Shaohua Wu

Peiru Zheng, Yun Zhao, Zhan Gong et al.

Many fields could benefit from the rapid development of the large language models (LLMs). The end-to-end autonomous driving (e2eAD) is one of the typically fields facing new opportunities as the LLMs have supported more and more modalities. Here, by utilizing vision-language model (VLM), we proposed an e2eAD method called SimpleLLM4AD. In our method, the e2eAD task are divided into four stages, which are perception, prediction, planning, and behavior. Each stage consists of several visual question answering (VQA) pairs and VQA pairs interconnect with each other constructing a graph called Graph VQA (GVQA). By reasoning each VQA pair in the GVQA through VLM stage by stage, our method could achieve e2e driving with language. In our method, vision transformers (ViT) models are employed to process nuScenes visual data, while VLM are utilized to interpret and reason about the information extracted from the visual inputs. In the perception stage, the system identifies and classifies objects from the driving environment. The prediction stage involves forecasting the potential movements of these objects. The planning stage utilizes the gathered information to develop a driving strategy, ensuring the safety and efficiency of the autonomous vehicle. Finally, the behavior stage translates the planned actions into executable commands for the vehicle. Our experiments demonstrate that SimpleLLM4AD achieves competitive performance in complex driving scenarios.

Shaohua Wu, Xudong Zhao, Shenling Wang et al.

In this work, we develop and release Yuan 2.0, a series of large language models with parameters ranging from 2.1 billion to 102.6 billion. The Localized Filtering-based Attention (LFA) is introduced to incorporate prior knowledge of local dependencies of natural language into Attention. A data filtering and generating system is presented to build pre-training and fine-tuning dataset in high quality. A distributed training method with non-uniform pipeline parallel, data parallel, and optimizer parallel is proposed, which greatly reduces the bandwidth requirements of intra-node communication, and achieves good performance in large-scale distributed training. Yuan 2.0 models display impressive ability in code generation, math problem-solving, and chatting compared with existing models. The latest version of YUAN 2.0, including model weights and source code, is accessible at Github.

Shaohua Wu, Tong Yu, Shenling Wang et al.

Diffusion models have shown remarkable capacity in image synthesis based on their U-shaped architecture and convolutional neural networks (CNN) as basic blocks. The locality of the convolution operation in CNN may limit the model's ability to understand long-range semantic information. To address this issue, we propose Yuan-TecSwin, a text-conditioned diffusion model with Swin-transformer in this work. The Swin-transformer blocks take the place of CNN blocks in the encoder and decoder, to improve the non-local modeling ability in feature extraction and image restoration. The text-image alignment is improved with a well-chosen text encoder, effective utilization of text embedding, and careful design in the incorporation of text condition. Using an adapted time step to search in different diffusion stages, inference performance is further improved by 10%. Yuan-TecSwin achieves the state-of-the-art FID score of 1.37 on ImageNet generation benchmark, without any additional models at different denoising stages. In a side-by-side comparison, we find it difficult for human interviewees to tell the model-generated images from the human-painted ones.

Yun Zhao, Zhan Gong, Peiru Zheng et al.

More and more research works fuse the LiDAR and camera information to improve the 3D object detection of the autonomous driving system. Recently, a simple yet effective fusion framework has achieved an excellent detection performance, fusing the LiDAR and camera features in a unified bird's-eye-view (BEV) space. In this paper, we propose a LiDAR-camera fusion framework, named SimpleBEV, for accurate 3D object detection, which follows the BEV-based fusion framework and improves the camera and LiDAR encoders, respectively. Specifically, we perform the camera-based depth estimation using a cascade network and rectify the depth results with the depth information derived from the LiDAR points. Meanwhile, an auxiliary branch that implements the 3D object detection using only the camera-BEV features is introduced to exploit the camera information during the training phase. Besides, we improve the LiDAR feature extractor by fusing the multi-scaled sparse convolutional features. Experimental results demonstrate the effectiveness of our proposed method. Our method achieves 77.6\% NDS accuracy on the nuScenes dataset, showcasing superior performance in the 3D object detection track.

Zuguang Li, Wen Wu, Shaohua Wu et al.

Split learning (SL) is a promising approach for training artificial intelligence (AI) models, in which devices collaborate with a server to train an AI model in a distributed manner, based on a same fixed split point. However, due to the device heterogeneity and variation of channel conditions, this way is not optimal in training delay and energy consumption. In this paper, we design an adaptive split learning (ASL) scheme which can dynamically select split points for devices and allocate computing resource for the server in wireless edge networks. We formulate an optimization problem to minimize the average training latency subject to long-term energy consumption constraint. The difficulties in solving this problem are the lack of future information and mixed integer programming (MIP). To solve it, we propose an online algorithm leveraging the Lyapunov theory, named OPEN, which decomposes it into a new MIP problem only with the current information. Then, a two-layer optimization method is proposed to solve the MIP problem. Extensive simulation results demonstrate that the ASL scheme can reduce the average training delay and energy consumption by 53.7% and 22.1%, respectively, as compared to the existing SL schemes.

Zuguang Li, Shaohua Wu, Liang Li et al.

In this letter, we propose an energy-efficient split learning (SL) framework for fine-tuning large language models (LLMs) using geo-distributed personal data at the network edge, where LLMs are split and alternately across massive mobile devices and an edge server. Considering the device heterogeneity and channel dynamics in edge networks, a \underline{C}ut l\underline{A}yer and computing \underline{R}esource \underline{D}ecision (CARD) algorithm is developed to minimize training delay and energy consumption. Simulation results demonstrate that the proposed approach reduces the average training delay and server's energy consumption by 70.8% and 53.1%, compared to the benchmarks, respectively.

Yifei Qiu, Tianle Liao, Xin Jin et al.

A space-air-ground-sea integrated network (SAGSIN) has emerged as a cornerstone of 6G systems, establishing a unified global architecture by integrating multi-domain network resources. Motivated by the demand for real-time situational awareness and intelligent operational maintenance, digital twin (DT) technology was initially regarded as a promising solution, owing to its capability to create virtual replicas and emulate physical system behaviors. However, in the context of SAGSIN, the high-fidelity, full-scale modeling paradigm inherent to conventional DTs encounters fundamental limitations, including prohibitive computational overhead, delayed model synchronization, and cross-system semantic gaps. To address these limitations, this survey paper proposes a novel twinning framework: goal-oriented semantic twin (GOST). Unlike DTs that pursue physical mirroring, GOST prioritizes ``utility'' over ``fidelity,'' leveraging semantic technologies and goal-oriented principles to construct lightweight, task-specific representations. This paper systematically articulates the GOST framework through three layers: knowledge-based semantics, data-driven semantics, and goal-oriented principles. Furthermore, we provide a comprehensive tutorial on constructing GOST by detailing its core enabling technologies and introduce a multidimensional evaluation framework for GOST. We present a case study targeting collaborative tracking tasks in remote satellite-UAV networks, demonstrating that GOST significantly outperforms conventional DTs in timeliness of perceptual data and collaborative tracking. Finally, we outline research directions, establishing GOST as a transformative twinning paradigm to guide the development of SAGSIN.

Peiru Zheng, Yun Zhao, Zhan Gong et al.

End-to-end autonomous driving has emerged as a promising paradigm for achieving robust and intelligent driving policies. However, existing end-to-end methods still face significant challenges, such as suboptimal decision-making in complex scenarios. In this paper,we propose SimpleVSF (Simple VLM-Scoring Fusion), a novel framework that enhances end-to-end planning by leveraging the cognitive capabilities of Vision-Language Models (VLMs) and advanced trajectory fusion techniques. We utilize the conventional scorers and the novel VLM-enhanced scorers. And we leverage a robust weight fusioner for quantitative aggregation and a powerful VLM-based fusioner for qualitative, context-aware decision-making. As the leading approach in the ICCV 2025 NAVSIM v2 End-to-End Driving Challenge, our SimpleVSF framework demonstrates state-of-the-art performance, achieving a superior balance between safety, comfort, and efficiency.

Zuguang Li, Wen Wu, Shaohua Wu et al.

Split learning (SL) has emerged as a computationally efficient approach for artificial intelligence (AI) model training, which can alleviate device-side computational workloads. However, complex AI model architectures pose high computational complexity to obtain the optimal model splitting. In this paper, we represent an arbitrary AI model as a directed acyclic graph (DAG), and then reformulate the optimal model splitting problem as a minimum s-t cut search problem. To solve the problem, we propose a fast DAG-based model splitting algorithm, which restructures the DAG to enable the optimal model splitting identification via a maximum flow method. Theoretical analysis indicates that the proposed algorithm is optimal. Furthermore, considering AI models with block structures, we propose a block-wise model splitting algorithm to reduce computational complexity. The algorithm abstracts each block, i.e., a component consisting of multiple layers, into a single vertex, thereby obtaining the optimal model splitting via a simplified DAG. Extensive experimental results demonstrate that the proposed algorithms can determine the optimal model splitting within milliseconds, as well as reduce training delay by 24.62%-38.95% in dynamic edge networks as compared to the state-of-the-art benchmarks.

Zuguang Li, Wen Wu, Shaohua Wu et al.

Large models (LMs) have immense potential in Internet of Things (IoT) systems, enabling applications such as intelligent voice assistants, predictive maintenance, and healthcare monitoring. However, training LMs on edge servers raises data privacy concerns, while deploying them directly on IoT devices is constrained by limited computational and memory resources. We analyze the key challenges of training LMs in IoT systems, including energy constraints, latency requirements, and device heterogeneity, and propose potential solutions such as dynamic resource management, adaptive model partitioning, and clustered collaborative training. Furthermore, we propose a split knowledge distillation framework to efficiently distill LMs into smaller, deployable versions for IoT devices while ensuring raw data remains local. This framework integrates knowledge distillation and split learning to minimize energy consumption and meet low model training delay requirements. A case study is presented to evaluate the feasibility and performance of the proposed framework.

Shaohua Wu, Xudong Zhao, Tong Yu et al.

Recent work like GPT-3 has demonstrated excellent performance of Zero-Shot and Few-Shot learning on many natural language processing (NLP) tasks by scaling up model size, dataset size and the amount of computation. However, training a model like GPT-3 requires huge amount of computational resources which makes it challengeable to researchers. In this work, we propose a method that incorporates large-scale distributed training performance into model architecture design. With this method, Yuan 1.0, the current largest singleton language model with 245B parameters, achieves excellent performance on thousands GPUs during training, and the state-of-the-art results on NLP tasks. A data processing method is designed to efficiently filter massive amount of raw data. The current largest high-quality Chinese corpus with 5TB high quality texts is built based on this method. In addition, a calibration and label expansion method is proposed to improve the Zero-Shot and Few-Shot performance, and steady improvement is observed on the accuracy of various tasks. Yuan 1.0 presents strong capacity of natural language generation, and the generated articles are difficult to distinguish from the human-written ones.