Yaoliang Bian (卞耀亮)

Exchanging Research Student 25'Fall @ NUS-ECE, supervised by Prof. Xingyu Liu.

B.Eng. (currently studying) in Electronic Science and Technology (Excellent Class)

Star of Inspiration (励学之星, top 0.1%),

Sep. 2022 - Jun. 2026 (expected)

Sep. 2019 - Jun. 2022

Undergraduate Research Program at USTC

Supervisor: Prof. Wei Gong

Existing backscatter technologies have limited compatibility with commercial wireless systems(such as WiFi and Bluetooth), particularly when dealing with multi-frequency carriers, where issues such as low utilization, uncertain latency, and connectivity limitations arise. DanBlue addressed these issues by introducing edge agents and a broadband channel hopping mechanism. However, currently, DanBlue only supports a single carrier source. We are trying to explore how to multiplex multiple carrier sources, especially when these carriers have different hopping sequences. Moreover, the distance from the carrier to the tag is related to the tag's sensitivity. We would like to increase the downlink distance by improving the tag's sensitivity or using low-noise amplifiers. To enable the tag to utilize ambient BLE signals, DanBlue introduces additional edge devices and a wide clock, which increases costs. We are working on reducing it by integrating it into existing devices. Last but not least, the current system design is primarily intended for backscatter beacons. In the future, application protocols based on wide data channels, such as BLE pairing, need to be developed to further enhance the system's functionality and security.

Supervisor: Prof. Ameer Abdelhadi

07/2024 ~ 09/2024, McMaster University (onsite)

Defense: 10/23/2024

This survey explores the development of domain-specific architectures for reinforcement learning (RL), highlighting advancements and challenges in implementing RL on specialized hardware. As RL algorithms grow more complex and computationally intensive, custom hardware solutions offer promising pathways to enhance performance, energy efficiency, and scalability. We review different architectures designed to accelerate RL algorithms as well as key contributions for various fields such as IoT applications, hardware prefetching and processors. Previous work primarily focused on either FPGA or GPU implementations, lacking extensive performance comparisons across various RL algorithms and configurations especially the modern ones. They also lack detailed discussions on integrating advanced neural network layers like CNNs and RNNs in FPGA designs. Our survey addresses these gaps by providing a comprehensive comparison of FPGA and GPU implementations, emphasizing fine-grained parallelism, on-chip memory usage, and integration with software-based environments. Furthermore, we explore near-memory computing and state-of-the-art DRL algorithms on custom hardware. We conclude with future research directions, including integrating advanced neural network layers in FPGA designs and exploring near-memory computing to further enhance RL capabilities on custom hardware.

Supervisor: Prof. Huichun Ye

05/2023 ~ 10/2023, USTC

Final: 10/22/2023

I built a robot with my teammates in USTC’s 2023 Robogame. I was responsible for the operation and maintenance of the core power supply module and the air pump system, as well as assisting with parameter tuning. Our Robot can independently identify, grab ores of different colors and transport them to the designated area in time.

Supervisor: Prof. Huichun Ye

11/2022 ~ 07/2023, USTC

Final: 07/21/2023

I participated in the power relay group of Anhui division with my passionate teammates, Weixing Chen, Xinyuan Zhang, Boxuan Niu. I was responsible for the PCB design of the core boards for the rescue vehicle and the rescued vehicle of the electrical energy relay team. Weixing Chen and I also provided help to the Duck Yummy team of Shanghai Jiao Tong University in the intelligent vision group of East China Division.

Team Introduction / Car Photo1 / Car Photo2 / Competition Site

Supervisor: Prof. Peng Li

09/2022 ~ 06/2023, USTC

Defense: 06/08/2023

This experiment aims to understand the physical properties and structural characteristics of Skyrmion through learning, and to study the influence of different magnetocrystalline anisotropy constants (PMA) on the magnitude of Skyrmion generated by current, as well as the influence of two-dimensional PMA gradient fields on the driving effect of Skyrmion, using an object-oriented micromagnetic simulation framework software. Finally, the conclusions of the integration leakage ignition model were obtained through program simulation, image analysis, and other methods. At the same time, the simulation process was summarized, reflected on, and improved.

Summary Essay / Demo: Effect of changing geometry (wedge gradient) on Skyrmion motion

standing out among all 39 competition group teams in USTC Robogame 2023

With Jiazhuo Liu, Zhenglang Weng, Yaxin Gong and Taowei Liu. Supervised by Prof. Huichun Ye.

Team: Miner Craft

worked in Prof. Ameer Abdelhadi's group on Hardware for Reinforcement Learning

- honor for undergraduate and graduate students at University of Science and Technology of China
- only 34 among about 25000 undergraduate and graduate students in the school (top 0.1%)
- the only 2 freshman to win the award in 2022

- awarded by USTC Office of International Cooperation

Learned Java and Python.

Participated in the camp held by[Cyrus Tang Foundation] and learned how to lead a team for public welfare.

Designer and developer of AI Exam Review Assitant based on Gemini AI open source model

Outcome: won the Highest Honor of the “Nanke Star” Award in Nanckathon[Report] and 1st prize in WaytoAGI Nanjing event[Report].