Transformer-based large language models (LLMs) have demonstrated outstanding performance across diverse domains, particularly in the emerging pretrain-then-finetune paradigm. LoRA, a parameter-efficient fine-tuning method, is commonly used to adapt a base LLM to multiple downstream tasks. Further, LLM platforms enable developers to fine-tune multiple models and develop various domain-specific applications simultaneously. However, existing model parallelism schemes suffer from high communication overhead and inefficient GPU utilization. In this paper, we present mLoRA, a parallelism-efficient fine-tuning system designed for training multiple LoRA across GPUs and machines. mLoRA introduces a novel LoRA-aware pipeline parallelism scheme that efficiently pipelines LoRA adapters and their distinct fine-tuning stages across GPUs and machines, along with a new LoRA-efficient operator to enhance GPU utilization. Our extensive evaluation shows that mLoRA can significantly reduce average fine-tuning task completion time, e.g., by 30%, compared to state-of-the-art methods like FSDP. More importantly, mLoRA enables simultaneous fine-tuning of larger models, e.g., two Llama-2-13B models on four NVIDIA RTX A6000 48GB GPUs, which is not feasible for FSDP due to high memory requirements. Hence, mLoRA not only increases fine-tuning efficiency but also makes it more accessible on cost-effective GPUs.

In light of global aging and prevalent stroke-related hemiplegia, this study addresses challenges in robot-assisted Sit-to-Stand (STS) movements, a daily activity prone to falls. Supernumerary Robotic Legs (SRL) serve as independent support, enhancing stability and limb movement range. Existing coordination control methods lack personalization for STS assistance, requiring solutions for human intent transmission and rapidly optimize coordination control challenges in the non-coupled human-robot system. The proposed human-SRL coordination control algorithm, grounded in personalized SRL-human coupling models, incorporates surface electromyography (sEMG) signals to design an intent-driven variable stiffness impedance control. The inclusion of incremental learning enables rapid optimization of impedance parameters, facilitating real-time adjustments in SRL assistance for adaptive coupling with users. Practical experiments involving both healthy participants and hemiparetic patients validate the algorithm’s effectiveness during STS. The results validate substantial reductions in STS time (39.54%) and muscle activity (28.01%), highlighting the efficacy of the proposed algorithm-controlled SRL support for hemiparetic individuals.

Supernumerary robotic limbs (SRLs) offer substantial potential in both the rehabilitation of hemiplegic patients and the enhancement of functional capabilities for healthy individuals. Designing a general-purpose SRL device is inherently challenging, particularly when developing a unified theoretical framework that meets the diverse functional requirements of both upper and lower limbs. In this paper, we propose a multi-objective optimization (MOO) design theory that integrates grasping workspace similarity, walking workspace similarity, braced force for sit-to-stand (STS) movements, and overall mass and inertia. A geometric vector quantification method is developed using an ellipsoid to represent the workspace, aiming to reduce computational complexity and address quantification challenges. The ellipsoid envelope transforms workspace points into ellipsoid attributes, providing a parametric description of the workspace. Furthermore, the STS static braced force assesses the effectiveness of force transmission. The overall mass and inertia restricts excessive link length. To facilitate rapid and stable convergence of the model to high-dimensional irregular Pareto fronts, we introduce a multi-subpopulation correction firefly algorithm. This algorithm incorporates a strategy involving attractive and repulsive domains to effectively handle the MOO task. The optimized solution is utilized to redesign the prototype for experimentation to meet specified requirements. Six healthy participants and two hemiplegia patients participated in real experiments. Compared to the pre-optimization results, the average grasp success rate improved by 7.2%, while the muscle activity during walking and STS tasks decreased by an average of 12.7% and 25.1%, respectively. The proposed design theory offers an efficient option for the design of multi-functional SRL mechanisms.

Multivariate time series anomaly detection (MT-SAD) plays a crucial role for the Internet of Things (IoT) systems. Various IoT systems rely on time series to monitor and identify anomalies, as well as to initiate remediation procedures. Existing contrastive learning methods for MTSAD have strong ability to learn invariant representations from augmented views. However, these methods rely on special data augmentation strategies and may not be suitable for certain time series. Besides, when abnormal points intensively occur in a segment, the similarity representations they learned from augmented views would make normal and abnormal points indistinguishable. To address these issues, we propose a novel Anchor-guided contrastive learning method with a general data augmentation strategy for multivariate time series Anomaly Detection (AgileAD). Specifically, this general strategy is a simple yet efficient data augmentation strategy to shuffle each univariate time series (i.e., metric) vertically. It can fit any time series to create different but correlated views. To improve the model discrimination in the presence of anomaly aggregation, AgileAD utilizes an anchor-guided contrastive structure module to learn the anchor representations of the raw input and capture temporal and intermetric dependencies of time series. Moreover, the triplet representation discrepancy is designed to promote the learning of shuffle invariant representations. It cooperates with the guided module to effectively distinguish between normal and abnormal points. Extensive experiments show that AgileAD achieves state-of-the-art results on multiple IoT benchmark datasets.

Drug-target interaction (DTI) prediction is of great importance for drug discovery and development. With the rapid development of biological and chemical technologies, computational methods for DTI prediction are becoming a promising strategy. However, there are few methods which explore solving the cold-start problem in DTI prediction scenarios due to most of existing methods require modeling under the existing interaction that can’t effectively capture information from new drugs and new targets which have few interactions in existing literature. In this paper, we propose a graph transformer method based on meta-learning named MGDTI to fill the gap. In particular, we employ drug-drug similarity and target-target similarity as additional information for network to mitigate the scarcity of interactions. Besides, we trained our model via meta-learning to be adaptive to cold-start tasks. Moreover, we introduced graph transformer to prevent over-smoothing by capturing long-range dependencies. Comparison results on the benchmark dataset demonstrate that our proposed MGDTI is effective in the DTI prediction.

To solve the poor compliance and safety problems in current rehabilitation robots, a novel two-degrees-of-freedom (2-DOF) soft ankle rehabilitation robot driven by pneumatic muscles (PMs) is presented, taking advantages of the PM's inherent compliance and the parallel structure's high stiffness and payload capacity. However, the PM's nonlinear, time-varying and hysteresis characteristics, and the coupling interference from parallel structure, as well as the unpredicted disturbance caused by arbitrary human behavior all raise difficulties in achieving high-precision control of the robot. In this paper, a multi-input-multi-output disturbance compensated sliding mode controller (MIMO-DCSMC) is proposed to tackle these problems. The proposed control method can tackle the un-modeled uncertainties and the coupling interference existed in multiple PMs' synchronous movement, even with the subject's participation. Experiment results on a healthy subject confirmed that the PMs-actuated ankle rehabilitation robot controlled by the proposed MIMO-DCSMC is able to assist patients to perform high-accuracy rehabilitation tasks by tracking the desired trajectory in a compliant manner.

Increasing the on-time rate of bus service can prompt the people’s willingness to travel by bus, which is an effective measure to mitigate the city traffic congestion. Performing queries on the bus arrival can be used to identify and analyze various kinds of non-on-time events that happened during the bus journey, which is helpful for detecting the factors of delaying events, and providing decision support for optimizing the bus schedules. We propose a data management model, called Bus-OLAP, for querying bus journey data, considering the characteristics of bus running and the scenarios of non-on-time analysis. While fulfilling typical requirements of bus journey data queries, Bus-OLAP not only provides a flexible way to manage the data and to implement multiple granularity data query and update, but it also supports distributed queries and computation. The experiments on real-world bus journey data verify that Bus-OLAP is effective and efficient.