Qingyuan Li

Affiliations:
  • Meituan Inc.
  • Xiaomi AI Lab, Beijing, China


According to our database1, Qingyuan Li authored at least 12 papers between 2019 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

2019
2020
2021
2022
2023
2024
0
1
2
3
4
2
2
1
2
1
1
2
1

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference.
CoRR, 2024

Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs.
CoRR, 2024

Norm Tweaking: High-Performance Low-Bit Quantization of Large Language Models.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
A Speed Odyssey for Deployable Quantization of LLMs.
CoRR, 2023

FPTQ: Fine-grained Post-Training Quantization for Large Language Models.
CoRR, 2023

2022
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications.
CoRR, 2022

EAPruning: Evolutionary Pruning for Vision Transformers and CNNs.
Proceedings of the 33rd British Machine Vision Conference 2022, 2022

2021
SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search.
Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2021

AutoKWS: Keyword Spotting with Differentiable Architecture Search.
Proceedings of the IEEE International Conference on Acoustics, 2021

2020
Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search.
Proceedings of the 25th International Conference on Pattern Recognition, 2020

2019
ScarletNAS: Bridging the Gap Between Scalability and Fairness in Neural Architecture Search.
CoRR, 2019

Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search.
CoRR, 2019


  Loading...