I am a third-year Ph.D. candidate in the Electrical Engineering Department at Yale University. I am a member of Intelligent Computing Lab, advised by Prof. Priya Panda. My research interests include efficient deep learning models and systems and biology-inspired artificial intelligence. I have focused on neural network quantization for efficient inference, neuromorphic AI with spiking neural networks, and bio-plausible optimization methods. My research is applied to the lastest topics like Diffusion Models and Large Language Models.

Prior to Yale, I graduated from UESTC in 2020. I did research assistant/internship at the National University of Singapore, SenseTime, and Amazon. I received the 2023 Baidu PhD Fellowship.

News

2024

• Apr: I had a talk in CoCoSyS.
• Mar: I passed my area exam and advanced to candidacy.
• Feb: A paper about ANN-SNN conversion has been accepted by IJCV.
• Jan: I received the 2023 Baidu PhD Fellowship (10 winners/year).

2023

• Sep: A paper about SNN with dynamic timesteps is accepted to NeurIPS 2023 and a paper about Post-Training Quantization in LLM is accepted to EMNLP 2023.
• Aug: I will serve as the Area Chair for EMNLP 2023.
• May: A paper about SNN with surrogate module learning is accepted to ICML 2024.

Selected Publications

Error-Aware Conversion from ANN to SNN via Post-training Parameter Calibration
Authors: Yuhang Li, Shikuang Deng, Xin Dong, Shi Gu International Journal of Computer Vision (2024): 1-24.
Paper Link

Outlier Suppression+: Accurate Quantization of Large Language Models by Equivalent and Optimal Shifting and Scaling
Authors: Xiuying Wei, Yunchen Zhang, Yuhang Li, Xiangguo Zhang, Ruihao Gong, Jinyang Guo, Xianglong Liu Conference on Empirical Methods in Natural Language Processing (2023).
Paper Link

SEENN: Towards Temporal Spiking Early-Exit Neural Networks
Authors: Yuhang Li, Tamar Geller, Youngeun Kim, Priyadarshini Panda Conference on Neural Information Processing System (2023).
Paper Link

Neuromorphic Data Augmentation for Training Spiking Neural Networks
Authors: Yuhang Li, Youngeun Kim, Hyoungseob Park, Tamar Geller, Priyadarshini Panda European Conference on Computer Vision (2022). Paper Link

Differentiable spike: Rethinking gradient-descent for training spiking neural networks
Authors: Yuhang Li, Yufei Guo, Shanghang Zhang, Shikuang Deng, Yongqing Hai, Shi Gu Conference on Neural Information Processing System (2021).
Paper Link

A free lunch from ANN: Towards efficient, accurate spiking neural networks calibration
Authors: Yuhang Li, Shikuang Deng, Xin Dong, Ruihao Gong, Shi Gu International Conference on Machine Learning (2021).
Paper Link

Brecq: Pushing the limit of post-training quantization by block reconstruction
Authors: Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, Shi Gu International Conference on Learning Representations (2021).
Paper Link

Additive powers-of-two quantization: An efficient non-uniform discretization for neural networks
Authors: Yuhang Li, Xin Dong, Wei Wang International Conference on Learning Representations (2020).
Paper Link