Jing Qiu

Glenn Jocher, Jing Qiu, Mengyu Liu et al.

Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware. The YOLO family has become widely deployed for this reason, yet most YOLO detectors still rely on non-maximum suppression at inference, carry heavy detection heads due to Distribution Focal Loss, require long training schedules, and can leave the smallest objects without positive label assignments. We present Ultralytics YOLO26, a unified real-time vision model family that addresses these limitations through coordinated architecture and training advances. YOLO26 uses a dual-head design for native NMS-free end-to-end inference and removes DFL entirely, yielding a lighter head with unconstrained regression range. Its training pipeline combines MuSGD, a hybrid Muon-SGD optimizer adapted from large language model training; Progressive Loss, which shifts supervision toward the inference-time head; and STAL, a label assignment strategy that guarantees positive coverage for small objects. Beyond detection, YOLO26 introduces task-specific head and loss designs for instance segmentation, pose estimation, and oriented detection, producing consistent gains across tasks and scales. The family spans five scales (n/s/m/l/x) and supports detection, instance segmentation, pose estimation, classification, and oriented detection in a single pipeline, with an open-vocabulary extension, YOLOE-26, for text-, visual-, and prompt-free inference. Across all scales, YOLO26 achieves 40.9-57.5 mAP on COCO at 1.7-11.8 ms T4 TensorRT latency, advancing the accuracy-latency Pareto front over prior real-time detectors, while YOLOE-26x reaches 40.6 AP on LVIS minival under text prompting. Code and models are available at https://github.com/ultralytics/ultralytics.

Jing Qiu, Weijun Fang, Shu-Tao Xia et al.

Maximum distance separable (MDS) codes are widely used in distributed storage, but naively repairing a single failure in an $(n,k)$ MDS code requires downloading the full contents of $k$ surviving nodes. Minimum storage regenerating (MSR) codes, introduced by Dimakis et al., minimize repair bandwidth while preserving the MDS property by contacting $d>k$ helper nodes and downloading only a fraction of each helper. For scalar MDS codes, Guruswami and Wootters established a linear repair framework, and Tamo, Ye, and Barg subsequently gave the first explicit Reed-Solomon (RS) codes achieving the MSR point. Their construction yields RS-MSR codes with subpacketization $\ell=s\prod_{i=1}^n p_i$, where $s=d+1-k$ and the distinct primes $p_i$ satisfy $p_i\equiv 1\pmod{s}$. In this paper, we show that this congruence condition is not intrinsic to the RS repair problem. We develop a basis-transformation approach to the construction of repair-enabling subspaces. The approach consists of three deterministic operations -- Euclidean Square Partition, Transposition, and Column Aggregation -- which construct the required repair-enabling subspaces directly from the standard monomial basis of the repair field. Consequently, we obtain RS-MSR codes with subpacketization $\ell=s\prod_{i=1}^n p_i$ for arbitrary distinct primes $p_i>s$. For fixed $s$, this improves the subpacketization of the Tamo--Ye--Barg construction by a factor asymptotic to $φ(s)^{n+\mathrm{o}(n)}$, where $φ(\cdot)$ denotes Euler's totient function.

Xinlei Wang, Maike Feng, Jing Qiu et al.

This paper introduces a novel approach that leverages Large Language Models (LLMs) and Generative Agents to enhance time series forecasting by reasoning across both text and time series data. With language as a medium, our method adaptively integrates social events into forecasting models, aligning news content with time series fluctuations to provide richer insights. Specifically, we utilize LLM-based agents to iteratively filter out irrelevant news and employ human-like reasoning to evaluate predictions. This enables the model to analyze complex events, such as unexpected incidents and shifts in social behavior, and continuously refine the selection logic of news and the robustness of the agent's output. By integrating selected news events with time series data, we fine-tune a pre-trained LLM to predict sequences of digits in time series. The results demonstrate significant improvements in forecasting accuracy, suggesting a potential paradigm shift in time series forecasting through the effective utilization of unstructured news data.

Jiaqi Ruan, Gaoqi Liang, Huan Zhao et al.

Applying large language models (LLMs) to modern power systems presents a promising avenue for enhancing decision-making and operational efficiency. However, this action may also incur potential security threats, which have not been fully recognized so far. To this end, this article analyzes potential threats incurred by applying LLMs to power systems, emphasizing the need for urgent research and development of countermeasures.

Xinlei Wang, Ruibo Ming, Jing Qiu et al.

The scaling-law era has transformed artificial intelligence from research into a global industry, but its rapid growth raises concerns over energy usage, carbon emissions, and environmental sustainability. Unlike traditional sectors, the AI industry still lacks systematic carbon accounting methods that support large-scale estimates without reproducing the original model. This leaves open questions about how large the problem is today and how large it might be in the near future. Given that the Hugging Face (HF) platform well represents the broader open-source community, we treat it as a large-scale, publicly accessible, and audit-ready corpus for carbon accounting. We propose a FLOPs-based framework to estimate aggregate training emissions of HF open-source models. Considering their uneven disclosure quality, we introduce a tiered approach to handle incomplete metadata, supported by empirical regressions that verify the statistical significance. Compute is also converted to AI training carbon intensity (ATCI, emissions per compute), a metric to assess the sustainability efficiency of model training. Our results show that training the most popular open-source models (with over 5,000 downloads) has resulted in approximately $5.8\times10^4$ metric tons of carbon emissions. This paper provides a scalable framework for emission estimations and a practical methodology to guide future standards and sustainability strategies in the AI industry.

Jinta Weng, Yue Hu, Jing Qiu et al.

The effectiveness of prompt learning has been demonstrated in different pre-trained language models. By formulating suitable template and choosing representative label mapping, prompt learning can be used as an efficient knowledge probe. However, finding suitable prompt in existing methods requires multiple experimental attempts or appropriate vector initialization on formulating suitable template and choosing representative label mapping, which it is more common in few-shot learning tasks. Motivating by PLM working process, we try to construct the prompt from task semantic perspective and thus propose the STPrompt -Semantic-guided and Task-driven Prompt model. Specifically, two novel prompts generated from the semantic dependency tree (Dep-prompt) and task-specific metadata description (Meta-prompt), are firstly constructed in a prompt augmented pool, and the proposed model would automatically select a suitable semantic prompt to motivating the prompt learning process. Our results show that the proposed model achieves the state-of-the-art performance in five different datasets of few-shot text classification tasks, which prove that more semantic and significant prompts could assume as a better knowledge proving tool.

Xin Lu, Jing Qiu, Jiafeng Lin et al.

Emerging connect-and-manage practices allow new transmission-connected mega-loads to connect while enforcing time-varying admissible power exchange limits at the point of common coupling (PCC) in real time. Hyperscale artificial intelligence data centers (AIDCs), whose demand can reach hundreds of megawatts and whose internal computing-cooling dynamics evolve rapidly, can therefore face frequent conflicts between workload continuity requirements and externally imposed PCC envelopes. This paper proposes a battery-assisted operational framework in which on-site battery energy storage (BESS) serves as a physical buffering interface to reconcile fast internal dynamics with time-varying interconnection limits. A continuity-aware energy-computation model is developed to jointly capture checkpoint-constrained AI training workloads, information technology (IT) computing power-throughput characteristics, and IT-cooling thermal dynamics. A two-stage decision framework is then formulated, consisting of scenario-based day-ahead workload commitment and a real-time receding-horizon delivery assurance controller that enforces battery, thermal, and grid-interaction constraints. Case studies on the IEEE 39-bus system with Australian real data demonstrate that BESS substantially increases credible day-ahead workload commitment and improves real-time delivery robustness under transmission congestion. Sensitivity analyses further reveal a regime-dependent role transition of BESS -- from feasibility-oriented continuity support when PCC limits are binding to economy-driven flexibility provision as transmission constraints are relaxed.

Zeyan Wang, Zhengmao Liu, Yongxin Cai et al.

Federated Unlearning (FU) aims to efficiently remove the influence of specific client data from a federated model while preserving utility for the remaining clients. However, three key challenges remain: (1) existing unlearning objectives often compromise model utility or increase vulnerability to Membership Inference Attacks (MIA); (2) there is a persistent conflict between forgetting and utility, where further unlearning inevitably harms retained performance; and (3) support for concurrent multi-client unlearning is poor, as gradient conflicts among clients degrade the quality of forgetting. To address these issues, we propose FUPareto, an efficient unlearning framework via Pareto-augmented optimization. We first introduce the Minimum Boundary Shift (MBS) Loss, which enforces unlearning by suppressing the target class logit below the highest non-target class logit; this can improve the unlearning efficiency and mitigate MIA risks. During the unlearning process, FUPareto performs Pareto improvement steps to preserve model utility and executes Pareto expansion to guarantee forgetting. Specifically, during Pareto expansion, the framework integrates a Null-Space Projected Multiple Gradient Descent Algorithm (MGDA) to decouple gradient conflicts. This enables effective, fair, and concurrent unlearning for multiple clients while minimizing utility degradation. Extensive experiments across diverse scenarios demonstrate that FUPareto consistently outperforms state-of-the-art FU methods in both unlearning efficacy and retained utility.

Xinlei Wang, Mingtian Tan, Jing Qiu et al.

Traditional time series analysis has long relied on pattern recognition, trained on static and well-established benchmarks. However, in real-world settings -- where policies shift, human behavior adapts, and unexpected events unfold -- effective analysis must go beyond surface-level trends to uncover the actual forces driving them. The recent rise of Large Language Models (LLMs) presents new opportunities for rethinking time series analysis by integrating multimodal inputs. However, as the use of LLMs becomes popular, we must remain cautious, asking why we use LLMs and how to exploit them effectively. Most existing LLM-based methods still employ their numerical regression ability and ignore their deeper reasoning potential. This paper argues for rethinking time series with LLMs as a reasoning task that prioritizes causal structure and explainability. This shift brings time series analysis closer to human-aligned understanding, enabling transparent and context-aware insights in complex real-world environments.

Mohammed Daba, Jing Qiu

Category-level generalization for robotic garment manipulation, such as bimanual smoothing, remains a significant hurdle due to high dimensionality, complex dynamics, and intra-category variations. Current approaches often struggle, either overfitting with concurrently learned visual features for a specific instance or, despite category-level perceptual generalization, failing to predict the value of synergistic bimanual actions. We propose the Feature-Conditioned Bimanual Value Network (FCBV-Net), operating on 3D point clouds to specifically enhance category-level policy generalization for garment smoothing. FCBV-Net conditions bimanual action value prediction on pre-trained, frozen dense geometric features, ensuring robustness to intra-category garment variations. Trainable downstream components then learn a task-specific policy using these static features. In simulated GarmentLab experiments with the CLOTH3D dataset, FCBV-Net demonstrated superior category-level generalization. It exhibited only an 11.5% efficiency drop (Steps80) on unseen garments compared to 96.2% for a 2D image-based baseline, and achieved 89% final coverage, outperforming an 83% coverage from a 3D correspondence-based baseline that uses identical per-point geometric features but a fixed primitive. These results highlight that the decoupling of geometric understanding from bimanual action value learning enables better category-level generalization.

Jing Qiu, Jiancheng Huang, Xiangdong Zhang et al.

Physics-informed deep learning has been developed as a novel paradigm for learning physical dynamics recently. While general physics-informed deep learning methods have shown early promise in learning fluid dynamics, they are difficult to generalize in arbitrary time instants in real-world scenario, where the fluid motion can be considered as a time-variant trajectory involved large-scale particles. Inspired by the advantage of diffusion model in learning the distribution of data, we first propose Pi-fusion, a physics-informed diffusion model for predicting the temporal evolution of velocity and pressure field in fluid dynamics. Physics-informed guidance sampling is proposed in the inference procedure of Pi-fusion to improve the accuracy and interpretability of learning fluid dynamics. Furthermore, we introduce a training strategy based on reciprocal learning to learn the quasiperiodical pattern of fluid motion and thus improve the generalizability of the model. The proposed approach are then evaluated on both synthetic and real-world dataset, by comparing it with state-of-the-art physics-informed deep learning methods. Experimental results show that the proposed approach significantly outperforms existing methods for predicting temporal evolution of velocity and pressure field, confirming its strong generalization by drawing probabilistic inference of forward process and physics-informed guidance sampling. The proposed Pi-fusion can also be generalized in learning other physical dynamics governed by partial differential equations.

Jinta Weng, Ying Gao, Jing Qiu et al.

Through the combination of crowdsourcing knowledge graph and teaching system, research methods to generate knowledge graph and its applications. Using two crowdsourcing approaches, crowdsourcing task distribution and reverse captcha generation, to construct knowledge graph in the field of teaching system. Generating a complete hierarchical knowledge graph of the teaching domain by nodes of school, student, teacher, course, knowledge point and exercise type. The knowledge graph constructed in a crowdsourcing manner requires many users to participate collaboratively with fully consideration of teachers' guidance and users' mobilization issues. Based on the three subgraphs of knowledge graph, prominent teacher, student learning situation and suitable learning route could be visualized. Personalized exercises recommendation model is used to formulate the personalized exercise by algorithm based on the knowledge graph. Collaborative creation model is developed to realize the crowdsourcing construction mechanism. Though unfamiliarity with the learning mode of knowledge graph and learners' less attention to the knowledge structure, system based on Crowdsourcing Knowledge Graph can still get high acceptance around students and teachers

Xiao-Lei Yin, Dong-Xue Liang, Lu Wang et al.

Cardiac coronary angiography is a major technology to assist doctors during cardiac interventional surgeries. Under the exposure of X-ray radiation, doctors inject contrast agents through catheters to determine the position and status of coronary vessels in real time. To get a coronary angiography video with a high frame rate, the doctor needs to increase the exposure frequency and intensity of the X-ray. This will inevitably increase the X-ray harm to both patients and surgeons. In this work, we innovatively utilize a deep-learning based video interpolation algorithm to interpolate coronary angiography videos. Moreover, we establish a new coronary angiography image dataset ,which contains 95,039 triplets images to retrain the video interpolation network model. Using the retrained network we synthesize high frame rate coronary angiography video from the low frame rate coronary angiography video. The average peak signal to noise ratio(PSNR) of those synthesized video frames reaches 34dB. Extensive experiment results demonstrate the feasibility of using the video frame interpolation algorithm to synthesize continuous and clear high frame rate coronary angiography video. With the help of this technology, doctors can significantly reduce exposure frequency and intensity of the X-ray during coronary angiography.

Lu Wang, Dong-xue Liang, Xiao-lei Yin et al.

Coronary angiography is an indispensable assistive technique for cardiac interventional surgery. Segmentation and extraction of blood vessels from coronary angiography videos are very essential prerequisites for physicians to locate, assess and diagnose the plaques and stenosis in blood vessels. This article proposes a new video segmentation framework that can extract the clearest and most comprehensive coronary angiography images from a video sequence, thereby helping physicians to better observe the condition of blood vessels. This framework combines a 3D convolutional layer to extract spatial--temporal information from a video sequence and a 2D CE--Net to accomplish the segmentation task of an image sequence. The input is a few continuous frames of angiographic video, and the output is a mask of segmentation result. From the results of segmentation and extraction, we can get good segmentation results despite the poor quality of coronary angiography video sequences.

Lu Wang, Dong-xue Liang, Xiao-lei Yin et al.

The reconstruction of three-dimensional models of coronary arteries is of great significance for the localization, evaluation and diagnosis of stenosis and plaque in the arteries, as well as for the assisted navigation of interventional surgery. In the clinical practice, physicians use a few angles of coronary angiography to capture arterial images, so it is of great practical value to perform 3D reconstruction directly from coronary angiography images. However, this is a very difficult computer vision task due to the complex shape of coronary blood vessels, as well as the lack of data set and key point labeling. With the rise of deep learning, more and more work is being done to reconstruct 3D models of human organs from medical images using deep neural networks. We propose an adversarial and generative way to reconstruct three dimensional coronary artery models, from two different views of angiographic images of coronary arteries. With 3D fully supervised learning and 2D weakly supervised learning schemes, we obtained reconstruction accuracies that outperform state-of-art techniques.

Zhihong Tian, Xiangsong Gao, Shen Su et al.

Conducting reputation management is very important for Internet of vehicles. However, most of the existing researches evaluate the effectiveness of their schemes with settled attacking behaviors in their simulation which cannot represent the scenarios in reality. In this paper, we propose to consider dynamical and diversity attacking strategies in the simulation of reputation management scheme evaluation. To that end, we apply evolutionary game theory to model the evolution process of malicious users' attacking strategies, and discuss the methodology of the evaluation simulations. We further apply our evaluation method to a reputation management scheme with multiple utility functions, and discuss the evaluation results. The results indicate that our evaluation method is able to depict the evolving process of the dynamic attacking strategies in a vehicular network, and the final state of the simulation could be used to quantify the protection effectiveness of the reputation management scheme.