# Research Papers — 2025-12 · bundle page 25 of 175 > Full-text markdown of papers #1201–1250 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/25 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/24.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/26.md) ### Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model Authors: Renping Zhou, Zanlin Ni, Tianyi Chen, Zeyu Liu, Yang Yue, Yulin Wang, Yuxuan Wang, Jingshu Liu, Gao Huang Published: 2025-12-25 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.22288v1 Recently, Masked Diffusion Models (MDMs) have shown promising potential across vision, language, and cross-modal generation. However, a notable discrepancy exists between their training and inference procedures. In particular, MDM inference is a multi-step, iterative process governed not only by the model itself but also by various schedules that dictate the token-decoding trajectory (e.g., how many tokens to decode at each step). In contrast, MDMs are typically trained using a simplified, single-step BERT-style objective that masks a subset of tokens and predicts all of them simultaneously. This step-level simplification fundamentally disconnects the training paradigm from the trajectory-level nature of inference, leaving the inference schedules never optimized during training. In this paper, we introduce Co-GRPO, which reformulates MDM generation as a unified Markov Decision Process (MDP) that jointly incorporates both the model and the inference schedule. By applying Group Relative Policy Optimization at the trajectory level, Co-GRPO cooperatively optimizes model parameters and schedule parameters under a shared reward, without requiring costly backpropagation through the multi-step generation process. This holistic optimization aligns training with inference more thoroughly and substantially improves generation quality. Empirical results across four benchmarks-ImageReward, HPS, GenEval, and DPG-Bench-demonstrate the effectiveness of our approach. For more details, please refer to our project page: https://co-grpo.github.io/ . --- ### Cluster Aggregated GAN (CAG): A Cluster-Based Hybrid Model for Appliance Pattern Generation Authors: Zikun Guo, Adeyinka. P. Adedigba, Rammohan Mallipeddi Published: 2025-12-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.22287v4 Synthetic appliance data are essential for developing non-intrusive load monitoring algorithms and enabling privacy preserving energy research, yet the scarcity of labeled datasets remains a significant barrier. Recent GAN-based methods have demonstrated the feasibility of synthesizing load patterns, but most existing approaches treat all devices uniformly within a single model, neglecting the behavioral differences between intermittent and continuous appliances and resulting in unstable training and limited output fidelity. To address these limitations, we propose the Cluster Aggregated GAN framework, a hybrid generative approach that routes each appliance to a specialized branch based on its behavioral characteristics. For intermittent appliances, a clustering module groups similar activation patterns and allocates dedicated generators for each cluster, ensuring that both common and rare operational modes receive adequate modeling capacity. Continuous appliances follow a separate branch that employs an LSTM-based generator to capture gradual temporal evolution while maintaining training stability through sequence compression. Extensive experiments on the UVIC smart plug dataset demonstrate that the proposed framework consistently outperforms baseline methods across metrics measuring realism, diversity, and training stability, and that integrating clustering as an active generative component substantially improves both interpretability and scalability. These findings establish the proposed framework as an effective approach for synthetic load generation in non-intrusive load monitoring research. --- ### A General Weighting Theory for Ensemble Learning: Beyond Variance Reduction via Spectral and Geometric Structure Authors: Ernest Fokoué Published: 2025-12-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.22286v1 Ensemble learning is traditionally justified as a variance-reduction strategy, explaining its strong performance for unstable predictors such as decision trees. This explanation, however, does not account for ensembles constructed from intrinsically stable estimators-including smoothing splines, kernel ridge regression, Gaussian process regression, and other regularized reproducing kernel Hilbert space (RKHS) methods whose variance is already tightly controlled by regularization and spectral shrinkage. This paper develops a general weighting theory for ensemble learning that moves beyond classical variance-reduction arguments. We formalize ensembles as linear operators acting on a hypothesis space and endow the space of weighting sequences with geometric and spectral constraints. Within this framework, we derive a refined bias-variance approximation decomposition showing how non-uniform, structured weights can outperform uniform averaging by reshaping approximation geometry and redistributing spectral complexity, even when variance reduction is negligible. Our main results provide conditions under which structured weighting provably dominates uniform ensembles, and show that optimal weights arise as solutions to constrained quadratic programs. Classical averaging, stacking, and recently proposed Fibonacci-based ensembles appear as special cases of this unified theory, which further accommodates geometric, sub-exponential, and heavy-tailed weighting laws. Overall, the work establishes a principled foundation for structure-driven ensemble learning, explaining why ensembles remain effective for smooth, low-variance base learners and setting the stage for distribution-adaptive and dynamically evolving weighting schemes developed in subsequent work. --- ### On Fibonacci Ensembles: An Alternative Approach to Ensemble Learning Inspired by the Timeless Architecture of the Golden Ratio Authors: Ernest Fokoué Published: 2025-12-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.22284v2 Nature rarely reveals her secrets bluntly, yet in the Fibonacci sequence she grants us a glimpse of her quiet architecture of growth, harmony, and recursive stability \citep{Koshy2001Fibonacci, Livio2002GoldenRatio}. From spiral galaxies to the unfolding of leaves, this humble sequence reflects a universal grammar of balance. In this work, we introduce \emph{Fibonacci Ensembles}, a mathematically principled yet philosophically inspired framework for ensemble learning that complements and extends classical aggregation schemes such as bagging, boosting, and random forests \citep{Breiman1996Bagging, Breiman2001RandomForests, Friedman2001GBM, Zhou2012Ensemble, HastieTibshiraniFriedman2009ESL}. Two intertwined formulations unfold: (1) the use of normalized Fibonacci weights -- tempered through orthogonalization and Rao--Blackwell optimization -- to achieve systematic variance reduction among base learners, and (2) a second-order recursive ensemble dynamic that mirrors the Fibonacci flow itself, enriching representational depth beyond classical boosting. The resulting methodology is at once rigorous and poetic: a reminder that learning systems flourish when guided by the same intrinsic harmonies that shape the natural world. Through controlled one-dimensional regression experiments using both random Fourier feature ensembles \citep{RahimiRecht2007RFF} and polynomial ensembles, we exhibit regimes in which Fibonacci weighting matches or improves upon uniform averaging and interacts in a principled way with orthogonal Rao--Blackwellization. These findings suggest that Fibonacci ensembles form a natural and interpretable design point within the broader theory of ensemble learning. --- ### Synergizing Kolmogorov-Arnold Networks with Dynamic Adaptive Weighting for High-Frequency and Multi-Scale PDE Solutions Authors: Guokan Chen, Yao Xiao, Bin Fan, Meixin Xionga, Zhicheng Lin, Yuanying Liu Published: 2025-12-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.22283v3 PINNs enhance scientific computing by incorporating physical laws into neural network structures, leading to significant advancements in scientific computing. However, PINNs struggle with multi-scale and high-frequency problems due to pathological gradient flow and spectral bias, which severely limit their predictive power. By combining an enhanced network architecture with a dynamically adaptive weighting mechanism featuring upper-bound constraints, we propose the Dynamic Balancing Adaptive Weighting Physics-Informed Kolmogorov-Arnold Network (DBAW-PIKAN). The proposed method effectively mitigates gradient-related failure modes and overcomes bottlenecks in function representation. Compared to baseline models, the proposed method accelerates the convergence process and improves solution accuracy by at least an order of magnitude without introducing additional computational complexity. Numerical results on the Klein-Gordon, Burgers, and Helmholtz equations demonstrate that DBAW-PIKAN achieves superior accuracy and generalization performance. --- ### Nonnegative matrix factorizations and related compositional models: Equivalence, identifiability, and an application on the grain-size analysis of sediments Authors: Qianqian Qi, Peter G. M. van der Heijden, Maarten A. Prins Published: 2025-12-25 Categories: stat.ML, cs.LG, math.OC, math.ST arXiv: https://arxiv.org/abs/2512.22282v2 Across fields such as machine learning, social science, and geology, considerable attention has been given to models that factorize a nonnegative matrix into the product of two or three matrices, subject to nonnegative or row-sum-to-1 constraints. Although these models are to a large extent similar or even equivalent, they are presented under different names, and their similarity is not well known. This paper highlights similarities among five models, latent budget analysis (LBA) and latent class analysis (LCA) from social science, end-member analysis (EMA) from geology, probabilistic latent semantic analysis (PLSA) and nonnegative matrix factorization (NMF) from machine learning. We focus on the identifiability of these models. We prove that the solution of LBA, EMA, LCA, PLSA is unique if and only if the solution of NMF is unique. Consequently, existing uniqueness theorems for NMF directly apply to LBA, EMA, LCA, PLSA, and vice versa. We also provide a brief review of algorithms for the estimation of these models. We illustrate NMF on a sedimentary grain-size distribution dataset from sedimentary geology, and end the paper with a discussion of closely related model: archetypal analysis. --- ### Valori: A Deterministic Memory Substrate for AI Systems Authors: Varshith Gudur Published: 2025-12-25 Categories: cs.LG, cs.AI, cs.DB, cs.DC arXiv: https://arxiv.org/abs/2512.22280v1 Modern AI systems rely on vector embeddings stored and searched using floating-point arithmetic. While effective for approximate similarity search, this design introduces fundamental non-determinism: identical models, inputs, and code can produce different memory states and retrieval results across hardware architectures (e.g., x86 vs. ARM). This prevents replayability and safe deployment, leading to silent data divergence that prevents post-hoc verification and compromises audit trails in regulated sectors. We present Valori, a deterministic AI memory substrate that replaces floating-point memory operations with fixed-point arithmetic (Q16.16) and models memory as a replayable state machine. Valori guarantees bit-identical memory states, snapshots, and search results across platforms. We demonstrate that non-determinism arises before indexing or retrieval and show how Valori enforces determinism at the memory boundary. Our results suggest that deterministic memory is a necessary primitive for trustworthy AI systems. The reference implementation is open-source and available at https://github.com/varshith-Git/Valori-Kernel (archived at https://zenodo.org/records/18022660). --- ### Hierarchical Stacking Optimization Using Dirichlet's Process (SoDip): Towards Accelerated Design for Graft Polymerization Authors: Amgad Ahmed Ali Ibrahim, Hein Htet, Ryoji Asahi Published: 2025-12-25 Categories: cs.LG, cs.CE, physics.app-ph arXiv: https://arxiv.org/abs/2512.22279v1 Radiation-induced grafting (RIG) enables precise functionalization of polymer films for ion-exchange membranes, CO2-separation membranes, and battery electrolytes by generating radicals on robust substrates to graft desired monomers. However, reproducibility remains limited due to unreported variability in base-film morphology (crystallinity, grain orientation, free volume), which governs monomer diffusion, radical distribution, and the Trommsdorff effect, leading to spatial graft gradients and performance inconsistencies. We present a hierarchical stacking optimization framework with a Dirichlet's Process (SoDip), a hierarchical data-driven framework integrating: (1) a decoder-only Transformer (DeepSeek-R1) to encode textual process descriptors (irradiation source, grafting type, substrate manufacturer); (2) TabNet and XGBoost for modelling multimodal feature interactions; (3) Gaussian Process Regression (GPR) with Dirichlet Process Mixture Models (DPMM) for uncertainty quantification and heteroscedasticity; and (4) Bayesian Optimization for efficient exploration of high-dimensional synthesis space. A diverse dataset was curated using ChemDataExtractor 2.0 and WebPlotDigitizer, incorporating numerical and textual variables across hundreds of RIG studies. In cross-validation, SoDip achieved ~33% improvement over GPR while providing calibrated confidence intervals that identify low-reproducibility regimes. Its stacked architecture integrates sparse textual and numerical inputs of varying quality, outperforming prior models and establishing a foundation for reproducible, morphology-aware design in graft polymerization research. --- ### FETAL-GAUGE: A Benchmark for Assessing Vision-Language Models in Fetal Ultrasound Authors: Hussain Alasmawi, Numan Saeed, Mohammad Yaqub Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22278v2 The growing demand for prenatal ultrasound imaging has intensified a global shortage of trained sonographers, creating barriers to essential fetal health monitoring. Deep learning has the potential to enhance sonographers' efficiency and support the training of new practitioners. Vision-Language Models (VLMs) are particularly promising for ultrasound interpretation, as they can jointly process images and text to perform multiple clinical tasks within a single framework. However, despite the expansion of VLMs, no standardized benchmark exists to evaluate their performance in fetal ultrasound imaging. This gap is primarily due to the modality's challenging nature, operator dependency, and the limited public availability of datasets. To address this gap, we present Fetal-Gauge, the first and largest visual question answering benchmark specifically designed to evaluate VLMs across various fetal ultrasound tasks. Our benchmark comprises over 42,000 images and 93,000 question-answer pairs, spanning anatomical plane identification, visual grounding of anatomical structures, fetal orientation assessment, clinical view conformity, and clinical diagnosis. We systematically evaluate several state-of-the-art VLMs, including general-purpose and medical-specific models, and reveal a substantial performance gap: the best-performing model achieves only 55\% accuracy, far below clinical requirements. Our analysis identifies critical limitations of current VLMs in fetal ultrasound interpretation, highlighting the urgent need for domain-adapted architectures and specialized training approaches. Fetal-Gauge establishes a rigorous foundation for advancing multimodal deep learning in prenatal care and provides a pathway toward addressing global healthcare accessibility challenges. Our benchmark will be publicly available once the paper gets accepted. --- ### The Illusion of Clinical Reasoning: A Benchmark Reveals the Pervasive Gap in Vision-Language Models for Clinical Competency Authors: Dingyu Wang, Zimu Yuan, Jiajun Liu, Shanggui Liu, Nan Zhou, Tianxing Xu, Di Huang, Dong Jiang Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.22275v1 Background: The rapid integration of foundation models into clinical practice and public health necessitates a rigorous evaluation of their true clinical reasoning capabilities beyond narrow examination success. Current benchmarks, typically based on medical licensing exams or curated vignettes, fail to capture the integrated, multimodal reasoning essential for real-world patient care. Methods: We developed the Bones and Joints (B&J) Benchmark, a comprehensive evaluation framework comprising 1,245 questions derived from real-world patient cases in orthopedics and sports medicine. This benchmark assesses models across 7 tasks that mirror the clinical reasoning pathway, including knowledge recall, text and image interpretation, diagnosis generation, treatment planning, and rationale provision. We evaluated eleven vision-language models (VLMs) and six large language models (LLMs), comparing their performance against expert-derived ground truth. Results: Our results demonstrate a pronounced performance gap between task types. While state-of-the-art models achieved high accuracy, exceeding 90%, on structured multiple-choice questions, their performance markedly declined on open-ended tasks requiring multimodal integration, with accuracy scarcely reaching 60%. VLMs demonstrated substantial limitations in interpreting medical images and frequently exhibited severe text-driven hallucinations, often ignoring contradictory visual evidence. Notably, models specifically fine-tuned for medical applications showed no consistent advantage over general-purpose counterparts. Conclusions: Current artificial intelligence models are not yet clinically competent for complex, multimodal reasoning. Their safe deployment should currently be limited to supportive, text-based roles. Future advancement in core clinical tasks awaits fundamental breakthroughs in multimodal integration and visual understanding. --- ### GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure Authors: Leslie Gu, Junhwa Hur, Charles Herrmann, Fangneng Zhan, Todd Zickler, Deqing Sun, Hanspeter Pfister Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22274v5 We introduce GeCo, a geometry-grounded metric for jointly detecting geometric deformation and occlusion-inconsistency artifacts in static scenes. By fusing residual motion and depth priors, GeCo produces interpretable, dense consistency maps that reveal these artifacts. We use GeCo to systematically benchmark recent video generation models, uncovering common failure modes, and further employ it as a training-free guidance loss to reduce deformation artifacts during video generation. --- ### Human-Aligned Generative Perception: Bridging Psychophysics and Generative Models Authors: Antara Titikhsha, Om Kulkarni, Dharun Muthaiah Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22272v1 Text-to-image diffusion models generate highly detailed textures, yet they often rely on surface appearance and fail to follow strict geometric constraints, particularly when those constraints conflict with the style implied by the text prompt. This reflects a broader semantic gap between human perception and current generative models. We investigate whether geometric understanding can be introduced without specialized training by using lightweight, off-the-shelf discriminators as external guidance signals. We propose a Human Perception Embedding (HPE) teacher trained on the THINGS triplet dataset, which captures human sensitivity to object shape. By injecting gradients from this teacher into the latent diffusion process, we show that geometry and style can be separated in a controllable manner. We evaluate this approach across three architectures: Stable Diffusion v1.5 with a U-Net backbone, the flow-matching model SiT-XL/2, and the diffusion transformer PixArt-Σ. Our experiments reveal that flow models tend to drift back toward their default trajectories without continuous guidance, and we demonstrate zero-shot transfer of complex three-dimensional shapes, such as an Eames chair, onto conflicting materials such as pink metal. This guided generation improves semantic alignment by about 80 percent compared to unguided baselines. Overall, our results show that small teacher models can reliably guide large generative systems, enabling stronger geometric control and broadening the creative range of text-to-image synthesis. --- ### S&P 500 Stock's Movement Prediction using CNN Authors: Rahul Gupta Published: 2025-12-25 Categories: cs.CV, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2512.21804v1 This paper is about predicting the movement of stock consist of S&P 500 index. Historically there are many approaches have been tried using various methods to predict the stock movement and being used in the market currently for algorithm trading and alpha generating systems using traditional mathematical approaches (1, 2). The success of artificial neural network recently created a lot of interest and paved the way to enable prediction using cutting-edge research in the machine learning and deep learning. Some of these papers have done a great job in implementing and explaining benefits of these new technologies. Although most these papers do not go into the complexity of the financial data and mostly utilize single dimension data, still most of these papers were successful in creating the ground for future research in this comparatively new phenomenon. In this paper, I am trying to use multivariate raw data including stock split/dividend events (as-is) present in real-world market data instead of engineered financial data. Convolution Neural Network (CNN), the best-known tool so far for image classification, is used on the multi-dimensional stock numbers taken from the market mimicking them as a vector of historical data matrices (read images) and the model achieves promising results. The predictions can be made stock by stock, i.e., a single stock, sector-wise or for the portfolio of stocks. --- ### CellMamba: Adaptive Mamba for Accurate and Efficient Cell Detection Authors: Ruochen Liu, Yi Tian, Jiahao Wang, Hongbin Liu, Xianxu Hou, Jingxin Liu Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21803v1 Cell detection in pathological images presents unique challenges due to densely packed objects, subtle inter-class differences, and severe background clutter. In this paper, we propose CellMamba, a lightweight and accurate one-stage detector tailored for fine-grained biomedical instance detection. Built upon a VSSD backbone, CellMamba integrates CellMamba Blocks, which couple either NC-Mamba or Multi-Head Self-Attention (MSA) with a novel Triple-Mapping Adaptive Coupling (TMAC) module. TMAC enhances spatial discriminability by splitting channels into two parallel branches, equipped with dual idiosyncratic and one consensus attention map, adaptively fused to preserve local sensitivity and global consistency. Furthermore, we design an Adaptive Mamba Head that fuses multi-scale features via learnable weights for robust detection under varying object sizes. Extensive experiments on two public datasets-CoNSeP and CytoDArk0-demonstrate that CellMamba outperforms both CNN-based, Transformer-based, and Mamba-based baselines in accuracy, while significantly reducing model size and inference latency. Our results validate CellMamba as an efficient and effective solution for high-resolution cell detection. --- ### Smart IoT-Based Leak Forecasting and Detection for Energy-Efficient Liquid Cooling in AI Data Centers Authors: Krishna Chaitanya Sunkara, Rambabu Konakanchi Published: 2025-12-25 Categories: cs.LG, cs.DC, cs.NI, eess.SY arXiv: https://arxiv.org/abs/2512.21801v1 AI data centers which are GPU centric, have adopted liquid cooling to handle extreme heat loads, but coolant leaks result in substantial energy loss through unplanned shutdowns and extended repair periods. We present a proof-of-concept smart IoT monitoring system combining LSTM neural networks for probabilistic leak forecasting with Random Forest classifiers for instant detection. Testing on synthetic data aligned with ASHRAE 2021 standards, our approach achieves 96.5% detection accuracy and 87% forecasting accuracy at 90% probability within plus or minus 30-minute windows. Analysis demonstrates that humidity, pressure, and flow rate deliver strong predictive signals, while temperature exhibits minimal immediate response due to thermal inertia in server hardware. The system employs MQTT streaming, InfluxDB storage, and Streamlit dashboards, forecasting leaks 2-4 hours ahead while identifying sudden events within 1 minute. For a typical 47-rack facility, this approach could prevent roughly 1,500 kWh annual energy waste through proactive maintenance rather than reactive emergency procedures. While validation remains synthetic-only, results establish feasibility for future operational deployment in sustainable data center operations. --- ### Deep Generative Models for Synthetic Financial Data: Applications to Portfolio and Risk Modeling Authors: Christophe D. Hounwanou, Yae Ulrich Gaba Published: 2025-12-25 Categories: q-fin.ST, cs.AI arXiv: https://arxiv.org/abs/2512.21798v2 Synthetic financial data provides a practical solution to the privacy, accessibility, and reproducibility challenges that often constrain empirical research in quantitative finance. This paper investigates the use of deep generative models, specifically Time-series Generative Adversarial Networks (TimeGAN) and Variational Autoencoders (VAEs) to generate realistic synthetic financial return series for portfolio construction and risk modeling applications. Using historical daily returns from the S and P 500 as a benchmark, we generate synthetic datasets under comparable market conditions and evaluate them using statistical similarity metrics, temporal structure tests, and downstream financial tasks. The study shows that TimeGAN produces synthetic data with distributional shapes, volatility patterns, and autocorrelation behaviour that are close to those observed in real returns. When applied to mean--variance portfolio optimization, the resulting synthetic datasets lead to portfolio weights, Sharpe ratios, and risk levels that remain close to those obtained from real data. The VAE provides more stable training but tends to smooth extreme market movements, which affects risk estimation. Finally, the analysis supports the use of synthetic datasets as substitutes for real financial data in portfolio analysis and risk simulation, particularly when models are able to capture temporal dynamics. Synthetic data therefore provides a privacy-preserving, cost-effective, and reproducible tool for financial experimentation and model development. --- ### Diffusion Posterior Sampling for Super-Resolution under Gaussian Measurement Noise Authors: Abu Hanif Muhammad Syarubany Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21797v1 This report studies diffusion posterior sampling (DPS) for single-image super-resolution (SISR) under a known degradation model. We implement a likelihood-guided sampling procedure that combines an unconditional diffusion prior with gradient-based conditioning to enforce measurement consistency for $4\times$ super-resolution with additive Gaussian noise. We evaluate posterior sampling (PS) conditioning across guidance scales and noise levels, using PSNR and SSIM as fidelity metrics and a combined selection score $(\mathrm{PSNR}/40)+\mathrm{SSIM}$. Our ablation shows that moderate guidance improves reconstruction quality, with the best configuration achieved at PS scale $0.95$ and noise standard deviation $σ=0.01$ (score $1.45231$). Qualitative results confirm that the selected PS setting restores sharper edges and more coherent facial details compared to the downsampled inputs, while alternative conditioning strategies (e.g., MCG and PS-annealed) exhibit different texture fidelity trade-offs. These findings highlight the importance of balancing diffusion priors and measurement-gradient strength to obtain stable, high-quality reconstructions without retraining the diffusion model for each operator. --- ### Multi-agent Adaptive Mechanism Design Authors: Qiushi Han, David Simchi-Levi, Renfei Tan, Zishuo Zhao Published: 2025-12-25 Categories: cs.GT, cs.AI, cs.LG, cs.MA, econ.TH arXiv: https://arxiv.org/abs/2512.21794v4 We study a sequential mechanism design problem in which a principal seeks to elicit truthful reports from multiple rational agents while starting with no prior knowledge of agents' beliefs. We introduce Distributionally Robust Adaptive Mechanism (DRAM), a general framework combining insights from both mechanism design and online learning to jointly address truthfulness and cost-optimality. Throughout the sequential game, the mechanism estimates agents' beliefs and iteratively updates a distributionally robust linear program with shrinking ambiguity sets to reduce payments while preserving truthfulness. Our mechanism guarantees truthful reporting with high probability while achieving $\tilde{O}(\sqrt{T})$ cumulative regret, and we establish a matching lower bound showing that no feasible adaptive mechanism can asymptotically do better. The framework generalizes to plug-in estimators, supporting structured priors and delayed feedback. To our knowledge, this is the first adaptive mechanism under general settings that maintains truthfulness and achieves optimal regret when incentive constraints are unknown and must be learned. --- ### AI for Mycetoma Diagnosis in Histopathological Images: The MICCAI 2024 Challenge Authors: Hyam Omar Ali, Sahar Alhesseen, Lamis Elkhair, Adrian Galdran, Ming Feng, Zhixiang Xiong, Zengming Lin, Kele Xu, Liang Hu, Benjamin Keel, Oliver Mills, James Battye et al. Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21792v2 Mycetoma is a neglected tropical disease caused by fungi or bacteria leading to severe tissue damage and disabilities. It affects poor and rural communities and presents medical challenges and socioeconomic burdens on patients and healthcare systems in endemic regions worldwide. Mycetoma diagnosis is a major challenge in mycetoma management, particularly in low-resource settings where expert pathologists are limited. To address this challenge, this paper presents an overview of the Mycetoma MicroImage: Detect and Classify Challenge (mAIcetoma) which was organized to advance mycetoma diagnosis through AI solutions. mAIcetoma focused on developing automated models for segmenting mycetoma grains and classifying mycetoma types from histopathological images. The challenge attracted the attention of several teams worldwide to participate and five finalist teams fulfilled the challenge objectives. The teams proposed various deep learning architectures for the ultimate goal of this challenge. Mycetoma database (MyData) was provided to participants as a standardized dataset to run the proposed models. Those models were evaluated using evaluation metrics. Results showed that all the models achieved high segmentation accuracy, emphasizing the necessitate of grain detection as a critical step in mycetoma diagnosis. In addition, the top-performing models show a significant performance in classifying mycetoma types. --- ### Synthetic Financial Data Generation for Enhanced Financial Modelling Authors: Christophe D. Hounwanou, Yae Ulrich Gaba, Pierre Ntakirutimana Published: 2025-12-25 Categories: cs.LG, q-fin.CP arXiv: https://arxiv.org/abs/2512.21791v1 Data scarcity and confidentiality in finance often impede model development and robust testing. This paper presents a unified multi-criteria evaluation framework for synthetic financial data and applies it to three representative generative paradigms: the statistical ARIMA-GARCH baseline, Variational Autoencoders (VAEs), and Time-series Generative Adversarial Networks (TimeGAN). Using historical S and P 500 daily data, we evaluate fidelity (Maximum Mean Discrepancy, MMD), temporal structure (autocorrelation and volatility clustering), and practical utility in downstream tasks, specifically mean-variance portfolio optimization and volatility forecasting. Empirical results indicate that ARIMA-GARCH captures linear trends and conditional volatility but fails to reproduce nonlinear dynamics; VAEs produce smooth trajectories that underestimate extreme events; and TimeGAN achieves the best trade-off between realism and temporal coherence (e.g., TimeGAN attained the lowest MMD: 1.84e-3, average over 5 seeds). Finally, we articulate practical guidelines for selecting generative models according to application needs and computational constraints. Our unified evaluation protocol and reproducible codebase aim to standardize benchmarking in synthetic financial data research. --- ### Five Years of SciCap: What We Learned and Future Directions for Scientific Figure Captioning Authors: Ting-Hao 'Kenneth' Huang, Ryan A. Rossi, Sungchul Kim, Tong Yu, Ting-Yao E. Hsu, Ho Yin, Ng, C. Lee Giles Published: 2025-12-25 Categories: cs.CL, cs.AI, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2512.21789v2 Between 2021 and 2025, the SciCap project grew from a small seed-funded idea at The Pennsylvania State University (Penn State) into one of the central efforts shaping the scientific figure-captioning landscape. Supported by a Penn State seed grant, Adobe, and the Alfred P. Sloan Foundation, what began as our attempt to test whether domain-specific training, which was successful in text models like SciBERT, could also work for figure captions expanded into a multi-institution collaboration. Over these five years, we curated, released, and continually updated a large collection of figure-caption pairs from arXiv papers, conducted extensive automatic and human evaluations on both generated and author-written captions, navigated the rapid rise of large language models (LLMs), launched annual challenges, and built interactive systems that help scientists write better captions. In this piece, we look back at the first five years of SciCap and summarize the key technical and methodological lessons we learned. We then outline five major unsolved challenges and propose directions for the next phase of research in scientific figure captioning. --- ### InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation Authors: Jinqi Xiao, Qing Yan, Liming Jiang, Zichuan Liu, Hao Kang, Shen Sang, Tiancheng Zhi, Jing Liu, Cheng Yang, Xin Lu, Bo Yuan Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21788v3 Parameter-Efficient Fine-Tuning of Diffusion Transformers (DiTs) for diverse, multi-conditional tasks often suffers from task interference when using monolithic adapters like LoRA. The Mixture of Low-rank Experts (MoLE) architecture offers a modular solution, but its potential is usually limited by routing policies that operate at a token level. Such local routing can conflict with the global nature of user instructions, leading to artifacts like spatial fragmentation and semantic drift in complex image generation tasks. To address these limitations, we introduce InstructMoLE, a novel framework that employs an Instruction-Guided Mixture of Low-Rank Experts. Instead of per-token routing, InstructMoLE utilizes a global routing signal, Instruction-Guided Routing (IGR), derived from the user's comprehensive instruction. This ensures that a single, coherently chosen expert council is applied uniformly across all input tokens, preserving the global semantics and structural integrity of the generation process. To complement this, we introduce an output-space orthogonality loss, which promotes expert functional diversity and mitigates representational collapse. Extensive experiments demonstrate that InstructMoLE significantly outperforms existing LoRA adapters and MoLE variants across challenging multi-conditional generation benchmarks. Our work presents a robust and generalizable framework for instruction-driven fine-tuning of generative models, enabling superior compositional control and fidelity to user intent. --- ### Ara-HOPE: Human-Centric Post-Editing Evaluation for Dialectal Arabic to Modern Standard Arabic Translation Authors: Abdullah Alabdullah, Lifeng Han, Chenghua Lin Published: 2025-12-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21787v2 Dialectal Arabic to Modern Standard Arabic (DA-MSA) translation is a challenging task in Machine Translation (MT) due to significant lexical, syntactic, and semantic divergences between Arabic dialects and MSA. Existing automatic evaluation metrics and general-purpose human evaluation frameworks struggle to capture dialect-specific MT errors, hindering progress in translation assessment. This paper introduces Ara-HOPE, a human-centric post-editing evaluation framework designed to systematically address these challenges. The framework includes a five-category error taxonomy and a decision-tree annotation protocol. Through comparative evaluation of three MT systems (Arabic-centric Jais, general-purpose GPT-3.5, and baseline NLLB-200), Ara-HOPE effectively highlights systematic performance differences between these systems. Our results show that dialect-specific terminology and semantic preservation remain the most persistent challenges in DA-MSA translation. Ara-HOPE establishes a new framework for evaluating Dialectal Arabic MT quality and provides actionable guidance for improving dialect-aware MT systems. For reproducibility, we make the annotation files and related materials publicly available at https://github.com/abdullahalabdullah/Ara-HOPE --- ### VAMP-Net: An Interpretable Multi-Path Network of Genomic Permutation-Invariant Set Attention and Quality-Aware 1D-CNN for MTB Drug Resistance Authors: Aicha Boutorh, Kamar Hibatallah Baghdadi, Anais Daoud Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21786v2 Genomic prediction of drug resistance in Mycobacterium tuberculosis is often hindered by complex epistatic interactions and variable sequencing quality. We present the Interpretable Variant-Aware Multi-Path Network (VAMP-Net), a novel architecture addressing these challenges through a dual-pathway approach. Path-1 utilizes a Set Attention Transformer to model permutation-invariant variant sets and capture epistatic dependencies, while Path-2 employs a 1D-CNN to analyze VCF quality metrics for adaptive confidence scoring. Evaluated on four critical anti-TB drugs, VAMP-Net significantly outperforms baseline CNN and MLP models, achieving accuracies > 95% and AUCs around 0.97 for Rifampicin and Rifabutin. Feature attribution analysis via Integrated Gradients successfully recovered canonical targets (rpoB, embB, katG) and discovered high-impact novel loci. Functional enrichment confirmed these novel variants constitute non-random metabolic modules (p=0.00239) centered on cell-wall remodeling. Furthermore, systematic ablation of the Quality-Aware pathway demonstrates that the model performs a learned "integrated audit," prioritizing the Fraction of Supporting Reads and relative confidence over raw depth to mitigate technical noise. This dual-layer interpretability, bridging genomic pathogenicity with technical reliability, establishes a new paradigm for robust, auditable, and clinically actionable resistance prediction, positioning VAMP-Net as an important tool for both diagnostic classification and mechanistic discovery in clinical genomics. --- ### Accelerating Scientific Discovery with Autonomous Goal-evolving Agents Authors: Yuanqi Du, Botao Yu, Tianyu Liu, Tony Shen, Junwu Chen, Jan G. Rittig, Kunyang Sun, Yikun Zhang, Aarti Krishnan, Yu Zhang, Daniel Rosen, Rosali Pirone et al. Published: 2025-12-25 Categories: cs.AI, cond-mat.mtrl-sci, cs.LG, physics.chem-ph arXiv: https://arxiv.org/abs/2512.21782v2 There has been unprecedented interest in developing agents that expand the boundary of scientific discovery, primarily by optimizing quantitative objective functions specified by scientists. However, for grand challenges in science, these objectives may only be imperfect proxies. We argue that automating objective function design is a central, yet unmet need for scientific discovery agents. In this work, we introduce the Scientific Autonomous Goal-evolving Agent (SAGA) to address this challenge. SAGA employs a bi-level architecture in which an outer loop of LLM agents analyzes optimization outcomes, proposes new objectives, and converts them into computable scoring functions, while an inner loop performs solution optimization under the current objectives. This bi-level design enables systematic exploration of the space of objectives and their trade-offs, rather than treating them as fixed inputs. We demonstrate the framework through a wide range of design applications, including antibiotics, nanobodies, functional DNA sequences, inorganic materials, and chemical processes. Notably, our experimental validation identifies a structurally novel hit with promising potency and safety profiles for E. coli in the antibiotic design task, and three de novo PD-L1 binders in the nanobody design task. These results suggest that automating objective formulation can substantially improve the effectiveness of scientific discovery agents. --- ### Scene-VLM: Multimodal Video Scene Segmentation via Vision-Language Models Authors: Nimrod Berman, Adam Botach, Emanuel Ben-Baruch, Shunit Haviv Hakimi, Asaf Gendler, Ilan Naiman, Erez Yosef, Igor Kviatkovsky Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21778v2 Segmenting long-form videos into semantically coherent scenes is a fundamental task in large-scale video understanding. Existing encoder-based methods are limited by visual-centric biases, classify each shot in isolation without leveraging sequential dependencies, and lack both narrative understanding and explainability. In this paper, we present Scene-VLM, the first fine-tuned vision-language model (VLM) framework for video scene segmentation. Scene-VLM jointly processes visual and textual cues including frames, transcriptions, and optional metadata to enable multimodal reasoning across consecutive shots. The model generates predictions sequentially with causal dependencies among shots and introduces a context-focus window mechanism to ensure sufficient temporal context for each shot-level decision. In addition, we propose a scheme to extract confidence scores from the token-level logits of the VLM, enabling controllable precision-recall trade-offs that were previously limited to encoder-based methods. Furthermore, we demonstrate that our model can be aligned to generate coherent natural-language rationales for its boundary decisions through minimal targeted supervision. Our approach achieves state-of-the-art performance on standard scene segmentation benchmarks. On MovieNet, for example, Scene-VLM yields significant improvements of +6 AP and +13.7 F1 over the previous leading method. --- ### Inference-based GAN Video Generation Authors: Jingbo Yang, Adrian G. Bors Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21776v2 Video generation has seen remarkable progress thanks to advancements in generative deep learning. However, generating long sequences remains a significant challenge. Generated videos should not only display coherent and continuous movement but also meaningful movement in successions of scenes. Models such as GANs, VAEs, and Diffusion Networks have been used for generating short video sequences, typically up to 16 frames. In this paper, we first propose a new type of video generator by enabling adversarial-based unconditional video generators with a variational encoder, akin to a VAE-GAN hybrid structure. The proposed model, as in other video deep learning-based processing frameworks, incorporates two processing branches, one for content and another for movement. However, existing models struggle with the temporal scaling of the generated videos. Classical approaches often result in degraded video quality when attempting to increase the generated video length, especially for significantly long sequences. To overcome this limitation, our research study extends the initially proposed VAE-GAN video generation model by employing a novel, memory-efficient approach to generate long videos composed of hundreds or thousands of frames ensuring their temporal continuity, consistency and dynamics. Our approach leverages a Markov chain framework with a recall mechanism, where each state represents a short-length VAE-GAN video generator. This setup enables the sequential connection of generated video sub-sequences, maintaining temporal dependencies and resulting in meaningful long video sequences. --- ### Compliance Rating Scheme: A Data Provenance Framework for Generative AI Datasets Authors: Matyas Bohacek, Ignacio Vilanova Echavarri Published: 2025-12-25 Categories: cs.AI, cs.CY, cs.DB arXiv: https://arxiv.org/abs/2512.21775v1 Generative Artificial Intelligence (GAI) has experienced exponential growth in recent years, partly facilitated by the abundance of large-scale open-source datasets. These datasets are often built using unrestricted and opaque data collection practices. While most literature focuses on the development and applications of GAI models, the ethical and legal considerations surrounding the creation of these datasets are often neglected. In addition, as datasets are shared, edited, and further reproduced online, information about their origin, legitimacy, and safety often gets lost. To address this gap, we introduce the Compliance Rating Scheme (CRS), a framework designed to evaluate dataset compliance with critical transparency, accountability, and security principles. We also release an open-source Python library built around data provenance technology to implement this framework, allowing for seamless integration into existing dataset-processing and AI training pipelines. The library is simultaneously reactive and proactive, as in addition to evaluating the CRS of existing datasets, it equally informs responsible scraping and construction of new datasets. --- ### BertsWin: Resolving Topological Sparsity in 3D Masked Autoencoders via Component-Balanced Structural Optimization Authors: Evgeny Alves Limarenko, Anastasiia Studenikina Published: 2025-12-25 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2512.21769v1 The application of self-supervised learning (SSL) and Vision Transformers (ViTs) approaches demonstrates promising results in the field of 2D medical imaging, but the use of these methods on 3D volumetric images is fraught with difficulties. Standard Masked Autoencoders (MAE), which are state-of-the-art solution for 2D, have a hard time capturing three-dimensional spatial relationships, especially when 75% of tokens are discarded during pre-training. We propose BertsWin, a hybrid architecture combining full BERT-style token masking using Swin Transformer windows, to enhance spatial context learning in 3D during SSL pre-training. Unlike the classic MAE, which processes only visible areas, BertsWin introduces a complete 3D grid of tokens (masked and visible), preserving the spatial topology. And to smooth out the quadratic complexity of ViT, single-level local Swin windows are used. We introduce a structural priority loss function and evaluate the results of cone beam computed tomography of the temporomandibular joints. The subsequent assessment includes TMJ segmentation on 3D CT scans. We demonstrate that the BertsWin architecture, by maintaining a complete three-dimensional spatial topology, inherently accelerates semantic convergence by a factor of 5.8x compared to standard ViT-MAE baselines. Furthermore, when coupled with our proposed GradientConductor optimizer, the full BertsWin framework achieves a 15-fold reduction in training epochs (44 vs 660) required to reach state-of-the-art reconstruction fidelity. Analysis reveals that BertsWin achieves this acceleration without the computational penalty typically associated with dense volumetric processing. At canonical input resolutions, the architecture maintains theoretical FLOP parity with sparse ViT baselines, resulting in a significant net reduction in total computational resources due to faster convergence. --- ### Assessing the Effectiveness of Membership Inference on Generative Music Authors: Kurtis Chow, Omar Samiullah, Vinesh Sridhar, Hewen Zhang Published: 2025-12-25 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.21762v1 Generative AI systems are quickly improving, now able to produce believable output in several modalities including images, text, and audio. However, this fast development has prompted increased scrutiny concerning user privacy and the use of copyrighted works in training. A recent attack on machine-learning models called membership inference lies at the crossroads of these two concerns. The attack is given as input a set of records and a trained model and seeks to identify which of those records may have been used to train the model. On one hand, this attack can be used to identify user data used to train a model, which may violate their privacy especially in sensitive applications such as models trained on medical data. On the other hand, this attack can be used by rights-holders as evidence that a company used their works without permission to train a model. Remarkably, it appears that no work has studied the effect of membership inference attacks (MIA) on generative music. Given that the music industry is worth billions of dollars and artists would stand to gain from being able to determine if their works were being used without permission, we believe this is a pressing issue to study. As such, in this work we begin a preliminary study into whether MIAs are effective on generative music. We study the effect of several existing attacks on MuseGAN, a popular and influential generative music model. Similar to prior work on generative audio MIAs, our findings suggest that music data is fairly resilient to known membership inference techniques. --- ### A-QCF-Net: An Adaptive Quaternion Cross-Fusion Network for Multimodal Liver Tumor Segmentation from Unpaired Datasets Authors: Arunkumar V, Firos V M, Senthilkumar S, Gangadharan G R Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21760v1 Multimodal medical imaging provides complementary information that is crucial for accurate delineation of pathology, but the development of deep learning models is limited by the scarcity of large datasets in which different modalities are paired and spatially aligned. This paper addresses this fundamental limitation by proposing an Adaptive Quaternion Cross-Fusion Network (A-QCF-Net) that learns a single unified segmentation model from completely separate and unpaired CT and MRI cohorts. The architecture exploits the parameter efficiency and expressive power of Quaternion Neural Networks to construct a shared feature space. At its core is the Adaptive Quaternion Cross-Fusion (A-QCF) block, a data driven attention module that enables bidirectional knowledge transfer between the two streams. By learning to modulate the flow of information dynamically, the A-QCF block allows the network to exchange abstract modality specific expertise, such as the sharp anatomical boundary information available in CT and the subtle soft tissue contrast provided by MRI. This mutual exchange regularizes and enriches the feature representations of both streams. We validate the framework by jointly training a single model on the unpaired LiTS (CT) and ATLAS (MRI) datasets. The jointly trained model achieves Tumor Dice scores of 76.7% on CT and 78.3% on MRI, significantly exceeding the strong unimodal nnU-Net baseline by margins of 5.4% and 4.7% respectively. Furthermore, comprehensive explainability analysis using Grad-CAM and Grad-CAM++ confirms that the model correctly focuses on relevant pathological structures, ensuring the learned representations are clinically meaningful. This provides a robust and clinically viable paradigm for unlocking the large unpaired imaging archives that are common in healthcare. --- ### How Do Agents Perform Code Optimization? An Empirical Study Authors: Huiyun Peng, Antonio Zhong, Ricardo Andrés Calvo Méndez, Kelechi G. Kalu, James C. Davis Published: 2025-12-25 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.21757v1 Performance optimization is a critical yet challenging aspect of software development, often requiring a deep understanding of system behavior, algorithmic tradeoffs, and careful code modifications. Although recent advances in AI coding agents have accelerated code generation and bug fixing, little is known about how these agents perform on real-world performance optimization tasks. We present the first empirical study comparing agent- and human-authored performance optimization commits, analyzing 324 agent-generated and 83 human-authored PRs from the AIDev dataset across adoption, maintainability, optimization patterns, and validation practices. We find that AI-authored performance PRs are less likely to include explicit performance validation than human-authored PRs (45.7\% vs. 63.6\%, $p=0.007$). In addition, AI-authored PRs largely use the same optimization patterns as humans. We further discuss limitations and opportunities for advancing agentic code optimization. --- ### Approximation Capabilities of Feedforward Neural Networks with GELU Activations Authors: Konstantin Yakovlev, Nikita Puchkin Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21749v1 We derive an approximation error bound that holds simultaneously for a function and all its derivatives up to any prescribed order. The bounds apply to elementary functions, including multivariate polynomials, the exponential function, and the reciprocal function, and are obtained using feedforward neural networks with the Gaussian Error Linear Unit (GELU) activation. In addition, we report the network size, weight magnitudes, and behavior at infinity. Our analysis begins with a constructive approximation of multiplication, where we prove the simultaneous validity of error bounds over domains of increasing size for a given approximator. Leveraging this result, we obtain approximation guarantees for division and the exponential function, ensuring that all higher-order derivatives of the resulting approximators remain globally bounded. --- ### Modified TSception for Analyzing Driver Drowsiness and Mental Workload from EEG Authors: Gourav Siddhad, Anurag Singh, Rajkumar Saini, Partha Pratim Roy Published: 2025-12-25 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2512.21747v2 Driver drowsiness is a leading cause of traffic accidents, necessitating real-time, reliable detection systems to ensure road safety. This study proposes a Modified TSception architecture for robust assessment of driver fatigue and mental workload using Electroencephalography (EEG). The model introduces a five-layer hierarchical temporal refinement strategy to capture multi-scale brain dynamics, surpassing the original TSception's three-layer approach. Key innovations include the use of Adaptive Average Pooling (ADP) for structural flexibility across varying EEG dimensions and a two-stage fusion mechanism to optimize spatiotemporal feature integration for improved stability. Evaluated on the SEED-VIG dataset, the Modified TSception achieves 83.46% accuracy, comparable to the original model (83.15%), but with a significantly reduced confidence interval (0.24 vs. 0.36), indicating better performance stability. The architecture's generalizability was further validated on the STEW mental workload dataset, achieving state-of-the-art accuracies of 95.93% and 95.35% for 2-class and 3-class classification, respectively. These results show that the proposed modifications improve consistency and cross-task generalizability, making the model a reliable framework for EEG-based safety monitoring. --- ### A Model of Causal Explanation on Neural Networks for Tabular Data Authors: Takashi Isozaki, Masahiro Yamamoto, Atsushi Noda Published: 2025-12-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.21746v1 The problem of explaining the results produced by machine learning methods continues to attract attention. Neural network (NN) models, along with gradient boosting machines, are expected to be utilized even in tabular data with high prediction accuracy. This study addresses the related issues of pseudo-correlation, causality, and combinatorial reasons for tabular data in NN predictors. We propose a causal explanation method, CENNET, and a new explanation power index using entropy for the method. CENNET provides causal explanations for predictions by NNs and uses structural causal models (SCMs) effectively combined with the NNs although SCMs are usually not used as predictive models on their own in terms of predictive accuracy. We show that CEN-NET provides such explanations through comparative experiments with existing methods on both synthetic and quasi-real data in classification tasks. --- ### Dynamic Feedback Engines: Layer-Wise Control for Self-Regulating Continual Learning Authors: Hengyi Wu, Zhenyi Wang, Heng Huang Published: 2025-12-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.21743v1 Continual learning aims to acquire new tasks while preserving performance on previously learned ones, but most methods struggle with catastrophic forgetting. Existing approaches typically treat all layers uniformly, often trading stability for plasticity or vice versa. However, different layers naturally exhibit varying levels of uncertainty (entropy) when classifying tasks. High-entropy layers tend to underfit by failing to capture task-specific patterns, while low-entropy layers risk overfitting by becoming overly confident and specialized. To address this imbalance, we propose an entropy-aware continual learning method that employs a dynamic feedback mechanism to regulate each layer based on its entropy. Specifically, our approach reduces entropy in high-entropy layers to mitigate underfitting and increases entropy in overly confident layers to alleviate overfitting. This adaptive regulation encourages the model to converge to wider local minima, which have been shown to improve generalization. Our method is general and can be seamlessly integrated with both replay- and regularization-based approaches. Experiments on various datasets demonstrate substantial performance gains over state-of-the-art continual learning baselines. --- ### SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild Authors: Xindi Zhang, Dechao Meng, Steven Xiao, Qi Wang, Peng Zhang, Bang Zhang Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21736v3 High-quality AI-powered video dubbing demands precise audio-lip synchronization, high-fidelity visual generation, and faithful preservation of identity and background. Most existing methods rely on a mask-based training strategy, where the mouth region is masked in talking-head videos, and the model learns to synthesize lip movements from corrupted inputs and target audios. While this facilitates lip-sync accuracy, it disrupts spatiotemporal context, impairing performance on dynamic facial motions and causing instability in facial structure and background consistency. To overcome this limitation, we propose SyncAnyone, a novel two-stage learning framework that achieves accurate motion modeling and high visual fidelity simultaneously. In Stage 1, we train a diffusion-based video transformer for masked mouth inpainting, leveraging its strong spatiotemporal modeling to generate accurate, audio-driven lip movements. However, due to input corruption, minor artifacts may arise in the surrounding facial regions and the background. In Stage 2, we develop a mask-free tuning pipeline to address mask-induced artifacts. Specifically, on the basis of the Stage 1 model, we develop a data generation pipeline that creates pseudo-paired training samples by synthesizing lip-synced videos from the source video and random sampled audio. We further tune the stage 2 model on this synthetic data, achieving precise lip editing and better background consistency. Extensive experiments show that our method achieves state-of-the-art results in visual quality, temporal coherence, and identity preservation under in-the wild lip-syncing scenarios. --- ### Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation Authors: Steven Xiao, Xindi Zhang, Dechao Meng, Qi Wang, Peng Zhang, Bang Zhang Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21734v2 Real-time portrait animation is essential for interactive applications such as virtual assistants and live avatars, requiring high visual fidelity, temporal coherence, ultra-low latency, and responsive control from dynamic inputs like reference images and driving signals. While diffusion-based models achieve strong quality, their non-causal nature hinders streaming deployment. Causal autoregressive video generation approaches enable efficient frame-by-frame generation but suffer from error accumulation, motion discontinuities at chunk boundaries, and degraded long-term consistency. In this work, we present a novel streaming framework named Knot Forcing for real-time portrait animation that addresses these challenges through three key designs: (1) a chunk-wise generation strategy with global identity preservation via cached KV states of the reference image and local temporal modeling using sliding window attention; (2) a temporal knot module that overlaps adjacent chunks and propagates spatio-temporal cues via image-to-video conditioning to smooth inter-chunk motion transitions; and (3) A "running ahead" mechanism that dynamically updates the reference frame's temporal coordinate during inference, keeping its semantic context ahead of the current rollout frame to support long-term coherence. Knot Forcing enables high-fidelity, temporally consistent, and interactive portrait animation over infinite sequences, achieving real-time performance with strong visual stability on consumer-grade GPUs. --- ### HELP: Hierarchical Embodied Language Planner for Household Tasks Authors: Alexandr V. Korchemnyi, Anatoly O. Onishchenko, Eva A. Bakaeva, Alexey K. Kovalev, Aleksandr I. Panov Published: 2025-12-25 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.21723v1 Embodied agents tasked with complex scenarios, whether in real or simulated environments, rely heavily on robust planning capabilities. When instructions are formulated in natural language, large language models (LLMs) equipped with extensive linguistic knowledge can play this role. However, to effectively exploit the ability of such models to handle linguistic ambiguity, to retrieve information from the environment, and to be based on the available skills of an agent, an appropriate architecture must be designed. We propose a Hierarchical Embodied Language Planner, called HELP, consisting of a set of LLM-based agents, each dedicated to solving a different subtask. We evaluate the proposed approach on a household task and perform real-world experiments with an embodied agent. We also focus on the use of open source LLMs with a relatively small number of parameters, to enable autonomous deployment. --- ### An Information Theoretic Perspective on Agentic System Design Authors: Shizhe He, Avanika Narayan, Ishan S. Khare, Scott W. Linderman, Christopher Ré, Dan Biderman Published: 2025-12-25 Categories: cs.LG, cs.AI, cs.CL, cs.IT arXiv: https://arxiv.org/abs/2512.21720v1 Agentic language model (LM) systems power modern applications like "Deep Research" and "Claude Code," and leverage multi-LM architectures to overcome context limitations. Beneath their apparent diversity lies a recurring pattern: smaller "compressor" LMs (that can even run locally) distill raw context into compact text that is then consumed by larger "predictor" LMs. Despite their popularity, the design of compressor-predictor systems remains largely ad hoc, with little guidance on how compressor and predictor choices shape downstream performance. In practice, attributing gains to compression versus prediction requires costly, task-specific pairwise sweeps. We argue that these agentic system design questions are, at root, information-theoretic. Viewing the compressor LM as a noisy channel, we introduce a simple estimator of mutual information between the context and its compression to quantify compression quality in a task-independent way. We show that mutual information strongly predicts downstream performance, independent of any specific task. Through an information-theoretic framework, we perform a comprehensive empirical analysis across five datasets and three model families. Results reveal that larger compressors not only are more accurate, but also more token-efficient, conveying more bits of information per token. A 7B Qwen-2.5 compressor, for instance, is $1.6\times$ more accurate, $4.6\times$ more concise, and conveys $5.5\times$ more bits of mutual information per token than its 1.5B sibling. Across datasets, scaling compressors is substantially more effective than scaling predictors, enabling larger on-device compressors to pair with smaller cloud predictors. Applied to a Deep Research system, these principles enable local compressors as small as 3B parameters to recover $99\%$ of frontier-LM accuracy at $26\%$ of API costs. --- ### Multiconnectivity for SAGIN: Current Trends, Challenges, AI-driven Solutions, and Opportunities Authors: Abd Ullah Khan, Adnan Shahid, Haejoon Jung, Hyundong Shin Published: 2025-12-25 Categories: cs.NI, cs.AI, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2512.21717v2 Space-air-ground-integrated network (SAGIN)-enabled multiconnectivity (MC) is emerging as a key enabler for next-generation networks, enabling users to simultaneously utilize multiple links across multi-layer non-terrestrial networks (NTN) and multi-radio access technology (multi-RAT) terrestrial networks (TN). However, the heterogeneity of TN and NTN introduces complex architectural challenges that complicate MC implementation. Specifically, the diversity of link types, spanning air-to-air, air-to-space, space-to-space, space-to-ground, and ground-to-ground communications, renders optimal resource allocation highly complex. Recent advancements in reinforcement learning (RL) and agentic artificial intelligence (AI) have shown remarkable effectiveness in optimal decision-making in complex and dynamic environments. In this paper, we review the current developments in SAGIN-enabled MC and outline the key challenges associated with its implementation. We further highlight the transformative potential of AI-driven approaches for resource optimization in a heterogeneous SAGIN environment. To this end, we present a case study on resource allocation optimization enabled by agentic RL for SAGIN-enabled MC involving diverse radio access technologies (RATs). Results show that learning-based methods can effectively handle complex scenarios and substantially enhance network performance in terms of latency and capacity while incurring a moderate increase in power consumption as an acceptable tradeoff. Finally, open research problems and future directions are presented to realize efficient SAGIN-enabled MC. --- ### CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generation Authors: Rui Ke, Jiahui Xu, Shenghao Yang, Kuang Wang, Feng Jiang, Haizhou Li Published: 2025-12-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.21715v1 Theme detection is a fundamental task in user-centric dialogue systems, aiming to identify the latent topic of each utterance without relying on predefined schemas. Unlike intent induction, which operates within fixed label spaces, theme detection requires cross-dialogue consistency and alignment with personalized user preferences, posing significant challenges. Existing methods often struggle with sparse, short utterances for accurate topic representation and fail to capture user-level thematic preferences across dialogues. To address these challenges, we propose CATCH (Controllable Theme Detection with Contextualized Clustering and Hierarchical Generation), a unified framework that integrates three core components: (1) context-aware topic representation, which enriches utterance-level semantics using surrounding topic segments; (2) preference-guided topic clustering, which jointly models semantic proximity and personalized feedback to align themes across dialogue; and (3) a hierarchical theme generation mechanism designed to suppress noise and produce robust, coherent topic labels. Experiments on a multi-domain customer dialogue benchmark (DSTC-12) demonstrate the effectiveness of CATCH with 8B LLM in both theme clustering and topic generation quality. --- ### AstraNav-World: World Model for Foresight Control and Consistency Authors: Jintao Chen, Junjun Hu, Haochen Bai, Minghua Luo, Xinda Xue, Botao Ren, Chengyu Bai, Shichao Xie, Ziyi Chen, Fei Liu, Zedong Chu, Xiaolong Wu et al. Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21714v2 Embodied navigation in open, dynamic environments demands accurate foresight of how the world will evolve and how actions will unfold over time. We propose AstraNav-World, an end-to-end world model that jointly reasons about future visual states and action sequences within a unified probabilistic framework. Our framework integrates a diffusion-based video generator with a vision-language policy, enabling synchronized rollouts where predicted scenes and planned actions are updated simultaneously. Training optimizes two complementary objectives: generating action-conditioned multi-step visual predictions and deriving trajectories conditioned on those predicted visuals. This bidirectional constraint makes visual predictions executable and keeps decisions grounded in physically consistent, task-relevant futures, mitigating cumulative errors common in decoupled "envision-then-plan" pipelines. Experiments across diverse embodied navigation benchmarks show improved trajectory accuracy and higher success rates. Ablations confirm the necessity of tight vision-action coupling and unified training, with either branch removal degrading both prediction quality and policy reliability. In real-world testing, AstraNav-World demonstrated exceptional zero-shot capabilities, adapting to previously unseen scenarios without any real-world fine-tuning. These results suggest that AstraNav-World captures transferable spatial understanding and planning-relevant navigation dynamics, rather than merely overfitting to simulation-specific data distribution. Overall, by unifying foresight vision and control within a single generative model, we move closer to reliable, interpretable, and general-purpose embodied agents that operate robustly in open-ended real-world settings. --- ### Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought Authors: Yuyi Zhang, Boyu Tang, Tianjie Ju, Sufeng Duan, Gongshen Liu Published: 2025-12-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.21711v1 Latent tokens are gaining attention for enhancing reasoning in large language models (LLMs), yet their internal mechanisms remain unclear. This paper examines the problem from a reliability perspective, uncovering fundamental weaknesses: latent tokens function as uninterpretable placeholders rather than encoding faithful reasoning. While resistant to perturbation, they promote shortcut usage over genuine reasoning. We focus on Chain-of-Continuous-Thought (COCONUT), which claims better efficiency and stability than explicit Chain-of-Thought (CoT) while maintaining performance. We investigate this through two complementary approaches. First, steering experiments perturb specific token subsets, namely COCONUT and explicit CoT. Unlike CoT tokens, COCONUT tokens show minimal sensitivity to steering and lack reasoning-critical information. Second, shortcut experiments evaluate models under biased and out-of-distribution settings. Results on MMLU and HotpotQA demonstrate that COCONUT consistently exploits dataset artifacts, inflating benchmark performance without true reasoning. These findings reposition COCONUT as a pseudo-reasoning mechanism: it generates plausible traces that conceal shortcut dependence rather than faithfully representing reasoning processes. --- ### RAPTOR: Real-Time High-Resolution UAV Video Prediction with Efficient Video Attention Authors: Zhan Chen, Zile Guo, Enze Zhu, Peirong Zhang, Xiaoxuan Liu, Lei Wang, Yidan Zhang Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21710v2 Video prediction is plagued by a fundamental trilemma: achieving high-resolution and perceptual quality typically comes at the cost of real-time speed, hindering its use in latency-critical applications. This challenge is most acute for autonomous UAVs in dense urban environments, where foreseeing events from high-resolution imagery is non-negotiable for safety. Existing methods, reliant on iterative generation (diffusion, autoregressive models) or quadratic-complexity attention, fail to meet these stringent demands on edge hardware. To break this long-standing trade-off, we introduce RAPTOR, a video prediction architecture that achieves real-time, high-resolution performance. RAPTOR's single-pass design avoids the error accumulation and latency of iterative approaches. Its core innovation is Efficient Video Attention (EVA), a novel translator module that factorizes spatiotemporal modeling. Instead of processing flattened spacetime tokens with $O((ST)^2)$ or $O(ST)$ complexity, EVA alternates operations along the spatial (S) and temporal (T) axes. This factorization reduces the time complexity to $O(S + T)$ and memory complexity to $O(max(S, T))$, enabling global context modeling at $512^2$ resolution and beyond, operating directly on dense feature maps with a patch-free design. Complementing this architecture is a 3-stage training curriculum that progressively refines predictions from coarse structure to sharp, temporally coherent details. Experiments show RAPTOR is the first predictor to exceed 30 FPS on a Jetson AGX Orin for $512^2$ video, setting a new state-of-the-art on UAVid, KTH, and a custom high-resolution dataset in PSNR, SSIM, and LPIPS. Critically, RAPTOR boosts the mission success rate in a real-world UAV navigation task by 18%, paving the way for safer and more anticipatory embodied agents. --- ### Detecting AI-Generated Paraphrases in Bengali: A Comparative Study of Zero-Shot and Fine-Tuned Transformers Authors: Md. Rakibul Islam, Most. Sharmin Sultana Samu, Md. Zahid Hossain, Farhad Uz Zaman, Md. Kamrozzaman Bhuiyan Published: 2025-12-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.21709v1 Large language models (LLMs) can produce text that closely resembles human writing. This capability raises concerns about misuse, including disinformation and content manipulation. Detecting AI-generated text is essential to maintain authenticity and prevent malicious applications. Existing research has addressed detection in multiple languages, but the Bengali language remains largely unexplored. Bengali's rich vocabulary and complex structure make distinguishing human-written and AI-generated text particularly challenging. This study investigates five transformer-based models: XLMRoBERTa-Large, mDeBERTaV3-Base, BanglaBERT-Base, IndicBERT-Base and MultilingualBERT-Base. Zero-shot evaluation shows that all models perform near chance levels (around 50% accuracy) and highlight the need for task-specific fine-tuning. Fine-tuning significantly improves performance, with XLM-RoBERTa, mDeBERTa and MultilingualBERT achieving around 91% on both accuracy and F1-score. IndicBERT demonstrates comparatively weaker performance, indicating limited effectiveness in fine-tuning for this task. This work advances AI-generated text detection in Bengali and establishes a foundation for building robust systems to counter AI-generated content. --- ### MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles Authors: Jing Han, Binwei Yan, Tianyu Guo, Zheyuan Bai, Mengyu Zheng, Hanting Chen, Ying Nie Published: 2025-12-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21708v1 Despite recent advancements of fine-tuning large language models (LLMs) to facilitate agent tasks, parameter-efficient fine-tuning (PEFT) methodologies for agent remain largely unexplored. In this paper, we introduce three key strategies for PEFT in agent tasks: 1) Inspired by the increasingly dominant Reason+Action paradigm, we first decompose the capabilities necessary for the agent tasks into three distinct roles: reasoner, executor, and summarizer. The reasoner is responsible for comprehending the user's query and determining the next role based on the execution trajectory. The executor is tasked with identifying the appropriate functions and parameters to invoke. The summarizer conveys the distilled information from conversations back to the user. 2) We then propose the Mixture-of-Roles (MoR) framework, which comprises three specialized Low-Rank Adaptation (LoRA) groups, each designated to fulfill a distinct role. By focusing on their respective specialized capabilities and engaging in collaborative interactions, these LoRAs collectively accomplish the agent task. 3) To effectively fine-tune the framework, we develop a multi-role data generation pipeline based on publicly available datasets, incorporating role-specific content completion and reliability verification. We conduct extensive experiments and thorough ablation studies on various LLMs and agent benchmarks, demonstrating the effectiveness of the proposed method. This project is publicly available at https://mor-agent.github.io. --- ### Spatiotemporal-Untrammelled Mixture of Experts for Multi-Person Motion Prediction Authors: Zheng Yin, Chengjian Li, Xiangbo Shu, Meiqi Cao, Rui Yan, Jinhui Tang Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21707v1 Comprehensively and flexibly capturing the complex spatio-temporal dependencies of human motion is critical for multi-person motion prediction. Existing methods grapple with two primary limitations: i) Inflexible spatiotemporal representation due to reliance on positional encodings for capturing spatiotemporal information. ii) High computational costs stemming from the quadratic time complexity of conventional attention mechanisms. To overcome these limitations, we propose the Spatiotemporal-Untrammelled Mixture of Experts (ST-MoE), which flexibly explores complex spatio-temporal dependencies in human motion and significantly reduces computational cost. To adaptively mine complex spatio-temporal patterns from human motion, our model incorporates four distinct types of spatiotemporal experts, each specializing in capturing different spatial or temporal dependencies. To reduce the potential computational overhead while integrating multiple experts, we introduce bidirectional spatiotemporal Mamba as experts, each sharing bidirectional temporal and spatial Mamba in distinct combinations to achieve model efficiency and parameter economy. Extensive experiments on four multi-person benchmark datasets demonstrate that our approach not only outperforms state-of-art in accuracy but also reduces model parameter by 41.38% and achieves a 3.6x speedup in training. The code is available at https://github.com/alanyz106/ST-MoE. --- ### Enabling Conversational Behavior Reasoning Capabilities in Full-Duplex Speech Authors: Shuchang Pan, Siddharth Banerjee, Dhruv Hebbar, Siddhant Patel, Akshaj Gupta, Kan Jen Cheng, Hanjo Kim, Zeyi Austin Li, Martin Q. Ma, Tingle Li, Gopala Anumanchipalli, Jiachen Lian Published: 2025-12-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.21706v1 Human conversation is organized by an implicit chain of thoughts that manifests as timed speech acts. Capturing this causal pathway is key to building natural full-duplex interactive systems. We introduce a framework that enables reasoning over conversational behaviors by modeling this process as causal inference within a Graph-of-Thoughts (GoT). Our approach formalizes the intent-to-action pathway with a hierarchical labeling scheme, predicting high-level communicative intents and low-level speech acts to learn their causal and temporal dependencies. To train this system, we develop a hybrid corpus that pairs controllable, event-rich simulations with human-annotated rationales and real conversational speech. The GoT framework structures streaming predictions as an evolving graph, enabling a multimodal transformer to forecast the next speech act, generate concise justifications for its decisions, and dynamically refine its reasoning. Experiments on both synthetic and real duplex dialogues show that the framework delivers robust behavior detection, produces interpretable reasoning chains, and establishes a foundation for benchmarking conversational reasoning in full duplex spoken dialogue systems. --- ### Zero-Shot to Zero-Lies: Detecting Bengali Deepfake Audio through Transfer Learning Authors: Most. Sharmin Sultana Samu, Md. Rakibul Islam, Md. Zahid Hossain, Md. Kamrozzaman Bhuiyan, Farhad Uz Zaman Published: 2025-12-25 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2512.21702v1 The rapid growth of speech synthesis and voice conversion systems has made deepfake audio a major security concern. Bengali deepfake detection remains largely unexplored. In this work, we study automatic detection of Bengali audio deepfakes using the BanglaFake dataset. We evaluate zeroshot inference with several pretrained models. These include Wav2Vec2-XLSR-53, Whisper, PANNsCNN14, WavLM and Audio Spectrogram Transformer. Zero-shot results show limited detection ability. The best model, Wav2Vec2-XLSR-53, achieves 53.80% accuracy, 56.60% AUC and 46.20% EER. We then f ine-tune multiple architectures for Bengali deepfake detection. These include Wav2Vec2-Base, LCNN, LCNN-Attention, ResNet18, ViT-B16 and CNN-BiLSTM. Fine-tuned models show strong performance gains. ResNet18 achieves the highest accuracy of 79.17%, F1 score of 79.12%, AUC of 84.37% and EER of 24.35%. Experimental results confirm that fine-tuning significantly improves performance over zero-shot inference. This study provides the first systematic benchmark of Bengali deepfake audio detection. It highlights the effectiveness of f ine-tuned deep learning models for this low-resource language. ---