Zhengyan Zhang's picture

1 14

Zhengyan Zhang

ZhengyanZhang

·

AI & ML interests

None yet

Recent Activity

authored a paper 6 days ago

mHC: Manifold-Constrained Hyper-Connections

authored a paper 11 months ago

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

upvoted a paper about 1 year ago

Densing Law of LLMs

View all activity

Organizations

authored a paper 6 days ago

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published 8 days ago • 225

authored a paper 11 months ago

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Paper • 2502.11089 • Published Feb 16, 2025 • 166

authored 2 papers over 1 year ago

Configurable Foundation Models: Building LLMs from a Modular Perspective

Paper • 2409.02877 • Published Sep 4, 2024 • 31

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters

Paper • 2406.05955 • Published Jun 10, 2024 • 27