# Research Papers — 2025-12 · bundle page 94 of 175 > Full-text markdown of papers #4651–4700 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/94 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/93.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/95.md) ### HydroDiffusion: Diffusion-Based Probabilistic Streamflow Forecasting with a State Space Backbone Authors: Yihan Wang, Annan Yu, Lujun Zhang, Charuleka Varadharajan, N. Benjamin Erichson Published: 2025-12-13 Categories: cs.LG, physics.geo-ph arXiv: https://arxiv.org/abs/2512.12183v1 Recent advances have introduced diffusion models for probabilistic streamflow forecasting, demonstrating strong early flood-warning skill. However, current implementations rely on recurrent Long Short-Term Memory (LSTM) backbones and single-step training objectives, which limit their ability to capture long-range dependencies and produce coherent forecast trajectories across lead times. To address these limitations, we developed HydroDiffusion, a diffusion-based probabilistic forecasting framework with a decoder-only state space model backbone. The proposed framework jointly denoises full multi-day trajectories in a single pass, ensuring temporal coherence and mitigating error accumulation common in autoregressive prediction. HydroDiffusion is evaluated across 531 watersheds in the contiguous United States (CONUS) in the CAMELS dataset. We benchmark HydroDiffusion against two diffusion baselines with LSTM backbones, as well as the recently proposed Diffusion-based Runoff Model (DRUM). Results show that HydroDiffusion achieves strong nowcast accuracy when driven by observed meteorological forcings, and maintains consistent performance across the full simulation horizon. Moreover, HydroDiffusion delivers stronger deterministic and probabilistic forecast skill than DRUM in operational forecasting. These results establish HydroDiffusion as a robust generative modeling framework for medium-range streamflow forecasting, providing both a new modeling benchmark and a foundation for future research on probabilistic hydrologic prediction at continental scales. --- ### TA-KAND: Two-stage Attention Triple Enhancement and U-KAN based Diffusion For Few-shot Knowledge Graph Completion Authors: Xinyu Gao Published: 2025-12-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.12182v2 Knowledge Graphs have become fundamental infrastructure for applications such as intelligent question answering and recommender systems due to their expressive representation. Nevertheless, real-world knowledge is heterogeneous, leading to a pronounced long-tailed distribution over relations. Previous studies mainly based on metric matching or meta learning. However, they often overlook the distributional characteristics of positive and negative triple samples. In this paper, we propose a few-shot knowledge graph completion framework that integrates two-stage attention triple enhancer with U-KAN based diffusion model. Extensive experiments on two public datasets show significant advantages of our methods. --- ### A Sensing Dataset Protocol for Benchmarking and Multi-Task Wireless Sensing Authors: Jiawei Huang, Di Zhang, Yuanhao Cui, Xiaowen Cao, Tony Xiao Han, Xiaojun Jing, Christos Masouros Published: 2025-12-13 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2512.12180v1 Wireless sensing has become a fundamental enabler for intelligent environments, supporting applications such as human detection, activity recognition, localization, and vital sign monitoring. Despite rapid advances, existing datasets and pipelines remain fragmented across sensing modalities, hindering fair comparison, transfer, and reproducibility. We propose the Sensing Dataset Protocol (SDP), a protocol-level specification and benchmark framework for large-scale wireless sensing. SDP defines how heterogeneous wireless signals are mapped into a unified perception data-block schema through lightweight synchronization, frequency-time alignment, and resampling, while a Canonical Polyadic-Alternating Least Squares (CP-ALS) pooling stage provides a task-agnostic representation that preserves multipath, spectral, and temporal structures. Built upon this protocol, a unified benchmark is established for detection, recognition, and vital-sign estimation with consistent preprocessing, training, and evaluation. Experiments under the cross-user split demonstrate that SDP significantly reduces variance (approximately 88%) across seeds while maintaining competitive accuracy and latency, confirming its value as a reproducible foundation for multi-modal and multitask sensing research. --- ### Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation Authors: Aydin Ayanzadeh, Tim Oates Published: 2025-12-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.12177v1 Indoor navigation remains a critical challenge for people with visual impairments. The current solutions mainly rely on infrastructure-based systems, which limit their ability to navigate safely in dynamic environments. We propose a novel navigation approach that utilizes a foundation model to transform floor plans into navigable knowledge graphs and generate human-readable navigation instructions. Floorplan2Guide integrates a large language model (LLM) to extract spatial information from architectural layouts, reducing the manual preprocessing required by earlier floorplan parsing methods. Experimental results indicate that few-shot learning improves navigation accuracy in comparison to zero-shot learning on simulated and real-world evaluations. Claude 3.7 Sonnet achieves the highest accuracy among the evaluated models, with 92.31%, 76.92%, and 61.54% on the short, medium, and long routes, respectively, under 5-shot prompting of the MP-1 floor plan. The success rate of graph-based spatial structure is 15.4% higher than that of direct visual reasoning among all models, which confirms that graphical representation and in-context learning enhance navigation performance and make our solution more precise for indoor navigation of Blind and Low Vision (BLV) users. --- ### Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation Perspective Authors: Haoyang Chen, Richong Zhang, Junfan Chen Published: 2025-12-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.12175v1 Large language models (LLMs) perform in-context learning (ICL) with minimal supervised examples, which benefits various natural language processing (NLP) tasks. One of the critical research focus is the selection of prompt demonstrations. Current approaches typically employ retrieval models to select the top-K most semantically similar examples as demonstrations. However, we argue that existing methods are limited since the label consistency is not guaranteed during demonstration selection. Our cognition derives from the Bayesian view of ICL and our rethinking of ICL from the transductive label propagation perspective. We treat ICL as a transductive learning method and incorporate latent concepts from Bayesian view and deduce that similar demonstrations guide the concepts of query, with consistent labels serving as estimates. Based on this understanding, we establish a label propagation framework to link label consistency with propagation error bounds. To model label consistency, we propose a data synthesis method, leveraging both semantic and label information, and use TopK sampling with Synthetic Data (TopK-SD) to acquire demonstrations with consistent labels. TopK-SD outperforms original TopK sampling on multiple benchmarks. Our work provides a new perspective for understanding the working mechanisms within ICL. --- ### Diffusion Language Model Inference with Monte Carlo Tree Search Authors: Zheng Huang, Kiran Ramnath, Yueyan Chen, Aosong Feng, Sangmin Woo, Balasubramaniam Srinivasan, Zhichao Xu, Kang Zhou, Shuai Wang, Haibo Ding, Lin Lee Cheong Published: 2025-12-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.12168v2 Diffusion language models (DLMs) have recently emerged as a compelling alternative to autoregressive generation, offering parallel generation and improved global coherence. During inference, DLMs generate text by iteratively denoising masked sequences in parallel; however, determining which positions to unmask and which tokens to commit forms a large combinatorial search problem. Existing inference methods approximate this search using heuristics, which often yield suboptimal decoding paths; other approaches instead rely on additional training to guide token selection. To introduce a principled search mechanism for DLMs inference, we introduce MEDAL, an inference-time scaling framework that integrates Monte Carlo Tree SEarch initialization for Diffusion LAnguage Model inference. We employ Monte Carlo Tree Search at the initialization stage to explore promising unmasking trajectories, providing a robust starting point for subsequent refinement. This design enables efficient inference-time scaling, allowing generation quality to improve as the search budget increases, without additional training. Across multiple benchmarks, MEDAL achieves up to 22.0% improvement over existing inference strategies, establishing a new paradigm for search-based inference in DLMs. --- ### Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings Authors: Yoav Gelberg, Koshi Eguchi, Takuya Akiba, Edoardo Cetin Published: 2025-12-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.12167v1 So far, expensive finetuning beyond the pretraining sequence length has been a requirement for effectively extending the context of language models (LM). In this work, we break this key bottleneck by Dropping the Positional Embeddings of LMs after training (DroPE). Our simple method is motivated by three key theoretical and empirical observations. First, positional embeddings (PEs) serve a crucial role during pretraining, providing an important inductive bias that significantly facilitates convergence. Second, over-reliance on this explicit positional information is also precisely what prevents test-time generalization to sequences of unseen length, even when using popular PE-scaling methods. Third, positional embeddings are not an inherent requirement of effective language modeling and can be safely removed after pretraining, following a short recalibration phase. Empirically, DroPE yields seamless zero-shot context extension without any long-context finetuning, quickly adapting pretrained LMs without compromising their capabilities in the original training context. Our findings hold across different models and dataset sizes, far outperforming previous specialized architectures and established rotary positional embedding scaling methods. --- ### Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video Authors: Daniel Adebi, Sagnik Majumder, Kristen Grauman Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12165v4 Understanding camera motion is a fundamental problem in embodied perception and 3D scene understanding. While visual methods have advanced rapidly, they often struggle under visually degraded conditions such as motion blur or occlusions. In this work, we show that passive scene sounds provide cues complementary to vision for relative camera pose estimation for in-the-wild videos. We introduce a simple but effective audio-visual framework that integrates direction-of-arrival (DOA) spectra and binauralized embeddings into a state-of-the-art vision-only pose estimation model. Our results on two large datasets show consistent gains over strong visual baselines, plus robustness when the visual information is corrupted. To our knowledge, this represents the first work to successfully leverage audio for relative camera pose estimation in real-world videos, and it establishes incidental, everyday audio as an unexpected but promising signal for a classic spatial challenge. Project: http://vision.cs.utexas.edu/projects/av_camera_pose. --- ### Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting Authors: Hua Ma, Ruoxi Sun, Minhui Xue, Xingliang Yuan, Carsten Rudolph, Surya Nepal, Ling Liu Published: 2025-12-13 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.12154v1 Accurate time-series forecasting is increasingly critical for planning and operations in low-carbon power systems. Emerging time-series large language models (TS-LLMs) now deliver this capability at scale, requiring no task-specific retraining, and are quickly becoming essential components within the Internet-of-Energy (IoE) ecosystem. However, their real-world deployment is complicated by a critical vulnerability: adversarial examples (AEs). Detecting these AEs is challenging because (i) adversarial perturbations are optimized across the entire input sequence and exploit global temporal dependencies, which renders local detection methods ineffective, and (ii) unlike traditional forecasting models with fixed input dimensions, TS-LLMs accept sequences of variable length, increasing variability that complicates detection. To address these challenges, we propose a plug-in detection framework that capitalizes on the TS-LLM's own variable-length input capability. Our method uses sampling-induced divergence as a detection signal. Given an input sequence, we generate multiple shortened variants and detect AEs by measuring the consistency of their forecasts: Benign sequences tend to produce stable predictions under sampling, whereas adversarial sequences show low forecast similarity, because perturbations optimized for a full-length sequence do not transfer reliably to shorter, differently-structured subsamples. We evaluate our approach on three representative TS-LLMs (TimeGPT, TimesFM, and TimeLLM) across three energy datasets: ETTh2 (Electricity Transformer Temperature), NI (Hourly Energy Consumption), and Consumption (Hourly Electricity Consumption and Production). Empirical results confirm strong and robust detection performance across both black-box and white-box attack scenarios, highlighting its practicality as a reliable safeguard for TS-LLM forecasting in real-world energy systems. --- ### Open Horizons: Evaluating Deep Models in the Wild Authors: Ayush Vaibhav Bhatti, Deniz Karakay, Debottama Das, Nilotpal Rajbongshi, Yuito Sugimoto Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12146v1 Open-world deployment requires models to recognize both known categories and remain reliable when novel classes appear. We present a unified experimental study spanning open-set recognition (OSR) and few-shot class-incremental learning (FSCIL) on CIFAR-10. For OSR, we compare three pretrained frozen visual encoders: ResNet-50, ConvNeXt-Tiny and CLIP ViT-B/16,using a linear probe and four post-hoc scoring functions, namely MSP, Energy, Mahalanobis and kNN. Across metrics,such as, AUROC, AUPR, FPR@95, and OSCR, CLIP consistently yields the strongest separability between known and unknown samples, with Energy providing the most stable performance across backbones. For FSCIL, we compare modified SPPR, OrCo, and ConCM using partially frozen ResNet-50 across 1-, 5-, and 10-shot scenarios. ConCM achieves 84.7% accuracy in the 10-shot setting with the cleanest confusion matrix, while all methods show saturation beyond 5 shots. Our controlled evaluation reveals how the backbone architecture and scoring mechanisms affect unknown detection and how prototype-based methods mitigate catastrophic forgetting during incremental adaptation. --- ### MeltwaterBench: Deep learning for spatiotemporal downscaling of surface meltwater Authors: Björn Lütjens, Patrick Alexander, Raf Antwerpen, Til Widmann, Guido Cervone, Marco Tedesco Published: 2025-12-13 Categories: cs.CV, cs.AI, cs.LG, physics.ao-ph, physics.data-an arXiv: https://arxiv.org/abs/2512.12142v2 The Greenland ice sheet is melting at an accelerated rate due to processes that are not fully understood and hard to measure. The distribution of surface meltwater can help understand these processes and is observable through remote sensing, but current maps of meltwater face a trade-off: They are either high-resolution in time or space, but not both. We develop a deep learning model that creates gridded surface meltwater maps at daily 100m resolution by fusing data streams from remote sensing observations and physics-based models. In particular, we spatiotemporally downscale regional climate model (RCM) outputs using synthetic aperture radar (SAR), passive microwave (PMW), and a digital elevation model (DEM) over the Helheim Glacier in Eastern Greenland from 2017-2023. Using SAR-derived meltwater as "ground truth", we show that a deep learning-based method that fuses all data streams is over 10 percentage points more accurate over our study area than existing non deep learning-based approaches that only rely on a regional climate model (83% vs. 95% Acc.) or passive microwave observations (72% vs. 95% Acc.). Alternatively, creating a gridded product through a running window calculation with SAR data underestimates extreme melt events, but also achieves notable accuracy (90%) and does not rely on deep learning. We evaluate standard deep learning methods (UNet and DeepLabv3+), and publish our spatiotemporally aligned dataset as a benchmark, MeltwaterBench, for intercomparisons with more complex data-driven downscaling methods. The code and data are available at github.com/blutjens/hrmelt. --- ### BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity Authors: Lucine L. Oganesian, Saba Hashemi, Maryam M. Shanechi Published: 2025-12-13 Categories: cs.LG, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2512.12135v1 Intracranial recordings have opened a unique opportunity to simultaneously measure activity across multiregional networks in the human brain. Recent works have focused on developing transformer-based neurofoundation models of such recordings that can generalize across subjects and datasets. However, these recordings exhibit highly complex spatiotemporal interactions across diverse spatial scales, from the single-channel scale to the scale of brain regions. As such, there remain critical open questions regarding how best to encode spatial information and how to design self-supervision tasks that enable the learning of brain network patterns and enhance downstream decoding performance using such high-dimensional, multiregional recordings. To allow for exploring these questions, we propose a new spatiotemporal transformer model of multiregional neural activity and a corresponding self-supervised masked latent reconstruction task, designed to enable flexibility in the spatial scale used for token encoding and masking. Applying this model on publicly available multiregional intracranial electrophysiology (iEEG) data, we demonstrate that adjusting the spatial scale for both token encoding and masked reconstruction significantly impacts downstream decoding. Further, we find that spatial encoding at larger scales than channel-level encoding, which is commonly used in existing iEEG transformer models, improves downstream decoding performance. Finally, we demonstrate that our method allows for region-level token encoding while also maintaining accurate channel-level neural reconstruction. Taken together, our modeling framework enables exploration of the spatial scales used for token encoding and masking, reveals their importance towards self-supervised pretraining of neurofoundation models of multiregional human brain activity, and enhances downstream decoding performance. --- ### Modeling Dabrafenib Response Using Multi-Omics Modality Fusion and Protein Network Embeddings Based on Graph Convolutional Networks Authors: La Ode Aman, A Mu'thi Andy Suryadi, Dizky Ramadani Putri Papeo, Hamsidar Hasan, Ariani H Hutuba, Netty Ino Ischak, Yuszda K. Salimi Published: 2025-12-13 Categories: q-bio.BM, cs.LG arXiv: https://arxiv.org/abs/2512.12134v1 Cancer cell response to targeted therapy arises from complex molecular interactions, making single omics insufficient for accurate prediction. This study develops a model to predict Dabrafenib sensitivity by integrating multiple omics layers (genomics, transcriptomics, proteomics, epigenomics, and metabolomics) with protein network embeddings generated using Graph Convolutional Networks (GCN). Each modality is encoded into low dimensional representations through neural network preprocessing. Protein interaction information from STRING is incorporated using GCN to capture biological topology. An attention based fusion mechanism assigns adaptive weights to each modality according to its relevance. Using GDSC cancer cell line data, the model shows that selective integration of two modalities, especially proteomics and transcriptomics, achieves the best test performance (R2 around 0.96), outperforming all single omics and full multimodal settings. Genomic and epigenomic data were less informative, while proteomic and transcriptomic layers provided stronger phenotypic signals related to MAPK inhibitor activity. These results show that attention guided multi omics fusion combined with GCN improves drug response prediction and reveals complementary molecular determinants of Dabrafenib sensitivity. The approach offers a promising computational framework for precision oncology and predictive modeling of targeted therapies. --- ### Approximation with SiLU Networks: Constant Depth and Exponential Rates for Basic Operations Authors: Koffi O. Ayena Published: 2025-12-13 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2512.12132v2 We present SiLU network constructions whose approximation efficiency depends critically on proper hyperparameter tuning. For the square function $x^2$, with optimally chosen shift $a$ and scale $β$, we achieve approximation error $\varepsilon$ using a two-layer network of constant width, where weights scale as $β^{\pm k}$ with $k = \mathcal{O}(\ln(1/\varepsilon))$. We then extend this approach through functional composition to Sobolev spaces, we obtain networks with depth $\mathcal{O}(1)$ and $\mathcal{O}(\varepsilon^{-d/n})$ parameters under optimal hyperparameters settings. Our work highlights the trade-off between architectural depth and activation parameter optimization in neural network approximation theory. --- ### BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models Authors: Zhengyang Wang, Ziyue Liu, Ruijie Zhang, Avinash Maurya, Paul Hovland, Bogdan Nicolae, Franck Cappello, Zheng Zhang Published: 2025-12-13 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2512.12131v2 The scale of transformer model pre-training is constrained by the increasing computation and communication cost. Low-rank bottleneck architectures offer a promising solution to significantly reduce the training time and memory footprint with minimum impact on accuracy. Despite algorithmic efficiency, bottleneck architectures scale poorly under standard tensor parallelism. Simply applying 3D parallelism designed for full-rank methods leads to excessive communication and poor GPU utilization. To address this limitation, we propose BOOST, an efficient training framework tailored for large-scale low-rank bottleneck architectures. BOOST introduces a novel Bottleneck-aware Tensor Parallelism, and combines optimizations such as online-RMSNorm, linear layer grouping, and low-rank activation checkpointing to achieve end-to-end training speedup. Evaluations on different low-rank bottleneck architectures demonstrate that BOOST achieves 1.46-1.91$\times$ speedup over full-rank model baselines and 1.87-2.27$\times$ speedup over low-rank model with naively integrated 3D parallelism, with improved GPU utilization and reduced communication overhead. --- ### A Benchmark Dataset for Spatially Aligned Road Damage Assessment in Small Uncrewed Aerial Systems Disaster Imagery Authors: Thomas Manzini, Priyankari Perali, Raisa Karnik, Robin R. Murphy Published: 2025-12-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.12128v1 This paper presents the largest known benchmark dataset for road damage assessment and road alignment, and provides 18 baseline models trained on the CRASAR-U-DRIODs dataset's post-disaster small uncrewed aerial systems (sUAS) imagery from 10 federally declared disasters, addressing three challenges within prior post-disaster road damage assessment datasets. While prior disaster road damage assessment datasets exist, there is no current state of practice, as prior public datasets have either been small-scale or reliant on low-resolution imagery insufficient for detecting phenomena of interest to emergency managers. Further, while machine learning (ML) systems have been developed for this task previously, none are known to have been operationally validated. These limitations are overcome in this work through the labeling of 657.25km of roads according to a 10-class labeling schema, followed by training and deploying ML models during the operational response to Hurricanes Debby and Helene in 2024. Motivated by observed road line misalignment in practice, 9,184 road line adjustments were provided for spatial alignment of a priori road lines, as it was found that when the 18 baseline models are deployed against real-world misaligned road lines, model performance degraded on average by 5.596\% Macro IoU. If spatial alignment is not considered, approximately 8\% (11km) of adverse conditions on road lines will be labeled incorrectly, with approximately 9\% (59km) of road lines misaligned off the actual road. These dynamics are gaps that should be addressed by the ML, CV, and robotics communities to enable more effective and informed decision-making during disasters. --- ### High-Dimensional Tensor Discriminant Analysis: Low-Rank Discriminant Structure, Representation Synergy, and Theoretical Guarantees Authors: Elynn Chen, Yuefeng Han, Jiayu Li Published: 2025-12-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.12122v1 High-dimensional tensor-valued predictors arise in modern applications, increasingly as learned representations from neural networks. Existing tensor classification methods rely on sparsity or Tucker structures and often lack theoretical guarantees. Motivated by empirical evidence that discriminative signals concentrate along a few multilinear components, we introduce CP low-rank structure for the discriminant tensor, a modeling perspective not previously explored. Under a Tensor Gaussian Mixture Model, we propose high-dimensional CP low-rank Tensor Discriminant Analysis (CP-TDA) with Randomized Composite PCA (\textsc{rc-PCA}) initialization, that is essential for handling dependent and anisotropic noise under weaker signal strength and incoherence conditions, followed by iterative refinement algorithm. We establish global convergence and minimax-optimal misclassification rates. To handle tensor data deviating from tensor normality, we develop the first semiparametric tensor discriminant model, in which learned tensor representations are mapped via deep generative models into a latent space tailored for CP-TDA. Misclassification risk decomposes into representation, approximation, and estimation errors. Numerical studies and real data analysis on graph classification demonstrate substantial gains over existing tensor classifiers and state-of-the-art graph neural networks, particularly in high-dimensional, small-sample regimes. --- ### MixtureKit: A General Framework for Composing, Training, and Visualizing Mixture-of-Experts Models Authors: Ahmad Chamma, Omar El Herraoui, Guokan Shang Published: 2025-12-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.12121v1 We introduce MixtureKit, a modular open-source framework for constructing, training, and analyzing Mixture-of-Experts (MoE) models from arbitrary pre-trained or fine-tuned models. MixtureKit currently supports three complementary methods: (i) \emph{Traditional MoE}, which uses a single router per transformer block to select experts, (ii) \emph{BTX} (Branch-Train-Mix), which introduces separate routers for each specified sub-layer enabling fine-grained token routing, and (iii) \emph{BTS} (Branch-Train-Stitch), which keeps experts fully intact and introduces trainable stitch layers for controlled information exchange between hub and experts. MixtureKit automatically modifies the model configuration, patches decoder and causal LM classes, and saves a unified checkpoint ready for inference or fine-tuning. We further provide a visualization interface to inspect per-token routing decisions, expert weight distributions, and layer-wise contributions. Experiments with multilingual code-switched data (e.g. Arabic-Latin) show that a BTX-based model trained using MixtureKit can outperform baseline dense models on multiple benchmarks. We release MixtureKit as a practical foundation for research and development of MoE-based systems across diverse domains. --- ### Citation-Grounded Code Comprehension: Preventing LLM Hallucination Through Hybrid Retrieval and Graph-Augmented Context Authors: Jahidul Arafat Published: 2025-12-13 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2512.12117v1 Large language models have become essential tools for code comprehension, enabling developers to query unfamiliar codebases through natural language interfaces. However, LLM hallucination, generating plausible but factually incorrect citations to source code, remains a critical barrier to reliable developer assistance. This paper addresses the challenges of achieving verifiable, citation grounded code comprehension through hybrid retrieval and lightweight structural reasoning. Our work is grounded in systematic evaluation across 30 Python repositories with 180 developer queries, comparing retrieval modalities, graph expansion strategies, and citation verification mechanisms. We find that challenges of citation accuracy arise from the interplay between sparse lexical matching, dense semantic similarity, and cross file architectural dependencies. Among these, cross file evidence discovery is the largest contributor to citation completeness, but it is largely overlooked because existing systems rely on pure textual similarity without leveraging code structure. We advocate for citation grounded generation as an architectural principle for code comprehension systems and demonstrate this need by achieving 92 percent citation accuracy with zero hallucinations. Specifically, we develop a hybrid retrieval system combining BM25 sparse matching, BGE dense embeddings, and Neo4j graph expansion via import relationships, which outperforms single mode baselines by 14 to 18 percentage points while discovering cross file evidence missed by pure text similarity in 62 percent of architectural queries. --- ### Neural CDEs as Correctors for Learned Time Series Models Authors: Muhammad Bilal Shahid, Zhanhong Jiang, Prajwal Koirala, Soumik Sarkar, Cody Fleming Published: 2025-12-13 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.12116v3 Learned time-series models, whether continuous or discrete, are widely used for forecasting the states of dynamical systems but suffer from error accumulation in multi-step forecasts. To address this issue, we propose a Predictor-Corrector framework in which the Predictor is a learned time-series model that generates multi-step forecasts and the Corrector is a neural controlled differential equation that corrects the forecast errors. The Corrector works with irregularly sampled time series and is compatible with both continuous- and discrete-time Predictors. We further introduce two regularization strategies that improve the Corrector's extrapolation performance and accelerate its training. We also provide theoretical guarantees on the stability and convergence of the proposed framework. Experiments on synthetic, physics-based, and real-world datasets show that the proposed framework consistently improves forecasting performance across diverse Predictors, including neural ordinary differential equations, ContiFormer, and DLinear, demonstrating its predictor-agnostic nature. --- ### A Neuro-Symbolic Framework for Accountability in Public-Sector AI Authors: Allen Daniel Sunny, Ido Sivan-Sevilla Published: 2025-12-13 Categories: cs.CY, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2512.12109v4 Automated eligibility systems increasingly determine access to essential public benefits, but the explanations they generate often fail to reflect the legal rules that authorize those decisions. This thesis develops a legally grounded explainability framework that links system-generated decision justifications to the statutory constraints of CalFresh, California's Supplemental Nutrition Assistance Program. The framework combines a structured ontology of eligibility requirements derived from the state's Manual of Policies and Procedures (MPP), a rule extraction pipeline that expresses statutory logic in a verifiable formal representation, and a solver-based reasoning layer to evaluate whether the explanation aligns with governing law. Case evaluations demonstrate the framework's ability to detect legally inconsistent explanations, highlight violated eligibility rules, and support procedural accountability by making the basis of automated determinations traceable and contestable. --- ### A Novel Patch-Based TDA Approach for Computed Tomography Imaging Authors: Dashti A. Ali, Aras T. Asaad, Jacob J. Peoples, Ahmad Bashir Barekzai, Camila Vilela, Hala Khasawneh, Jayasree Chakraborty, João Miranda, Mohammad Hamghalam, Natalie Gangai, Natally Horvat, Richard K. G. Do et al. Published: 2025-12-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.12108v5 The development of machine learning models based on computed tomography (CT) imaging has been a major focus due to the promise that imaging holds for diagnosis, staging, and prognostication. These models often rely on the extraction of hand-crafted features where incorporating robust feature engineering improves the performance of these models. Topological data analysis (TDA), based on the mathematical field of algebraic topology, focuses on data from a topological perspective, extracting deeper insight and higher dimensional structures. Persistent homology (PH), a fundamental tool in TDA, extracts topological features such as connected components, cycles, and voids. A popular approach to construct PH from 3D CT images is to utilize 3D cubical complex filtration, a method adapted for grid-structured data. However, this approach is subject to poor performance and high computational cost with higher resolution images. This study introduces a novel patch-based PH construction approach designed for volumetric CT imaging data that improves performance and reduces computational time. This study conducts a series of experiments to comprehensively analyze the performance of the proposed method and benchmarks against the cubical complex algorithm and radiomic features. Our results highlight the dominance of the patch-based TDA approach in terms of both classification performance and computational time. The proposed approach outperformed the cubical complex method and radiomic features, achieving average improvement of 7.2%, 3.6%, 2.7%, 8.0%, and 7.2% in accuracy, AUC, sensitivity, specificity, and F1 score, respectively, across all datasets. Finally, we provide a convenient Python package, Patch-TDA, to facilitate the utilization of the proposed approach. --- ### EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography Authors: Yuheng Li, Yue Zhang, Abdoul Aziz Amadou, Yuxiang Lai, Jike Zhong, Tiziano Passerini, Dorin Comaniciu, Puneet Sharma Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12107v1 Echocardiography is the most widely used imaging modality in cardiology, yet its interpretation remains labor-intensive and inherently multimodal, requiring view recognition, quantitative measurements, qualitative assessments, and guideline-based reasoning. While recent vision-language models (VLMs) have achieved broad success in natural images and certain medical domains, their potential in echocardiography has been limited by the lack of large-scale, clinically grounded image-text datasets and the absence of measurement-based reasoning central to echo interpretation. We introduce EchoGround-MIMIC, the first measurement-grounded multimodal echocardiography dataset, comprising 19,065 image-text pairs from 1,572 patients with standardized views, structured measurements, measurement-grounded captions, and guideline-derived disease labels. Building on this resource, we propose EchoVLM, a vision-language model that incorporates two novel pretraining objectives: (i) a view-informed contrastive loss that encodes the view-dependent structure of echocardiographic imaging, and (ii) a negation-aware contrastive loss that distinguishes clinically critical negative from positive findings. Across five types of clinical applications with 36 tasks spanning multimodal disease classification, image-text retrieval, view classification, chamber segmentation, and landmark detection, EchoVLM achieves state-of-the-art performance (86.5% AUC in zero-shot disease classification and 95.1% accuracy in view classification). We demonstrate that clinically grounded multimodal pretraining yields transferable visual representations and establish EchoVLM as a foundation model for end-to-end echocardiography interpretation. We will release EchoGround-MIMIC and the data curation code, enabling reproducibility and further research in multimodal echocardiography interpretation. --- ### AI-Augmented Pollen Recognition in Optical and Holographic Microscopy for Veterinary Imaging Authors: Swarn S. Warshaneyan, Maksims Ivanovs, Blaž Cugmas, Inese Bērziņa, Laura Goldberga, Mindaugas Tamosiunas, Roberts Kadiķis Published: 2025-12-13 Categories: cs.CV, cs.LG, q-bio.QM, stat.ML arXiv: https://arxiv.org/abs/2512.12101v1 We present a comprehensive study on fully automated pollen recognition across both conventional optical and digital in-line holographic microscopy (DIHM) images of sample slides. Visually recognizing pollen in unreconstructed holographic images remains challenging due to speckle noise, twin-image artifacts and substantial divergence from bright-field appearances. We establish the performance baseline by training YOLOv8s for object detection and MobileNetV3L for classification on a dual-modality dataset of automatically annotated optical and affinely aligned DIHM images. On optical data, detection mAP50 reaches 91.3% and classification accuracy reaches 97%, whereas on DIHM data, we achieve only 8.15% for detection mAP50 and 50% for classification accuracy. Expanding the bounding boxes of pollens in DIHM images over those acquired in aligned optical images achieves 13.3% for detection mAP50 and 54% for classification accuracy. To improve object detection in DIHM images, we employ a Wasserstein GAN with spectral normalization (WGAN-SN) to create synthetic DIHM images, yielding an FID score of 58.246. Mixing real-world and synthetic data at the 1.0 : 1.5 ratio for DIHM images improves object detection up to 15.4%. These results demonstrate that GAN-based augmentation can reduce the performance divide, bringing fully automated DIHM workflows for veterinary imaging a small but important step closer to practice. --- ### CHIME: Chiplet-based Heterogeneous Near-Memory Acceleration for Edge Multimodal LLM Inference Authors: Yanru Chen, Runyang Tian, Yue Pan, Zheyu Li, Weihong Xu, Tajana Rosing Published: 2025-12-12 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2601.19908v1 The proliferation of large language models (LLMs) is accelerating the integration of multimodal assistants into edge devices, where inference is executed under stringent latency and energy constraints, often exacerbated by intermittent connectivity. These challenges become particularly acute in the context of multimodal LLMs (MLLMs), as high-dimensional visual inputs are transformed into extensive token sequences, thereby inflating the key-value (KV) cache and imposing substantial data movement overheads to the LLM backbone. To address these issues, we present CHIME, a chiplet-based heterogeneous near-memory acceleration for edge MLLMs inference. CHIME leverages the complementary strengths of integrated monolithic 3D (M3D) DRAM and RRAM chiplets: DRAM supplies low-latency bandwidth for attention, while RRAM offers dense, non-volatile storage for weights. This heterogeneous hardware is orchestrated by a co-designed mapping framework that executes fused kernels near data, minimizing cross-chiplet traffic to maximize effective bandwidth. On FastVLM (0.6B/1.7B) and MobileVLM (1.7B/3B), CHIME achieves up to 54x speedup and up to 246x better energy efficiency per inference as compared to the edge GPU NVIDIA Jetson Orin NX. It sustains 116.5-266.5 token/J compared to Jetson's 0.7-1.1 token/J. Furthermore, it delivers up to 69.2x higher throughput than the state-of-the-art PIM accelerator FACIL. Compared to the M3D DRAM-only design, CHIME's heterogeneous memory further improves energy efficiency by 7% and performance by 2.4x. --- ### Operation Veja: Fixing Fundamental Concepts Missing from Modern Roleplaying Training Paradigms Authors: Yueze Liu, Ajay Nagi Reddy Kumdam, Ronit Kanjilal, Hao Yang, Yichi Zhang Published: 2025-12-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06039v1 Modern roleplaying models are increasingly sophisticated, yet they consistently struggle to capture the essence of believable, engaging characters. We argue this failure stems from training paradigms that overlook the dynamic interplay of a character's internal world. Current approaches, including Retrieval-Augmented Generation (RAG), fact-based priming, literature-based learning, and synthetic data generation, exhibit recurring limitations in modeling the deliberative, value-conflicted reasoning that defines human interaction. In this paper, we identify four core concepts essential for character authenticity: Values, Experiences, Judgments, and Abilities (VEJA). We propose the VEJA framework as a new paradigm for data curation that addresses these systemic limitations. To illustrate the qualitative ceiling enabled by our framework, we present a pilot study comparing a manually curated, VEJA-grounded dataset against a state-of-the-art synthetic baseline. Using an LLM-as-judge evaluation, our findings demonstrate a significant quality gap, suggesting that a shift toward conceptually grounded data curation, as embodied by VEJA, is necessary for creating roleplaying agents with genuine depth and narrative continuity. The full dataset is available at https://github.com/HyouinKyoumaIRL/Operation-Veja --- ### TeleMem: Building Long-Term and Multimodal Memory for Agentic AI Authors: Chunliang Chen, Ming Guan, Xiao Lin, Jiaxu Li, Luxi Lin, Qiyi Wang, Xiangyu Chen, Jixiang Luo, Changzhi Sun, Dell Zhang, Xuelong Li Published: 2025-12-12 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.06037v4 Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories. Retrieval-augmented generation (RAG) mitigates this issue but lacks reliable mechanisms for updating or refining stored memories, leading to schema-driven hallucinations, inefficient write operations, and minimal support for multimodal reasoning.To address these challenges, we propose TeleMem, a unified long-term and multimodal memory system that maintains coherent user profiles through narrative dynamic extraction, ensuring that only dialogue-grounded information is preserved. TeleMem further introduces a structured writing pipeline that batches, retrieves, clusters, and consolidates memory entries, substantially improving storage efficiency, reducing token usage, and accelerating memory operations. Additionally, a multimodal memory module combined with ReAct-style reasoning equips the system with a closed-loop observe, think, and act process that enables accurate understanding of complex video content in long-term contexts. Experimental results show that TeleMem surpasses the state-of-the-art Mem0 baseline with 19% higher accuracy, 43% fewer tokens, and a 2.1x speedup on the ZH-4O long-term role-play gaming benchmark. --- ### TrueBrief: Faithful Summarization through Small Language Models Authors: Kumud Lakara, Ruibo Shi, Fran Silavong Published: 2025-12-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.04212v1 Large language models (LLMs) have exhibited remarkable proficiency in generating high-quality text; however, their propensity for producing hallucinations poses a significant challenge for their deployment in security-critical domains. In this work, we present TrueBrief, an end-to-end framework specifically designed to enhance the faithfulness of small LLMs (SLMs) primarily for the task of text summarization through a preference-optimization paradigm. Central to our framework is a data generation module that facilitates controlled hallucination injection to generate synthetic preference data. Our work provides insights into the impact of data quality and model size on preference-based optimization, highlighting the conditions under which these methods are most effective. --- ### LeafTutor: An AI Agent for Programming Assignment Tutoring Authors: Madison Bochard, Tim Conser, Alyssa Duran, Lazaro Martull, Pu Tian, Yalong Wu Published: 2025-12-12 Categories: cs.CY, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2601.02375v1 High enrollment in STEM-related degree programs has created increasing demand for scalable tutoring support, as universities experience a shortage of qualified instructors and teaching assistants (TAs). To address this challenge, LeafTutor, an AI tutoring agent powered by large language models (LLMs), was developed to provide step-by-step guidance for students. LeafTutor was evaluated through real programming assignments. The results indicate that the system can deliver step-by-step programming guidance comparable to human tutors. This work demonstrates the potential of LLM-driven tutoring solutions to enhance and personalize learning in STEM education. If any reader is interested in collaboration with our team to improve or test LeafTutor, please contact Pu Tian (pu.tian@stockton.edu) or Yalong Wu (wuy@uhcl.edu). --- ### Forecasting N-Body Dynamics: A Comparative Study of Neural Ordinary Differential Equations and Universal Differential Equations Authors: Suriya R S, Prathamesh Dinesh Joshi, Rajat Dandekar, Raj Dandekar, Sreedath Panat Published: 2025-12-12 Categories: cs.LG, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2512.20643v1 The n body problem, fundamental to astrophysics, simulates the motion of n bodies acting under the effect of their own mutual gravitational interactions. Traditional machine learning models that are used for predicting and forecasting trajectories are often data intensive black box models, which ignore the physical laws, thereby lacking interpretability. Whereas Scientific Machine Learning ( Scientific ML ) directly embeds the known physical laws into the machine learning framework. Through robust modelling in the Julia programming language, our method uses the Scientific ML frameworks: Neural ordinary differential equations (NODEs) and Universal differential equations (UDEs) to predict and forecast the system dynamics. In addition, an essential component of our analysis involves determining the forecasting breakdown point, which is the smallest possible amount of training data our models need to predict future, unseen data accurately. We employ synthetically created noisy data to simulate real-world observational limitations. Our findings indicate that the UDE model is much more data efficient, needing only 20% of data for a correct forecast, whereas the Neural ODE requires 90%. --- ### Flow Gym: A framework for the development, benchmarking, training, and deployment of flow-field quantification methods Authors: Francesco Banelli, Antonio Terpin, Alan Bonomi, Raffaello D'Andrea Published: 2025-12-12 Categories: physics.flu-dyn, cs.CV, cs.SE, physics.comp-ph arXiv: https://arxiv.org/abs/2512.20642v2 Particle image velocimetry (PIV) and related optical-flow methods are widely used to quantify fluid motion, but their development and evaluation are often hindered by fragmented software, inconsistent interfaces, and limited reproducibility. To address these challenges, we present Flow Gym, a framework for developing, benchmarking, training, and deploying flow-field quantification methods, with a primary focus on PIV. Its core contribution is a standardized interface that allows classical and learning-based algorithms to be integrated, compared, and deployed within a common pipeline. The framework includes JAX implementations and wrappers for existing methods, modular pre-processing and post-processing components, and utilities for training and benchmarking. By leveraging JAX, Flow Gym supports hardware-accelerated execution while remaining interoperable with external implementations from libraries such as OpenCV and PyTorch. It can operate on both synthetic and experimental data and supports the same workflow for offline benchmarking and real-time deployment. Flow Gym is designed to improve reproducibility, reduce barriers to method development, and facilitate the translation of flow-field quantification algorithms from research to experimental settings. --- ### Generative AI for Analysts Authors: Jian Xue, Qian Zhang, Wu Zhu Published: 2025-12-12 Categories: q-fin.ST, cs.AI, econ.GN, q-fin.GN arXiv: https://arxiv.org/abs/2512.19705v2 We study how generative artificial intelligence (GenAI) reshapes financial analysts' information production. Using the 2023 integration of GenAI into FACTSET as a plausibly exogenous change in AI access, we find that FACTSET-associated reports become markedly richer--featuring 26% more distinct information sources, 24% broader topical coverage, and 21% more analytical methods--while also improving timeliness. However, these gains do not uniformly improve decision quality: relative forecast accuracy declines when analysts face greater information-processing demands. Yet, a machine-learning benchmark processing the same observable inputs shows no analogous deterioration, pointing to a human processing constraint rather than poorer underlying information. Placebo tests using other data vendors make a common platform-wide technology trend unlikely. Overall, GenAI relaxes information-acquisition constraints while making human attention a more important bottleneck. --- ### A 96pJ/Frame/Pixel and 61pJ/Event Anti-UAV System with Hybrid Object Tracking Modes Authors: Yuncheng Lu, Yucen Shi, Aobo Li, Zehao Li, Junying Li, Bo Wang, Tony Tae-Hyoung Kim Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17939v2 We present an energy-efficient anti-UAV system that integrates frame-based and event-driven object tracking to enable reliable detection of small and fast-moving drones. The system reconstructs binary event frames using run-length encoding, generates region proposals, and adaptively switches between frame mode and event mode based on object size and velocity. A Fast Object Tracking Unit improves robustness for high-speed targets through adaptive thresholding and trajectory-based classification. The neural processing unit supports both grayscale-patch and trajectory inference with a custom instruction set and a zero-skipping MAC architecture, reducing redundant neural computations by more than 97 percent. Implemented in 40 nm CMOS technology, the 2 mm^2 chip achieves 96 pJ per frame per pixel and 61 pJ per event at 0.8 V, and reaches 98.2 percent recognition accuracy on public UAV datasets across 50 to 400 m ranges and 5 to 80 pixels per second speeds. The results demonstrate state-of-the-art end-to-end energy efficiency for anti-UAV systems. --- ### Data-Chain Backdoor: Do You Trust Diffusion Models as Generative Data Supplier? Authors: Junchi Lu, Xinke Li, Yuheng Liu, Qi Alfred Chen Published: 2025-12-12 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.15769v2 The increasing use of generative models such as diffusion models for synthetic data augmentation has greatly reduced the cost of data collection and labeling in downstream perception tasks. However, this new data source paradigm may introduce important security concerns. Publicly available generative models are often reused without verification, raising a fundamental question of their safety and trustworthiness. This work investigates backdoor propagation in such emerging generative data supply chain, namely, Data-Chain Backdoor (DCB). Specifically, we find that open-source diffusion models can become hidden carriers of backdoors. Their strong distribution-fitting ability causes them to memorize and reproduce backdoor triggers in generation, which are subsequently inherited by downstream models, resulting in severe security risks. This threat is particularly concerning under clean-label attack scenarios, as it remains effective while having negligible impact on the utility of the synthetic data. We study two attacker choices to obtain a backdoor-carried generator, training from scratch and fine-tuning. While naive fine-tuning leads to weak inheritance of the backdoor, we find that novel designs in the loss objectives and trigger processing can substantially improve the generator's ability to preserve trigger patterns, making fine-tuning a low-cost attack path. We evaluate the effectiveness of DCB under the standard augmentation protocol and further assess data-scarce settings. Across multiple trigger types, we observe that the trigger pattern can be consistently retained in the synthetic data with attack efficacy comparable to the conventional backdoor attack. --- ### PHANTOM: Progressive High-fidelity Adversarial Network for Threat Object Modeling Authors: Jamal Al-Karaki, Muhammad Al-Zafar Khan, Rand Derar Mohammad Al Athamneh Published: 2025-12-12 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.15768v1 The scarcity of cyberattack data hinders the development of robust intrusion detection systems. This paper introduces PHANTOM, a novel adversarial variational framework for generating high-fidelity synthetic attack data. Its innovations include progressive training, a dual-path VAE-GAN architecture, and domain-specific feature matching to preserve the semantics of attacks. Evaluated on 100,000 network traffic samples, models trained on PHANTOM data achieve 98% weighted accuracy on real attacks. Statistical analyses confirm that the synthetic data preserves authentic distributions and diversity. Limitations in generating rare attack types are noted, highlighting challenges with severe class imbalance. This work advances the generation of synthetic data for training robust, privacy-preserving detection systems. --- ### Bridging Data and Physics: A Graph Neural Network-Based Hybrid Twin Framework Authors: M. Gorpinich, B. Moya, S. Rodriguez, F. Meraghni, Y. Jaafra, A. Briot, M. Henner, R. Leon, F. Chinesta Published: 2025-12-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.15767v2 Simulating complex unsteady physical phenomena relies on detailed mathematical models, simulated for instance by using the Finite Element Method (FEM). However, these models often exhibit discrepancies from the reality due to unmodeled effects or simplifying assumptions. We refer to this gap as the ignorance model. While purely data-driven approaches attempt to learn full system behavior, they require large amounts of high-quality data across the entire spatial and temporal domain. In real-world scenarios, such information is unavailable, making full data-driven modeling unreliable. To overcome this limitation, we model of the ignorance component using a hybrid twin approach, instead of simulating phenomena from scratch. Since physics-based models approximate the overall behavior of the phenomena, the remaining ignorance is typically lower in complexity than the full physical response, therefore, it can be learned with significantly fewer data. A key difficulty, however, is that spatial measurements are sparse, also obtaining data measuring the same phenomenon for different spatial configurations is challenging in practice. Our contribution is to overcome this limitation by using Graph Neural Networks (GNNs) to represent the ignorance model. GNNs learn the spatial pattern of the missing physics even when the number of measurement locations is limited. This allows us to enrich the physics-based model with data-driven corrections without requiring dense spatial, temporal and parametric data. To showcase the performance of the proposed method, we evaluate this GNN-based hybrid twin on nonlinear heat transfer problems across different meshes, geometries, and load positions. Results show that the GNN successfully captures the ignorance and generalizes corrections across spatial configurations, improving simulation accuracy and interpretability, while minimizing data requirements. --- ### LOOPRAG: Enhancing Loop Transformation Optimization with Retrieval-Augmented Large Language Models Authors: Yijie Zhi, Yayu Cao, Jianhua Dai, Xiaoyang Han, Jingwen Pu, Qingran Wu, Sheng Cheng, Ming Cai Published: 2025-12-12 Categories: cs.PL, cs.AI, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2512.15766v1 Loop transformations are semantics-preserving optimization techniques, widely used to maximize objectives such as parallelism. Despite decades of research, applying the optimal composition of loop transformations remains challenging due to inherent complexities, including cost modeling for optimization objectives. Recent studies have explored the potential of Large Language Models (LLMs) for code optimization. However, our key observation is that LLMs often struggle with effective loop transformation optimization, frequently leading to errors or suboptimal optimization, thereby missing opportunities for performance improvements. To bridge this gap, we propose LOOPRAG, a novel retrieval-augmented generation framework designed to guide LLMs in performing effective loop optimization on Static Control Part. We introduce a parameter-driven method to harness loop properties, which trigger various loop transformations, and generate diverse yet legal example codes serving as a demonstration source. To effectively obtain the most informative demonstrations, we propose a loop-aware algorithm based on loop features, which balances similarity and diversity for code retrieval. To enhance correct and efficient code generation, we introduce a feedback-based iterative mechanism that incorporates compilation, testing and performance results as feedback to guide LLMs. Each optimized code undergoes mutation, coverage and differential testing for equivalence checking. We evaluate LOOPRAG on PolyBench, TSVC and LORE benchmark suites, and compare it against compilers (GCC-Graphite, Clang-Polly, Perspective and ICX) and representative LLMs (DeepSeek and GPT-4). The results demonstrate average speedups over base compilers of up to 11.20$\times$, 14.34$\times$, and 9.29$\times$ for PolyBench, TSVC, and LORE, respectively, and speedups over base LLMs of up to 11.97$\times$, 5.61$\times$, and 11.59$\times$. --- ### Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization Authors: Mélissa Tamine, Otmane Sakhi, Benjamin Heymann, Maxime Vono, Patrick Loiseau Published: 2025-12-12 Categories: cs.LG, cs.GT, stat.ML arXiv: https://arxiv.org/abs/2512.15765v4 Data valuation is a natural framework for understanding which data sources matter most when aligning a Large Language Model (LLM) from multiple sources. The standard game-theoretic approach treats each source, or equivalently each preference dataset, as a player in a cooperative game and assigns it a contribution score through the Shapley value. In practice, however, Shapley-based valuation is computationally prohibitive because it requires aligning a separate model for every possible coalition of sources, i.e., an exponential number of alignments. We address this challenge for Direct Alignment Algorithms (DAAs), including IPO, which learn through log-policy ratios with respect to a reference policy. We show that, when a model is aligned sequentially source by source, exact optimization makes each stage contribute additively to the log-probability of a full response, up to a prompt-dependent normalization constant. This allows the log-probability assigned by any coalition to a fixed response to be reconstructed from the base policy and the policies trained on each source individually. This reduces the alignment cost of Shapley-based valuation from exponential to linear, since only one model per source needs to be trained to evaluate coalition scores. We test whether this theoretical property remains approximately valid under finite training across several base models and real-world data sources. We finally compute the Shapley values of these sources under multiple reward models, showing how their estimated contributions vary across evaluation criteria. --- ### AdaGradSelect: An adaptive gradient-guided layer selection method for efficient fine-tuning of SLMs Authors: Anshul Kumar, Gagan Raj Gupta, Manisha Chawla Published: 2025-12-12 Categories: cs.LG, cs.AI, cs.PF arXiv: https://arxiv.org/abs/2512.15764v1 Large Language Models (LLMs) can perform many NLP tasks well, but fully fine-tuning them is expensive and requires a lot of memory. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA reduce this cost by adding small low-rank updates to frozen model weights. However, these methods restrict the training to a limited subspace, which can sometimes reduce performance. For Small Language Models (SLMs), where efficiency gains matter even more, we introduce AdaGradSelect, an adaptive method that selects which transformer blocks to update based on gradients. Early observations showed that updating only the transformer blocks with the highest gradient norms can achieve performance close to full fine-tuning. Building on this insight, AdaGradSelect adaptively chooses which blocks to train. It uses a combination of Dirichlet-based sampling, which depends on how frequently blocks were updated in the past, and an epsilon-greedy exploration strategy. This lets the method explore different blocks in early training and gradually focus on the most important ones in later epochs. Experiments show that AdaGradSelect trains about 12 percent faster and uses 35 percent less GPU memory while delivering performance very close to full fine-tuning. On the GSM8K dataset, it outperforms LoRA (rank 256) by about 3 percent on average across models such as Qwen2.5-0.5B, LLaMA3.2-1B, and Phi4-mini-3.8B. It also achieves similar accuracy on the MATH dataset. Overall, AdaGradSelect provides a more effective and resource-efficient alternative to traditional fine-tuning methods. --- ### Cross-Sample Augmented Test-Time Adaptation for Personalized Intraoperative Hypotension Prediction Authors: Kanxue Li, Yibing Zhan, Hua Jin, Chongchong Qi, Xu Lin, Baosheng Yu Published: 2025-12-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.15762v1 Intraoperative hypotension (IOH) poses significant surgical risks, but accurate prediction remains challenging due to patient-specific variability. While test-time adaptation (TTA) offers a promising approach for personalized prediction, the rarity of IOH events often leads to unreliable test-time training. To address this, we propose CSA-TTA, a novel Cross-Sample Augmented Test-Time Adaptation framework that enhances training by incorporating hypotension events from other individuals. Specifically, we first construct a cross-sample bank by segmenting historical data into hypotensive and non-hypotensive samples. Then, we introduce a coarse-to-fine retrieval strategy for building test-time training data: we initially apply K-Shape clustering to identify representative cluster centers and subsequently retrieve the top-K semantically similar samples based on the current patient signal. Additionally, we integrate both self-supervised masked reconstruction and retrospective sequence forecasting signals during training to enhance model adaptability to rapid and subtle intraoperative dynamics. We evaluate the proposed CSA-TTA on both the VitalDB dataset and a real-world in-hospital dataset by integrating it with state-of-the-art time series forecasting models, including TimesFM and UniTS. CSA-TTA consistently enhances performance across settings-for instance, on VitalDB, it improves Recall and F1 scores by +1.33% and +1.13%, respectively, under fine-tuning, and by +7.46% and +5.07% in zero-shot scenarios-demonstrating strong robustness and generalization. --- ### Machine Learning Framework for Thrombosis Risk Prediction in Rotary Blood Pumps Authors: Christopher Blum, Michael Neidlin Published: 2025-12-12 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2512.15761v1 Thrombosis in rotary blood pumps arises from complex flow conditions that remain difficult to translate into reliable and interpretable risk predictions using existing computational models. This limitation reflects an incomplete understanding of how specific flow features contribute to thrombus initiation and growth. This study introduces an interpretable machine learning framework for spatial thrombosis assessment based directly on computational fluid dynamics-derived flow features. A logistic regression (LR) model combined with a structured feature-selection pipeline is used to derive a compact and physically interpretable feature set, including nonlinear feature combinations. The framework is trained using spatial risk patterns from a validated, macro-scale thrombosis model for two representative scenarios. The model reproduces the labeled risk distributions and identifies distinct sets of flow features associated with increased thrombosis risk. When applied to a centrifugal pump, despite training on a single axial pump operating point, the model predicts plausible thrombosis-prone regions. These results show that interpretable machine learning can link local flow features to thrombosis risk while remaining computationally efficient and mechanistically transparent. The low computational cost enables rapid thrombogenicity screening without repeated or costly simulations. The proposed framework complements physics-based thrombosis modeling and provides a methodological basis for integrating interpretable machine learning into CFD-driven thrombosis analysis and device design workflows. --- ### A Tutorial on Dimensionless Learning: Geometric Interpretation and the Effect of Noise Authors: Zhengtao Jake Gan, Xiaoyu Xie Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15760v1 Dimensionless learning is a data-driven framework for discovering dimensionless numbers and scaling laws from experimental measurements. This tutorial introduces the method, explaining how it transforms experimental data into compact physical laws that reveal compact dimensional invariance between variables. The approach combines classical dimensional analysis with modern machine learning techniques. Starting from measurements of physical quantities, the method identifies the fundamental ways to combine variables into dimensionless groups, then uses neural networks to discover which combinations best predict the experimental output. A key innovation is a regularization technique that encourages the learned coefficients to take simple, interpretable values like integers or half-integers, making the discovered laws both accurate and physically meaningful. We systematically investigate how measurement noise and discrete sampling affect the discovery process, demonstrating that the regularization approach provides robustness to experimental uncertainties. The method successfully handles cases with single or multiple dimensionless numbers, revealing how different but equivalent representations can capture the same underlying physics. Despite recent progress, key challenges remain, including managing the computational cost of identifying multiple dimensionless groups, understanding the influence of data characteristics, automating the selection of relevant input variables, and developing user-friendly tools for experimentalists. This tutorial serves as both an educational resource and a practical guide for researchers seeking to apply dimensionless learning to their experimental data. --- ### Semantic-Constrained Federated Aggregation: Convergence Theory and Privacy-Utility Bounds for Knowledge-Enhanced Distributed Learning Authors: Jahidul Arafat Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15759v1 Federated learning enables collaborative model training across distributed data sources but suffers from slow convergence under non-IID data conditions. Existing solutions employ algorithmic modifications treating all client updates identically, ignoring semantic validity. We introduce Semantic-Constrained Federated Aggregation (SCFA), a theoretically-grounded framework incorporating domain knowledge constraints into distributed optimization. We prove SCFA achieves convergence rate O(1/sqrt(T) + rho) where rho represents constraint violation rate, establishing the first convergence theory for constraint-based federated learning. Our analysis shows constraints reduce effective data heterogeneity by 41% and improve privacy-utility tradeoffs through hypothesis space reduction by factor theta=0.37. Under (epsilon,delta)-differential privacy with epsilon=10, constraint regularization maintains utility within 3.7% of non-private baseline versus 12.1% degradation for standard federated learning, representing 2.7x improvement. We validate our framework on manufacturing predictive maintenance using Bosch production data with 1.18 million samples and 968 sensor features, constructing knowledge graphs encoding 3,000 constraints from ISA-95 and MASON ontologies. Experiments demonstrate 22% faster convergence, 41.3% model divergence reduction, and constraint violation thresholds where rho<0.05 maintains 90% optimal performance while rho>0.18 causes catastrophic failure. Our theoretical predictions match empirical observations with R^2>0.90 across convergence, privacy, and violation-performance relationships. --- ### Yantra AI -- An intelligence platform which interacts with manufacturing operations Authors: Varshini Krishnamurthy Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15758v1 Industry 4.0 is growing quickly, which has changed smart production by encouraging the use of real-time tracking, machine learning, and AI-driven systems to make operations run more smoothly. The main focus of this dissertation is on creating and testing an intelligent production system for XRIT that solves important problems like energy management, predictive maintenance, and AI-powered decision support. Machine learning models are built into the system, such as the Random Forest Classifier for proactive maintenance and the Isolation Forest for finding outliers. These models help with decision-making and reducing downtime. Streamlit makes real-time data visualisation possible, giving workers access to dashboards that they can interact with and see real-time observations.The system was tested with fake data and is made to be scalable, so it can be used in real time in XRIT's production setting. Adding an AI-powered virtual assistant made with GPT-4 lets workers get real-time, useful information that makes complicated questions easier to answer and improves operational decisions. The testing shows that the system makes working efficiency, energy management, and the ability to plan repairs much better. Moving the system to real-time data merging and looking for other ways to make it better will be the main focus of future work. --- ### Twin Restricted Kernel Machines for Multiview Classification Authors: A. Quadir, M. Sajid, Mushir Akhtar, M. Tanveer Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15757v1 Multi-view learning (MVL) is an emerging field in machine learning that focuses on improving generalization performance by leveraging complementary information from multiple perspectives or views. Various multi-view support vector machine (MvSVM) approaches have been developed, demonstrating significant success. Moreover, these models face challenges in effectively capturing decision boundaries in high-dimensional spaces using the kernel trick. They are also prone to errors and struggle with view inconsistencies, which are common in multi-view datasets. In this work, we introduce the multiview twin restricted kernel machine (TMvRKM), a novel model that integrates the strengths of kernel machines with the multiview framework, addressing key computational and generalization challenges associated with traditional kernel-based approaches. Unlike traditional methods that rely on solving large quadratic programming problems (QPPs), the proposed TMvRKM efficiently determines an optimal separating hyperplane through a regularized least squares approach, enhancing both computational efficiency and classification performance. The primal objective of TMvRKM includes a coupling term designed to balance errors across multiple views effectively. By integrating early and late fusion strategies, TMvRKM leverages the collective information from all views during training while remaining flexible to variations specific to individual views. The proposed TMvRKM model is rigorously tested on UCI, KEEL, and AwA benchmark datasets. Both experimental results and statistical analyses consistently highlight its exceptional generalization performance, outperforming baseline models in every scenario. --- ### Scientific feedback reveals productive regimes beyond training conventions Authors: Yoon Pyo Lee, Samrendra Roy, Souvik Chakraborty, Syed Bahauddin Alam Published: 2025-12-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.15756v2 Human-imposed design conventions can restrict the alternatives represented in scientific training data and shape the search preferences learned by generative models. We show that scientific performance feedback can redirect the learned search distribution toward productive regions beyond those conventions, without explicitly rewarding departures from them. We test this process in reactor lattice design with simulated feedback and chemical reaction-condition selection with measured yields, using a pretrained sequence policy and a small non-language policy, respectively. In both settings, adaptation improves scientific performance while increasing generation of choices excluded from the corresponding supervised data. In measured reactions, probability on task-specific ligand choices excluded from training rises from 0.29 to 0.70-0.71 as expected yield error decreases. Controls in the lattice setting show that the productive region identified during adaptation provides reusable information to random search, while aligned generation produces useful candidates more frequently than informed random sampling. Removing the target penalty redirects four of five matched runs, linking the direction of adaptation to the scientific objective. Together, these results show how scientific feedback reshapes inherited search preferences and reveals productive alternatives beyond training conventions, with attribution controls distinguishing learned redistribution from candidate availability and reusable search information. --- ### KAN-Matrix: Visualizing Nonlinear Pairwise and Multivariate Contributions for Physical Insight Authors: Luis A. De la Fuente, Hernan A. Moreno, Laura V. Alvarez, Hoshin V. Gupta Published: 2025-12-12 Categories: cs.LG, physics.app-ph, physics.data-an arXiv: https://arxiv.org/abs/2512.15755v1 Interpreting complex datasets remains a major challenge for scientists, particularly due to high dimensionality and collinearity among variables. We introduce a novel application of Kolmogorov-Arnold Networks (KANs) to enhance interpretability and parsimony beyond what traditional correlation analyses offer. We present two interpretable, color-coded visualization tools: the Pairwise KAN Matrix (PKAN) and the Multivariate KAN Contribution Matrix (MKAN). PKAN characterizes nonlinear associations between pairs of variables, while MKAN serves as a nonlinear feature-ranking tool that quantifies the relative contributions of inputs in predicting a target variable. These tools support pre-processing (e.g., feature selection, redundancy analysis) and post-processing (e.g., model explanation, physical insights) in model development workflows. Through experimental comparisons, we demonstrate that PKAN and MKAN yield more robust and informative results than Pearson Correlation and Mutual Information. By capturing the strength and functional forms of relationships, these matrices facilitate the discovery of hidden physical patterns and promote domain-informed model development. --- ### Factor(U,T): Controlling Untrusted AI by Monitoring their Plans Authors: Edward Lue Chee Lip, Anthony Channg, Diana Kim, Aaron Sandoval, Kevin Zhu Published: 2025-12-12 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.14745v1 As AI capabilities advance, we increasingly rely on powerful models to decompose complex tasks $\unicode{x2013}$ but what if the decomposer itself is malicious? Factored cognition protocols decompose complex tasks into simpler child tasks: one model creates the decomposition, while other models implement the child tasks in isolation. Prior work uses trusted (weaker but reliable) models for decomposition, which limits usefulness for tasks where decomposition itself is challenging. We introduce Factor($U$,$T$), in which an untrusted (stronger but potentially malicious) model decomposes while trusted models implement child tasks. Can monitors detect malicious activity when observing only natural language task instructions, rather than complete solutions? We baseline and red team Factor($U$,$T$) in control evaluations on BigCodeBench, a dataset of Python coding tasks. Monitors distinguishing malicious from honest decompositions perform poorly (AUROC 0.52) compared to monitors evaluating complete Python solutions (AUROC 0.96). Furthermore, Factor($D$,$U$), which uses a trusted decomposer and monitors concrete child solutions, achieves excellent discrimination (AUROC 0.96) and strong safety (1.2% ASR), demonstrating that implementation-context monitoring succeeds where decomposition-only monitoring fails. --- ### VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation Authors: Adewale Akinfaderin, Shreyas Subramanian Published: 2025-12-12 Categories: q-fin.CP, cs.AI arXiv: https://arxiv.org/abs/2512.14744v1 Financial AI systems suffer from a critical blind spot: while Retrieval-Augmented Generation (RAG) excels at finding relevant documents, language models still generate calculation errors and regulatory violations during reasoning, even with perfect retrieval. This paper introduces VERAFI (Verified Agentic Financial Intelligence), an agentic framework with neurosymbolic policy generation for verified financial intelligence. VERAFI combines state-of-the-art dense retrieval and cross-encoder reranking with financial tool-enabled agents and automated reasoning policies covering GAAP compliance, SEC requirements, and mathematical validation. Our comprehensive evaluation on FinanceBench demonstrates remarkable improvements: while traditional dense retrieval with reranking achieves only 52.4\% factual correctness, VERAFI's integrated approach reaches 94.7\%, an 81\% relative improvement. The neurosymbolic policy layer alone contributes a 4.3 percentage point gain over pure agentic processing, specifically targeting persistent mathematical and logical errors. By integrating financial domain expertise directly into the reasoning process, VERAFI offers a practical pathway toward trustworthy financial AI that meets the stringent accuracy demands of regulatory compliance, investment decisions, and risk management. --- ### Quantum-Augmented AI/ML for O-RAN: Hierarchical Threat Detection with Synergistic Intelligence and Interpretability (Technical Report) Authors: Tan Le, Van Le, Sachin Shetty Published: 2025-12-12 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.14742v1 Open Radio Access Networks (O-RAN) enhance modularity and telemetry granularity but also widen the cybersecurity attack surface across disaggregated control, user and management planes. We propose a hierarchical defense framework with three coordinated layers-anomaly detection, intrusion confirmation, and multiattack classification-each aligned with O-RAN's telemetry stack. Our approach integrates hybrid quantum computing and machine learning, leveraging amplitude- and entanglement-based feature encodings with deep and ensemble classifiers. We conduct extensive benchmarking across synthetic and real-world telemetry, evaluating encoding depth, architectural variants, and diagnostic fidelity. The framework consistently achieves near-perfect accuracy, high recall, and strong class separability. Multi-faceted evaluation across decision boundaries, probabilistic margins, and latent space geometry confirms its interpretability, robustness, and readiness for slice-aware diagnostics and scalable deployment in near-RT and non-RT RIC domains. ---