Large-scale language models like ChatGPT and GPT-4 have gained attention for their impressive conversational and generative capabilities. However, the creation of supervised paired question-answering data for instruction tuning presents formidable challenges. This endeavor necessitates substantial human effort for data annotation and wrestles with issues concerning data quality, diversity, accuracy, and other related factors. To overcome these obstacles, we introduce an innovative framework named Self-QA, which replaces the traditional practice of human-written instruction seeds with a vast amount of unsupervised knowledge, enabling the model to generate a larger quantity of correct and domain-specific instruction data. The effectiveness of our proposed method is demonstrated through experiments conducted on unsupervised corpora from various domains.

In recent years, pre-trained language models have undergone rapid development with the emergence of large-scale models. However, there is a lack of open-sourced chat models specifically designed for the Chinese language, especially in the field of Chinese finance, at the scale of hundreds of billions. To address this gap, we introduce XuanYuan 2.0, the largest Chinese chat model to date, built upon the BLOOM-176B architecture. Additionally, we propose a novel training method called hybrid-tuning to mitigate catastrophic forgetting. By combining general-domain with domain-specific knowledge and integrating the stages of pre-training and fine-tuning, XuanYuan 2.0 is capable of providing accurate and contextually appropriate responses in the Chinese financial domain.

The study of electromagnetic detection satellite scheduling problem (EDSSP) has attracted attention due to the detection requirements for a large number of targets. This paper proposes a mixed-integer programming model for the EDSSP problem and a genetic algorithm based on reinforcement learning (RL-GA). Numerous factors that affect electromagnetic detection are considered in the model, such as detection mode, bandwidth, and other factors. The RL-GA embeds a Q-learning method into an improved genetic algorithm, and the evolution of each individual depends on the decision of the agent. Q-learning is used to guide the population search process by choosing evolution operators. In this way, the search information can be effectively used by the reinforcement learning method. In the algorithm, we design a reward function to update the Q value. According to the problem characteristics, a new combination of is proposed. The RL-GA also uses an elite individual retention strategy to improve search performance. After that, a task time window selection algorithm (TTWSA) is proposed to evaluate the performance of population evolution. Several experiments are used to examine the scheduling effect of the proposed algorithm. Through the experimental verification of multiple instances, it can be seen that the RL-GA can solve the EDSSP problem effectively. Compared with the state-of-the-art algorithms, the RL-GA performs better in several aspects.

Metaverse is expected to create a virtual world closely connected with reality to provide users with immersive experience with the support of 5G high data rate communication technique. A huge amount of data in physical world needs to be synchronized to the virtual world to provide immersive experience for users, and there will be higher requirements on coverage to include more users into Metaverse. However, 5G signal suffers severe attenuation, which makes it more expensive to maintain the same coverage. Unmanned aerial vehicle (UAV) is a promising candidate technique for future implementation of Metaverse as a low-cost and high-mobility platform for communication devices. In this paper, we propose a proximal policy optimization (PPO) based double-agent cooperative reinforcement learning method for channel allocation and trajectory control of UAV to collect and synchronize data from the physical world to the virtual world, and expand the coverage of Metaverse services economically. Simulation results show that our proposed method is able to achieve better performance compared to the benchmark approaches.

To enable the pre-trained models to be fine-tuned with local data on edge devices without sharing data with the cloud, we design an efficient split fine-tuning (SFT) framework for edge and cloud collaborative learning. We propose three novel techniques in this framework. First, we propose a matrix decomposition-based method to compress the intermediate output of a neural network to reduce the communication volume between the edge device and the cloud server. Second, we eliminate particular links in the model without affecting the convergence performance in fine-tuning. Third, we implement our system atop PyTorch to allow users to easily extend their existing training scripts to enjoy the efficient edge and cloud collaborative learning. Experiments results on 9 NLP datasets show that our framework can reduce the communication traffic by 96 times with little impact on the model accuracy.

Modern cloud computing systems contain hundreds to thousands of computing and storage servers. Such a scale, combined with ever-growing system complexity, is causing a key challenge to failure and resource management for dependable cloud computing. Autonomic failure detection is a crucial technique for understanding emergent, cloud-wide phenomena and self-managing cloud resources for system-level dependability assurance. To detect failures, we need to monitor the cloud execution and collect runtime performance data. These data are usually unlabeled, and thus a prior failure history is not always available in production clouds. In this paper, we present a \emph{self-evolving anomaly detection} (SEAD) framework for cloud dependability assurance. Our framework self-evolves by recursively exploring newly verified anomaly records and continuously updating the anomaly detector online. As a distinct advantage of our framework, cloud system administrators only need to check a small number of detected anomalies, and their decisions are leveraged to update the detector. Thus, the detector evolves following the upgrade of system hardware, update of the software stack, and change of user workloads. Moreover, we design two types of detectors, one for general anomaly detection and the other for type-specific anomaly detection. With the help of self-evolving techniques, our detectors can achieve 88.94\% in sensitivity and 94.60\% in specificity on average, which makes them suitable for real-world deployment.

To improve the execution speed and efficiency of neural networks in embedded systems, it is crucial to decrease the model size and computational complexity. In addition to conventional compression techniques, e.g., weight pruning and quantization, removing unimportant activations can reduce the amount of data communication and the computation cost. Unlike weight parameters, the pattern of activations is directly related to input data and thereby changes dynamically. To regulate the dynamic activation sparsity (DAS), in this work, we propose a generic low-cost approach based on winners-take-all (WTA) dropout technique. The network enhanced by the proposed WTA dropout, namely \textit{DASNet}, features structured activation sparsity with an improved sparsity level. Compared to the static feature map pruning methods, DASNets provide better computation cost reduction. The WTA technique can be easily applied in deep neural networks without incurring additional training variables. More importantly, DASNet can be seamlessly integrated with other compression techniques, such as weight pruning and quantization, without compromising on accuracy. Our experiments on various networks and datasets present significant run-time speedups with negligible accuracy loss.

With rapidly scaling up of deep neural networks (DNNs), extensive research studies on network model compression such as weight pruning have been performed for improving deployment efficiency. This work aims to advance the compression beyond the weights to neuron activations. We propose an end-to-end Joint Pruning (JP) technique which integrates the activation pruning with the weight pruning. By distinguishing and taking on the different significance of neuron responses and connections during learning, the generated network, namely JPnet, optimizes the sparsity of activations and weights for improving execution efficiency. To our best knowledge, JP is the first technique that simultaneously explores the redundancy in both weights and activations. The derived deep sparsification in the JPnet reveals more optimizing potentialities for the existing DNN accelerators dedicated for sparse matrix operations. The effectiveness of JP technique is thoroughly evaluated through various network models with different activation functions and on different datasets. With $<0.4\%$ degradation on testing accuracy, a JPnet can save $71.1\% \sim 96.35\%$ of computation cost, compared to the original dense models with up to $5.8\times$ and $10\times$ reductions in activation and weight numbers, respectively. Compared to state-of-the-art weight pruning technique, JPnet can further reduce the computation cost $1.2\times \sim 2.7\times$.