Hongyu Wang

Orcid: 0000-0003-1811-3903

Affiliations:

Institute of Computing Technology, Chinese Academy of Sciences, China

According to our database¹, Hongyu Wang authored at least 11 papers between 2022 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

Scaling Large Language Models with Fully Sparse Activations.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2026

2025

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs.

[BibT_eX]

[DOI]

Hongyu Wang

Shuming Ma

Furu Wei

CoRR, April, 2025

BitNet: 1-bit Pre-training for Large Language Models.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2025

2024

DeepNet: Scaling Transformers to 1,000 Layers.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., October, 2024

Q-Sparse: All Large Language Models can be Fully Sparsely-Activated.

[BibT_eX]

[DOI]

CoRR, 2024

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.

[BibT_eX]

[DOI]

CoRR, 2024

2023

BitNet: Scaling 1-bit Transformers for Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

Magneto: A Foundation Transformer.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

2022

TorchScale: Transformers at Scale.

[BibT_eX]

[DOI]

CoRR, 2022

Foundation Transformers.

[BibT_eX]

[DOI]

CoRR, 2022

DeepNet: Scaling Transformers to 1, 000 Layers.

[BibT_eX]

[DOI]

CoRR, 2022

Hongyu Wang

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...