Yue Zhao

zhaoyue-zephyrus's activity

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

upvoted a paper 3 months ago

Reconstruction Alignment Improves Unified Multimodal Models

Paper • 2509.07295 • Published Sep 8 • 40

upvoted 3 papers 8 months ago

Perception Encoder: The best visual embeddings are not at the output of the network

Paper • 2504.13181 • Published Apr 17 • 34

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Paper • 2504.13180 • Published Apr 17 • 19

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published Apr 7 • 110

upvoted a collection 10 months ago

QLIP

Collection

QLIP is a family of image tokenizers with SOTA reconstruction quality and zero-shot image understanding. • 3 items • Updated 7 days ago • 10

upvoted a paper 10 months ago

QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation

Paper • 2502.05178 • Published Feb 7 • 10

upvoted a collection 10 months ago

Eagle

Collection

Eagle is a family of frontier vision-language models with data-centric strategies. The model supports both HD image and long-context video input. • 15 items • Updated 7 days ago • 38

upvoted a paper over 1 year ago

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Paper • 2408.15998 • Published Aug 28, 2024 • 87