# Research Papers — 2025-12 · bundle page 27 of 175 > Full-text markdown of papers #1301–1350 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/27 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/26.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/28.md) ### nncase: An End-to-End Compiler for Efficient LLM Deployment on Heterogeneous Storage Architectures Authors: Hui Guo, Qihang Zheng, Chenghai Huo, Dongliang Guo, Haoqi Yang, Yang Zhang Published: 2025-12-25 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2512.21571v1 The efficient deployment of large language models (LLMs) is hindered by memory architecture heterogeneity, where traditional compilers suffer from fragmented workflows and high adaptation costs. We present nncase, an open-source, end-to-end compilation framework designed to unify optimization across diverse targets. Central to nncase is an e-graph-based term rewriting engine that mitigates the phase ordering problem, enabling global exploration of computation and data movement strategies. The framework integrates three key modules: Auto Vectorize for adapting to heterogeneous computing units, Auto Distribution for searching parallel strategies with cost-aware communication optimization, and Auto Schedule for maximizing on-chip cache locality. Furthermore, a buffer-aware Codegen phase ensures efficient kernel instantiation. Evaluations show that nncase outperforms mainstream frameworks like MLC LLM and Intel IPEX on Qwen3 series models and achieves performance comparable to the hand-optimized llama.cpp on CPUs, demonstrating the viability of automated compilation for high-performance LLM deployment. The source code is available at https://github.com/kendryte/nncase. --- ### AnchorGK: Anchor-based Incremental and Stratified Graph Learning Framework for Inductive Spatio-Temporal Kriging Authors: Xiaobin Ren, Kaiqi Zhao, Katerina Taškova, Patricia Riddle Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21569v1 Spatio-temporal kriging is a fundamental problem in sensor networks, driven by the sparsity of deployed sensors and the resulting missing observations. Although recent approaches model spatial and temporal correlations, they often under-exploit two practical characteristics of real deployments: the sparse spatial distribution of locations and the heterogeneous availability of auxiliary features across locations. To address these challenges, we propose AnchorGK, an Anchor-based Incremental and Stratified Graph Learning framework for inductive spatio-temporal kriging. AnchorGK introduces anchor locations to stratify the data in a principled manner. Anchors are constructed according to feature availability, and strata are then formed around these anchors. This stratification serves two complementary roles. First, it explicitly represents and continuously updates correlations between unobserved regions and surrounding observed locations within a graph learning framework. Second, it enables the systematic use of all available features across strata via an incremental representation mechanism, mitigating feature incompleteness without discarding informative signals. Building on the stratified structure, we design a dual-view graph learning layer that jointly aggregates feature-relevant and location-relevant information, learning stratum-specific representations that support accurate inference under inductive settings. Extensive experiments on multiple benchmark datasets demonstrate that AnchorGK consistently outperforms state-of-the-art baselines for spatio-temporal kriging. --- ### Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management Authors: Changzhi Sun, Xiangyu Chen, Jixiang Luo, Dell Zhang, Xuelong Li Published: 2025-12-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21567v1 External memory is a key component of modern large language model (LLM) systems, enabling long-term interaction and personalization. Despite its importance, memory management is still largely driven by hand-designed heuristics, offering little insight into the long-term and uncertain consequences of memory decisions. In practice, choices about what to read or write shape future retrieval and downstream behavior in ways that are difficult to anticipate. We argue that memory management should be viewed as a sequential decision-making problem under uncertainty, where the utility of memory is delayed and dependent on future interactions. To this end, we propose DAM (Decision-theoretic Agent Memory), a decision-theoretic framework that decomposes memory management into immediate information access and hierarchical storage maintenance. Within this architecture, candidate operations are evaluated via value functions and uncertainty estimators, enabling an aggregate policy to arbitrate decisions based on estimated long-term utility and risk. Our contribution is not a new algorithm, but a principled reframing that clarifies the limitations of heuristic approaches and provides a foundation for future research on uncertainty-aware memory systems. --- ### Discovering Sparse Recovery Algorithms Using Neural Architecture Search Authors: Patrick Yubeaton, Sarthak Gupta, M. Salman Asif, Chinmay Hegde Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21563v1 The design of novel algorithms for solving inverse problems in signal processing is an incredibly difficult, heuristic-driven, and time-consuming task. In this short paper, we the idea of automated algorithm discovery in the signal processing context through meta-learning tools such as Neural Architecture Search (NAS). Specifically, we examine the Iterative Shrinkage Thresholding Algorithm (ISTA) and its accelerated Fast ISTA (FISTA) variant as candidates for algorithm rediscovery. We develop a meta-learning framework which is capable of rediscovering (several key elements of) the two aforementioned algorithms when given a search space of over 50,000 variables. We then show how our framework can apply to various data distributions and algorithms besides ISTA/FISTA. --- ### Exploration of Reproducible Generated Image Detection Authors: Yihang Duan Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21562v1 While the technology for detecting AI-Generated Content (AIGC) images has advanced rapidly, the field still faces two core issues: poor reproducibility and insufficient gen eralizability, which hinder the practical application of such technologies. This study addresses these challenges by re viewing 7 key papers on AIGC detection, constructing a lightweight test dataset, and reproducing a representative detection method. Through this process, we identify the root causes of the reproducibility dilemma in the field: firstly, papers often omit implicit details such as prepro cessing steps and parameter settings; secondly, most detec tion methods overfit to exclusive features of specific gener ators rather than learning universal intrinsic features of AIGC images. Experimental results show that basic perfor mance can be reproduced when strictly following the core procedures described in the original papers. However, de tection performance drops sharply when preprocessing dis rupts key features or when testing across different genera tors. This research provides empirical evidence for improv ing the reproducibility of AIGC detection technologies and offers reference directions for researchers to disclose ex perimental details more comprehensively and verify the generalizability of their proposed methods. --- ### Toward Intelligent Scene Augmentation for Context-Aware Object Placement and Sponsor-Logo Integration Authors: Unnati Saraswat, Tarun Rao, Namah Gupta, Shweta Swami, Shikhar Sharma, Prateek Narang, Dhruv Kumar Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21560v1 Intelligent image editing increasingly relies on advances in computer vision, multimodal reasoning, and generative modeling. While vision-language models (VLMs) and diffusion models enable guided visual manipulation, existing work rarely ensures that inserted objects are \emph{contextually appropriate}. We introduce two new tasks for advertising and digital media: (1) \emph{context-aware object insertion}, which requires predicting suitable object categories, generating them, and placing them plausibly within the scene; and (2) \emph{sponsor-product logo augmentation}, which involves detecting products and inserting correct brand logos, even when items are unbranded or incorrectly branded. To support these tasks, we build two new datasets with category annotations, placement regions, and sponsor-product labels. --- ### Bidirectional Human-AI Alignment in Education for Trustworthy Learning Environments Authors: Hua Shen Published: 2025-12-25 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2512.21552v1 Artificial intelligence (AI) is transforming education, offering unprecedented opportunities to personalize learning, enhance assessment, and support educators. Yet these opportunities also introduce risks related to equity, privacy, and student autonomy. This chapter develops the concept of bidirectional human-AI alignment in education, emphasizing that trustworthy learning environments arise not only from embedding human values into AI systems but also from equipping teachers, students, and institutions with the skills to interpret, critique, and guide these technologies. Drawing on emerging research and practical case examples, we explore AI's evolution from support tool to collaborative partner, highlighting its impacts on teacher roles, student agency, and institutional governance. We propose actionable strategies for policymakers, developers, and educators to ensure that AI advances equity, transparency, and human flourishing rather than eroding them. By reframing AI adoption as an ongoing process of mutual adaptation, the chapter envisions a future in which humans and intelligent systems learn, innovate, and grow together. --- ### Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures Authors: Hua Shen, Tiffany Knearem, Divy Thakkar, Pat Pataranutaporn, Anoop Sinha, Yike, Shi, Jenny T. Liang, Lama Ahmad, Tanu Mitra, Brad A. Myers, Yang Li Published: 2025-12-25 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.21551v1 The rapid integration of generative AI into everyday life underscores the need to move beyond unidirectional alignment models that only adapt AI to human values. This workshop focuses on bidirectional human-AI alignment, a dynamic, reciprocal process where humans and AI co-adapt through interaction, evaluation, and value-centered design. Building on our past CHI 2025 BiAlign SIG and ICLR 2025 Workshop, this workshop will bring together interdisciplinary researchers from HCI, AI, social sciences and more domains to advance value-centered AI and reciprocal human-AI collaboration. We focus on embedding human and societal values into alignment research, emphasizing not only steering AI toward human values but also enabling humans to critically engage with and evolve alongside AI systems. Through talks, interdisciplinary discussions, and collaborative activities, participants will explore methods for interactive alignment, frameworks for societal impact evaluation, and strategies for alignment in dynamic contexts. This workshop aims to bridge the disciplines' gaps and establish a shared agenda for responsible, reciprocal human-AI futures. --- ### EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal Authors: Sanghyun Jo, Donghwan Lee, Eunji Jung, Seong Je Oh, Kyungsu Kim Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21545v2 Object removal must prevent the masked target from reappearing and reconstruct the occluded background with structural and contextual fidelity, rather than merely filling a hole plausibly. Recent dataset-free approaches manipulate the diffusion model's internal self-attention to prevent it from referencing the masked region, yet they fail in two critical ways: (i) they treat the masked region as the sole foreground, misinterpreting non-target objects as background and regenerating them, and (ii) they apply uniform attention constraints without distinguishing diverse background subtypes, leading to textural blurring and structural misalignment. Both failures stem from the absence of explicit background-aware reasoning. We propose EraseLoRA, a dataset-free framework that replaces attention surgery with background-aware reasoning and test-time adaptation. The first stage, Background-aware Foreground Exclusion (BFE), leverages a multimodal large-language model to separate target foreground, non-target foregrounds, and clean background from a single image-mask pair. The second stage, Background-aware Reconstruction with Subtype Aggregation (BRSA), performs test-time optimization that treats inferred background subtypes as complementary pieces, enforcing their consistent integration through reconstruction and alignment objectives without explicit attention intervention. As a model-agnostic plug-in applicable to diverse diffusion backbones, EraseLoRA reconstructs backgrounds at least 23% more faithful to the original scene than previous dataset-free methods while nearly halving unwanted foreground re-generation, and surpasses all dataset-driven approaches in both aspects despite requiring no training data. Code is available at https://shjo-april.github.io/EraseLoRA. --- ### AVP-Fusion: Adaptive Multi-Modal Fusion and Contrastive Learning for Two-Stage Antiviral Peptide Identification Authors: Xinru Wen, Weizhong Lin, Xuan Xiao Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21544v1 Accurate identification of antiviral peptides (AVPs) is critical for accelerating novel drug development. However, current computational methods struggle to capture intricate sequence dependencies and effectively handle ambiguous, hard-to-classify samples. To address these challenges, we propose AVP-Fusion, a novel two-stage deep learning framework integrating adaptive feature fusion and contrastive learning. Unlike traditional static feature concatenation, we construct a panoramic feature space using 10 distinct descriptors and introduce an Adaptive Gating Mechanism.This mechanism dynamically regulates the weights of local motifs extracted by CNNs and global dependencies captured by BiLSTMs based on sequence context. Furthermore, to address data distribution challenges, we employ a contrastive learning strategy driven by Online Hard Example Mining (OHEM) and BLOSUM62-based data augmentation, which significantly sharpens the model's decision boundaries. Experimental results on the benchmark Set 1 dataset demonstrate that AVP-Fusion achieves an accuracy of 0.9531 and an MCC of 0.9064, significantly outperforming state-of-the-art methods. In the second stage, leveraging transfer learning, the model enables precise subclass prediction for six viral families and eight specific viruses, even under limited sample sizes. In summary, AVP-Fusion serves as a robust and interpretable tool for high-throughput antiviral drug screening. --- ### Vision Transformers are Circulant Attention Learners Authors: Dongchen Han, Tianyu Li, Ziyi Wang, Gao Huang Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21542v1 The self-attention mechanism has been a key factor in the advancement of vision Transformers. However, its quadratic complexity imposes a heavy computational burden in high-resolution scenarios, restricting the practical application. Previous methods attempt to mitigate this issue by introducing handcrafted patterns such as locality or sparsity, which inevitably compromise model capacity. In this paper, we present a novel attention paradigm termed \textbf{Circulant Attention} by exploiting the inherent efficient pattern of self-attention. Specifically, we first identify that the self-attention matrix in vision Transformers often approximates the Block Circulant matrix with Circulant Blocks (BCCB), a kind of structured matrix whose multiplication with other matrices can be performed in $\mathcal{O}(N\log N)$ time. Leveraging this interesting pattern, we explicitly model the attention map as its nearest BCCB matrix and propose an efficient computation algorithm for fast calculation. The resulting approach closely mirrors vanilla self-attention, differing only in its use of BCCB matrices. Since our design is inspired by the inherent efficient paradigm, it not only delivers $\mathcal{O}(N\log N)$ computation complexity, but also largely maintains the capacity of standard self-attention. Extensive experiments on diverse visual tasks demonstrate the effectiveness of our approach, establishing circulant attention as a promising alternative to self-attention for vision Transformer architectures. Code is available at https://github.com/LeapLabTHU/Circulant-Attention. --- ### Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model Authors: Yanhao Li, Lu Ma, Jiaran Zhang, Lexiang Tang, Wentao Zhang, Guibo Luo Published: 2025-12-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.21540v1 Existing approaches typically rely on fixed length penalties, but such penalties are hard to tune and fail to adapt to the evolving reasoning abilities of LLMs, leading to suboptimal trade-offs between accuracy and conciseness. To address this challenge, we propose Leash (adaptive LEngth penAlty and reward SHaping), a reinforcement learning framework for efficient reasoning in LLMs. We formulate length control as a constrained optimization problem and employ a Lagrangian primal-dual method to dynamically adjust the penalty coefficient. When generations exceed the target length, the penalty is intensified; when they are shorter, it is relaxed. This adaptive mechanism guides models toward producing concise reasoning without sacrificing task performance. Experiments on Deepseek-R1-Distill-Qwen-1.5B and Qwen3-4B-Thinking-2507 show that Leash reduces the average reasoning length by 60% across diverse tasks - including in-distribution mathematical reasoning and out-of-distribution domains such as coding and instruction following - while maintaining competitive performance. Our work thus presents a practical and effective paradigm for developing controllable and efficient LLMs that balance reasoning capabilities with computational budgets. --- ### Hierarchy-Aware Fine-Tuning of Vision-Language Models Authors: Jiayu Li, Rajesh Gangireddy, Samet Akcay, Wei Cheng, Juhua Hu Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21529v1 Vision-Language Models (VLMs) learn powerful multimodal representations through large-scale image-text pretraining, but adapting them to hierarchical classification is underexplored. Standard approaches treat labels as flat categories and require full fine-tuning, which is expensive and produces inconsistent predictions across taxonomy levels. We propose an efficient hierarchy-aware fine-tuning framework that updates a few parameters while enforcing structural consistency. We combine two objectives: Tree-Path KL Divergence (TP-KL) aligns predictions along the ground-truth label path for vertical coherence, while Hierarchy-Sibling Smoothed Cross-Entropy (HiSCE) encourages consistent predictions among sibling classes. Both losses work in the VLM's shared embedding space and integrate with lightweight LoRA adaptation. Experiments across multiple benchmarks show consistent improvements in Full-Path Accuracy and Tree-based Inconsistency Error with minimal parameter overhead. Our approach provides an efficient strategy for adapting VLMs to structured taxonomies. --- ### Generative Actor Critic Authors: Aoyang Qin, Deqian Kong, Wei Wang, Ying Nian Wu, Song-Chun Zhu, Sirui Xie Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21527v1 Conventional Reinforcement Learning (RL) algorithms, typically focused on estimating or maximizing expected returns, face challenges when refining offline pretrained models with online experiences. This paper introduces Generative Actor Critic (GAC), a novel framework that decouples sequential decision-making by reframing \textit{policy evaluation} as learning a generative model of the joint distribution over trajectories and returns, $p(τ, y)$, and \textit{policy improvement} as performing versatile inference on this learned model. To operationalize GAC, we introduce a specific instantiation based on a latent variable model that features continuous latent plan vectors. We develop novel inference strategies for both \textit{exploitation}, by optimizing latent plans to maximize expected returns, and \textit{exploration}, by sampling latent plans conditioned on dynamically adjusted target returns. Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods, even in absence of step-wise rewards. --- ### Selective LLM-Guided Regularization for Enhancing Recommendation Models Authors: Shanglin Yang, Zhan Shi Published: 2025-12-25 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.21526v1 Large language models provide rich semantic priors and strong reasoning capabilities, making them promising auxiliary signals for recommendation. However, prevailing approaches either deploy LLMs as standalone recommender or apply global knowledge distillation, both of which suffer from inherent drawbacks. Standalone LLM recommender are costly, biased, and unreliable across large regions of the user item space, while global distillation forces the downstream model to imitate LLM predictions even when such guidance is inaccurate. Meanwhile, recent studies show that LLMs excel particularly in re-ranking and challenging scenarios, rather than uniformly across all contexts.We introduce Selective LLM Guided Regularization, a model-agnostic and computation efficient framework that activates LLM based pairwise ranking supervision only when a trainable gating mechanism informing by user history length, item popularity, and model uncertainty predicts the LLM to be reliable. All LLM scoring is performed offline, transferring knowledge without increasing inference cost. Experiments across multiple datasets show that this selective strategy consistently improves overall accuracy and yields substantial gains in cold start and long tail regimes, outperforming global distillation baselines. --- ### First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions Authors: Egor Shulgin, Grigory Malinovsky, Sarit Khirirat, Peter Richtárik Published: 2025-12-25 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2512.21521v1 Federated Learning (FL) enables collaborative training on decentralized data. Differential privacy (DP) is crucial for FL, but current private methods often rely on unrealistic assumptions (e.g., bounded gradients or heterogeneity), hindering practical application. Existing works that relax these assumptions typically neglect practical FL features, including multiple local updates and partial client participation. We introduce Fed-$α$-NormEC, the first differentially private FL framework providing provable convergence and DP guarantees under standard assumptions while fully supporting these practical features. Fed-$α$-NormE integrates local updates (full and incremental gradient steps), separate server and client stepsizes, and, crucially, partial client participation, which is essential for real-world deployment and vital for privacy amplification. Our theoretical guarantees are corroborated by experiments on private deep learning tasks. --- ### Global-Graph Guided and Local-Graph Weighted Contrastive Learning for Unified Clustering on Incomplete and Noise Multi-View Data Authors: Hongqing He, Jie Xu, Wenyuan Yang, Yonghua Zhu, Guoqiu Wen, Xiaofeng Zhu Published: 2025-12-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.21516v1 Recently, contrastive learning (CL) plays an important role in exploring complementary information for multi-view clustering (MVC) and has attracted increasing attention. Nevertheless, real-world multi-view data suffer from data incompleteness or noise, resulting in rare-paired samples or mis-paired samples which significantly challenges the effectiveness of CL-based MVC. That is, rare-paired issue prevents MVC from extracting sufficient multi-view complementary information, and mis-paired issue causes contrastive learning to optimize the model in the wrong direction. To address these issues, we propose a unified CL-based MVC framework for enhancing clustering effectiveness on incomplete and noise multi-view data. First, to overcome the rare-paired issue, we design a global-graph guided contrastive learning, where all view samples construct a global-view affinity graph to form new sample pairs for fully exploring complementary information. Second, to mitigate the mis-paired issue, we propose a local-graph weighted contrastive learning, which leverages local neighbors to generate pair-wise weights to adaptively strength or weaken the pair-wise contrastive learning. Our method is imputation-free and can be integrated into a unified global-local graph-guided contrastive learning framework. Extensive experiments on both incomplete and noise settings of multi-view data demonstrate that our method achieves superior performance compared with state-of-the-art approaches. --- ### Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training Authors: Lei Liu, Hao Zhu, Yue Shen, Zhixuan Chu, Jian Wang, Jinjie Gu, Kui Ren Published: 2025-12-25 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.21515v1 Continual Pre-training (CPT) serves as a fundamental approach for adapting foundation models to domain-specific applications. Scaling laws for pre-training define a power-law relationship between dataset size and the test loss of an LLM. However, the marginal gains from simply increasing data for CPT diminish rapidly, yielding suboptimal data utilization and inefficient training. To address this challenge, we propose a novel perplexity-aware data scaling law to establish a predictive relationship between the perplexity landscape of domain-specific data and the test loss. Our approach leverages the perplexity derived from the pre-trained model on domain data as a proxy for estimating the knowledge gap, effectively quantifying the informational perplexity landscape of candidate training samples. By fitting this scaling law across diverse perplexity regimes, we enable adaptive selection of high-utility data subsets, prioritizing content that maximizes knowledge absorption while minimizing redundancy and noise. Extensive experiments demonstrate that our method consistently identifies near-optimal training subsets and achieves superior performance on both medical and general-domain benchmarks. --- ### DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO Authors: Henglin Liu, Huijuan Huang, Jing Wang, Chang Liu, Xiu Li, Xiangyang Ji Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21514v1 Reinforcement learning (RL), particularly GRPO, improves image generation quality significantly by comparing the relative performance of images generated within the same group. However, in the later stages of training, the model tends to produce homogenized outputs, lacking creativity and visual diversity, which restricts its application scenarios. This issue can be analyzed from both reward modeling and generation dynamics perspectives. First, traditional GRPO relies on single-sample quality as the reward signal, driving the model to converge toward a few high-reward generation modes while neglecting distribution-level diversity. Second, conventional GRPO regularization neglects the dominant role of early-stage denoising in preserving diversity, causing a misaligned regularization budget that limits the achievable quality--diversity trade-off. Motivated by these insights, we revisit the diversity degradation problem from both reward modeling and generation dynamics. At the reward level, we propose a distributional creativity bonus based on semantic grouping. Specifically, we construct a distribution-level representation via spectral clustering over samples generated from the same caption, and adaptively allocate exploratory rewards according to group sizes to encourage the discovery of novel visual modes. At the generation level, we introduce a structure-aware regularization, which enforces stronger early-stage constraints to preserve diversity without compromising reward optimization efficiency. Experiments demonstrate that our method achieves a 13\%--18\% improvement in semantic diversity under matched quality scores, establishing a new Pareto frontier between image quality and diversity for GRPO-based image generation. --- ### MuS-Polar3D: A Benchmark Dataset for Computational Polarimetric 3D Imaging under Multi-Scattering Conditions Authors: Puyun Wang, Kaimin Yu, Huayang He, Xianyu Wu Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21513v1 Polarization-based underwater 3D imaging exploits polarization cues to suppress background scattering, exhibiting distinct advantages in turbid water. Although data-driven polarization-based underwater 3D reconstruction methods show great potential, existing public datasets lack sufficient diversity in scattering and observation conditions, hindering fair comparisons among different approaches, including single-view and multi-view polarization imaging methods. To address this limitation, we construct MuS-Polar3D, a benchmark dataset comprising polarization images of 42 objects captured under seven quantitatively controlled scattering conditions and five viewpoints, together with high-precision 3D models (+/- 0.05 mm accuracy), normal maps, and foreground masks. The dataset supports multiple vision tasks, including normal estimation, object segmentation, descattering, and 3D reconstruction. Inspired by computational imaging, we further decouple underwater 3D reconstruction under scattering into a two-stage pipeline, namely descattering followed by 3D reconstruction, from an imaging-chain perspective. Extensive evaluations using multiple baseline methods under complex scattering conditions demonstrate the effectiveness of the proposed benchmark, achieving a best mean angular error of 15.49 degrees. To the best of our knowledge, MuS-Polar3D is the first publicly available benchmark dataset for quantitative turbidity underwater polarization-based 3D imaging, enabling accurate reconstruction and fair algorithm evaluation under controllable scattering conditions. The dataset and code are publicly available at https://github.com/WangPuyun/MuS-Polar3D. --- ### Fixed-Threshold Evaluation of a Hybrid CNN-ViT for AI-Generated Image Detection Across Photos and Art Authors: Md Ashik Khan, Arafat Alam Jion Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21512v1 AI image generators create both photorealistic images and stylized art, necessitating robust detectors that maintain performance under common post-processing transformations (JPEG compression, blur, downscaling). Existing methods optimize single metrics without addressing deployment-critical factors such as operating point selection and fixed-threshold robustness. This work addresses misleading robustness estimates by introducing a fixed-threshold evaluation protocol that holds decision thresholds, selected once on clean validation data, fixed across all post-processing transformations. Traditional methods retune thresholds per condition, artificially inflating robustness estimates and masking deployment failures. We report deployment-relevant performance at three operating points (Low-FPR, ROC-optimal, Best-F1) under systematic degradation testing using a lightweight CNN-ViT hybrid with gated fusion and optional frequency enhancement. Our evaluation exposes a statistically validated forensic-semantic spectrum: frequency-aided CNNs excel on pristine photos but collapse under compression (93.33% to 61.49%), whereas ViTs degrade minimally (92.86% to 88.36%) through robust semantic pattern recognition. Multi-seed experiments demonstrate that all architectures achieve 15% higher AUROC on artistic content (0.901-0.907) versus photorealistic images (0.747-0.759), confirming that semantic patterns provide fundamentally more reliable detection cues than forensic artifacts. Our hybrid approach achieves balanced cross-domain performance: 91.4% accuracy on tiny-genimage photos, 89.7% on AiArtData art/graphics, and 98.3% (competitive) on CIFAKE. Fixed-threshold evaluation eliminates retuning inflation, reveals genuine robustness gaps, and yields actionable deployment guidance: prefer CNNs for clean photo verification, ViTs for compressed content, and hybrids for art/graphics screening. --- ### Missing Pattern Tree based Decision Grouping and Ensemble for Enhancing Pair Utilization in Deep Incomplete Multi-View Clustering Authors: Jie Xu, Wenyuan Yang, Yazhou Ren, Lifang He, Philip S. Yu, Xiaofeng Zhu Published: 2025-12-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.21510v2 Real-world multi-view data often exhibit highly inconsistent missing patterns, posing significant challenges for incomplete multi-view clustering (IMVC). Although existing IMVC methods have made progress from both imputation-based and imputation-free routes, they largely overlook the issue of pair underutilization. Specifically, inconsistent missing patterns prevent incomplete but available multi-view pairs from being fully exploited, thereby limiting the model performance. To address this limitation, we propose a novel missing-pattern tree based IMVC framework. Specifically, to fully leverage available multi-view pairs, we first introduce a missing-pattern tree model to group data into multiple decision sets according to their missing patterns, and then perform multi-view clustering within each set. Furthermore, a multi-view decision ensemble module is proposed to aggregate clustering results across all decision sets. This module infers uncertainty-based weights to suppress unreliable clustering decisions and produce robust outputs. Finally, we develop an ensemble-to-individual knowledge distillation module module, which transfers ensemble knowledge to view-specific clustering models. This design enables mutual enhancement between ensemble and individual modules by optimizing cross-view consistency and inter-cluster discrimination losses. Extensive theoretical analysis supports our key designs, and empirical experiments on multiple benchmark datasets demonstrate that our method effectively mitigates the pair underutilization issue and achieve superior IMVC performance. --- ### Fixed-Budget Parameter-Efficient Training with Frozen Encoders Improves Multimodal Chest X-Ray Classification Authors: Md Ashik Khan, Md Nahid Siddique Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21508v1 Multimodal chest X-Ray analysis often fine-tunes large vision-language models, which is computationally costly. We study parameter-efficient training (PET) strategies, including frozen encoders, BitFit, LoRA, and adapters for multi-label classification on the Indiana University Chest X-Ray dataset (3,851 image-report pairs; 579 test samples). To mitigate data leakage, we redact pathology terms from reports used as text inputs while retaining clinical context. Under a fixed parameter budget (2.37M parameters, 2.51% of total), all PET variants achieve AUROC between 0.892 and 0.908, outperforming full fine-tuning (0.770 AUROC), which uses 94.3M trainable parameters, a 40x reduction. External validation on CheXpert (224,316 images, 58x larger) confirms scalability: all PET methods achieve >0.69 AUROC with <9% trainable parameters, with Adapter achieving best performance (0.7214 AUROC). Budget-matched comparisons reveal that vision-only models (0.653 AUROC, 1.06M parameters) outperform budget-matched multimodal models (0.641 AUROC, 1.06M parameters), indicating improvements arise primarily from parameter allocation rather than cross-modal synergy. While PET methods show degraded calibration (ECE: 0.29-0.34) compared to simpler models (ECE: 0.049), this represents a tractable limitation addressable through post-hoc calibration methods. These findings demonstrate that frozen encoder strategies provide superior discrimination at substantially reduced computational cost, though calibration correction is essential for clinical deployment. --- ### SVBench: Evaluation of Video Generation Models on Social Reasoning Authors: Wenshuo Peng, Gongxuan Wang, Tianmeng Yang, Chuanhao Li, Xiaojie Xu, Hui He, Kaipeng Zhang Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21507v5 Recent text-to-video generation models have made remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they still struggle to produce socially coherent behavior. Unlike humans, who readily infer intentions, beliefs, emotions, and social norms from brief visual cues, current models often generate literal scenes without capturing the underlying causal and psychological dynamics. To systematically assess this limitation, we introduce the first benchmark for social reasoning in video generation. Grounded in developmental and social psychology, the benchmark covers thirty classic social cognition paradigms spanning seven core dimensions: mental-state inference, goal-directed action, joint attention, social coordination, prosocial behavior, social norms, and multi-agent strategy. To operationalize these paradigms, we build a fully training-free agent-based pipeline that distills the reasoning structure of each paradigm, synthesizes diverse video-ready scenarios, enforces conceptual neutrality and difficulty control through cue-based critique, and evaluates generated videos with a high-capacity VLM judge along five interpretable dimensions of social reasoning. Using this framework, we conduct the first large-scale evaluation of seven state-of-the-art video generation systems. Results show a clear gap between surface-level plausibility and deeper social reasoning, suggesting that current models remain limited in their ability to generate socially grounded behavior. https://github.com/Gloria2tt/SVBench-Evaluation --- ### MotionTeller: Multi-modal Integration of Wearable Time-Series with LLMs for Health and Behavioral Understanding Authors: Aiwei Zhang, Arvind Pillai, Andrew Campbell, Nicholas C. Jacobson Published: 2025-12-25 Categories: cs.LG, cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2512.21506v1 As wearable sensing becomes increasingly pervasive, a key challenge remains: how can we generate natural language summaries from raw physiological signals such as actigraphy - minute-level movement data collected via accelerometers? In this work, we introduce MotionTeller, a generative framework that natively integrates minute-level wearable activity data with large language models (LLMs). MotionTeller combines a pretrained actigraphy encoder with a lightweight projection module that maps behavioral embeddings into the token space of a frozen decoder-only LLM, enabling free-text, autoregressive generation of daily behavioral summaries. We construct a novel dataset of 54383 (actigraphy, text) pairs derived from real-world NHANES recordings, and train the model using cross-entropy loss with supervision only on the language tokens. MotionTeller achieves high semantic fidelity (BERTScore-F1 = 0.924) and lexical accuracy (ROUGE-1 = 0.722), outperforming prompt-based baselines by 7 percent in ROUGE-1. The average training loss converges to 0.38 by epoch 15, indicating stable optimization. Qualitative analysis confirms that MotionTeller captures circadian structure and behavioral transitions, while PCA plots reveal enhanced cluster alignment in embedding space post-training. Together, these results position MotionTeller as a scalable, interpretable system for transforming wearable sensor data into fluent, human-centered descriptions, introducing new pathways for behavioral monitoring, clinical review, and personalized health interventions. --- ### Generative Multi-Focus Image Fusion Authors: Xinzhe Xie, Buyu Guo, Bolin Li, Shuangyan He, Yanzhen Gu, Qingyan Jiang, Peiliang Li Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21495v1 Multi-focus image fusion aims to generate an all-in-focus image from a sequence of partially focused input images. Existing fusion algorithms generally assume that, for every spatial location in the scene, there is at least one input image in which that location is in focus. Furthermore, current fusion models often suffer from edge artifacts caused by uncertain focus estimation or hard-selection operations in complex real-world scenarios. To address these limitations, we propose a generative multi-focus image fusion framework, termed GMFF, which operates in two sequential stages. In the first stage, deterministic fusion is implemented using StackMFF V4, the latest version of the StackMFF series, and integrates the available focal plane information to produce an initial fused image. The second stage, generative restoration, is realized through IFControlNet, which leverages the generative capabilities of latent diffusion models to reconstruct content from missing focal planes, restore fine details, and eliminate edge artifacts. Each stage is independently developed and functions seamlessly in a cascaded manner. Extensive experiments demonstrate that GMFF achieves state-of-the-art fusion performance and exhibits significant potential for practical applications, particularly in scenarios involving complex multi-focal content. The implementation is publicly available at https://github.com/Xinzhe99/StackMFF-Series. --- ### Oogiri-Master: Benchmarking Humor Understanding via Oogiri Authors: Soichiro Murakami, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura Published: 2025-12-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.21494v1 Humor is a salient testbed for human-like creative thinking in large language models (LLMs). We study humor using the Japanese creative response game Oogiri, in which participants produce witty responses to a given prompt, and ask the following research question: What makes such responses funny to humans? Previous work has offered only limited reliable means to answer this question. Existing datasets contain few candidate responses per prompt, expose popularity signals during ratings, and lack objective and comparable metrics for funniness. Thus, we introduce Oogiri-Master and Oogiri-Corpus, which are a benchmark and dataset designed to enable rigorous evaluation of humor understanding in LLMs. Each prompt is paired with approximately 100 diverse candidate responses, and funniness is rated independently by approximately 100 human judges without access to others' ratings, reducing popularity bias and enabling robust aggregation. Using Oogiri-Corpus, we conduct a quantitative analysis of the linguistic factors associated with funniness, such as text length, ambiguity, and incongruity resolution, and derive objective metrics for predicting human judgments. Subsequently, we benchmark a range of LLMs and human baselines in Oogiri-Master, demonstrating that state-of-the-art models approach human performance and that insight-augmented prompting improves the model performance. Our results provide a principled basis for evaluating and advancing humor understanding in LLMs. --- ### Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism Authors: Xinglin Pan, Shaohuai Shi, Wenxiang Lin, Yuxin Wang, Zhenheng Tang, Wei Wang, Xiaowen Chu Published: 2025-12-25 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2512.21487v1 The mixture-of-experts (MoE) architecture scales model size with sublinear computational increase but suffers from memory-intensive inference due to KV caches and sparse expert activation. Recent disaggregated expert parallelism (DEP) distributes attention and experts to dedicated GPU groups but lacks support for shared experts and efficient task scheduling, limiting performance. We propose FinDEP, a fine-grained task scheduling algorithm for DEP that maximizes task overlap to improve MoE inference throughput. FinDEP introduces three innovations: 1) partitioning computation/communication into smaller tasks for fine-grained pipelining, 2) formulating a scheduling optimization supporting variable granularity and ordering, and 3) developing an efficient solver for this large search space. Experiments on four GPU systems with DeepSeek-V2 and Qwen3-MoE show FinDEP improves throughput by up to 1.61x over prior methods, achieving up to 1.24x speedup on a 32-GPU system. --- ### When Bayesian Tensor Completion Meets Multioutput Gaussian Processes: Functional Universality and Rank Learning Authors: Siyuan Li, Shikai Fang, Lei Cheng, Feng Yin, Yik-Chung Wu, Peter Gerstoft, Sergios Theodoridis Published: 2025-12-25 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2512.21486v1 Functional tensor decomposition can analyze multi-dimensional data with real-valued indices, paving the path for applications in machine learning and signal processing. A limitation of existing approaches is the assumption that the tensor rank-a critical parameter governing model complexity-is known. However, determining the optimal rank is a non-deterministic polynomial-time hard (NP-hard) task and there is a limited understanding regarding the expressive power of functional low-rank tensor models for continuous signals. We propose a rank-revealing functional Bayesian tensor completion (RR-FBTC) method. Modeling the latent functions through carefully designed multioutput Gaussian processes, RR-FBTC handles tensors with real-valued indices while enabling automatic tensor rank determination during the inference process. We establish the universal approximation property of the model for continuous multi-dimensional signals, demonstrating its expressive power in a concise format. To learn this model, we employ the variational inference framework and derive an efficient algorithm with closed-form updates. Experiments on both synthetic and real-world datasets demonstrate the effectiveness and superiority of the RR-FBTC over state-of-the-art approaches. The code is available at https://github.com/OceanSTARLab/RR-FBTC. --- ### LogicLens: Visual-Logical Co-Reasoning for Text-Centric Forgery Analysis Authors: Fanwei Zeng, Changtao Miao, Jing Huang, Zhiya Tan, Shutao Gong, Xiaoming Yu, Yang Wang, Huazhe Tan, Weibin Yao, Jianshu Li Published: 2025-12-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.21482v1 Sophisticated text-centric forgeries, fueled by rapid AIGC advancements, pose a significant threat to societal security and information authenticity. Current methods for text-centric forgery analysis are often limited to coarse-grained visual analysis and lack the capacity for sophisticated reasoning. Moreover, they typically treat detection, grounding, and explanation as discrete sub-tasks, overlooking their intrinsic relationships for holistic performance enhancement. To address these challenges, we introduce LogicLens, a unified framework for Visual-Textual Co-reasoning that reformulates these objectives into a joint task. The deep reasoning of LogicLens is powered by our novel Cross-Cues-aware Chain of Thought (CCT) mechanism, which iteratively cross-validates visual cues against textual logic. To ensure robust alignment across all tasks, we further propose a weighted multi-task reward function for GRPO-based optimization. Complementing this framework, we first designed the PR$^2$ (Perceiver, Reasoner, Reviewer) pipeline, a hierarchical and iterative multi-agent system that generates high-quality, cognitively-aligned annotations. Then, we constructed RealText, a diverse dataset comprising 5,397 images with fine-grained annotations, including textual explanations, pixel-level segmentation, and authenticity labels for model training. Extensive experiments demonstrate the superiority of LogicLens across multiple benchmarks. In a zero-shot evaluation on T-IC13, it surpasses the specialized framework by 41.4% and GPT-4o by 23.4% in macro-average F1 score. Moreover, on the challenging dense-text T-SROIE dataset, it establishes a significant lead over other MLLM-based methods in mF1, CSS, and the macro-average F1. Our dataset, model, and code will be made publicly available. --- ### Quantum Nondecimated Wavelet Transform: Theory, Circuits, and Applications Authors: Brani Vidakovic Published: 2025-12-25 Categories: quant-ph, cs.LG, physics.data-an, stat.CO arXiv: https://arxiv.org/abs/2512.21478v1 The nondecimated or translation-invariant wavelet transform (NDWT) is a central tool in classical multiscale signal analysis, valued for its stability, redundancy, and shift invariance. This paper develops two complementary quantum formulations of the NDWT that embed these classical properties coherently into quantum computation. The first formulation is based on the epsilon-decimated interpretation of the NDWT and realizes all circularly shifted wavelet transforms simultaneously by promoting the shift index to a quantum register and applying controlled circular shifts followed by a wavelet analysis unitary. The resulting construction yields an explicit, fully unitary quantum representation of redundant wavelet coefficients and supports coherent postprocessing, including quantum shrinkage via ancilla-driven completely positive trace preserving maps. The second formulation is based on the Hadamard test and uses diagonal phase operators to probe scale-shift wavelet structure through interference, providing direct access to shift-invariant energy scalograms and multiscale spectra without explicit coefficient reconstruction. Together, these two approaches demonstrate that redundancy and translation invariance can be exploited rather than avoided in the quantum setting. Applications to denoising, feature extraction, and spectral scaling illustrate how quantum NDWTs provide a flexible and physically meaningful foundation for multiscale quantum signal processing. --- ### GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification Authors: Suncheng Xiang, Xiaoyang Wang, Junjie Jiang, Hejia Wang, Dahong Qian Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21476v2 Colonoscopic Polyp Re-Identification (ReID) aims to match the same polyp across a large gallery of images captured from different viewpoints and with different cameras, playing a critical role in computer-aided diagnosis for the prevention and treatment of colorectal cancer. However, the coarse granularity of high-level features often limits performance on small polyps, where fine-grained details are essential for accurate matching. To address this challenge, we propose a novel multimodal feature fusion architecture, termed the Gated Progressive Fusion Network, which selectively integrates features from multiple levels through fully connected gating mechanisms. Building on this framework, we introduce a gated progressive fusion strategy that enables layer-wise refinement of semantic information, facilitating multi-level feature interactions to enhance both generalization ability and robustness. Extensive experiments on standard benchmarks demonstrate the advantages of the multimodal setting over state-of-the-art unimodal ReID models, particularly when combined with the proposed fusion strategy tailored for general-purpose scenarios. --- ### IMA++: ISIC Archive Multi-Annotator Dermoscopic Skin Lesion Segmentation Dataset Authors: Kumar Abhishek, Jeremy Kawahara, Ghassan Hamarneh Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21472v2 Multi-annotator medical image segmentation is an important research problem, but requires annotated datasets that are expensive to collect. Dermoscopic skin lesion imaging allows human experts and AI systems to observe morphological structures otherwise not discernable from regular clinical photographs. However, currently there are no large-scale publicly available multi-annotator skin lesion segmentation (SLS) datasets with annotator-labels for dermoscopic skin lesion imaging. We introduce ISIC MultiAnnot++, a large public multi-annotator skin lesion segmentation dataset for images from the ISIC Archive. The final dataset contains 17,684 segmentation masks spanning 14,967 dermoscopic images, where 2,394 dermoscopic images have 2-5 segmentations per image, making it the largest publicly available SLS dataset. Further, metadata about the segmentation, including the annotators' skill level and segmentation tool, is included, enabling research on topics such as annotator-specific preference modeling for segmentation and annotator metadata analysis. We provide an analysis on the characteristics of this dataset, curated data partitions, and consensus segmentation masks. --- ### CCAD: Compressed Global Feature Conditioned Anomaly Detection Authors: Xiao Jin, Liang Diao, Qixin Xiao, Yifan Hu, Ziqi Zhang, Yuchen Liu, Haisong Gu Published: 2025-12-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.21459v1 Anomaly detection holds considerable industrial significance, especially in scenarios with limited anomalous data. Currently, reconstruction-based and unsupervised representation-based approaches are the primary focus. However, unsupervised representation-based methods struggle to extract robust features under domain shift, whereas reconstruction-based methods often suffer from low training efficiency and performance degradation due to insufficient constraints. To address these challenges, we propose a novel method named Compressed Global Feature Conditioned Anomaly Detection (CCAD). CCAD synergizes the strengths of both paradigms by adapting global features as a new modality condition for the reconstruction model. Furthermore, we design an adaptive compression mechanism to enhance both generalization and training efficiency. Extensive experiments demonstrate that CCAD consistently outperforms state-of-the-art methods in terms of AUC while achieving faster convergence. In addition, we contribute a reorganized and re-annotated version of the DAGM 2007 dataset with new annotations to further validate our method's effectiveness. The code for reproducing main results is available at https://github.com/chloeqxq/CCAD. --- ### Statistical vs. Deep Learning Models for Estimating Substance Overdose Excess Mortality in the US Authors: Sukanya Krishna, Marie-Laure Charpignon, Maimuna Majumder Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21456v1 Substance overdose mortality in the United States claimed over 80,000 lives in 2023, with the COVID-19 pandemic exacerbating existing trends through healthcare disruptions and behavioral changes. Estimating excess mortality, defined as deaths beyond expected levels based on pre-pandemic patterns, is essential for understanding pandemic impacts and informing intervention strategies. However, traditional statistical methods like SARIMA assume linearity, stationarity, and fixed seasonality, which may not hold under structural disruptions. We present a systematic comparison of SARIMA against three deep learning (DL) architectures (LSTM, Seq2Seq, and Transformer) for counterfactual mortality estimation using national CDC data (2015-2019 for training/validation, 2020-2023 for projection). We contribute empirical evidence that LSTM achieves superior point estimation (17.08% MAPE vs. 23.88% for SARIMA) and better-calibrated uncertainty (68.8% vs. 47.9% prediction interval coverage) when projecting under regime change. We also demonstrate that attention-based models (Seq2Seq, Transformer) underperform due to overfitting to historical means rather than capturing emergent trends. Ourreproducible pipeline incorporates conformal prediction intervals and convergence analysis across 60+ trials per configuration, and we provide an open-source framework deployable with 15 state health departments. Our findings establish that carefully validated DL models can provide more reliable counterfactual estimates than traditional methods for public health planning, while highlighting the need for calibration techniques when deploying neural forecasting in high-stakes domains. --- ### Intelligent recognition of GPR road hidden defect images based on feature fusion and attention mechanism Authors: Haotian Lv, Yuhui Zhang, Jiangbo Dai, Hanli Wu, Jiaji Wang, Dawei Wang Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21452v1 Ground Penetrating Radar (GPR) has emerged as a pivotal tool for non-destructive evaluation of subsurface road defects. However, conventional GPR image interpretation remains heavily reliant on subjective expertise, introducing inefficiencies and inaccuracies. This study introduces a comprehensive framework to address these limitations: (1) A DCGAN-based data augmentation strategy synthesizes high-fidelity GPR images to mitigate data scarcity while preserving defect morphology under complex backgrounds; (2) A novel Multi-modal Chain and Global Attention Network (MCGA-Net) is proposed, integrating Multi-modal Chain Feature Fusion (MCFF) for hierarchical multi-scale defect representation and Global Attention Mechanism (GAM) for context-aware feature enhancement; (3) MS COCO transfer learning fine-tunes the backbone network, accelerating convergence and improving generalization. Ablation and comparison experiments validate the framework's efficacy. MCGA-Net achieves Precision (92.8%), Recall (92.5%), and mAP@50 (95.9%). In the detection of Gaussian noise, weak signals and small targets, MCGA-Net maintains robustness and outperforms other models. This work establishes a new paradigm for automated GPR-based defect detection, balancing computational efficiency with high accuracy in complex subsurface environments. --- ### An approach to Fisher-Rao metric for infinite dimensional non-parametric information geometry Authors: Bing Cheng, Howell Tong Published: 2025-12-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.21451v2 Being infinite dimensional, non-parametric information geometry has long faced an "intractability barrier" due to the fact that the Fisher-Rao metric is now a functional incurring difficulties in defining its inverse. This paper introduces a novel framework to resolve the intractability with an Orthogonal Decomposition of the Tangent Space ($T_fM = S \oplus S^{\perp}$), where $S$ represents an observable covariate subspace. Through the decomposition, we derive the Covariate Fisher Information Matrix (cFIM), denoted as ${\bf G}_f$, which is a finite-dimensional and computable representative of information extractable from the manifold's geometry. Significantly, by proving the Trace Theorem: $H_G(f) = \text{Tr}({\bf G}_f)$, we establish a rigorous foundation for the G-entropy previously introduced by us, thereby identifying it as a fundamental geometric invariant representing the total explainable statistical information captured by the probability distribution associated with a model. Furthermore, we establish a link between ${\bf G}_f$ and the second derivative (i.e. the curvature) of the KL-divergence, leading to the notion of Covariate Cramér-Rao Lower Bound(CRLB). We demonstrate that ${\bf G}_f$ is congruent to the Efficient Fisher Information Matrix, thereby providing fundamental limits of variance for semi-parametric estimators. Finally, we apply our geometric framework to the Manifold Hypothesis, lifting the latter from a heuristic assumption into a testable condition of rank-deficiency within the cFIM. By defining the Information Capture Ratio, we provide a rigorous method for estimating intrinsic dimensionality in high-dimensional data. In short, our work bridges the gap between abstract information geometry and the demand of explainable AI, by providing a tractable path for assessing the statistical coverage and the efficiency of non-parametric models. --- ### RLLaVA: An RL-central Framework for Language and Vision Assistants Authors: Lei Zhao, Zihao Ma, Boyu Lin, Yuhe Liu, Wenjun Wu, Lei Huang Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21450v1 We present an RL-central framework for Language and Vision Assistants (RLLaVA) with its formulation of Markov decision process (MDP). RLLaVA decouples RL algorithmic logic from model architecture and distributed execution, supporting researchers in implementing new RL algorithms with minimal code, and to plug in a broad family of RL methods and vision-language models (VLMs) while remaining agnostic to specific training and inference engines. RLLaVA makes resource-efficient training of 1B--7B models feasible on common GPUs; notably, 4B-scale models can be trained end-to-end with full-parameter updates on a single 24GB GPU. Experiments on multi-modal and agentic tasks demonstrate that RLLaVA has task extensibility, and the models trained with it consistently improve performance over base models, competitive with other specially engineered RL frameworks. The code is available at https://github.com/TinyLoopX/RLLaVA. --- ### Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Research Authors: Derguene Mbaye, Tatiana D. P. Mbengue, Madoune R. Seye, Moussa Diallo, Mamadou L. Ndiaye, Dimitri S. Adjanohoun, Cheikh S. Wade, Djiby Sow, Jean-Claude B. Munyaka, Jerome Chenal Published: 2025-12-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.09716v2 Natural Language Processing (NLP) is rapidly transforming research methodologies across disciplines, yet African languages remain largely underrepresented in this technological shift. This paper provides the first comprehensive overview of NLP progress and challenges for the six national languages officially recognized by the Senegalese Constitution: Wolof, Pulaar, Sérère, Diola, Mandingue, and Soninké. We synthesize linguistic, socio-technical, and infrastructural factors that shape their digital readiness and identify gaps in data, tools, and benchmarks. Building on existing initiatives and research works, we analyze ongoing efforts in various tasks, covering both text and speech modalities. We also provide a centralized GitHub repository that compiles publicly accessible resources for a range of NLP tasks across these languages, designed to facilitate collaboration and reproducibility. A special focus is devoted to the application of NLP to the social sciences, where multilingual transcription, translation, and retrieval pipelines can significantly enhance the efficiency and inclusiveness of field research. The paper concludes by outlining a roadmap toward sustainable, community-centered NLP ecosystems for Senegalese languages, emphasizing ethical data governance, open resources, and interdisciplinary collaboration. --- ### Introducing Axlerod: An LLM-based Chatbot for Assisting Independent Insurance Agents Authors: Adam Bradley, John Hastings, Khandaker Mamun Ahmed Published: 2025-12-24 Categories: cs.CL, cs.AI, cs.HC, cs.IR arXiv: https://arxiv.org/abs/2601.09715v1 The insurance industry is undergoing a paradigm shift through the adoption of artificial intelligence (AI) technologies, particularly in the realm of intelligent conversational agents. Chatbots have evolved into sophisticated AI-driven systems capable of automating complex workflows, including policy recommendation and claims triage, while simultaneously enabling dynamic, context-aware user engagement. This paper presents the design, implementation, and empirical evaluation of Axlerod, an AI-powered conversational interface designed to improve the operational efficiency of independent insurance agents. Leveraging natural language processing (NLP), retrieval-augmented generation (RAG), and domain-specific knowledge integration, Axlerod demonstrates robust capabilities in parsing user intent, accessing structured policy databases, and delivering real-time, contextually relevant responses. Experimental results underscore Axlerod's effectiveness, achieving an overall accuracy of 93.18% in policy retrieval tasks while reducing the average search time by 2.42 seconds. This work contributes to the growing body of research on enterprise-grade AI applications in insurtech, with a particular focus on agent-assistive rather than consumer-facing architectures. --- ### Evaluating Novelty in AI-Generated Research Plans Using Multi-Workflow LLM Pipelines Authors: Devesh Saraogi, Rohit Singhee, Dhruv Kumar Published: 2025-12-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.09714v1 The integration of Large Language Models (LLMs) into the scientific ecosystem raises fundamental questions about the creativity and originality of AI-generated research. Recent work has identified ``smart plagiarism'' as a concern in single-step prompting approaches, where models reproduce existing ideas with terminological shifts. This paper investigates whether agentic workflows -- multi-step systems employing iterative reasoning, evolutionary search, and recursive decomposition -- can generate more novel and feasible research plans. We benchmark five reasoning architectures: Reflection-based iterative refinement, Sakana AI v2 evolutionary algorithms, Google Co-Scientist multi-agent framework, GPT Deep Research (GPT-5.1) recursive decomposition, and Gemini~3 Pro multimodal long-context pipeline. Using evaluations from thirty proposals each on novelty, feasibility, and impact, we find that decomposition-based and long-context workflows achieve mean novelty of 4.17/5, while reflection-based approaches score significantly lower (2.33/5). Results reveal varied performance across research domains, with high-performing workflows maintaining feasibility without sacrificing creativity. These findings support the view that carefully designed multi-stage agentic workflows can advance AI-assisted research ideation. --- ### LLM-Driven Preference Data Synthesis for Proactive Prediction of the Next User Utterance in Human-Machine Dialogue Authors: Jinqiang Wang, Huansheng Ning, Jianguo Ding, Tao Zhu, Liming Chen, Chris Nugent Published: 2025-12-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.09713v1 Proactively predicting a users next utterance in human-machine dialogue can streamline interaction and improve user experience. Existing commercial API-based solutions are subject to privacy concerns while deploying general-purpose LLMs locally remains computationally expensive. As such, training a compact, task-specific LLM provides a practical alternative. Although user simulator methods can predict a user's next utterance, they mainly imitate their speaking style rather than advancing the dialogue. Preference data synthesis has been investigated to generate data for proactive next utterance prediction and help align LLMs with user preferences. Yet existing methods lack the ability to explicitly model the intent reasoning that leads to the user's next utterance and to define and synthesize preference and non-preference reasoning processes for predicting the user's next utterance.To address these challenges, we propose ProUtt, an LLM-driven preference data synthesis method for proactive next utterance prediction. ProUtt converts dialogue history into an intent tree and explicitly models intent reasoning trajectories by predicting the next plausible path from both exploitation and exploration perspectives. It then constructs preference and non-preference reasoning processes by perturbing or revising intent tree paths at different future turns. Extensive evaluations using LLM-as-a-judge and human judgments demonstrate that ProUtt consistently outperforms existing data synthesis methods, user simulators, and commercial LLM APIs across four benchmark datasets. We release both the code and the synthesized datasets to facilitate future research. --- ### The Environmental Impact of AI Servers and Sustainable Solutions Authors: Aadi Patel, Nikhil Mahalingam, Rusheen Patel Published: 2025-12-24 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.06063v1 The rapid expansion of artificial intelligence has significantly increased the electricity, water, and carbon demands of modern data centers, raising sustainability concerns. This study evaluates the environmental footprint of AI server operations and examines feasible technological and infrastructural strategies to mitigate these impacts. Using a literature-based methodology supported by quantitative projections and case-study analysis, we assessed trends in global electricity consumption, cooling-related water use, and carbon emissions. Projections indicate that global data center electricity demand may increase from approximately 415 TWh in 2024 to nearly 945 TWh by 2030, with AI workloads accounting for a disproportionate share of this growth. In the United States alone, AI servers are expected to drive annual increases in water consumption of 200--300 billion gallons and add 24--44 million metric tons of CO2 quivalent emissions by 2030. The results show that the design of the cooling system and the geographic location influence the environmental impact as strongly as the efficiency of the hardware. Advanced cooling technologies can reduce cooling energy by up to 50%, while location in low-carbon and water-secure regions can cut combined footprints by nearly half. In general, the study concludes that sustainable AI expansion requires coordinated improvements in cooling efficiency, renewable energy integration, and strategic deployment decisions. --- ### From Values to Frameworks: A Qualitative Study of Ethical Reasoning in Agentic AI Practitioners Authors: Theodore Roberts, Bahram Zarrin Published: 2025-12-24 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2601.06062v1 Agentic artificial intelligence systems are autonomous technologies capable of pursuing complex goals with minimal human oversight and are rapidly emerging as the next frontier in AI. While these systems promise major gains in productivity, they also raise new ethical challenges. Prior research has examined how different populations prioritize Responsible AI values, yet little is known about how practitioners actually reason through the trade-offs inherent in designing these autonomous systems. This paper investigates the ethical reasoning of AI practitioners through qualitative interviews centered on structured dilemmas in agentic AI deployment. We find that the responses of practitioners do not merely reflect value preferences but rather align with three distinct reasoning frameworks. First is a Customer-Centric framework where choices are justified by business interests, legality, and user autonomy. Second is a Design-Centric framework emphasizing technical safeguards and system constraints. Third is an Ethics-Centric framework prioritizing social good and moral responsibility beyond compliance. We argue that these frameworks offer distinct and necessary insights for navigating ethical trade-offs. Consequently, providers of agentic AI must look beyond general principles and actively manage how these diverse reasoning frameworks are represented in their decision-making processes to ensure robust ethical outcomes. --- ### AgentTutor: Empowering Personalized Learning with Multi-Turn Interactive Teaching in Intelligent Education Systems Authors: Yuxin Liu, Zeqing Song, Jiong Lou, Chentao Wu, Jie Li Published: 2025-12-24 Categories: cs.CY, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2601.04219v1 The rapid advancement of large-scale language models (LLMs) has shown their potential to transform intelligent education systems (IESs) through automated teaching and learning support applications. However, current IESs often rely on single-turn static question-answering, which fails to assess learners' cognitive levels, cannot adjust teaching strategies based on real-time feedback, and is limited to providing simple one-off responses. To address these issues, we introduce AgentTutor, a multi-turn interactive intelligent education system to empower personalized learning. It features an LLM-powered generative multi-agent system and a learner-specific personalized learning profile environment that dynamically optimizes and delivers teaching strategies based on learners' learning status, personalized goals, learning preferences, and multimodal study materials. It includes five key modules: curriculum decomposition, learner assessment, dynamic strategy, teaching reflection, and knowledge & experience memory. We conducted extensive experiments on multiple benchmark datasets, AgentTutor significantly enhances learners' performance while demonstrating strong effectiveness in multi-turn interactions and competitiveness in teaching quality among other baselines. --- ### LLM_annotate: A Python package for annotating and analyzing fiction characters Authors: Hannes Rosenbusch Published: 2025-12-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03274v1 LLM_annotate is a Python package for analyzing the personality of fiction characters with large language models. It standardizes workflows for annotating character behaviors in full texts (e.g., books and movie scripts), inferring character traits, and validating annotation/inference quality via a human-in-the-loop GUI. The package includes functions for text chunking, LLM-based annotation, character name disambiguation, quality scoring, and computation of character-level statistics and embeddings. Researchers can use any LLM, commercial, open-source, or custom, within LLM_annotate. Through tutorial examples using The Simpsons Movie and the novel Pride and Prejudice, I demonstrate the usage of the package for efficient and reproducible character analyses. --- ### Tree of Preferences for Diversified Recommendation Authors: Hanyang Yuan, Ning Tang, Tongya Zheng, Jiarong Xu, Xintong Hu, Renhong Huang, Shunyu Liu, Jiacong Hu, Jiawei Chen, Mingli Song Published: 2025-12-24 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2601.02386v1 Diversified recommendation has attracted increasing attention from both researchers and practitioners, which can effectively address the homogeneity of recommended items. Existing approaches predominantly aim to infer the diversity of user preferences from observed user feedback. Nonetheless, due to inherent data biases, the observed data may not fully reflect user interests, where underexplored preferences can be overwhelmed or remain unmanifested. Failing to capture these preferences can lead to suboptimal diversity in recommendations. To fill this gap, this work aims to study diversified recommendation from a data-bias perspective. Inspired by the outstanding performance of large language models (LLMs) in zero-shot inference leveraging world knowledge, we propose a novel approach that utilizes LLMs' expertise to uncover underexplored user preferences from observed behavior, ultimately providing diverse and relevant recommendations. To achieve this, we first introduce Tree of Preferences (ToP), an innovative structure constructed to model user preferences from coarse to fine. ToP enables LLMs to systematically reason over the user's rationale behind their behavior, thereby uncovering their underexplored preferences. To guide diversified recommendations using uncovered preferences, we adopt a data-centric approach, identifying candidate items that match user preferences and generating synthetic interactions that reflect underexplored preferences. These interactions are integrated to train a general recommender for diversification. Moreover, we scale up overall efficiency by dynamically selecting influential users during optimization. Extensive evaluations of both diversity and relevance show that our approach outperforms existing methods in most cases and achieves near-optimal performance in others, with reasonable inference latency. --- ### Decomposing LLM Self-Correction: The Accuracy-Correction Paradox and Error Depth Hypothesis Authors: Yin Li Published: 2025-12-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.00828v1 Large Language Models (LLMs) are widely believed to possess self-correction capabilities, yet recent studies suggest that intrinsic self-correction--where models correct their own outputs without external feedback--remains largely ineffective. In this work, we systematically decompose self-correction into three distinct sub-capabilities: error detection, error localization, and error correction. Through cross-model experiments on GSM8K-Complex (n=500 per model, 346 total errors) with three major LLMs, we uncover a striking Accuracy-Correction Paradox: weaker models (GPT-3.5, 66% accuracy) achieve 1.6x higher intrinsic correction rates than stronger models (DeepSeek, 94% accuracy)--26.8% vs 16.7%. We propose the Error Depth Hypothesis: stronger models make fewer but deeper errors that resist self-correction. Error detection rates vary dramatically across architectures (10% to 82%), yet detection capability does not predict correction success--Claude detects only 10% of errors but corrects 29% intrinsically. Surprisingly, providing error location hints hurts all models. Our findings challenge linear assumptions about model capability and self-improvement, with important implications for the design of self-refinement pipelines. --- ### Speak the Art: A Direct Speech to Image Generation Framework Authors: Mariam Saeed, Manar Amr, Farida Adel, Nada Hassan, Nour Walid, Eman Mohamed, Mohamed Hussein, Marwan Torki Published: 2025-12-24 Categories: eess.AS, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2601.00827v2 Direct speech-to-image generation has recently shown promising results. However, compared to text-to-image generation, there is still a large gap to enclose. Current approaches use two stages to tackle this task: speech encoding network and image generative adversarial network (GAN). The speech encoding networks in these approaches produce embeddings that do not capture sufficient linguistic information to semantically represent the input speech. GANs suffer from issues such as non-convergence, mode collapse, and diminished gradient, which result in unstable model parameters, limited sample diversity, and ineffective generator learning, respectively. To address these weaknesses, we introduce a framework called Speak the Art (STA) which consists of a speech encoding network and a VQ-Diffusion network conditioned on speech embeddings. To improve speech embeddings, the speech encoding network is supervised by a large pre-trained image-text model during training. Replacing GANs with diffusion leads to more stable training and the generation of diverse images. Additionally, we investigate the feasibility of extending our framework to be multilingual. As a proof of concept, we trained our framework with two languages: English and Arabic. Finally, we show that our results surpass state-of-the-art models by a large margin. --- ### Evolutionary optimization of spatially-distributed multi-sensors placement for indoor surveillance environments with security levels Authors: Luis M. Moreno-Saavedra, Vinıcius G. Costa, Adrian Garrido-Saez, Silvia Jimenez-Fernandez, Antonio Portilla-Figueras, Sancho Salcedo-Sanz Published: 2025-12-24 Categories: cs.NE arXiv: https://arxiv.org/abs/2601.00826v1 The surveillance multisensor placement is an important optimization problem that consists of positioning several sensors of different types to maximize the coverage of a determined area while minimizing the cost of the deployment. In this work, we tackle a modified version of the problem, consisting of spatially distributed multisensor placement for indoor surveillance. Our approach is focused on security surveillance of sensible indoor spaces, such as military installations, where distinct security levels can be considered. We propose an evolutionary algorithm to solve the problem, in which a novel special encoding,integer encoding with binary conversion, and effective initialization have been defined to improve the performance and convergence of the proposed algorithm. We also consider the probability of detection for each surveillance point, which depends on the distance to the sensor at hand, to better model real-life scenarios. We have tested the proposed evolutionary approach in different instances of the problem, varying both size and difficulty, and obtained excellent results in terms of the cost of sensors placement and convergence time of the algorithm. ---