Xiaosong Peng

Xiaosong Peng

Auto-generated profile, based on publicly available information

Xiaosong Peng

School of Computer Science and Technology Hainan University Hainan China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 April 2025 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
XPXiaosong Peng
Xiaosong Peng
Laurence YangLaurence Yang
Laurence Yang
JLJie Li
Jie Li
WJWenjun Jiang
Wenjun Jiang

18 August 2025 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
HLHaixv Lu
Haixv Lu
DLDebin Liu
Debin Liu
Laurence YangLaurence Yang
Laurence Yang
RZRuonan Zhao
Ruonan Zhao
SLShijie Lv
Shijie Lv
XPXiaosong Peng
Xiaosong Peng
In today’s competitive market, smarter and higher-performing consumer electronics are increasingly attractive to the public. These products not only need to perform basic functions but also offer personalized services to enhance user experience and drive sales growth. To solve this problem, this paper proposes a multimodal emotion recognition model based on Share Token Tensorized Attention Fusion (STF), which improves the intelligence of electronic products by providing in-depth understanding of the user’s emotional state.The STF method constrains the modal feature fusion by introducing the share token and combines with the tensorized attention for feature fusion, which significantly improves the accuracy of emotion recognition, improves the robustness of the model, and reduces the learning cost compared to the Transformer-based multimodal emotion recognition model. The STF-based multimodal emotion recognition model can ensure model performance and faster response speed in noisy environments, and it is easier to meet the consumers’ pursuit of consumer electronics experience.

26 November 2025 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
SLShijie Lv
Shijie Lv
DLDebin Liu
Debin Liu
Laurence YangLaurence Yang
Laurence Yang
XPXiaosong Peng
Xiaosong Peng
RZRuonan Zhao
Ruonan Zhao
Jun FengJun Feng
Jun Feng
Large language models in deep learning have numerous parameters, requiring significant storage space and computational resources. Compression techniques are highly effective in addressing these challenges. With the development of hardware like Graphics Processing Unit (GPU), Tensor Core can accelerate low-precision matrix multiplication but achieve acceleration for sparse matrices is challenging. Due to its sparsity, the utilization of Tensor Cores is relatively low. To address this, we propose the based on Tensor Core Compressed Sparse Row format (TC-CSR), which facilitates data loading on GPUs and matrix operations on Tensor Cores. Based on this format, we designed block Sparse Matrix-Matrix Multiplication (SpMM) and Sampled Dense-Dense Matrix Multiplication (SDDMM) kernels, which are common operations in deep learning. Utilizing these designs, we achieved a $\mathbf {1.41\times }$ speedup on Sputnik in scenarios of moderate sparsity and a $\mathbf {1.38\times }$ speedup with large-scale highly sparse matrices. Benefit from our design, we achieved a $\mathbf {1.75\times }$ speedup in end-to-end inference with sparse Transformers and save memory.


1 July 2026 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
XPXiaosong Peng
Xiaosong Peng
Laurence YangLaurence Yang
Laurence Yang
XWXiaokang Wang
Xiaokang Wang
SLShijie Lv
Shijie Lv

9 December 2025 in Concurrency and Computation: Practice and Experience
Verified
Journal Article
Closed access
TZTinghua Zhang
Tinghua Zhang
JLJunxin Li
Junxin Li
XPXiaosong Peng
Xiaosong Peng
ZZZhixuan Zhao
Zhixuan Zhao
FWFeng Wu
Feng Wu
XWXiaokang Wang
Xiaokang Wang