2 7 5

Yue Zhao

zhaoyue-zephyrus

https://zhaoyue-zephyrus.github.io/

zhaoyue-zephyrus

AI & ML interests

None yet

Recent Activity

upvoted a paper 9 days ago

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

upvoted a paper 9 days ago

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

authored a paper 20 days ago

Image and Video Tokenization with Binary Spherical Quantization

View all activity

Organizations

None yet

zhaoyue-zephyrus's activity

upvoted 2 papers 9 days ago

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

Paper • 2504.13181 • Published 11 days ago • 31

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

Paper • 2504.13180 • Published 11 days ago • 17

authored 2 papers 20 days ago

Image and Video Tokenization with Binary Spherical Quantization

Paper • 2406.07548 • Published Jun 11, 2024

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published 21 days ago • 99

upvoted a paper 20 days ago

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published 21 days ago • 99

commented a paper 20 days ago

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published 21 days ago • 99 •

liked 3 models 2 months ago

upvoted a collection 3 months ago

QLIP

Collection

QLIP is a family of image tokenizers with SOTA reconstruction quality and zero-shot image understanding. • 3 items • Updated 5 days ago • 8

authored a paper 3 months ago

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

Paper • 2502.05178 • Published Feb 7 • 10

upvoted a paper 3 months ago

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

Paper • 2502.05178 • Published Feb 7 • 10

commented a paper 3 months ago

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

Paper • 2502.05178 • Published Feb 7 • 10 •

upvoted a collection 3 months ago

Eagle 2

Collection

Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated 5 days ago • 33

liked a model 6 months ago

jozhang97/ism_t33_650M_uc30pdb

Updated 29 days ago • 897 • 5

liked a Space 8 months ago

Eagle X5 13B Chat

🚀

Combine text and images to generate responses

upvoted a paper 8 months ago

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

Paper • 2408.15998 • Published Aug 28, 2024 • 88

authored 3 papers 11 months ago

Learning Video Representations from Large Language Models

Paper • 2212.04501 • Published Dec 8, 2022

Distilling Vision-Language Models on Millions of Videos

Paper • 2401.06129 • Published Jan 11, 2024 • 17

LEAP: Liberate Sparse-view 3D Modeling from Camera Poses

Paper • 2310.01410 • Published Oct 2, 2023 • 1