activity
20202023
most citedSpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

408 citations · 709 across the 22 of their papers we have counts for

collaborators
Showing 2023Show all

5 papers · 1 filter

cs.AI2023★ 3 cited

A Neural Network Based Choice Model for Assortment Optimization

Hanzhao Wang, Zhongze Cai, Xiaocheng Li +1

Discrete-choice models are used in economics, marketing and revenue management to predict customer purchase probabilities, say as a function of prices and other features of the off…

quant-ph2023

DISQ: Dynamic Iteration Skipping for Variational Quantum Algorithms

Junyao Zhang, Hanrui Wang, Gokul Subramanian Ravi +4

This paper proposes DISQ to craft a stable landscape for VQA training and tackle the noise drift challenge. DISQ adopts a "drift detector" with a reference circuit to identify and…

cs.LG2023

When No-Rejection Learning is Consistent for Regression with Rejection

Xiaocheng Li, Shang Liu, Chunlin Sun +1

Learning with rejection has been a prototypical model for studying the human-AI interaction on prediction tasks. Upon the arrival of a sample instance, the model first uses a rejec…

cs.ET2023★ 2 cited

Lightening-Transformer: A Dynamically-operated Optically-interconnected Photonic Transformer Accelerator

Hanqing Zhu, Jiaqi Gu, Hanrui Wang +7

The wide adoption and significant computing resource of attention-based transformers, e.g., Vision Transformers and large language models (LLM), have driven the demand for efficien…

quant-ph2023★ 1 cited

Towards Advantages of Parameterized Quantum Pulses

Zhiding Liang, Jinglei Cheng, Zhixin Song +7

The advantages of quantum pulses over quantum gates have attracted increasing attention from researchers. Quantum pulses offer benefits such as flexibility, high fidelity, scalabil…