Referring Multi-Object Tracking (RMOT) aims to achieve precise object detection and tracking through natural language instructions, representing a fundamental capability for intelligent robotic systems. However, current RMOT research remains mostly confined to ground-level scenarios, which constrains their ability to capture broad-scale scene contexts and perform comprehensive tracking and path planning. In contrast, Unmanned Aerial Vehicles (UAVs) leverage their expansive aerial perspectives and superior maneuverability to enable wide-area surveillance. Moreover, UAVs have emerged as critical platforms for Embodied Intelligence, which has given rise to an unprecedented demand for intelligent aerial systems capable of natural language interaction. To this end, we introduce AerialMind, the first large-scale RMOT benchmark in UAV scenarios, which aims to bridge this research gap. To facilitate its construction, we develop an innovative semi-automated collaborative agent-based labeling assistant (COALA) framework that significantly reduces labor costs while maintaining annotation quality. Furthermore, we propose HawkEyeTrack (HETrack), a novel method that collaboratively enhances vision-language representation learning and improves the perception of UAV scenarios. Comprehensive experiments validated the challenging nature of our dataset and the effectiveness of our method.

Electrocardiogram (ECG), as a crucial fine-grained cardiac feature, has been successfully recovered from radar signals in the literature, but the performance heavily relies on the high-quality radar signal and numerous radar-ECG pairs for training, restricting the applications in new scenarios due to data scarcity. Therefore, this work focuses on radar-based ECG recovery in new scenarios with limited data and proposes a cardio-focusing and-tracking (CFT) algorithm to precisely track the cardiac location to ensure an efficient acquisition of high quality radar signals. Furthermore, a transfer learning model (RFcardi) is proposed to extract cardio-related information from the radar signal without ECG ground truth based on the intrinsic sparsity of cardiac features, and only a few synchronous radar ECG pairs are required to fine-tune the pre-trained model for ECG recovery. The experimental results reveal that the proposed CFT can dynamically identify the cardiac location, and the RFcardi model can effectively generate faithful ECG recoveries after using a small number of radar-ECG pairs for training. The code and dataset will be made available after publication.

Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online RL agents trained in imperfect simulation environments can suffer from severe sim-to-real issues. Offline RL approaches although bypass the need for simulators, often pose demanding requirements on the size and quality of the offline datasets. The recently emerged hybrid offline-and-online RL provides an attractive framework that enables joint use of limited offline data and imperfect simulator for transferable policy learning. In this paper, we develop a new algorithm, called$\mathrm{H} 2 \mathrm{O}+$, which offers great flexibility to bridge various choices of offline and online learning methods, while also accounting for dynamics gaps between the real and simulation environments. Through extensive simulation and real-world robotics experiments, we demonstrate superior performance and flexibility of$\mathbf{H 2 O}+$over advanced cross-domain online and offline RL algorithms.

4D millimeter-wave (MMW) radar, which provides both height information and dense point cloud data over 3D MMW radar, has become increasingly popular in 3D object detection. In recent years, radar-vision fusion models have demonstrated performance close to that of LiDAR-based models, offering advantages in terms of lower hardware costs and better resilience in extreme conditions. However, many radar-vision fusion models treat radar as a sparse LiDAR, underutilizing radar-specific information. Additionally, these multi-modal networks are often sensitive to the failure of a single modality, particularly vision. To address these challenges, we propose the Radar Depth Lift-Splat-Shoot (RDL) module, which integrates radar-specific data into the depth prediction process, enhancing the quality of visual Bird's-Eye View (BEV) features. We further introduce a Unified Feature Fusion (UFF) approach that extracts BEV features across different modalities using shared module. To assess the robustness of multimodal models, we develop a novel Failure Test (FT) ablation experiment, which simulates vision modality failure by injecting Gaussian noise. We conduct extensive experiments on the View-of-Delft (VoD) and TJ4D datasets. The results demonstrated that our proposed Unified BEVFusion (UniBEVFusion) network significantly outperforms state-of-the-art models on the TJ4D dataset, with improvements of 3.96% in 3D and 4.17% in BEV object detection accuracy.

Recently, visual grounding and multi-sensors setting have been incorporated into perception system for terrestrial autonomous driving systems and Unmanned Surface Vessels (USVs), yet the high complexity of modern learning-based visual grounding model using multi-sensors prevents such model to be deployed on USVs in the real-life. To this end, we design a low-power multi-task model named NanoMVG for waterway embodied perception, guiding both camera and 4D millimeter-wave radar to locate specific object(s) through natural language. NanoMVG can perform both box-level and mask-level visual grounding tasks simultaneously. Compared to other visual grounding models, NanoMVG achieves highly competitive performance on the WaterVG dataset, particularly in harsh environments. Moreover, the real-world experiments with deployment of NanoMVG on embedded edge device of USV demonstrates its fast inference speed for real-time perception and capability of boasting ultra-low power consumption for long endurance.

Autonomous drone racing presents a challenging control problem, requiring real-time decision-making and robust handling of nonlinear system dynamics. While iterative learning model predictive control (LMPC) offers a promising framework for iterative performance improvement, its direct application to drone racing faces challenges like real-time compatibility or the trade-off between time-optimal and safe traversal. In this paper, we enhance LMPC with three key innovations: (1) an adaptive cost function that dynamically weights time-optimal tracking against centerline adherence, (2) a shifted local safe set to prevent excessive shortcutting and enable more robust iterative updates, and (3) a Cartesian-based formulation that accommodates safety constraints without the singularities or integration errors associated with Frenet-frame transformations. Results from extensive simulation and real-world experiments demonstrate that our improved algorithm can optimize initial trajectories generated by a wide range of controllers with varying levels of tuning for a maximum improvement in lap time by 60.85%. Even applied to the most aggressively tuned state-of-the-art model-based controller, MPCC++, on a real drone, a 6.05% improvement is still achieved. Overall, the proposed method pushes the drone toward faster traversal and avoids collisions in simulation and real-world experiments, making it a practical solution to improve the peak performance of drone racing.

Over the past decade, the size of neural network models has gradually increased in both breadth and depth, leading to a growing interest in the application of neural network pruning. Unstructured pruning provides fine-grained sparsity and achieves better inference acceleration under specific hardware support. Unstructured Pruning at Initialization (PaI) optimizes the iterative pruning pipeline, but sparse weights increase the risk of underfitting during training. More importantly, almost all PaI algorithms focus only on obtaining the best pruning mask without considering whether the retained weights are suitable for training. Introducing Lipschitz constants during model initialization can reduce the risk of model underfitting and overfitting. As a result, we firstly analyze the impact of Lipschitz initialization on model training and propose the Repaired Initialization (ReI) algorithm for common modules with BatchNorm. Then, we utilize the same idea to repair the weight of unstructured pruned model, and name it Repaired Pruning at Initialization Resilience (RePaIR) algorithm. Extensive experiments and demonstrate that our proposed ReI and RePaIR can improve the training robustness of unpruned and pruned models, respectively, and achieve up to 1.7% accuracy gain with the same sparse pruning mask on TinyImageNet. Furthermore, we provide an improved SynFlow algorithm called Repair SynFlow (ReSynFlow), which employs Lipschitz scaling to overcome the problem of score computation in deeper models. ReSynFlow can effectively improve the maximum compression rate and is suitable for deeper models, with an accuracy improvement of up to 1.3% compared to the SynFlow algorithm on TinyImageNet.

In the current era of multi-modal and large models gradually revealing their potential, neural network pruning has emerged as a crucial means of model compression. It is widely recognized that models tend to be over-parameterized, and pruning enables the removal of unimportant weights, leading to improved inference speed while preserving accuracy. From early methods such as gradient-based, and magnitude-based pruning to modern algorithms like iterative magnitude pruning, lottery ticket hypothesis, and pruning at initialization, researchers have strived to increase the compression ratio of model parameters while maintaining high accuracy. Currently, mainstream algorithms focus on the global pruning of neural networks using various scoring functions, followed by different pruning strategies to enhance the accuracy of sparse model. Recent studies have shown that random pruning with varying layer-wise sparsity ratio has achieved robust results for large models and out-of-distribution data. Based on this discovery, we propose a new score called FeatIO, which is based on module input and output feature map sizes. As a score function used in PaI, FeatIO surpasses the performance of other PaI score functions. Additionally, we propose a novel pruning strategy called Pruning with Layer-wise Sparsity Ratio (PLSR), which conbines the layer-wise sparsity ratios and magnitude-based score function, resulting in optimal evaluation performance. Almost all algorithms exhibit improved performance when using our novel pruning strategy. The combination of PLSR and FeatIO consistently outperforms other algorithms in testing, demonstrating the significant potential of our proposed approach. Our code will be available here.

Higher education at scale, such as in the California public post-secondary system, has promoted upward socioeconomic mobility by supporting student transfer from 2-year community colleges to 4-year degree granting universities. Among the barriers to transfer is earning enough credit at 2-year institutions that qualify for the transfer credit required by 4-year degree programs. Defining which course at one institution will count as credit for an equivalent course at another institution is called course articulation, and it is an intractable task when attempting to manually articulate every set of courses at every institution with one another. In this paper, we present a methodology towards making tractable this process of defining and maintaining articulations by leveraging the information contained within historic enrollment patterns and course catalog descriptions. We provide a proof-of-concept analysis using data from a 4-year and 2-year institution to predict articulation pairs between them, produced from machine translation models and validated by a set of 65 institutionally pre-established course-to-course articulations. Finally, we create a report of proposed articulations for consumption by the institutions and close with a discussion of limitations and the challenges to adoption.