques: $k$ nearest neighbor, kernel smoothing, linear regression, and kernel ridge regression. We establish convergence rates, derive the optimal allocation of the computational budget $Γ$ between the number of design covariates and the per-covariate simulation effort, and demonstrate the convergence rate can approximately achieve $Γ^{-1}$ under appropriate smoothing technique and sample-allocation rule. Finally, through a numerical study, we validate the theoretical findings and demonstrate the effectiveness and practical value of the proposed approach. --- ### TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splatting Authors: Quan Tran, Tuan Dang Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06269v1 3D Gaussian Splatting is crucial for real-time novel view synthesis due to its efficiency and ability to render photorealistic images. However, building a 3D Gaussian is guided solely by photometric loss, which can result in inconsistencies in reconstruction. This under-constrained process often results in "floater" artifacts and unstructured geometry, preventing the extraction of high-fidelity surfaces. To address this issue, our paper introduces a novel method that improves reconstruction by enforcing global geometry consistency through constrained multi-view triangulation. Our approach aims to achieve a consensus on 3D representation in the physical world by utilizing various estimated views. We optimize this process by penalizing the deviation of a rendered 3D point from a robust consensus point, which is re-triangulated from a bundle of neighboring views in a self-supervised fashion. We demonstrate the effectiveness of our method across multiple datasets, achieving state-of-the-art results. On the DTU dataset, our method attains a mean Chamfer Distance of 0.50 mm, outperforming comparable explicit methods. We will make our code open-source to facilitate community validation and ensure reproducibility. --- ### Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models Authors: Chen Yang, Guangyue Peng, Jiaying Zhu, Ran Le, Ruixiang Feng, Tao Zhang, Wei Ruan, Xiaoqi Liu, Xiaoxue Cheng, Xiyun Xu, Yang Song, Yanzipeng Gao et al. Published: 2025-12-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06266v1 We present Nanbeige4-3B, a family of small-scale but high-performing language models. Pretrained on 23T high-quality tokens and finetuned on over 30 million diverse instructions, we extend the boundary of the scaling law for small language models. In pre-training, we design a Fine-Grained Warmup-Stable-Decay (FG-WSD) training scheduler, which progressively refines data mixtures across stages to boost model performance. In post-training, to improve the quality of the SFT data, we design a joint mechanism that integrates deliberative generation refinement and chain-of-thought reconstruction, yielding substantial gains on complex tasks. Following SFT, we employ our flagship reasoning model to distill Nanbeige4-3B through our proposed Dual Preference Distillation (DPD) method, which leads to further performance gains. Finally, a multi-stage reinforcement learning phase was applied, leveraging verifiable rewards and preference modeling to strengthen abilities on both reasoning and human alignment. Extensive evaluations show that Nanbeige4-3B not only significantly outperforms models of comparable parameter scale but also rivals much larger models across a wide range of benchmarks. The model checkpoints are available at https://huggingface.co/Nanbeige. --- ### Who Will Top the Charts? Multimodal Music Popularity Prediction via Adaptive Fusion of Modality Experts and Temporal Engagement Modeling Authors: Yash Choudhary, Preeti Rao, Pushpak Bhattacharyya Published: 2025-12-06 Categories: cs.SD, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.06259v1 Predicting a song's commercial success prior to its release remains an open and critical research challenge for the music industry. Early prediction of music popularity informs strategic decisions, creative planning, and marketing. Existing methods suffer from four limitations:(i) temporal dynamics in audio and lyrics are averaged away; (ii) lyrics are represented as a bag of words, disregarding compositional structure and affective semantics; (iii) artist- and song-level historical performance is ignored; and (iv) multimodal fusion approaches rely on simple feature concatenation, resulting in poorly aligned shared representations. To address these limitations, we introduce GAMENet, an end-to-end multimodal deep learning architecture for music popularity prediction. GAMENet integrates modality-specific experts for audio, lyrics, and social metadata through an adaptive gating mechanism. We use audio features from Music4AllOnion processed via OnionEnsembleAENet, a network of autoencoders designed for robust feature extraction; lyric embeddings derived through a large language model pipeline; and newly introduced Career Trajectory Dynamics (CTD) features that capture multi-year artist career momentum and song-level trajectory statistics. Using the Music4All dataset (113k tracks), previously explored in MIR tasks but not popularity prediction, GAMENet achieves a 12% improvement in R^2 over direct multimodal feature concatenation. Spotify audio descriptors alone yield an R^2 of 0.13. Integrating aggregate CTD features increases this to 0.69, with an additional 7% gain from temporal CTD features. We further validate robustness using the SpotGenTrack Popularity Dataset (100k tracks), achieving a 16% improvement over the previous baseline. Extensive ablations confirm the model's effectiveness and the distinct contribution of each modality. --- ### Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs Authors: Chaoyang Wang, Yangfan He, Yiyang Zhou, Yixuan Wang, Jiaqi Liu, Peng Xia, Zhengzhong Tu, Mohit Bansal, Huaxiu Yao Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06258v1 We reveal a critical yet underexplored flaw in Large Vision-Language Models (LVLMs): even when these models know the correct answer, they frequently arrive there through incorrect reasoning paths. The core issue is not a lack of knowledge, but a path selection bias within the vast reasoning search space. Although LVLMs are often capable of sampling correct solution trajectories, they disproportionately favor unstable or logically inconsistent ones, leading to erratic and unreliable outcomes. The substantial disparity between Pass@K (with large K) and Pass@1 across numerous models provides compelling evidence that such failures primarily stem from misreasoning rather than ignorance. To systematically investigate and address this issue, we propose PSO (Path-Select Optimization), a two-stage post-training framework designed to enhance both the reasoning performance and stability of existing LVLMs. In the first stage, we employ Group Relative Policy Optimization (GRPO) with template and answer-based rewards to cultivate structured, step-by-step reasoning. In the second stage, we conduct online preference optimization, where the model samples reasoning paths from GRPO-generated data, self-evaluates them, and aligns itself toward the preferred trajectories. Incorrect or suboptimal paths are concurrently stored in a Negative Replay Memory (NRM) as hard negatives, which are periodically revisited to prevent the model from repeating prior mistakes and to facilitate continual reasoning refinement. Extensive experiments show that PSO effectively prunes invalid reasoning paths, substantially enhances reasoning accuracy (with 7.4% improvements on average), and yields more stable and consistent chains of thought. Our code will be available at https://github.com/aiming-lab/PSO. --- ### Convergence of Outputs When Two Large Language Models Interact in a Multi-Agentic Setup Authors: Aniruddha Maiti, Satya Nimmagadda, Kartha Veerya Jammuladinne, Niladri Sengupta, Ananya Jana Published: 2025-12-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.06256v1 In this work, we report what happens when two large language models respond to each other for many turns without any outside input in a multi-agent setup. The setup begins with a short seed sentence. After that, each model reads the other's output and generates a response. This continues for a fixed number of steps. We used Mistral Nemo Base 2407 and Llama 2 13B hf. We observed that most conversations start coherently but later fall into repetition. In many runs, a short phrase appears and repeats across turns. Once repetition begins, both models tend to produce similar output rather than introducing a new direction in the conversation. This leads to a loop where the same or similar text is produced repeatedly. We describe this behavior as a form of convergence. It occurs even though the models are large, trained separately, and not given any prompt instructions. To study this behavior, we apply lexical and embedding-based metrics to measure how far the conversation drifts from the initial seed and how similar the outputs of the two models becomes as the conversation progresses. --- ### Language-driven Fine-grained Retrieval Authors: Shijie Wang, Xin Yu, Yadan Luo, Zijian Wang, Pengfei Zhang, Zi Huang Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06255v1 Existing fine-grained image retrieval (FGIR) methods learn discriminative embeddings by adopting semantically sparse one-hot labels derived from category names as supervision. While effective on seen classes, such supervision overlooks the rich semantics encoded in category names, hindering the modeling of comparability among cross-category details and, in turn, limiting generalization to unseen categories. To tackle this, we introduce LaFG, a Language-driven framework for Fine-Grained Retrieval that converts class names into attribute-level supervision using large language models (LLMs) and vision-language models (VLMs). Treating each name as a semantic anchor, LaFG prompts an LLM to generate detailed, attribute-oriented descriptions. To mitigate attribute omission in these descriptions, it leverages a frozen VLM to project them into a vision-aligned space, clustering them into a dataset-wide attribute vocabulary while harvesting complementary attributes from related categories. Leveraging this vocabulary, a global prompt template selects category-relevant attributes, which are aggregated into category-specific linguistic prototypes. These prototypes supervise the retrieval model to steer --- ### Learning Without Time-Based Embodiment Resets in Soft-Actor Critic Authors: Homayoon Farrahi, A. Rupam Mahmood Published: 2025-12-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06252v1 When creating new reinforcement learning tasks, practitioners often accelerate the learning process by incorporating into the task several accessory components, such as breaking the environment interaction into independent episodes and frequently resetting the environment. Although they can enable the learning of complex intelligent behaviors, such task accessories can result in unnatural task setups and hinder long-term performance in the real world. In this work, we explore the challenges of learning without episode terminations and robot embodiment resets using the Soft Actor-Critic (SAC) algorithm. To learn without terminations, we present a continuing version of the SAC algorithm and show that, with simple modifications to the reward functions of existing tasks, continuing SAC can perform as well as or better than episodic SAC while reducing the sensitivity of performance to the value of the discount rate $γ$. On a modified Gym Reacher task, we investigate possible explanations for the failure of continuing SAC when learning without embodiment resets. Our results suggest that embodiment resets help with exploration of the state space in the SAC algorithm, and removing embodiment resets can lead to poor exploration of the state space and failure of or significantly slower learning. Finally, on additional simulated tasks and a real-robot vision task, we show that increasing the entropy of the policy when performance trends worse or remains static is an effective intervention for recovering the performance lost due to not using embodiment resets. --- ### NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks Authors: Fangzhou Lin, Yuping Wang, Yuliang Guo, Zixun Huang, Xinyu Huang, Haichong Zhang, Kazunori Yamada, Zhengzhong Tu, Liu Ren, Ziming Zhang Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06251v2 Partially Supervised Multi-Task Learning (PS-MTL) aims to leverage knowledge across tasks when annotations are incomplete. Existing approaches, however, have largely focused on the simpler setting of homogeneous, dense prediction tasks, leaving the more realistic challenge of learning from structurally diverse tasks unexplored. To this end, we introduce NexusFlow, a novel, lightweight, and plug-and-play framework effective in both settings. NexusFlow introduces a set of surrogate networks with invertible coupling layers to align the latent feature distributions of tasks, creating a unified representation that enables effective knowledge transfer. The coupling layers are bijective, preserving information while mapping features into a shared canonical space. This invertibility avoids representational collapse and enables alignment across structurally different tasks without reducing expressive capacity. We first evaluate NexusFlow on the core challenge of domain-partitioned autonomous driving, where dense map reconstruction and sparse multi-object tracking are supervised in different geographic regions, creating both structural disparity and a strong domain gap. NexusFlow sets a new state-of-the-art result on nuScenes, outperforming strong partially supervised baselines. To demonstrate generality, we further test NexusFlow on NYUv2 using three homogeneous dense prediction tasks, segmentation, depth, and surface normals, as a representative N-task PS-MTL scenario. NexusFlow yields consistent gains across all tasks, confirming its broad applicability. --- ### Learning When to Switch: Adaptive Policy Selection via Reinforcement Learning Authors: Chris Tava Published: 2025-12-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06250v1 Autonomous agents often require multiple strategies to solve complex tasks, but determining when to switch between strategies remains challenging. This research introduces a reinforcement learning technique to learn switching thresholds between two orthogonal navigation policies. Using maze navigation as a case study, this work demonstrates how an agent can dynamically transition between systematic exploration (coverage) and goal-directed pathfinding (convergence) to improve task performance. Unlike fixed-threshold approaches, the agent uses Q-learning to adapt switching behavior based on coverage percentage and distance to goal, requiring only minimal domain knowledge: maze dimensions and target location. The agent does not require prior knowledge of wall positions, optimal threshold values, or hand-crafted heuristics; instead, it discovers effective switching strategies dynamically during each run. The agent discretizes its state space into coverage and distance buckets, then adapts which coverage threshold (20-60\%) to apply based on observed progress signals. Experiments across 240 test configurations (4 maze sizes from 16$\times$16 to 128$\times$128 $\times$ 10 unique mazes $\times$ 6 agent variants) demonstrate that adaptive threshold learning outperforms both single-strategy agents and fixed 40\% threshold baselines. Results show 23-55\% improvements in completion time, 83\% reduction in runtime variance, and 71\% improvement in worst-case scenarios. The learned switching behavior generalizes within each size class to unseen wall configurations. Performance gains scale with problem complexity: 23\% improvement for 16$\times$16 mazes, 34\% for 32$\times$32, and 55\% for 64$\times$64, demonstrating that as the space of possible maze structures grows, the value of adaptive policy selection over fixed heuristics increases proportionally. --- ### DUET: Agentic Design Understanding via Experimentation and Testing Authors: Gus Henry Smith, Sandesh Adhikary, Vineet Thumuluri, Karthik Suresh, Vivek Pandit, Kartik Hegde, Hamid Shojaei, Chandra Bhagavatula Published: 2025-12-06 Categories: cs.SE, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2512.06247v2 AI agents powered by large language models (LLMs) are being used to solve increasingly complex software engineering challenges, but struggle with hardware design tasks. Register Transfer Level (RTL) code presents a unique challenge for LLMs, as it encodes complex, dynamic, time-evolving behaviors using the low-level language features of SystemVerilog. LLMs struggle to infer these complex behaviors from the syntax of RTL alone, which limits their ability to complete all downstream tasks like code completion, documentation, or verification. In response to this issue, we present DUET: a general methodology for developing Design Understanding via Experimentation and Testing. DUET mimics how hardware design experts develop an understanding of complex designs: not just via a one-off readthrough of the RTL, but via iterative experimentation using a number of tools. DUET iteratively generates hypotheses, tests them with EDA tools (e.g., simulation, waveform inspection, and formal verification), and integrates the results to build a bottom-up understanding of the design. In our evaluations, we show that DUET improves AI agent performance on formal verification, when compared to a baseline flow without experimentation. --- ### Auto-exploration for online reinforcement learning Authors: Caleb Ju, Guanghui Lan Published: 2025-12-06 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2512.06244v4 The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and action discounted RL problems address this by assuming sufficient exploration over both state and action spaces. However, this yields non-implementable algorithms and sub-optimal performance. To resolve these limitations, we introduce a new class of methods with auto-exploration, or methods that automatically explore both state and action spaces. Auto-exploration can be applied in both the tabular and linear function approximation setting. Under algorithm-independent assumptions on the existence of an exploring optimal policy, both settings attain $O(ε^{-2})$ sample complexity to solve to $ε$ error. These complexities are novel since they avoid algorithm-dependent parameters seen in prior works, which may be arbitrarily large. The methods are also simple to implement because they are parameter-free. We achieve these results by integrating auto-exploration into policy mirror descent to avoid the (unknown) stationary distribution seen in prior art. In the tabular setting, we introduce a dynamic exploration time with a data-driven stopping time, while for linear function approximation we propose a new sampling distribution based on the discounted visitation distribution that covers a more general class of Markov chains. --- ### Quantization Blindspots: How Model Compression Breaks Backdoor Defenses Authors: Rohan Pandey, Eric Ye Published: 2025-12-06 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2512.06243v1 Backdoor attacks embed input-dependent malicious behavior into neural networks while preserving high clean accuracy, making them a persistent threat for deployed ML systems. At the same time, real-world deployments almost never serve full-precision models: post-training quantization to INT8 or lower precision is now standard practice for reducing memory and latency. This work asks a simple question: how do existing backdoor defenses behave under standard quantization pipelines? We conduct a systematic empirical study of five representative defenses across three precision settings (FP32, INT8 dynamic, INT4 simulated) and two standard vision benchmarks using a canonical BadNet attack. We observe that INT8 quantization reduces the detection rate of all evaluated defenses to 0% while leaving attack success rates above 99%. For INT4, we find a pronounced dataset dependence: Neural Cleanse remains effective on GTSRB but fails on CIFAR-10, even though backdoors continue to survive quantization with attack success rates above 90%. Our results expose a mismatch between how defenses are commonly evaluated (on FP32 models) and how models are actually deployed (in quantized form), and they highlight quantization robustness as a necessary axis in future evaluations and designs of backdoor defenses. --- ### AI Application in Anti-Money Laundering for Sustainable and Transparent Financial Systems Authors: Chuanhao Nie, Yunbo Liu, Chao Wang Published: 2025-12-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.06240v1 Money laundering and financial fraud remain major threats to global financial stability, costing trillions annually and challenging regulatory oversight. This paper reviews how artificial intelligence (AI) applications can modernize Anti-Money Laundering (AML) workflows by improving detection accuracy, lowering false-positive rates, and reducing the operational burden of manual investigations, thereby supporting more sustainable development. It further highlights future research directions including federated learning for privacy-preserving collaboration, fairness-aware and interpretable AI, reinforcement learning for adaptive defenses, and human-in-the-loop visualization systems to ensure that next-generation AML architectures remain transparent, accountable, and robust. In the final part, the paper proposes an AI-driven KYC application that integrates graph-based retrieval-augmented generation (RAG Graph) with generative models to enhance efficiency, transparency, and decision support in KYC processes related to money-laundering detection. Experimental results show that the RAG-Graph architecture delivers high faithfulness and strong answer relevancy across diverse evaluation settings, thereby enhancing the efficiency and transparency of KYC CDD/EDD workflows and contributing to more sustainable, resource-optimized compliance practices. --- ### LOCUS: A System and Method for Low-Cost Customization for Universal Specialization Authors: Dhanasekar Sundararaman, Keying Li, Wayne Xiong, Aashna Garg Published: 2025-12-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06239v1 We present LOCUS (LOw-cost Customization for Universal Specialization), a pipeline that consumes few-shot data to streamline the construction and training of NLP models through targeted retrieval, synthetic data generation, and parameter-efficient tuning. With only a small number of labeled examples, LOCUS discovers pertinent data in a broad repository, synthesizes additional training samples via in-context data generation, and fine-tunes models using either full or low-rank (LoRA) parameter adaptation. Our approach targets named entity recognition (NER) and text classification (TC) benchmarks, consistently outperforming strong baselines (including GPT-4o) while substantially lowering costs and model sizes. Our resultant memory-optimized models retain 99% of fully fine-tuned accuracy while using barely 5% of the memory footprint, also beating GPT-4o on several benchmarks with less than 1% of its parameters. --- ### Empowering GNNs for Domain Adaptation via Denoising Target Graph Authors: Haiyang Yu, Meng-Chieh Lee, Xiang song, Qi Zhu, Christos Faloutsos Published: 2025-12-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06236v2 We explore the node classification task in the context of graph domain adaptation, which uses both source and target graph structures along with source labels to enhance the generalization capabilities of Graph Neural Networks (GNNs) on target graphs. Structure domain shifts frequently occur, especially when graph data are collected at different times or from varying areas, resulting in poor performance of GNNs on target graphs. Surprisingly, we find that simply incorporating an auxiliary loss function for denoising graph edges on target graphs can be extremely effective in enhancing GNN performance on target graphs. Based on this insight, we propose our framework, GraphDeT, a framework that integrates this auxiliary edge task into GNN training for node classification under domain adaptation. Our theoretical analysis connects this auxiliary edge task to the graph generalization bound with -distance, demonstrating such auxiliary task can imposes a constraint which tightens the bound and thereby improves generalization. The experimental results demonstrate superior performance compared to the existing baselines in handling both time and regional domain graph shifts. --- ### Opinion: Learning Intuitive Physics May Require More than Visual Data Authors: Ellen Su, Solim Legris, Todd M. Gureckis, Mengye Ren Published: 2025-12-06 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.06232v1 Humans expertly navigate the world by building rich internal models founded on an intuitive understanding of physics. Meanwhile, despite training on vast quantities of internet video data, state-of-the-art deep learning models still fall short of human-level performance on intuitive physics benchmarks. This work investigates whether data distribution, rather than volume, is the key to learning these principles. We pretrain a Video Joint Embedding Predictive Architecture (V-JEPA) model on SAYCam, a developmentally realistic, egocentric video dataset partially capturing three children's everyday visual experiences. We find that training on this dataset, which represents 0.01% of the data volume used to train SOTA models, does not lead to significant performance improvements on the IntPhys2 benchmark. Our results suggest that merely training on a developmentally realistic dataset is insufficient for current architectures to learn representations that support intuitive physics. We conclude that varying visual data volume and distribution alone may not be sufficient for building systems with artificial intuitive physics. --- ### GPU-GLMB: Assessing the Scalability of GPU-Accelerated Multi-Hypothesis Tracking Authors: Pranav Balakrishnan, Sidisha Barik, Sean M. O'Rourke, Benjamin M. Marlin Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06230v1 Much recent research on multi-target tracking has focused on multi-hypothesis approaches leveraging random finite sets. Of particular interest are labeled random finite set methods that maintain temporally coherent labels for each object. While these methods enjoy important theoretical properties as closed-form solutions to the multi-target Bayes filter, the maintenance of multiple hypotheses under the standard measurement model is highly computationally expensive, even when hypothesis pruning approximations are applied. In this work, we focus on the Generalized Labeled Multi-Bernoulli (GLMB) filter as an example of this class of methods. We investigate a variant of the filter that allows multiple detections per object from the same sensor, a critical capability when deploying tracking in the context of distributed networks of machine learning-based virtual sensors. We show that this breaks the inter-detection dependencies in the filter updates of the standard GLMB filter, allowing updates with significantly improved parallel scalability and enabling efficient deployment on GPU hardware. We report the results of a preliminary analysis of a GPU-accelerated implementation of our proposed GLMB tracker, with a focus on run time scalability with respect to the number of objects and the maximum number of retained hypotheses. --- ### Policy-based Sentence Simplification: Replacing Parallel Corpora with LLM-as-a-Judge Authors: Xuanxin Wu, Yuki Arase, Masaaki Nagata Published: 2025-12-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06228v1 Sentence simplification aims to modify a sentence to make it easier to read and understand while preserving the meaning. Different applications require distinct simplification policies, such as replacing only complex words at the lexical level or rewriting the entire sentence while trading off details for simplicity. However, achieving such policy-driven control remains an open challenge. In this work, we introduce a simple yet powerful approach that leverages Large Language Model-as-a-Judge (LLM-as-a-Judge) to automatically construct policy-aligned training data, completely removing the need for costly human annotation or parallel corpora. Our method enables building simplification systems that adapt to diverse simplification policies. Remarkably, even small-scale open-source LLMs such as Phi-3-mini-3.8B surpass GPT-4o on lexical-oriented simplification, while achieving comparable performance on overall rewriting, as verified by both automatic metrics and human evaluations. The consistent improvements across model families and sizes demonstrate the robustness of our approach. --- ### Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety Authors: Junyu Mao, Anthony Hills, Talia Tseriotou, Maria Liakata, Aya Shamir, Dan Sayda, Dana Atzil-Slonim, Natalie Djohari, Pamela Ugwudike, Mahesan Niranjan, Stuart E. Middleton Published: 2025-12-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.06227v3 Real-world indicators play an important role in many Natural Language Processing (NLP) applications, such as life events for mental health analysis and risky behaviours for online safety, yet labelling such information is often costly and/or difficult due to its multi-label and dynamic nature. Large Language Models (LLMs) show promising potential for automated annotation, but the multi-label setting remains challenging. In this work, we propose a Confidence-Aware Fine-Grained Debate (CFD) framework that simulates human collaborative annotation using fine-grained communication to better support automated multi-label enrichment. We introduce two expert-annotated resources: life-event and symptom annotation for a mental health well-being dataset, and a new online safety sharenting dataset. Experiments show that CFD achieves the most robust enrichment performance across tasks, and that the benefit of fine-grained confidence is influenced by its quality and variability. We further evaluate training-free strategies for incorporating enrichment indicators into downstream tasks and show that automated enrichment consistently improves performance, by up to 9.9 Macro-F1 points, with the most effective integration format depending on how the indicator relates to the downstream objective. --- ### Revisiting SVD and Wavelet Difference Reduction for Lossy Image Compression: A Reproducibility Study Authors: Alena Makarova Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06221v1 This work presents an independent reproducibility study of a lossy image compression technique that integrates singular value decomposition (SVD) and wavelet difference reduction (WDR). The original paper claims that combining SVD and WDR yields better visual quality and higher compression ratios than JPEG2000 and standalone WDR. I re-implemented the proposed method, carefully examined missing implementation details, and replicated the original experiments as closely as possible. I then conducted additional experiments on new images and evaluated performance using PSNR and SSIM. In contrast to the original claims, my results indicate that the SVD+WDR technique generally does not surpass JPEG2000 or WDR in terms of PSNR, and only partially improves SSIM relative to JPEG2000. The study highlights ambiguities in the original description (e.g., quantization and threshold initialization) and illustrates how such gaps can significantly impact reproducibility and reported performance. --- ### Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation Authors: Pengzhen Xie, Huizhi Liang Published: 2025-12-05 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.22215v1 Large Language Models (LLMs) demonstrate potential in the field of scientific idea generation. However, the generated results often lack controllable academic context and traceable inspiration pathways. To bridge this gap, this paper proposes a scientific idea generation system called GYWI, which combines author knowledge graphs with retrieval-augmented generation (RAG) to form an external knowledge base to provide controllable context and trace of inspiration path for LLMs to generate new scientific ideas. We first propose an author-centered knowledge graph construction method and inspiration source sampling algorithms to construct external knowledge base. Then, we propose a hybrid retrieval mechanism that is composed of both RAG and GraphRAG to retrieve content with both depth and breadth knowledge. It forms a hybrid context. Thirdly, we propose a Prompt optimization strategy incorporating reinforcement learning principles to automatically guide LLMs optimizing the results based on the hybrid context. To evaluate the proposed approaches, we constructed an evaluation dataset based on arXiv (2018-2023). This paper also develops a comprehensive evaluation method including empirical automatic assessment in multiple-choice question task, LLM-based scoring, human evaluation, and semantic space visualization analysis. The generated ideas are evaluated from the following five dimensions: novelty, feasibility, clarity, relevance, and significance. We conducted experiments on different LLMs including GPT-4o, DeepSeek-V3, Qwen3-8B, and Gemini 2.5. Experimental results show that GYWI significantly outperforms mainstream LLMs in multiple metrics such as novelty, reliability, and relevance. --- ### FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback Authors: Xueqing Wu, Zihan Xue, Da Yin, Shuyan Zhou, Kai-Wei Chang, Nanyun Peng, Yeming Wen Published: 2025-12-05 Categories: cs.CL, cs.CV, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2601.04203v3 We present FronTalk, a benchmark for front-end code generation that pioneers the study of a unique interaction dynamic: conversational code generation with multi-modal feedback. In front-end development, visual artifacts such as sketches, mockups and annotated creenshots are essential for conveying design intent, yet their role in multi-turn code generation remains largely unexplored. To address this gap, we focus on the front-end development task and curate FronTalk, a collection of 100 multi-turn dialogues derived from real-world websites across diverse domains such as news, finance, and art. Each turn features both a textual instruction and an equivalent visual instruction, each representing the same user intent. To comprehensively evaluate model performance, we propose a novel agent-based evaluation framework leveraging a web agent to simulate users and explore the website, and thus measuring both functional correctness and user experience. Evaluation of 20 models reveals two key challenges that are under-explored systematically in the literature: (1) a significant forgetting issue where models overwrite previously implemented features, resulting in task failures, and (2) a persistent challenge in interpreting visual feedback, especially for open-source vision-language models (VLMs). We propose a strong baseline to tackle the forgetting issue with AceCoder, a method that critiques the implementation of every past instruction using an autonomous web agent. This approach significantly reduces forgetting to nearly zero and improves the performance by up to 9.3% (56.0% to 65.3%). Overall, we aim to provide a solid foundation for future research in front-end development and the general interaction dynamics of multi-turn, multi-modal code generation. Code and data are released at https://github.com/shirley-wu/frontalk --- ### TeleTables: A Benchmark for Large Language Models in Telecom Table Interpretation Authors: Anas Ezzakri, Nicola Piovesan, Mohamed Sana, Antonio De Domenico, Fadhel Ayed, Haozhe Zhang Published: 2025-12-05 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.04202v2 Large Language Models (LLMs) are increasingly applied to telecom engineering tasks, yet perform poorly on 3GPP specifications. These standards encode much of their technical information in complex tables, but LLM knowledge and interpretation of such tables remain largely unexplored. We introduce TeleTables, a benchmark comprising 2,220 tables from 13 3GPP specifications in four formats and 500 human-verified MCQs spanning direct retrieval to multi-step reasoning. Evaluating 20 open-weight LLMs across non reasoning, multimodal, reasoning, and table specialized architectures reveals two distinct performance bottlenecks. In the closed-book setting, domain knowledge is the primary constraint, with no general-purpose model exceeding 41% accuracy. When the table is provided as context, the best models exceed 90%, but performance degrades systematically with reasoning depth, evidence scope, and structural complexity, with a 32.2pp spread across reasoning skills. Table specialization on non-telecom data provides no consistent benefit, while strong reasoning capabilities remain essential for reliable interpretation of complex technical tables. --- ### Collective Narrative Grounding: Community-Coordinated Data Contributions to Improve Local AI Systems Authors: Zihan Gao, Mohsin Y. K. Yousufi, Jacob Thebault-Spieker Published: 2025-12-05 Categories: cs.CL, cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2601.04201v1 Large language model (LLM) question-answering systems often fail on community-specific queries, creating "knowledge blind spots" that marginalize local voices and reinforce epistemic injustice. We present Collective Narrative Grounding, a participatory protocol that transforms community stories into structured narrative units and integrates them into AI systems under community governance. Learning from three participatory mapping workshops with N=24 community members, we designed elicitation methods and a schema that retain narrative richness while enabling entity, time, and place extraction, validation, and provenance control. To scope the problem, we audit a county-level benchmark of 14,782 local information QA pairs, where factual gaps, cultural misunderstandings, geographic confusions, and temporal misalignments account for 76.7% of errors. On a participatory QA set derived from our workshops, a state-of-the-art LLM answered fewer than 21% of questions correctly without added context, underscoring the need for local grounding. The missing facts often appear in the collected narratives, suggesting a direct path to closing the dominant error modes for narrative items. Beyond the protocol and pilot, we articulate key design tensions, such as representation and power, governance and control, and privacy and consent, providing concrete requirements for retrieval-first, provenance-visible, locally governed QA systems. Together, our taxonomy, protocol, and participatory evaluation offer a rigorous foundation for building community-grounded AI that better answers local questions. --- ### Attribute-Aware Controlled Product Generation with LLMs for E-commerce Authors: Virginia Negri, Víctor Martínez Gómez, Sergio A. Balanya, Subburam Rajaram Published: 2025-12-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.04200v1 Product information extraction is crucial for e-commerce services, but obtaining high-quality labeled datasets remains challenging. We present a systematic approach for generating synthetic e-commerce product data using Large Language Models (LLMs), introducing a controlled modification framework with three strategies: attribute-preserving modification, controlled negative example generation, and systematic attribute removal. Using a state-of-the-art LLM with attribute-aware prompts, we enforce store constraints while maintaining product coherence. Human evaluation of 2000 synthetic products demonstrates high effectiveness, with 99.6% rated as natural, 96.5% containing valid attribute values, and over 90% showing consistent attribute usage. On the public MAVE dataset, our synthetic data achieves 60.5% accuracy, performing on par with real training data (60.8%) and significantly improving upon the 13.4% zero-shot baseline. Hybrid configurations combining synthetic and real data further improve performance, reaching 68.8% accuracy. Our framework provides a practical solution for augmenting e-commerce datasets, particularly valuable for low-resource scenarios. ---