Yifang Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yifang Zhao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Weimin Fu
Mike Wiegers Department of Electrical and Computer Engineering, Kansas State University, Manhattan, KS, USA
3 shared publications - Xiaolong Guo
Kansas State University, Manhattan, KS, USA
3 shared publications - Yier Jin
University of Science and Technology of China
3 shared publications - Shijie Li
School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China
2 shared publications - Kaichen Yang
Michigan Technological University
1 shared publication - Xuan Zhang
Northeastern University, Boston, MA, USA
1 shared publication
Latest Publications
- Open Access
- 29 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 659-666
Intelligence In The Fence: Construct A Privacy and Reliable Hardware Design Assistant LLM
- 29 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 659-666
Open AccessIntelligence In The Fence: Construct A Privacy and Reliable Hardware Design Assistant LLM
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 5060-5062
Poster: Enhance Hardware Domain Specific Large Language Model with Reinforcement Learning for Resilience
To enhance the performance of large language models (LLMs) on hardware design tasks, we focus on training with reinforcement learning(RL) to improve LLMs' syntax synthesis and functional verification performance. We observed significant gains in power, performance, and area (PPA) metrics by applying RL. Specifically, DeepSeek Code saw a 23.6% performance increase, while the RTLCoder improved by 7.86%. Our findings demonstrate the effectiveness of RL in refining LLMs for more accurate hardware generation, considering power and area consumption. This approach offers a promising direction for generating hardware resilient to side-channel attacks in computer systems.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 5060-5062
Open AccessPoster: Enhance Hardware Domain Specific Large Language Model with Reinforcement Learning for Resilience
To enhance the performance of large language models (LLMs) on hardware design tasks, we focus on training with reinforcement learning(RL) to improve LLMs' syntax synthesis and functional verification performance. We observed significant gains in power, performance, and area (PPA) metrics by applying RL. Specifically, DeepSeek Code saw a 23.6% performance increase, while the RTLCoder improved by 7.86%. Our findings demonstrate the effectiveness of RL in refining LLMs for more accurate hardware generation, considering power and area consumption. This approach offers a promising direction for generating hardware resilient to side-channel attacks in computer systems.
- 26 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 72 (2) , 623-636
A Generalize Hardware Debugging Approach for Large Language Models Semi-Synthetic, Datasets
Large Language Models (LLMs) have precipitated emerging trends towards intelligent automation. However, integrating LLMs into the hardware debug domain encounters challenges: the datasets for LLMs for hardware are often plagued by a dual dilemma – scarcity and subpar quality. Traditional hardware debug approaches that rely on experienced labor to generate detailed prompts are not cheaply scalable. Similarly, strategies that depend on existing LLMs and randomly generated prompts fail to achieve sufficient reliability. We propose a directed, semi-synthetic data synthetic method that leverages version control information and journalistic event descriptions. To produce high-quality data, this approach utilizes version control data from hardware projects combined with the 5W1H (Who, What, When, Where, Why, How) journalistic principles. It facilitates the linear scaling of dataset volumes without depending on skilled labor. We have implemented this method on a collected dataset of open-source hardware designs and fine-tuned fifteen general-purpose LLMs to enable their capability in hardware debugging tasks, thereby validating the efficacy of our approach.
- 26 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 72 (2) , 623-636
A Generalize Hardware Debugging Approach for Large Language Models Semi-Synthetic, Datasets
Large Language Models (LLMs) have precipitated emerging trends towards intelligent automation. However, integrating LLMs into the hardware debug domain encounters challenges: the datasets for LLMs for hardware are often plagued by a dual dilemma – scarcity and subpar quality. Traditional hardware debug approaches that rely on experienced labor to generate detailed prompts are not cheaply scalable. Similarly, strategies that depend on existing LLMs and randomly generated prompts fail to achieve sufficient reliability. We propose a directed, semi-synthetic data synthetic method that leverages version control information and journalistic event descriptions. To produce high-quality data, this approach utilizes version control data from hardware projects combined with the 5W1H (Who, What, When, Where, Why, How) journalistic principles. It facilitates the linear scaling of dataset volumes without depending on skilled labor. We have implemented this method on a collected dataset of open-source hardware designs and fine-tuned fifteen general-purpose LLMs to enable their capability in hardware debugging tasks, thereby validating the efficacy of our approach.