Zhekai Zhang

According to our database1, Zhekai Zhang authored at least 14 papers between 2018 and 2025.

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

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer.
CoRR, January, 2025

2024
Interactive learning for multi-finger dexterous hand: A model-free hierarchical deep reinforcement learning approach.
Knowl. Based Syst., 2024

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models.
CoRR, 2024

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers.
CoRR, 2024

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving.
CoRR, 2024

Grasp with push policy for multi-finger dexterity hand based on deep reinforcement learning.
Appl. Soft Comput., 2024

Lightening-Transformer: A Dynamically-Operated Optically-Interconnected Photonic Transformer Accelerator.
Proceedings of the IEEE International Symposium on High-Performance Computer Architecture, 2024

2023
DOTA: A Dynamically-Operated Photonic Tensor Core for Energy-Efficient Transformer Accelerator.
CoRR, 2023

2021
PointAcc: Efficient Point Cloud Accelerator.
Proceedings of the MICRO '21: 54th Annual IEEE/ACM International Symposium on Microarchitecture, 2021

SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning.
Proceedings of the IEEE International Symposium on High-Performance Computer Architecture, 2021


2020
Once-for-All: Train One Network and Specialize it for Efficient Deployment.
Proceedings of the 8th International Conference on Learning Representations, 2020

SpArch: Efficient Architecture for Sparse Matrix Multiplication.
Proceedings of the IEEE International Symposium on High Performance Computer Architecture, 2020

2018
Benchmark Visual Question Answer Models by using Focus Map.
CoRR, 2018


  Loading...