Bohan Zhuang

BohanZ

·

https://bohanzhuang.github.io/

AI & ML interests

AI infra; Efficient AI; Multimodal agent

Recent Activity

authored a paper 17 days ago

Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation

authored a paper 17 days ago

MixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D Refinement

authored a paper 17 days ago

HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing

View all activity

Organizations

liked a model 4 months ago

lhmd/TriSplat

Image-to-3D • Updated May 31 • 15

liked 2 models 5 months ago

zwave/K-Forcing

Text Generation • Updated Jun 10 • 2

lxazjk/Emu3.5-Image-FlashAR

Text-to-Image • 38B • Updated May 12 • 15 • 3

liked a model 11 months ago

GYP666/BLADE

Updated Jan 26 • 6

liked a model over 1 year ago

lhmd/ZPressor

Image-to-3D • Updated Mar 15 • 3

liked a model about 2 years ago

microsoft/Phi-3-mini-128k-instruct

Text Generation • 4B • Updated Dec 10, 2025 • 232k • 1.71k

liked 2 models over 2 years ago

mistralai/Mixtral-8x7B-v0.1

47B • Updated Jul 24, 2025 • 42k • 1.85k

meta-llama/Meta-Llama-3-8B

Text Generation • 8B • Updated Sep 27, 2024 • 136k • • 6.77k

liked 2 Spaces almost 3 years ago

Snnetv2 Semantic Segmentation

Snnetv2 Image Classification