Xiaoyi Zhang

xyzhang626's activity

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

upvoted a paper 9 days ago

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paper • 2607.19064 • Published 10 days ago • 73

updated a dataset 10 months ago

xyzhang626/LongVideoBenchmarkCaptions

Updated Oct 15, 2025 • 30

published a dataset 10 months ago

xyzhang626/LongVideoBenchmarkCaptions

Updated Oct 15, 2025 • 30

commented a paper about 1 year ago

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding

Paper • 2505.18079 • Published May 23, 2025 • 5 •

2

New activity in microsoft/Phi-3-vision-128k-instruct about 2 years ago

Should Phi-3V provide support in llama.cpp?

6

#24 opened about 2 years ago by

haohoo

authored 4 papers over 2 years ago

Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators

Paper • 2306.01242 • Published Jun 2, 2023 • 3

Unifying Layout Generation with a Decoupled Diffusion Model

Paper • 2303.05049 • Published Mar 9, 2023

Understanding Mobile GUI: from Pixel-Words to Screen-Sentences

Paper • 2105.11941 • Published May 25, 2021

Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API

Paper • 2310.04716 • Published Oct 7, 2023

updated 4 models over 2 years ago

xyzhang626/vit-mae-base-patch16-256

Image Feature Extraction • 85.8M • Updated Mar 14, 2024 • 2

xyzhang626/vit-mae-large-patch16-256

Image Feature Extraction • 0.3B • Updated Mar 14, 2024 • 2

xyzhang626/dinov2-large-patch16-256

Image Feature Extraction • 0.3B • Updated Mar 13, 2024 • 3

xyzhang626/dinov2-base-patch16-256

Image Feature Extraction • 86.7M • Updated Mar 12, 2024 • 2

New activity in madebyollin/sdxl-vae-fp16-fix over 2 years ago

Curious about the methodology of finetuning

13

#15 opened over 2 years ago by

zwd125

Curious about the methodology of finetuning

13

#15 opened over 2 years ago by

zwd125