A5102424493- Human Motion and Animation
- Magnesium Oxide Properties and Applications
- Advanced Memory and Neural Computing
- Bone Tissue Engineering Materials
- CCD and CMOS Imaging Sensors
- Innovative concrete reinforcement materials
- Speech Recognition and Synthesis
- Concrete and Cement Materials Research
- Music and Audio Processing
- Hand Gesture Recognition Systems
- Recycled Aggregate Concrete Performance
- Computer Graphics and Visualization Techniques
- Fuel Cells and Related Materials
- Materials Engineering and Processing
- Advanced Neural Network Applications
- Hybrid Renewable Energy Systems
- Quantum-Dot Cellular Automata
- Structural Load-Bearing Analysis
- Video Analysis and Summarization
- Image Processing and 3D Reconstruction
- Simulation and Modeling Applications
- Human Pose and Action Recognition
- Speech and Audio Processing
- Structural Behavior of Reinforced Concrete
- Advanced battery technologies research
Tsinghua University
2024-2025
University Town of Shenzhen
2024
Collaborative Innovation Center of Chemistry for Energy Materials
2024
Tan Kah Kee Innovation Laboratory
2024
Key Laboratory of Guangdong Province
2023-2024
Ministry of Education of the People's Republic of China
2023-2024
Guangzhou University
2021-2024
Xiamen University
2024
Proton exchange membrane water electrolysis (PEMWE) is a promising solution for the conversion and storage of fluctuating renewable energy sources. Although tremendously efficient materials have been developed, commercial PEMWE products still cannot fulfill industrial demands regarding efficiency stability. In this work, we demonstrate that stress distribution, purely mechanical parameter in electrolyzer assembly, plays critical role overall The conventional cell structure, which usually...
Abstract Attention‐based transformer model has achieved remarkable performance in various artificial intelligence fields, while the attention computation, being a combination of matrix multiplication and softmax function, is still sub‐optimized terms hardware implementation. Normally, it needs 3 pass input memory access to compute attention, on‐chip storage requirement coupled with length, both which pose significant issues. Further, computation burden heavy for long inputs. This paper...
The incorporation of coconut fiber (CF) into magnesium phosphate cement (MPC) can effectively improve upon its high brittleness and ease cracking. In practical engineering, fiber-reinforced (CF-MPC) will likely work in cold environments. Therefore, it is essential to understand the effects various types low-temperature curing on CF-MPC performances, but there are very few studies this area. study, static compression three-point bending test were utilized examine compressive flexural...
The present study experimentally and analytically investigated the push-out behaviour of H-shaped steel section embedded in ultrahigh-performance fibre-reinforced concrete (UHPFRC). effect significant parameters such as types, fibre content, length, transverse reinforcement ratio cover on bond stress, development stress along length failure mechanism has been reported. test results show that slip steel-UHPFRC is different from steel-normal steel-high strength concrete. bond-slip curves...
Magnesium phosphate cement (MPC), a new type of inorganic cementitious material, is favored in engineering and construction because its fast setting speed high bonding strength, but limited practical application due to production cost excessive release hydration heat. Relevant research has investigated the discarded oyster shell powder (OSP) replacing mortar reported certain improvements performance. Consequently, focusing on discovering more effects OSP MPC performance, this study, by using...
We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. first utilize large language models (LLMs) to generate the initial layout and introduce a layout-guided Gaussian representation content generation adaptive geometric constraints. then propose an object-scene optimization mechanism conditioned diffusion collaboratively realistic scenes consistent geometry, texture, scale, accurate interactions among multiple objects while...
Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects human-machine interaction. While previous works mostly generate structural human skeletons, resulting omission appearance information, we focus on direct generation audio-driven co-speech gesture videos this work. There are two main challenges: 1) A suitable motion feature is needed to describe complex movements with crucial information. 2) Gestures and speech exhibit inherent dependencies...
Attention-based Transformer model has achieved remarkable performance in various artificial intelligence fields, while the attention computation, being a combination of matrix multiplication and softmax function, is still sub-optimized terms hardware implementation. Normally, it needs 3 pass input memory access to compute attention, on-chip storage requirement coupled with length, both which pose significant issues. Further, computation burden heavy for long inputs. This paper proposes an...