9 citations · 14 across the 7 of their papers we have counts for
7 papers
Solving Boltzmann equation with neural sparse representation
Zhengyi Li, Yanli Wang, Hongsheng Liu +2
We consider the neural sparse representation to solve Boltzmann equation with BGK and quadratic collision model, where a network-based ansatz that can approximate the distribution…
Efficient Adaptive Activation Rounding for Post-Training Quantization
Zhengyi Li, Cong Guo, Zhanda Zhu +5
Post-training quantization attracts increasing attention due to its convenience in deploying quantized neural networks. Although rounding-to-nearest remains the prevailing method f…
Transkimmer: Transformer Learns to Layer-wise Skim
Yue Guan, Zhengyi Li, Jingwen Leng +2
Transformer architecture has become the de-facto model for many machine learning tasks from natural language processing and computer vision. As such, improving its computational ef…
A brute-force search for R-symmetric Wess-Zumino models
James Brister, Shihao Kou, Zhengyi Li +2
This work makes an exhaustive search for generic renormalizable R-symmetric Wess-Zumino models with up to 5 chiral fields, and checks the consistency of their vacuum solutions with…
Block-Skim: Efficient Question Answering for Transformer
Yue Guan, Zhengyi Li, Jingwen Leng +3
Transformer models have achieved promising results on natural language processing (NLP) tasks including extractive question answering (QA). Common Transformer encoders used in NLP…
Learning invariance preserving moment closure model for Boltzmann-BGK equation
Zhengyi Li, Bin Dong, Yanli Wang
As one of the main governing equations in kinetic theory, the Boltzmann equation is widely utilized in aerospace, microscopic flow, etc. Its high-resolution simulation is crucial i…
The Nelson-Seiberg theorem generalized with nonpolynomial superpotentials
Zhengyi Li, Zheng Sun
The Nelson-Seiberg theorem relates R-symmetries to F-term supersymmetry breaking, and provides a guiding rule for new physics model building beyond the Standard Model. A revision o…