# Research Papers — 2026-01 · bundle page 179 of 189 > Full-text markdown of papers #8901–8950 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-01/page/179 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/178.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/180.md) ### AirSpatialBot: A Spatially-Aware Aerial Agent for Fine-Grained Vehicle Attribute Recognization and Retrieval Authors: Yue Zhou, Ran Ding, Xue Yang, Xue Jiang, Xingzhao Liu Published: 2026-01-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01416v1 Despite notable advancements in remote sensing vision-language models (VLMs), existing models often struggle with spatial understanding, limiting their effectiveness in real-world applications. To push the boundaries of VLMs in remote sensing, we specifically address vehicle imagery captured by drones and introduce a spatially-aware dataset AirSpatial, which comprises over 206K instructions and introduces two novel tasks: Spatial Grounding and Spatial Question Answering. It is also the first remote sensing grounding dataset to provide 3DBB. To effectively leverage existing image understanding of VLMs to spatial domains, we adopt a two-stage training strategy comprising Image Understanding Pre-training and Spatial Understanding Fine-tuning. Utilizing this trained spatially-aware VLM, we develop an aerial agent, AirSpatialBot, which is capable of fine-grained vehicle attribute recognition and retrieval. By dynamically integrating task planning, image understanding, spatial understanding, and task execution capabilities, AirSpatialBot adapts to diverse query requirements. Experimental results validate the effectiveness of our approach, revealing the spatial limitations of existing VLMs while providing valuable insights. The model, code, and datasets will be released at https://github.com/VisionXLab/AirSpatialBot --- ### Reliable Grid Forecasting: State Space Models for Safety-Critical Energy Systems Authors: Sunki Hong, Jisoo Lee Published: 2026-01-04 Categories: eess.SY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.01410v6 Accurate grid load forecasting is safety-critical: under-predictions risk supply shortfalls, while symmetric error metrics can mask this operational asymmetry. We introduce an operator-legible evaluation framework -- Under-Prediction Rate (UPR), tail $\text{Reserve}_{99.5}^{\%}$ requirements, and explicit inflation diagnostics ($\text{Bias}_{24h}$/OPR) -- to quantify one-sided reliability risk beyond MAPE. Using this framework, we evaluate five neural architectures -- two state space models (S-Mamba, PowerMamba), two Transformers (iTransformer, PatchTST), an LSTM, and a probabilistic SSM variant (Mamba-ProbTSF) -- on a weather-aligned California Independent System Operator (CAISO) dataset spanning Nov 2023--Nov 2025 (84,498 hourly records across 5 regional transmission areas) under a rolling-origin walk-forward backtest. We develop and evaluate thermal-lag-aligned weather fusion strategies matched to each architecture's inductive bias. Our results demonstrate that standard accuracy metrics are insufficient proxies for operational safety: models with comparable MAPE can imply materially different tail reserve requirements ($\text{Reserve}_{99.5}^{\%}$). We show that explicit weather integration narrows error distributions, with the magnitude of improvement being architecturally determined -- iTransformer's cross-variate attention benefits significantly more than PatchTST's channel-independent design. Crucially, we identify a widespread susceptibility to "fake safety" in risk-averse forecasting: while probabilistic calibration reduces upper-tail errors, it achieves this by systematically inflating schedules (e.g., increasing bias by over 1,700 MW in severe cases) if left unconstrained. To solve this, we introduce Bias/OPR-constrained objectives that enable auditable trade-offs between minimizing tail risk and preventing trivial over-forecasting. --- ### Mask-Guided Multi-Task Network for Face Attribute Recognition Authors: Gong Gao, Zekai Wang, Jian Zhao, Ziqi Xie, Xianhui Liu, Weidong Zhao Published: 2026-01-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01408v1 Face Attribute Recognition (FAR) plays a crucial role in applications such as person re-identification, face retrieval, and face editing. Conventional multi-task attribute recognition methods often process the entire feature map for feature extraction and attribute classification, which can produce redundant features due to reliance on global regions. To address these challenges, we propose a novel approach emphasizing the selection of specific feature regions for efficient feature learning. We introduce the Mask-Guided Multi-Task Network (MGMTN), which integrates Adaptive Mask Learning (AML) and Group-Global Feature Fusion (G2FF) to address the aforementioned limitations. Leveraging a pre-trained keypoint annotation model and a fully convolutional network, AML accurately localizes critical facial parts (e.g., eye and mouth groups) and generates group masks that delineate meaningful feature regions, thereby mitigating negative transfer from global region usage. Furthermore, G2FF combines group and global features to enhance FAR learning, enabling more precise attribute identification. Extensive experiments on two challenging facial attribute recognition datasets demonstrate the effectiveness of MGMTN in improving FAR performance. --- ### From Emotion Classification to Emotional Reasoning: Enhancing Emotional Intelligence in Large Language Models Authors: Arjhun Sreedar, Rohan Pillay, Laukik Patade Published: 2026-01-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.01407v1 This work investigates whether synthetic emotional chain-of-thought data can improve the emotional reasoning abilities of smaller open large language models (LLMs). We design a multi-agent generation pipeline that produces therapy-style conversations and converts them into structured emotion multiple-choice questions (MCQs) with explanations. We propose that fine-tuning a variety of 7B models on this dataset should yield substantial gains in emotional understanding and emotional awareness on EmoBench-style evaluations, suggesting that emotional reasoning can be induced without architectural changes. Our results demonstrate that fine-tuned Mistral 7B achieves EU improvements from 10.5 to 20.5 and EA improvements from 40.5 to 60.0, validating the effectiveness of synthetic emotional reasoning data for enhancing model capabilities in nuanced emotional tasks. --- ### SwinIFS: Landmark Guided Swin Transformer For Identity Preserving Face Super Resolution Authors: Habiba Kausar, Saeed Anwar, Omar Jamal Hammad, Ibrahim Radwan, Abdul Bais Published: 2026-01-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.01406v3 Face super-resolution aims to recover high-quality facial images from severely degraded low-resolution inputs, but remains challenging due to the loss of fine structural details and identity-specific features. This work introduces SwinIFS, a landmark-guided super-resolution framework that integrates structural priors with hierarchical attention mechanisms to achieve identity-preserving reconstruction at both moderate and extreme upscaling factors. The method incorporates dense Gaussian heatmaps of key facial landmarks into the input representation, enabling the network to focus on semantically important facial regions from the earliest stages of processing. A compact Swin Transformer backbone is employed to capture long-range contextual information while preserving local geometry, allowing the model to restore subtle facial textures and maintain global structural consistency. Extensive experiments on the CelebA benchmark demonstrate that SwinIFS achieves superior perceptual quality, sharper reconstructions, and improved identity retention; it consistently produces more photorealistic results and exhibits strong performance even under $8\times$ magnification, where most methods fail to recover meaningful structure. SwinIFS also provides an advantageous balance between reconstruction accuracy and computational efficiency, making it suitable for real-world applications in facial enhancement, surveillance, and digital restoration. Our code, model weights, and results are available at https://github.com/Habiba123-stack/SwinIFS. --- ### Exact and Approximate Range Queries in Ball Mapper Authors: Jay-Anne Bulauan, John Rick Manzanares Published: 2026-01-04 Categories: cs.CG, cs.LG arXiv: https://arxiv.org/abs/2601.01405v3 Ball Mapper summarizes a finite metric dataset by covering the sample with closed balls centered at selected landmarks and connecting landmarks whose balls share observations. Its construction therefore depends critically on repeated fixed radius range queries, yet the effect of replacing exact queries by approximate search has not been systematically characterized. We formulate Ball Mapper through an abstract range query procedure that separates the mathematical construction from the search backend used to realize it. Under fixed ordering, exact procedures preserve the landmark sequence, cover, graph, and membership-based colorings. For approximate procedures, we derive deterministic bounds on covering radius and landmark separation under additive and multiplicative query errors, prove inclusions for the induced nerve, characterize edge survival through witness redundancy for conservative approximations, and bound perturbations of mean vertex colorings. The accompanying implementation provides independent exact reference backends together with exhaustive and approximate search methods under a common closed ball convention. Experiments on Gaussian, mixture, and noisy curve data across three seeds show that approximation fidelity depends strongly on geometry and that edges supported by multiple witnesses are substantially more robust to missed memberships. At 20,000 observations, the approximate indexes did not outperform exhaustive FAISS Flat search. The results therefore establish a framework for controlled approximation rather than a universal speed advantage, and identify the geometric and combinatorial quantities that govern when approximate range search preserves the Ball Mapper summary. --- ### A Graph-based Framework for Online Time Series Anomaly Detection Using Model Ensemble Authors: Zewei Yu, Jianqiu Xu, Caimin Li Published: 2026-01-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.01403v1 With the increasing volume of streaming data in industrial systems, online anomaly detection has become a critical task. The diverse and rapidly evolving data patterns pose significant challenges for online anomaly detection. Many existing anomaly detection methods are designed for offline settings or have difficulty in handling heterogeneous streaming data effectively. This paper proposes GDME, an unsupervised graph-based framework for online time series anomaly detection using model ensemble. GDME maintains a dynamic model pool that is continuously updated by pruning underperforming models and introducing new ones. It utilizes a dynamic graph structure to represent relationships among models and employs community detection on the graph to select an appropriate subset for ensemble. The graph structure is also used to detect concept drift by monitoring structural changes, allowing the framework to adapt to evolving streaming data. Experiments on seven heterogeneous time series demonstrate that GDME outperforms existing online anomaly detection methods, achieving improvements of up to 24%. In addition, its ensemble strategy provides superior detection performance compared with both individual models and average ensembles, with competitive computational efficiency. --- ### LANCET: Neural Intervention via Structural Entropy for Mitigating Faithfulness Hallucinations in LLMs Authors: Chenxu Wang, Chaozhuo Li, Pengbo Wang, Litian Zhang, Songyang Liu, Ji Qi, Jiahui Hu, Yushan Cai, Hao Zhao, Rui Pu Published: 2026-01-04 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.01401v1 Large Language Models have revolutionized information processing, yet their reliability is severely compromised by faithfulness hallucinations. While current approaches attempt to mitigate this issue through node-level adjustments or coarse suppression, they often overlook the distributed nature of neural information, leading to imprecise interventions. Recognizing that hallucinations propagate through specific forward transmission pathways like an infection, we aim to surgically block this flow using precise structural analysis. To leverage this, we propose Lancet, a novel framework that achieves precise neural intervention by leveraging structural entropy and hallucination difference ratios. Lancet first locates hallucination-prone neurons via gradient-driven contrastive analysis, then maps their propagation pathways by minimizing structural entropy, and finally implements a hierarchical intervention strategy that preserves general model capabilities. Comprehensive evaluations across hallucination benchmark datasets demonstrate that Lancet significantly outperforms state-of-the-art methods, validating the effectiveness of our surgical approach to neural intervention. --- ### EternalMath: A Living Benchmark of Frontier Mathematics that Evolves with Human Discovery Authors: Jicheng Ma, Guohua Wang, Xinhua Feng, Yiming Liu, Zhichao Hu, Yuhong Liu Published: 2026-01-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.01400v2 Current evaluations of mathematical reasoning in large language models (LLMs) are dominated by static benchmarks, either derived from competition-style problems or curated through costly expert effort, resulting in limited coverage of research-level mathematics and rapid performance saturation. We propose a fully automated, theorem-grounded pipeline for evaluating frontier mathematical reasoning, which directly transforms recent peer-reviewed mathematical literature into executable and verifiable reasoning tasks. The pipeline identifies constructive or quantitative results, instantiates them into parameterized problem templates, and generates deterministic solutions through execution-based verification, enabling scalable, reproducible, and continuously updatable evaluation without reliance on large-scale expert authoring. By design, this approach supports temporal extensibility, intrinsic correctness checking, and domain-specific customization across mathematical subfields. Applying this pipeline yields \textbf{EternalMath}, an evolving evaluation suite derived from contemporary research papers. Experiments with state-of-the-art LLMs reveal substantial performance gaps, indicating that mathematical reasoning at the research frontier remains far from saturated and underscoring the need for evaluation methodologies that evolve in step with human mathematical discovery. --- ### Evaluation of Convolutional Neural Network For Image Classification with Agricultural and Urban Datasets Authors: Shamik Shafkat Avro, Nazira Jesmin Lina, Shahanaz Sharmin Published: 2026-01-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01393v1 This paper presents the development and evaluation of a custom Convolutional Neural Network (CustomCNN) created to study how architectural design choices affect multi-domain image classification tasks. The network uses residual connections, Squeeze-and-Excitation attention mechanisms, progressive channel scaling, and Kaiming initialization to improve its ability to represent data and speed up training. The model is trained and tested on five publicly available datasets: unauthorized vehicle detection, footpath encroachment detection, polygon-annotated road damage and manhole detection, MangoImageBD and PaddyVarietyBD. A comparison with popular CNN architectures shows that the CustomCNN delivers competitive performance while remaining efficient in computation. The results underscore the importance of thoughtful architectural design for real-world Smart City and agricultural imaging applications. --- ### SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning Authors: Peidong Wang, Zhiming Ma, Xin Dai, Yongkang Liu, Shi Feng, Xiaocui Yang, Wenxing Hu, Zhihao Wang, Mingjun Pan, Li Yuan, Daling Wang Published: 2026-01-04 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2601.01392v1 Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This limits their effectiveness against complex deceptive strategies. To address these challenges, we first propose \textbf{SAFE-QAQ}, an end-to-end comprehensive framework for audio-based slow-thinking fraud detection. First, the SAFE-QAQ framework eliminates the impact of transcription errors on detection performance. Secondly, we propose rule-based slow-thinking reward mechanisms that systematically guide the system to identify fraud-indicative patterns by accurately capturing fine-grained audio details, through hierarchical reasoning processes. Besides, our framework introduces a dynamic risk assessment framework during live calls, enabling early detection and prevention of fraud. Experiments on the TeleAntiFraud-Bench demonstrate that SAFE-QAQ achieves dramatic improvements over existing methods in multiple key dimensions, including accuracy, inference efficiency, and real-time processing capabilities. Currently deployed and analyzing over 70,000 calls daily, SAFE-QAQ effectively automates complex fraud detection, reducing human workload and financial losses. Code: https://anonymous.4open.science/r/SAFE-QAQ. --- ### Bayesian Negative Binomial Regression of Afrobeats Chart Persistence Authors: Ian Jacob Cabansag, Paul Ntegeka Published: 2026-01-04 Categories: eess.AS, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2601.01391v1 Afrobeats songs compete for attention on streaming platforms, where chart visibility can influence both revenue and cultural impact. This paper examines whether collaborations help songs remain on the charts longer, using daily Nigeria Spotify Top 200 data from 2024. Each track is summarized by the number of days it appears in the Top 200 during the year and its total annual streams in Nigeria. A Bayesian negative binomial regression is applied, with days on chart as the outcome and collaboration status (solo versus multi-artist) and log total streams as predictors. This approach is well suited for overdispersed count data and allows the effect of collaboration to be interpreted while controlling for overall popularity. Posterior inference is conducted using Markov chain Monte Carlo, and results are assessed using rate ratios, posterior probabilities, and predictive checks. The findings indicate that, after accounting for total streams, collaboration tracks tend to spend slightly fewer days on the chart than comparable solo tracks. --- ### Scale-Adaptive Power Flow Analysis with Local Topology Slicing and Multi-Task Graph Learning Authors: Yongzhe Li, Lin Guan, Zihan Cai, Zuxian Lin, Jiyu Huang, Liukai Chen Published: 2026-01-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.01387v1 Developing deep learning models with strong adaptability to topological variations is of great practical significance for power flow analysis. To enhance model performance under variable system scales and improve robustness in branch power prediction, this paper proposes a Scale-adaptive Multi-task Power Flow Analysis (SaMPFA) framework. SaMPFA introduces a Local Topology Slicing (LTS) sampling technique that extracts subgraphs of different scales from the complete power network to strengthen the model's cross-scale learning capability. Furthermore, a Reference-free Multi-task Graph Learning (RMGL) model is designed for robust power flow prediction. Unlike existing approaches, RMGL predicts bus voltages and branch powers instead of phase angles. This design not only avoids the risk of error amplification in branch power calculation but also guides the model to learn the physical relationships of phase angle differences. In addition, the loss function incorporates extra terms that encourage the model to capture the physical patterns of angle differences and power transmission, further improving consistency between predictions and physical laws. Simulations on the IEEE 39-bus system and a real provincial grid in China demonstrate that the proposed model achieves superior adaptability and generalization under variable system scales, with accuracy improvements of 4.47% and 36.82%, respectively. --- ### ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parking Authors: Xiaobao Wei, Zhangjie Ye, Yuxiang Gu, Zunjie Zhu, Yunfei Guo, Yingying Shen, Shan Zhao, Ming Lu, Haiyang Sun, Bing Wang, Guang Chen, Rongfeng Lu et al. Published: 2026-01-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.01386v1 Parking is a critical task for autonomous driving systems (ADS), with unique challenges in crowded parking slots and GPS-denied environments. However, existing works focus on 2D parking slot perception, mapping, and localization, 3D reconstruction remains underexplored, which is crucial for capturing complex spatial geometry in parking scenarios. Naively improving the visual quality of reconstructed parking scenes does not directly benefit autonomous parking, as the key entry point for parking is the slots perception module. To address these limitations, we curate the first benchmark named ParkRecon3D, specifically designed for parking scene reconstruction. It includes sensor data from four surround-view fisheye cameras with calibrated extrinsics and dense parking slot annotations. We then propose ParkGaussian, the first framework that integrates 3D Gaussian Splatting (3DGS) for parking scene reconstruction. To further improve the alignment between reconstruction and downstream parking slot detection, we introduce a slot-aware reconstruction strategy that leverages existing parking perception methods to enhance the synthesis quality of slot regions. Experiments on ParkRecon3D demonstrate that ParkGaussian achieves state-of-the-art reconstruction quality and better preserves perception consistency for downstream tasks. The code and dataset will be released at: https://github.com/wm-research/ParkGaussian --- ### Data Complexity-aware Deep Model Performance Forecasting Authors: Yen-Chia Chen, Hsing-Kuo Pao, Hanjuan Huang Published: 2026-01-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.01383v1 Deep learning models are widely used across computer vision and other domains. When working on the model induction, selecting the right architecture for a given dataset often relies on repetitive trial-and-error procedures. This procedure is time-consuming, resource-intensive, and difficult to automate. While previous work has explored performance prediction using partial training or complex simulations, these methods often require significant computational overhead or lack generalizability. In this work, we propose an alternative approach: a lightweight, two-stage framework that can estimate model performance before training given the understanding of the dataset and the focused deep model structures. The first stage predicts a baseline based on the analysis of some measurable properties of the dataset, while the second stage adjusts the estimation with additional information on the model's architectural and hyperparameter details. The setup allows the framework to generalize across datasets and model types. Moreover, we find that some of the underlying features used for prediction - such as dataset variance - can offer practical guidance for model selection, and can serve as early indicators of data quality. As a result, the framework can be used not only to forecast model performance, but also to guide architecture choices, inform necessary preprocessing procedures, and detect potentially problematic datasets before training begins. --- ### Empowering Small Language Models with Factual Hallucination-Aware Reasoning for Financial Classification Authors: Han Yuan, Yilin Wu, Li Zhang, Zheng Ma Published: 2026-01-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.01378v1 Small language models (SLMs) are increasingly used for financial classification due to their fast inference and local deployability. However, compared with large language models, SLMs are more prone to factual hallucinations in reasoning and exhibit weaker classification performance. This raises a natural question: Can mitigating factual hallucinations improve SLMs' financial classification? To address this, we propose a three-step pipeline named AAAI (Association Identification, Automated Detection, and Adaptive Inference). Experiments on three representative SLMs reveal that: (1) factual hallucinations are positively correlated with misclassifications; (2) encoder-based verifiers effectively detect factual hallucinations; and (3) incorporating feedback on factual errors enables SLMs' adaptive inference that enhances classification performance. We hope this pipeline contributes to trustworthy and effective applications of SLMs in finance. --- ### UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models Authors: Qundong Shi, Jie Zhou, Biyuan Lin, Junbo Cui, Guoyang Zeng, Yixuan Zhou, Ziyang Wang, Xin Liu, Zhen Luo, Yudong Wang, Zhiyuan Liu Published: 2026-01-04 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2601.01373v1 The development of audio foundation models has accelerated rapidly since the emergence of GPT-4o. However, the lack of comprehensive evaluation has become a critical bottleneck for further progress in the field, particularly in audio generation. Current audio evaluation faces three major challenges: (1) audio evaluation lacks a unified framework, with datasets and code scattered across various sources, hindering fair and efficient cross-model comparison;(2) audio codecs, as a key component of audio foundation models, lack a widely accepted and holistic evaluation methodology; (3) existing speech benchmarks are heavily reliant on English, making it challenging to objectively assess models' performance on Chinese. To address the first issue, we introduce UltraEval-Audio, a unified evaluation framework for audio foundation models, specifically designed for both audio understanding and generation tasks. UltraEval-Audio features a modular architecture, supporting 10 languages and 14 core task categories, while seamlessly integrating 24 mainstream models and 36 authoritative benchmarks. To enhance research efficiency, the framework provides a one-command evaluation feature, accompanied by real-time public leaderboards. For the second challenge, UltraEval-Audio adopts a novel comprehensive evaluation scheme for audio codecs, evaluating performance across three key dimensions: semantic accuracy, timbre fidelity, and acoustic quality. To address the third issue, we propose two new Chinese benchmarks, SpeechCMMLU and SpeechHSK, designed to assess Chinese knowledge proficiency and language fluency. We wish that UltraEval-Audio will provide both academia and industry with a transparent, efficient, and fair platform for comparison of audio models. Our code, benchmarks, and leaderboards are available at https://github.com/OpenBMB/UltraEval-Audio. --- ### SGD with Dependent Data: Optimal Estimation, Regret, and Inference Authors: Yinan Shen, Yichen Zhang, Wen-Xin Zhou Published: 2026-01-04 Categories: math.ST, cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2601.01371v1 This work investigates the performance of the final iterate produced by stochastic gradient descent (SGD) under temporally dependent data. We consider two complementary sources of dependence: $(i)$ martingale-type dependence in both the covariate and noise processes, which accommodates non-stationary and non-mixing time series data, and $(ii)$ dependence induced by sequential decision making. Our formulation runs in parallel with classical notions of (local) stationarity and strong mixing, while neither framework fully subsumes the other. Remarkably, SGD is shown to automatically accommodate both independent and dependent information under a broad class of stepsize schedules and exploration rate schemes. Non-asymptotically, we show that SGD simultaneously achieves statistically optimal estimation error and regret, extending and improving existing results. In particular, our tail bounds remain sharp even for potentially infinite horizon $T=+\infty$. Asymptotically, the SGD iterates converge to a Gaussian distribution with only an $O_{\PP}(1/\sqrt{t})$ remainder, demonstrating that the supposed estimation-regret trade-off claimed in prior work can in fact be avoided. We further propose a new ``conic'' approximation of the decision region that allows the covariates to have unbounded support. For online sparse regression, we develop a new SGD-based algorithm that uses only $d$ units of storage and requires $O(d)$ flops per iteration, achieving the long term statistical optimality. Intuitively, each incoming observation contributes to estimation accuracy, while aggregated summary statistics guide support recovery. --- ### Differentiable Causal Discovery for Singular Linear Models under Confounding Authors: Mujin Zhou, Ignavier Ng, Junzhe Zhang Published: 2026-01-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.01368v2 Score-based causal discovery in the presence of unobserved confounders requires both a consistent scoring criterion and an efficient search over graph structures. Linear causal models with correlated errors are naturally represented by acyclic directed mixed graphs (ADMGs), whose induced model families include singular statistical models for which the standard Bayesian Information Criterion is inconsistent. We develop a score-based framework for causal discovery over linear Gaussian ADMGs grounded in singular learning theory. We first verify that the conditions for consistency of the Widely Applicable Bayesian Information Criterion (WBIC) are satisfied by the linear causal model class. We then propose a scalable approximation of the WBIC via Automatic Differentiation Variational Inference (ADVI). Finally, we introduce a differentiable search over ADMGs through Gumbel-Softmax relaxations of both directed and bidirected adjacency. Experiments on synthetic and real-world benchmarks demonstrate improvements over the BIC-scored baseline on both singular and generic ADMGs under unobserved confounding. --- ### KGCE: Knowledge-Augmented Dual-Graph Evaluator for Cross-Platform Educational Agent Benchmarking with Multimodal Language Models Authors: Zixian Liu, Sihao Liu, Yuqi Zhao Published: 2026-01-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.01366v1 With the rapid adoption of multimodal large language models (MLMs) in autonomous agents, cross-platform task execution capabilities in educational settings have garnered significant attention. However, existing benchmark frameworks still exhibit notable deficiencies in supporting cross-platform tasks in educational contexts, especially when dealing with school-specific software (such as XiaoYa Intelligent Assistant, HuaShi XiaZi, etc.), where the efficiency of agents often significantly decreases due to a lack of understanding of the structural specifics of these private-domain software. Additionally, current evaluation methods heavily rely on coarse-grained metrics like goal orientation or trajectory matching, making it challenging to capture the detailed execution and efficiency of agents in complex tasks. To address these issues, we propose KGCE (Knowledge-Augmented Dual-Graph Evaluator for Cross-Platform Educational Agent Benchmarking with Multimodal Language Models), a novel benchmarking platform that integrates knowledge base enhancement and a dual-graph evaluation framework. We first constructed a dataset comprising 104 education-related tasks, covering Windows, Android, and cross-platform collaborative tasks. KGCE introduces a dual-graph evaluation framework that decomposes tasks into multiple sub-goals and verifies their completion status, providing fine-grained evaluation metrics. To overcome the execution bottlenecks of existing agents in private-domain tasks, we developed an enhanced agent system incorporating a knowledge base specific to school-specific software. The code can be found at https://github.com/Kinginlife/KGCE. --- ### Unsupervised SE(3) Disentanglement for in situ Macromolecular Morphology Identification from Cryo-Electron Tomography Authors: Mostofa Rafid Uddin, Mahek Vora, Qifeng Wu, Muyuan Chen, Min Xu Published: 2026-01-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01364v1 Cryo-electron tomography (cryo-ET) provides direct 3D visualization of macromolecules inside the cell, enabling analysis of their in situ morphology. This morphology can be regarded as an SE(3)-invariant, denoised volumetric representation of subvolumes extracted from tomograms. Inferring morphology is therefore an inverse problem of estimating both a template morphology and its SE(3) transformation. Existing expectation-maximization based solution to this problem often misses rare but important morphologies and requires extensive manual hyperparameter tuning. Addressing this issue, we present a disentangled deep representation learning framework that separates SE(3) transformations from morphological content in the representation space. The framework includes a novel multi-choice learning module that enables this disentanglement for highly noisy cryo-ET data, and the learned morphological content is used to generate template morphologies. Experiments on simulated and real cryo-ET datasets demonstrate clear improvements over prior methods, including the discovery of previously unidentified macromolecular morphologies. --- ### A unified multimodal understanding and generation model for cross-disciplinary scientific research Authors: Xiaomeng Yang, Zhiyu Tan, Xiaohui Zhong, Mengping Yang, Qiusheng Huang, Lei Chen, Libo Wu, Hao Li Published: 2026-01-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.01363v1 Scientific discovery increasingly relies on integrating heterogeneous, high-dimensional data across disciplines nowadays. While AI models have achieved notable success across various scientific domains, they typically remain domain-specific or lack the capability of simultaneously understanding and generating multimodal scientific data, particularly for high-dimensional data. Yet, many pressing global challenges and scientific problems are inherently cross-disciplinary and require coordinated progress across multiple fields. Here, we present FuXi-Uni, a native unified multimodal model for scientific understanding and high-fidelity generation across scientific domains within a single architecture. Specifically, FuXi-Uni aligns cross-disciplinary scientific tokens within natural language tokens and employs science decoder to reconstruct scientific tokens, thereby supporting both natural language conversation and scientific numerical prediction. Empirically, we validate FuXi-Uni in Earth science and Biomedicine. In Earth system modeling, the model supports global weather forecasting, tropical cyclone (TC) forecast editing, and spatial downscaling driven by only language instructions. FuXi-Uni generates 10-day global forecasts at 0.25° resolution that outperform the SOTA physical forecasting system. It shows superior performance for both TC track and intensity prediction relative to the SOTA physical model, and generates high-resolution regional weather fields that surpass standard interpolation baselines. Regarding biomedicine, FuXi-Uni outperforms leading multimodal large language models on multiple biomedical visual question answering benchmarks. By unifying heterogeneous scientific modalities within a native shared latent space while maintaining strong domain-specific performance, FuXi-Uni provides a step forward more general-purpose, multimodal scientific models. --- ### Investigating the Multilingual Calibration Effects of Language Model Instruction-Tuning Authors: Jerry Huang, Peng Lu, Qiuhao Zeng, Yusuke Iwasawa, Yutaka Matsuo, Sarath Chandar, Edison Marrese-Taylor, Irene Li Published: 2026-01-04 Categories: cs.CL, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.01362v1 Ensuring that deep learning models are well-calibrated in terms of their predictive uncertainty is essential in maintaining their trustworthiness and reliability, yet despite increasing advances in foundation model research, the relationship between such large language models (LLMs) and their calibration remains an open area of research. In this work, we look at a critical gap in the calibration of LLMs within multilingual settings, in an attempt to better understand how the data scarcity can potentially lead to different calibration effects and how commonly used techniques can apply in these settings. Our analysis on two multilingual benchmarks, over 29 and 42 languages respectively, reveals that even in low-resource languages, model confidence can increase significantly after instruction-tuning on high-resource language SFT datasets. However, improvements in accuracy are marginal or non-existent, resulting in mis-calibration, highlighting a critical shortcoming of standard SFT for multilingual languages. Furthermore, we observe that the use of label smoothing to be a reasonable method alleviate this concern, again without any need for low-resource SFT data, maintaining better calibration across all languages. Overall, this highlights the importance of multilingual considerations for both training and tuning LLMs in order to improve their reliability and fairness in downstream use. --- ### Garment Inertial Denoiser (GID): Endowing Accurate Motion Capture via Loose IMU Denoiser Authors: Jiawei Fang, Ruonan Zheng, Xiaoxia Gao, Shifan Jiang, Anjun Chen, Qi Ye, Shihui Guo Published: 2026-01-04 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2601.01360v1 Wearable inertial motion capture (MoCap) provides a portable, occlusion-free, and privacy-preserving alternative to camera-based systems, but its accuracy depends on tightly attached sensors - an intrusive and uncomfortable requirement for daily use. Embedding IMUs into loose-fitting garments is a desirable alternative, yet sensor-body displacement introduces severe, structured, and location-dependent corruption that breaks standard inertial pipelines. We propose GID (Garment Inertial Denoiser), a lightweight, plug-and-play Transformer that factorizes loose-wear MoCap into three stages: (i) location-specific denoising, (ii) adaptive cross-wear fusion, and (iii) general pose prediction. GID uses a location-aware expert architecture, where a shared spatio-temporal backbone models global motion while per-IMU expert heads specialize in local garment dynamics, and a lightweight fusion module ensures cross-part consistency. This inductive bias enables stable training and effective learning from limited paired loose-tight IMU data. We also introduce GarMoCap, a combined public and newly collected dataset covering diverse users, motions, and garments. Experiments show that GID enables accurate, real-time denoising from single-user training and generalizes across unseen users, motions, and garment types, consistently improving state-of-the-art inertial MoCap methods when used as a drop-in module. --- ### A New Framework for Explainable Rare Cell Identification in Single-Cell Transcriptomics Data Authors: Di Su, Kai Ming Ting, Jie Zhang, Xiaorui Zhang, Xinpeng Li Published: 2026-01-04 Categories: q-bio.GN, cs.LG arXiv: https://arxiv.org/abs/2601.01358v1 The detection of rare cell types in single-cell transcriptomics data is crucial for elucidating disease pathogenesis and tissue development dynamics. However, a critical gap that persists in current methods is their inability to provide an explanation based on genes for each cell they have detected as rare. We identify three primary sources of this deficiency. First, the anomaly detectors often function as "black boxes", designed to detect anomalies but unable to explain why a cell is anomalous. Second, the standard analytical framework hinders interpretability by relying on dimensionality reduction techniques, such as Principal Component Analysis (PCA), which transform meaningful gene expression data into abstract, uninterpretable features. Finally, existing explanation algorithms cannot be readily applied to this domain, as single-cell data is characterized by high dimensionality, noise, and substantial sparsity. To overcome these limitations, we introduce a framework for explainable anomaly detection in single-cell transcriptomics data which not only identifies individual anomalies, but also provides a visual explanation based on genes that makes an instance anomalous. This framework has two key ingredients that are not existed in current methods applied in this domain. First, it eliminates the PCA step which is deemed to be an essential component in previous studies. Second, it employs the state-of-art anomaly detector and explainer as the efficient and effective means to find each rare cell and the relevant gene subspace in order to provide explanations for each rare cell as well as the typical normal cell associated with the rare cell's closest normal cells. --- ### Towards LLM-enabled autonomous combustion research: A literature-aware agent for self-corrective modeling workflows Authors: Ke Xiao, Haoze Zhang, Runze Mao, Han Li, Zhi X. Chen Published: 2026-01-04 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2601.01357v1 The rapid evolution of large language models (LLMs) is transforming artificial intelligence into autonomous research partners, yet a critical gap persists in complex scientific domains such as combustion modeling. Here, practical AI assistance requires the seamless integration of domain literature knowledge with robust execution capabilities for expertise-intensive tools such as computational fluid dynamics (CFD) codes. To bridge this gap, we introduce FlamePilot, an LLM agent designed to empower combustion modeling research through automated and self-corrective CFD workflows. FlamePilot differentiates itself through an architecture that leverages atomic tools to ensure the robust setup and execution of complex simulations in both OpenFOAM and extended frameworks such as DeepFlame. The system is also capable of learning from scientific articles, extracting key information to guide the simulation from initial setup to optimized results. Validation on a public benchmark shows FlamePilot achieved a perfect 1.0 executability score and a 0.438 success rate, surpassing the prior best reported agent scores of 0.625 and 0.250, respectively. Furthermore, a detailed case study on Moderate or Intense Low-oxygen Dilution (MILD) combustion simulation demonstrates its efficacy as a collaborative research copilot, where FlamePilot autonomously translated a research paper into a configured simulation, conducted the simulation, post-processed the results, proposed evidence-based refinements, and managed a multi-step parameter study to convergence under minimal human intervention. By adopting a transparent and interpretable paradigm, FlamePilot establishes a foundational framework for AI-empowered combustion modeling, fostering a collaborative partnership where the agent manages workflow orchestration, freeing the researcher for high-level analysis. --- ### Advanced Machine Learning Approaches for Enhancing Person Re-Identification Performance Authors: Dang H. Pham, Tu N. Nguyen, Hoa N. Nguyen Published: 2026-01-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01356v1 Person re-identification (ReID) plays a critical role in intelligent surveillance systems by linking identities across multiple cameras in complex environments. However, ReID faces significant challenges such as appearance variations, domain shifts, and limited labeled data. This dissertation proposes three advanced approaches to enhance ReID performance under supervised, unsupervised domain adaptation (UDA), and fully unsupervised settings. First, SCM-ReID integrates supervised contrastive learning with hybrid loss optimization (classification, center, triplet, and centroid-triplet losses), improving discriminative feature representation and achieving state-of-the-art accuracy on Market-1501 and CUHK03 datasets. Second, for UDA, IQAGA and DAPRH combine GAN-based image augmentation, domain-invariant mapping, and pseudo-label refinement to mitigate domain discrepancies and enhance cross-domain generalization. Experiments demonstrate substantial gains over baseline methods, with mAP and Rank-1 improvements up to 12% in challenging transfer scenarios. Finally, ViTC-UReID leverages Vision Transformer-based feature encoding and camera-aware proxy learning to boost unsupervised ReID. By integrating global and local attention with camera identity constraints, this method significantly outperforms existing unsupervised approaches on large-scale benchmarks. Comprehensive evaluations across CUHK03, Market-1501, DukeMTMC-reID, and MSMT17 confirm the effectiveness of the proposed methods. The contributions advance ReID research by addressing key limitations in feature learning, domain adaptation, and label noise handling, paving the way for robust deployment in real-world surveillance systems. --- ### Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding Authors: Yixuan Lai, He Wang, Kun Zhou, Tianjia Shao Published: 2026-01-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.01352v2 Human identity-preserving text-to-video generation remains challenging under large changes in viewpoint, facial expression, illumination, and motion. Existing methods condition the generator on a single reference portrait, but a static image cannot capture how identity-bearing cues evolve across views and expressions, leading to face deformation, pose locking, identity drift, or over-smoothed faces. We observe that a short reference clip naturally provides richer temporal and multi-view identity cues than any single image, motivating a video-referential formulation. This richer signal, however, introduces a new challenge: identity evidence is distributed across many frames and must be distilled into a compact, stable representation under a limited token budget. To this end, we propose Slot-ID, a lightweight identity-conditioning framework built on a frozen text-to-video backbone. Slot-ID employs a slot-based temporal identity encoder with Sinkhorn-routed iterative reading to distill a compact, stable set of identity tokens from the reference clip, complemented by an image-anchor stream for dual-source conditioning. Extensive experiments demonstrate that Slot-ID outperforms state-of-the-art methods in identity preservation and visual naturalness while remaining competitive in prompt following, with particularly large gains under challenging pose, expression, and motion variations. --- ### FC-CONAN: An Exhaustively Paired Dataset for Robust Evaluation of Retrieval Systems Authors: Juan Junqueras, Florian Boudin, May-Myo Zin, Ha-Thanh Nguyen, Wachara Fungwacharakorn, Damián Ariel Furman, Akiko Aizawa, Ken Satoh Published: 2026-01-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.01350v1 Hate speech (HS) is a critical issue in online discourse, and one promising strategy to counter it is through the use of counter-narratives (CNs). Datasets linking HS with CNs are essential for advancing counterspeech research. However, even flagship resources like CONAN (Chung et al., 2019) annotate only a sparse subset of all possible HS-CN pairs, limiting evaluation. We introduce FC-CONAN (Fully Connected CONAN), the first dataset created by exhaustively considering all combinations of 45 English HS messages and 129 CNs. A two-stage annotation process involving nine annotators and four validators produces four partitions-Diamond, Gold, Silver, and Bronze-that balance reliability and scale. None of the labeled pairs overlap with CONAN, uncovering hundreds of previously unlabelled positives. FC-CONAN enables more faithful evaluation of counterspeech retrieval systems and facilitates detailed error analysis. The dataset is publicly available. --- ### From Classification to Generation: An Open-Ended Paradigm for Adverse Drug Reaction Prediction Based on Graph-Motif Feature Fusion Authors: Yuyan Pi, Min Jin, Wentao Xie, Xinhua Liu Published: 2026-01-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.01347v1 Computational biology offers immense potential for reducing the high costs and protracted cycles of new drug development through adverse drug reaction (ADR) prediction. However, current methods remain impeded by drug data scarcity-induced cold-start challenge, closed label sets, and inadequate modeling of label dependencies. Here we propose an open-ended ADR prediction paradigm based on Graph-Motif feature fusion and Multi-Label Generation (GM-MLG). Leveraging molecular structure as an intrinsic and inherent feature, GM-MLG constructs a dual-graph representation architecture spanning the atomic level, the local molecular level (utilizing fine-grained motifs dynamically extracted via the BRICS algorithm combined with additional fragmentation rules), and the global molecular level. Uniquely, GM-MLG pioneers transforming ADR prediction from multi-label classification into Transformer Decoder-based multi-label generation. By treating ADR labels as discrete token sequences, it employs positional embeddings to explicitly capture dependencies and co-occurrence relationships within large-scale label spaces, generating predictions via autoregressive decoding to dynamically expand the prediction space. Experiments demonstrate GM-MLG achieves up to 38% improvement and an average gain of 20%, expanding the prediction space from 200 to over 10,000 types. Furthermore, it elucidates non-linear structure-activity relationships between ADRs and motifs via retrosynthetic motif analysis, providing interpretable and innovative support for systematic risk reduction in drug safety. --- ### Reasoning Over Recall: Evaluating the Efficacy of Generalist Architectures vs. Specialized Fine-Tunes in RAG-Based Mental Health Dialogue Systems Authors: Md Abdullah Al Kafi, Raka Moni, Sumit Kumar Banshal Published: 2026-01-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.01341v1 The deployment of Large Language Models (LLMs) in mental health counseling faces the dual challenges of hallucinations and lack of empathy. While the former may be mitigated by RAG (retrieval-augmented generation) by anchoring answers in trusted clinical sources, there remains an open question as to whether the most effective model under this paradigm would be one that is fine-tuned on mental health data, or a more general and powerful model that succeeds purely on the basis of reasoning. In this paper, we perform a direct comparison by running four open-source models through the same RAG pipeline using ChromaDB: two generalist reasoners (Qwen2.5-3B and Phi-3-Mini) and two domain-specific fine-tunes (MentalHealthBot-7B and TherapyBot-7B). We use an LLM-as-a-Judge framework to automate evaluation over 50 turns. We find a clear trend: the generalist models outperform the domain-specific ones in empathy (3.72 vs. 3.26, $p < 0.001$) in spite of being much smaller (3B vs. 7B), and all models perform well in terms of safety, but the generalist models show better contextual understanding and are less prone to overfitting as we observe in the domain-specific models. Overall, our results indicate that for RAG-based therapy systems, strong reasoning is more important than training on mental health-specific vocabulary; i.e. a well-reasoned general model would provide more empathetic and balanced support than a larger narrowly fine-tuned model, so long as the answer is already grounded in clinical evidence. --- ### Achieving Fine-grained Cross-modal Understanding through Brain-inspired Hierarchical Representation Learning Authors: Weihang You, Hanqi Jiang, Yi Pan, Junhao Chen, Tianming Liu, Fei Dou Published: 2026-01-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01339v1 Understanding neural responses to visual stimuli remains challenging due to the inherent complexity of brain representations and the modality gap between neural data and visual inputs. Existing methods, mainly based on reducing neural decoding to generation tasks or simple correlations, fail to reflect the hierarchical and temporal processes of visual processing in the brain. To address these limitations, we present NeuroAlign, a novel framework for fine-grained fMRI-video alignment inspired by the hierarchical organization of the human visual system. Our framework implements a two-stage mechanism that mirrors biological visual pathways: global semantic understanding through Neural-Temporal Contrastive Learning (NTCL) and fine-grained pattern matching through enhanced vector quantization. NTCL explicitly models temporal dynamics through bidirectional prediction between modalities, while our DynaSyncMM-EMA approach enables dynamic multi-modal fusion with adaptive weighting. Experiments demonstrate that NeuroAlign significantly outperforms existing methods in cross-modal retrieval tasks, establishing a new paradigm for understanding visual cognitive mechanisms. --- ### FLOP-Efficient Training: Early Stopping Based on Test-Time Compute Awareness Authors: Hossam Amer, Maryam Dialameh, Hossein Rajabzadeh, Walid Ahmed, Weiwei Zhang, Yang Liu Published: 2026-01-04 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.01332v1 Scaling training compute, measured in FLOPs, has long been shown to improve the accuracy of large language models, yet training remains resource-intensive. Prior work shows that increasing test-time compute (TTC)-for example through iterative sampling-can allow smaller models to rival or surpass much larger ones at lower overall cost. We introduce TTC-aware training, where an intermediate checkpoint and a corresponding TTC configuration can together match or exceed the accuracy of a fully trained model while requiring substantially fewer training FLOPs. Building on this insight, we propose an early stopping algorithm that jointly selects a checkpoint and TTC configuration to minimize training compute without sacrificing accuracy. To make this practical, we develop an efficient TTC evaluation method that avoids exhaustive search, and we formalize a break-even bound that identifies when increased inference compute compensates for reduced training compute. Experiments demonstrate up to 92\% reductions in training FLOPs while maintaining and sometimes remarkably improving accuracy. These results highlight a new perspective for balancing training and inference compute in model development, enabling faster deployment cycles and more frequent model refreshes. Codes will be publicly released. --- ### AppellateGen: A Benchmark for Appellate Legal Judgment Generation Authors: Hongkun Yang, Lionel Z. Wang, Wei Fan, Yiran Hu, Lixu Wang, Chenyu Liu, Yu Zeng, Shenghong Fu, Lei Gong, Zhengxin Zhang, Haoyang Li, Jiexin Zheng et al. Published: 2026-01-04 Categories: cs.CY, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.01331v3 Legal judgment generation is a critical task in legal intelligence. However, existing research in legal judgment generation has predominantly focused on first-instance trials, relying on static fact-to-verdict mappings while neglecting the dialectical nature of appellate (second-instance) review. To address this, we introduce AppellateGen, a benchmark for second-instance legal judgment generation comprising 7,351 case pairs. The task requires models to draft legally binding judgments by reasoning over the initial verdict and evidentiary updates, thereby modeling the causal dependency between trial stages. We further propose a judicial Standard Operating Procedure (SOP)-based Legal Multi-Agent System (SLMAS) to simulate judicial workflows, which decomposes the generation process into discrete stages of issue identification, retrieval, and drafting. Experimental results indicate that while SLMAS improves logical consistency, the complexity of appellate reasoning remains a substantial challenge for current LLMs. The dataset and code are publicly available at: https://anonymous.4open.science/r/AppellateGen-5763. --- ### Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale Authors: Shengji Tang, Weihao Lin, Peng Ye, Jingqi Ye, Hao Li, Yiqun Zhang, Xiaosong Wang, Bo Zhang, Shuyue Hu, Tao Chen, Lei Bai, Wanli Ouyang Published: 2026-01-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.01330v2 Large Language Models (LLMs) have rapidly advanced, with Gemini-3-Pro setting a new performance milestone. In this work, we explore collective intelligence as an alternative to monolithic scaling, and demonstrate that open-source LLMs' collaboration can surpass Gemini-3-Pro. We first revisit LLM routing and aggregation at scale and identify three key bottlenecks: (1) current train-free routers are limited by a query-based paradigm focusing solely on textual similarity; (2) recent aggregation methods remain largely static, failing to select appropriate aggregators for different tasks;(3) the complementarity of routing and aggregation remains underutilized. To address these problems, we introduce JiSi, a novel framework designed to release the full potential of LLMs' collaboration through three innovations: (1) Query-Response Mixed Routing capturing both semantic information and problem difficulty; (2) Support-Set-based Aggregator Selection jointly evaluating the aggregation and domain capacity of aggregators; (3) Adaptive Routing-Aggregation Switch dynamically leveraging the advantages of routing and aggregation. Comprehensive experiments on nine benchmarks demonstrate that JiSi can surpass Gemini-3-Pro with only 47% costs by orchestrating ten open-source LLMs, while outperforming mainstream baselines. It suggests that collective intelligence represents a novel path towards Artificial General Intelligence (AGI). --- ### LinMU: Multimodal Understanding Made Linear Authors: Hongjie Wang, Niraj K. Jha Published: 2026-01-04 Categories: cs.CV, cs.AI, cs.LG, cs.MM, eess.IV arXiv: https://arxiv.org/abs/2601.01322v2 Modern Vision-Language Models (VLMs) achieve impressive performance but are limited by the quadratic complexity of self-attention, which prevents their deployment on edge devices and makes their understanding of high-resolution images and long-context videos prohibitively expensive. To address this challenge, we introduce LinMU (Linear-complexity Multimodal Understanding), a VLM design that achieves linear complexity for the language model decoder without using any quadratic-complexity modules while maintaining the performance of global-attention-based VLMs. LinMU replaces every self-attention layer in the language model decoder with an M-MATE block: a dual-branch module that combines a bidirectional state-space model for global context (Flex-MA branch) with localized Swin-style window attention (Local-Swin branch) for adjacent correlations. To transform a pre-trained VLM into the LinMU architecture, we propose a three-stage distillation framework that (i) initializes both branches with self-attention weights and trains the Flex-MA branch alone, (ii) unfreezes the Local-Swin branch and fine-tunes it jointly with the Flex-MA branch, and (iii) unfreezes the remaining blocks and fine-tunes them using LoRA adapters, while regressing on hidden states and token-level logits of the frozen VLM teacher. On MMMU, TextVQA, LongVideoBench, Video-MME, and other benchmarks, LinMU matches the performance of teacher models, yet reduces Time-To-First-Token (TTFT) by up to 2.7$\times$ and improves token throughput by up to 9.0$\times$ on minute-length videos. Ablations confirm the importance of each distillation stage and the necessity of the two branches of the M-MATE block. The proposed framework demonstrates that state-of-the-art multimodal reasoning can be achieved without quadratic attention, thus opening up avenues for long-context VLMs that can deal with high-resolution images and long videos. --- ### Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models Authors: Rong Zhou, Dongping Chen, Zihan Jia, Yao Su, Yixin Liu, Yiwen Lu, Dongwei Shi, Yue Huang, Tianyang Xu, Yi Pan, Xinliang Li, Yohannes Abate et al. Published: 2026-01-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.01321v1 Digital twins, as precise digital representations of physical systems, have evolved from passive simulation tools into intelligent and autonomous entities through the integration of artificial intelligence technologies. This paper presents a unified four-stage framework that systematically characterizes AI integration across the digital twin lifecycle, spanning modeling, mirroring, intervention, and autonomous management. By synthesizing existing technologies and practices, we distill a unified four-stage framework that systematically characterizes how AI methodologies are embedded across the digital twin lifecycle: (1) modeling the physical twin through physics-based and physics-informed AI approaches, (2) mirroring the physical system into a digital twin with real-time synchronization, (3) intervening in the physical twin through predictive modeling, anomaly detection, and optimization strategies, and (4) achieving autonomous management through large language models, foundation models, and intelligent agents. We analyze the synergy between physics-based modeling and data-driven learning, highlighting the shift from traditional numerical solvers to physics-informed and foundation models for physical systems. Furthermore, we examine how generative AI technologies, including large language models and generative world models, transform digital twins into proactive and self-improving cognitive systems capable of reasoning, communication, and creative scenario generation. Through a cross-domain review spanning eleven application domains, including healthcare, aerospace, smart manufacturing, robotics, and smart cities, we identify common challenges related to scalability, explainability, and trustworthiness, and outline directions for responsible AI-driven digital twin systems. --- ### Adaptive Hierarchical Evaluation of LLMs and SAST tools for CWE Prediction in Python Authors: Muntasir Adnan, Carlos C. N. Kuhn Published: 2026-01-04 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.01320v1 Large Language Models have become integral to software development, yet they frequently generate vulnerable code. Existing code vulnerability detection benchmarks employ binary classification, lacking the CWE-level specificity required for actionable feedback in iterative correction systems. We present ALPHA (Adaptive Learning via Penalty in Hierarchical Assessment), the first function-level Python benchmark that evaluates both LLMs and SAST tools using hierarchically aware, CWE-specific penalties. ALPHA distinguishes between over-generalisation, over-specification, and lateral errors, reflecting practical differences in diagnostic utility. Evaluating seven LLMs and two SAST tools, we find LLMs substantially outperform SAST, though SAST demonstrates higher precision when detections occur. Critically, prediction consistency varies dramatically across models (8.26%-81.87% agreement), with significant implications for feedback-driven systems. We further outline a pathway for future work incorporating ALPHA penalties into supervised fine-tuning, which could provide principled hierarchy-aware vulnerability detection pending empirical validation. --- ### Benchmarking Continuous Dynamic Multi-Objective Optimization: Survey and Generalized Test Suite Authors: Chang Shao, Qi Zhao, Nana Pu, Shi Cheng, Jing Jiang, Yuhui Shi Published: 2026-01-04 Categories: cs.NE arXiv: https://arxiv.org/abs/2601.01317v2 The field of Dynamic Multi-Objective Optimization (DMOO) has witnessed a surge of interest from both academia and industry, as numerous time-evolving real-world applications can be naturally formulated as Dynamic Multi-Objective Optimization Problems (DMOPs). This growing demand thus necessitates advanced benchmarks to rigorously evaluate optimization algorithms under realistic conditions. This paper introduces a comprehensive and principled framework for constructing highly realistic and challenging DMOO benchmarks. The proposed framework incorporates several novel components, including: a generalized formulation that allows the Pareto-optimal Set (PS) to change on hypersurfaces; a mechanism for creating controlled variable contribution imbalances to generate heterogeneous landscapes; and dynamic rotation matrices for inducing time-varying variable interactions and non-separability. Furthermore, we incorporate a temporal perturbation mechanism to simulate irregular environmental changes and propose a generalized time-linkage mechanism that systematically embeds historical solution quality into future problems, thereby capturing critical real-world phenomena such as error accumulation and time-deception. Extensive experimental results validate the effectiveness of the proposed framework, demonstrating its superiority over conventional benchmarks in terms of realism, complexity, and its capability for discriminating state-of-the-art algorithmic performance. Thus, this work establishes a new standard for dynamic multi-objective optimization benchmarking and provides a powerful tool for the development and evaluation of next-generation algorithms capable of addressing the complexities of real-world dynamic systems. --- ### Quantifying Local Strain Field and Deformation in Active Contraction of Bladder Using a Pretrained Transformer Model: A Speckle-Free Approach Authors: Alireza Asadbeygi, Anne M. Robertson, Yasutaka Tobe, Masoud Zamani, Sean D. Stocker, Paul Watton, Naoki Yoshimura, Simon C Watkins Published: 2026-01-04 Categories: q-bio.TO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.01315v1 Accurate quantification of local strain fields during bladder contraction is essential for understanding the biomechanics of bladder micturition, in both health and disease. Conventional digital image correlation (DIC) methods have been successfully applied to various biological tissues; however, this approach requires artificial speckling, which can alter both passive and active properties of the tissue. In this study, we introduce a speckle-free framework for quantifying local strain fields using a state-of-the-art, zero-shot transformer model, CoTracker3. We utilized a custom-designed, portable isotonic biaxial apparatus compatible with multiphoton microscopy (MPM) to demonstrate this approach, successfully tracking natural bladder lumen textures without artificial markers. Benchmark tests validated the method's high pixel accuracy and low strain errors. Our framework effectively captured heterogeneous deformation patterns, despite complex folding and buckling, which conventional DIC often fails to track. Application to in vitro active bladder contractions in four rat specimens (n=4) revealed statistically significant anisotropy (p<0.01), with higher contraction longitudinally compared to circumferentially. Multiphoton microscopy further illustrated and confirmed heterogeneous morphological changes, such as large fold formation during active contraction. This non-invasive approach eliminates speckle-induced artifacts, enabling more physiologically relevant measurements, and has broad applicability for material testing of other biological and engineered systems. --- ### Spectral-Window Hybrid (SWH) Authors: Vladimer Khasia Published: 2026-01-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.01313v1 Scaling sequence modeling to extreme contexts requires balancing computational efficiency with representational expressivity. While Transformers provide precise retrieval via the attention mechanism, their quadratic $\mathcal{O}(T^2)$ complexity limits their application to long-horizon tasks. In this work, we propose the \textbf{Spectral-Window Hybrid (SWH)}, an architecture that decouples sequence modeling into two \textit{parallel} streams: a global branch utilizing the Convolution Theorem to model long-range decay dynamics in $\mathcal{O}(T \log T)$ time, and a local branch employing sliding-window attention for token interactions within a bounded context. By aggregating these representations, SWH avoids the computational bottleneck of global attention while retaining local precision. We demonstrate that SWH matches the perplexity of standard Transformers on short contexts while enabling efficient linear scaling to extended sequences. The code is available at https://github.com/VladimerKhasia/SWH --- ### VReID-XFD: Video-based Person Re-identification at Extreme Far Distance Challenge Results Authors: Kailash A. Hambarde, Hugo Proença, Md Rashidunnabi, Pranita Samale, Qiwei Yang, Pingping Zhang, Zijing Gong, Yuhao Wang, Xi Zhang, Ruoshui Qu, Qiaoyun He, Yuhang Zhang et al. Published: 2026-01-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01312v1 Person re-identification (ReID) across aerial and ground views at extreme far distances introduces a distinct operating regime where severe resolution degradation, extreme viewpoint changes, unstable motion cues, and clothing variation jointly undermine the appearance-based assumptions of existing ReID systems. To study this regime, we introduce VReID-XFD, a video-based benchmark and community challenge for extreme far-distance (XFD) aerial-to-ground person re-identification. VReID-XFD is derived from the DetReIDX dataset and comprises 371 identities, 11,288 tracklets, and 11.75 million frames, captured across altitudes from 5.8 m to 120 m, viewing angles from oblique (30 degrees) to nadir (90 degrees), and horizontal distances up to 120 m. The benchmark supports aerial-to-aerial, aerial-to-ground, and ground-to-aerial evaluation under strict identity-disjoint splits, with rich physical metadata. The VReID-XFD-25 Challenge attracted 10 teams with hundreds of submissions. Systematic analysis reveals monotonic performance degradation with altitude and distance, a universal disadvantage of nadir views, and a trade-off between peak performance and robustness. Even the best-performing SAS-PReID method achieves only 43.93 percent mAP in the aerial-to-ground setting. The dataset, annotations, and official evaluation protocols are publicly available at https://www.it.ubi.pt/DetReIDX/ . --- ### Concave Certificates: Geometric Framework for Distributionally Robust Risk and Complexity Analysis Authors: Hong T. M. Chu Published: 2026-01-04 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2601.01311v2 Distributionally Robust (DR) optimization aims to certify worst-case risk within a Wasserstein uncertainty set. Current certifications typically rely either on global Lipschitz bounds, which are often conservative, or on local gradient information, which provides only a first-order approximation. This paper introduces a novel geometric framework based on the least concave majorants of the growth rate functions. Our proposed concave certificate establishes a tight bound on DR risk that remains applicable to non-Lipschitz and non-differentiable losses. We extend this framework to complexity analysis, introducing the worst-case generalization bound that complements the standard statistical generalization bound. Furthermore, we utilize this certificate to bound the gap between adversarial and empirical Rademacher complexity, demonstrating that dependencies on input diameter, network width, and depth can be eliminated. For practical application in deep learning, we introduce the adversarial score as a tractable relaxation of the concave certificate that enables efficient and layer-wise analysis of neural networks. We validate our theoretical results in various numerical experiments on classification and regression tasks using real-world data. --- ### Making MoE-based LLM Inference Resilient with Tarragon Authors: Songyu Zhang, Aaron Tam, Myungjin Lee, Shixiong Qi, K. K. Ramakrishnan Published: 2026-01-04 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2601.01310v2 Mixture-of-Experts (MoE) models are increasingly used to serve LLMs at scale, but failures become common as deployment scale grows. Existing systems exhibit poor failure resilience: even a single worker failure triggers a coarse-grained, service-wide restart, discarding accumulated progress and halting the entire inference pipeline during recovery--an approach clearly ill-suited for latency-sensitive, LLM services. We present Tarragon, a resilient MoE inference framework that confines the failures impact to individual workers while allowing the rest of the pipeline to continue making forward progress. Tarragon exploits the natural separation between the attention and expert computation in MoE-based transformers, treating attention workers (AWs) and expert workers (EWs) as distinct failure domains. Tarragon introduces a reconfigurable datapath to mask failures by rerouting requests to healthy workers. On top of this datapath, Tarragon implements a self-healing mechanism that relaxes the tightly synchronized execution of existing MoE frameworks. For stateful AWs, Tarragon performs asynchronous, incremental KV cache checkpointing with per-request restoration, and for stateless EWs, it leverages residual GPU memory to deploy shadow experts. These together keep recovery cost and recomputation overhead extremely low. Our evaluation shows that, compared to state-of-the-art MegaScale-Infer, Tarragon reduces failure-induced stalls by 160-213x (from ~64 s down to 0.3-0.4 s) while preserving performance when no failures occur. --- ### Towards a Principled Muon under $μ\mathsf{P}$: Ensuring Spectral Conditions throughout Training Authors: John Zhao Published: 2026-01-04 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2601.01306v2 The $μ$-parameterization ($μ$P) provides a principled foundation for large language model (LLM) training by prescribing width-independent learning dynamics, which in turn enables predictable scaling behavior and robust hyperparameter transfer across model sizes. A central requirement of $μ$P is the satisfaction of certain spectral conditions on weight matrices, which ensure consistent feature learning and optimization behavior as model width grows. While these conditions are well understood in theory, guaranteeing their validity in practical training for matrix-based optimizers such as Muon is still under studied. Existing works that study Muon under $μ$P exhibit important limitations: they either do not ensure that the spectral conditions hold throughout the entire training horizon, or require repeated spectral normalization (or Newton-Schulz iterations) applied to both weights and updates, leading to significant computational overhead and reduced practicality. In this work, we show how to reliably guarantee the spectral conditions required by $μ$P for Muon during the entire training process. Our key insight is that for moderately large models, maintaining spectral control at the level of optimizer updates alone is sufficient to preserve $μ$P-compatible scaling, eliminating the need for explicit spectral normalization of the weights. Based on this principle, we develop a variant of Muon, namely Muon++, that satisfies spectral condition throughout the training process. Our results bridge the gap between the theoretical promises of $μ$P and the practical deployment of matrix-based optimizers in long-horizon training. We also take the first step towards an adaptive spectral condition by incorporating data-dependent effects, making it better suited for long-horizon LLM training. --- ### ShadowGS: Shadow-Aware 3D Gaussian Splatting for Satellite Imagery Authors: Feng Luo, Hongbo Pan, Xiang Yang, Baoyu Jiang, Fengqing Liu, Tao Huang Published: 2026-01-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00939v1 3D Gaussian Splatting (3DGS) has emerged as a novel paradigm for 3D reconstruction from satellite imagery. However, in multi-temporal satellite images, prevalent shadows exhibit significant inconsistencies due to varying illumination conditions. To address this, we propose ShadowGS, a novel framework based on 3DGS. It leverages a physics-based rendering equation from remote sensing, combined with an efficient ray marching technique, to precisely model geometrically consistent shadows while maintaining efficient rendering. Additionally, it effectively disentangles different illumination components and apparent attributes in the scene. Furthermore, we introduce a shadow consistency constraint that significantly enhances the geometric accuracy of 3D reconstruction. We also incorporate a novel shadow map prior to improve performance with sparse-view inputs. Extensive experiments demonstrate that ShadowGS outperforms current state-of-the-art methods in shadow decoupling accuracy, 3D reconstruction precision, and novel view synthesis quality, with only a few minutes of training. ShadowGS exhibits robust performance across various settings, including RGB, pansharpened, and sparse-view satellite inputs. --- ### Is He Extroverted? Identifying Missing Relevant Personas for Faithful User Simulation Authors: Weiwen Su, Yuhan Zhou, Zihan Wang, Naoki Yoshinaga, Masashi Toyoda Published: 2026-01-03 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.15832v2 Existing user simulation approaches focus on generating user-like responses in dialogue. They often assume that the provided persona is sufficient for producing such responses, without verifying whether critical personas are supplied. This raises concerns about the validity of simulation results. To address this issue, we study the task of identifying persona dimensions (e.g., "whether the user is price-sensitive") that are relevant but missing in simulating a user's reply for a given dialogue context. We introduce PICQ-drama (constructed from TVShowGuess), a benchmark of context-aware choice questions, annotated with missing persona dimensions whose absence leads to ambiguous user choices. We further design diverse evaluation criteria for missing persona identification. Benchmarking leading LLMs on our PICQ-drama dataset demonstrates the feasibility of this task. Evaluation across diverse criteria, along with further analyses, reveals cognitive differences between LLMs and humans and highlights the distinct roles of different persona categories in shaping responses. --- ### What Artificial Intelligence can do for High-Performance Computing systems? Authors: Pierrick Pochelu, Hyacinthe Cartiaux, Julien Schleich Published: 2026-01-03 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2602.00014v1 High-performance computing (HPC) centers consume substantial power, incurring environmental and operational costs. This review assesses how artificial intelligence (AI), including machine learning (ML) and optimization, improves the efficiency of operational HPC systems. Approximately 1,800 publications from 2019 to 2025 were manually screened using predefined inclusion/exclusion criteria; 74 "AI for HPC" papers were retained and grouped into six application areas: performance estimation, performance optimization, scheduling, surrogate modeling, fault detection, and language-model-based automation. Scheduling is the most active area, spanning research-oriented reinforcement-learning schedulers to production-friendly hybrids that combine ML with heuristics. Supervised performance estimation is foundational for both scheduling and optimization. Graph neural networks and time-series models strengthen anomaly detection by capturing spatio-temporal dependencies in production telemetry. Domain-specialized language models for HPC can outperform general-purpose LLMs on targeted coding and automation tasks. Together, these findings highlight integration opportunities such as LLM-based operating-system concepts and underscore the need for advances in MLOps, standardization of AI components, and benchmarking methodology. --- ### M3Kang: Evaluating Multilingual Multimodal Mathematical Reasoning in Vision-Language Models Authors: Aleix Torres-Camps, Nathaniel Mitrani Hadida, Víctor Conchello Vendrell, Àlex Batlle Casellas, Arnau Padrés Masdemont, Jordi Ros-Giralt Published: 2026-01-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.16218v1 Despite state-of-the-art vision-language models (VLMs) have demonstrated strong reasoning capabilities, their performance in multilingual mathematical reasoning remains underexplored, particularly when compared to human performance. To bridge this gap, we introduce M3Kang, the first massively multilingual, multimodal mathematical reasoning dataset for VLMs. It is derived from the Kangaroo Math Competition, the world's largest mathematics contest, which annually engages over six million participants under the age of 18 across more than 90 countries. M3Kang includes 1,747 unique multiple-choice problems organized by grade-level difficulty, with translations into 108 culturally diverse languages, some of them including diagrams essential for solving them. Using this dataset, we conduct extensive benchmarking on both closed- and open-source SOTA models. We observe that, despite recent advances, models still struggle with basic math and diagram-based reasoning, with performance scaling with language presence and model size, but not with grade level. We also find that multilingual techniques can be effectively extended to the multimodal setting, resulting in significant improvements over baseline approaches. Our analysis also incorporates performance data from over 68,000 students, enabling direct comparison with human performance. We are open-sourcing M3Kang, including the English-only subset M2Kang, along with the framework and codebase used to construct the dataset. --- ### Let Me Try Again: Examining Replay Behavior by Tracing Students' Latent Problem-Solving Pathways Authors: Shan Zhang, Siddhartha Pradhan, Ji-Eun Lee, Ashish Gurung, Anthony F. Botelho Published: 2026-01-03 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.11586v1 Prior research has shown that students' problem-solving pathways in game-based learning environments reflect their conceptual understanding, procedural knowledge, and flexibility. Replay behaviors, in particular, may indicate productive struggle or broader exploration, which in turn foster deeper learning. However, little is known about how these pathways unfold sequentially across problems or how the timing of replays and other problem-solving strategies relates to proximal and distal learning outcomes. This study addresses these gaps using Markov Chains and Hidden Markov Models (HMMs) on log data from 777 seventh graders playing the game-based learning platform of From Here to There!. Results show that within problem sequences, students often persisted in states or engaged in immediate replay after successful completions, while across problems, strong self-transitions indicated stable strategic pathways. Four latent states emerged from HMMs: Incomplete-dominant, Optimal-ending, Replay, and Mixed. Regression analyses revealed that engagement in replay-dominant and optimal-ending states predicted higher conceptual knowledge, flexibility, and performance compared with the Incomplete-dominant state. Immediate replay consistently supported learning outcomes, whereas delayed replay was weakly or negatively associated in relation to Non-Replay. These findings suggest that replay in digital learning is not uniformly beneficial but depends on timing, with immediate replay supporting flexibility and more productive exploration. ---