Yuannuo Feng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuannuo Feng has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Guangyao Wang
School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China
2 shared publications - Wang Kang
Beihang University, Beijing, Beijing, CHINA
2 shared publications Guilin Zhao
School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China
1 shared publication- Hanjie Liu
School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China
1 shared publication Jenny Ma
Zhicun Research Lab, Beijing, China
1 shared publication- Jing Kou
Beihang University, Beijing, Beijing, CHINA
1 shared publication
Latest Publications
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. PP (02780070) , 1
NoiseGuard: A Comprehensive Framework with Noise Modeling, Noise-Aware Training and Noise Compensation for In-Memory Computing SoC
Despite the tremendous potential of in-memory computing (IMC) for AI applications, analog IMC still faces critical challenges related to noise sensitivity and computational accuracy, largely due to intrinsic non-idealities. These limitations significantly restrict the scalability and real-world deployability of analog IMC systems. To address accuracy degradation caused by hardware noise, we propose a comprehensive framework integrating noise modeling, noise-aware training (NAT), and hardware-adaptive compensation (HAC). Specifically, a noise model is derived from empirical measurements of a 40nm eFlash-based IMC SoC to capture diverse noise sources. The NAT scheme embeds the noise model into the training pipeline to enhance algorithm robustness, while the noise model guides HAC to mitigate the effects of device- and circuit-level variations during inference. Experimental results demonstrate that the noise model achieves a cosine similarity above 0.99 with actual chip behavior. In a speech denoising task, NAT improves the perceptual evaluation of speech quality (PESQ) by 0.168 (6.82%), while HAC reduces the output error variance by an average of 74.68%. Applied to multiple tasks including speech wake-up, speech denoising and image super-resolution, our framework achieves improvements of 13.5% in wake-up accuracy, 0.7 (29.2%) in PESQ, and 2.82 dB (7.2%) in peak signal-to-noise ratio (PSNR), respectively. These results demonstrate the generality and effectiveness of the proposed framework across a range of AI tasks.
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. PP (02780070) , 1
NoiseGuard: A Comprehensive Framework with Noise Modeling, Noise-Aware Training and Noise Compensation for In-Memory Computing SoC
Despite the tremendous potential of in-memory computing (IMC) for AI applications, analog IMC still faces critical challenges related to noise sensitivity and computational accuracy, largely due to intrinsic non-idealities. These limitations significantly restrict the scalability and real-world deployability of analog IMC systems. To address accuracy degradation caused by hardware noise, we propose a comprehensive framework integrating noise modeling, noise-aware training (NAT), and hardware-adaptive compensation (HAC). Specifically, a noise model is derived from empirical measurements of a 40nm eFlash-based IMC SoC to capture diverse noise sources. The NAT scheme embeds the noise model into the training pipeline to enhance algorithm robustness, while the noise model guides HAC to mitigate the effects of device- and circuit-level variations during inference. Experimental results demonstrate that the noise model achieves a cosine similarity above 0.99 with actual chip behavior. In a speech denoising task, NAT improves the perceptual evaluation of speech quality (PESQ) by 0.168 (6.82%), while HAC reduces the output error variance by an average of 74.68%. Applied to multiple tasks including speech wake-up, speech denoising and image super-resolution, our framework achieves improvements of 13.5% in wake-up accuracy, 0.7 (29.2%) in PESQ, and 2.82 dB (7.2%) in peak signal-to-noise ratio (PSNR), respectively. These results demonstrate the generality and effectiveness of the proposed framework across a range of AI tasks.