Zhuoyang Zhang

zhuoyang20's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 21 days ago

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

Paper • 2502.14866 • Published 22 days ago • 12

upvoted a paper 3 months ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 58

updated a model 4 months ago

mit-han-lab/efficientvit-sam

Mask Generation • Updated Jan 6 • 39

New activity in mit-han-lab/vila-u-7b-256 5 months ago

Add pipeline tag

1

#1 opened 5 months ago by

nielsr

liked 2 models 5 months ago

mit-han-lab/efficientvit-sam

Mask Generation • Updated Jan 6 • 39

mit-han-lab/vila-u-7b-256

Any-to-Any • Updated Oct 29, 2024 • 110 • 20

updated a collection 5 months ago

VILA-U-7B

Collection

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation • 2 items • Updated Jan 13 • 5

updated a model 7 months ago

mit-han-lab/SparseRefine

Updated Aug 30, 2024

New activity in mit-han-lab/SparseRefine 7 months ago

Add Mask2Former-L low-resolution checkpoint

#3 opened 7 months ago by

Skhaki

Add Mask2Former-T low-resolution checkpoint

#2 opened 7 months ago by

Skhaki

Add HRNet low-resolution checkpoint

#1 opened 7 months ago by

Skhaki

New activity in mit-han-lab/efficientvit-sam 11 months ago

Create distilled_models

#5 opened 11 months ago by

zhuoyang20

upvoted a paper about 1 year ago

EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss

Paper • 2402.05008 • Published Feb 7, 2024 • 22

authored a paper about 1 year ago

EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss

Paper • 2402.05008 • Published Feb 7, 2024 • 22

authored a paper over 1 year ago

One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion

Paper • 2311.07885 • Published Nov 14, 2023 • 40