Zhong-Yu Li

lzyhha

·

https://lzyhha.github.io/

lzyhha

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions

upvoted a paper 2 months ago

See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding

upvoted a paper 5 months ago

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

View all activity

Organizations

liked 4 models about 1 year ago

VisualCloze/VisualClozePipeline-LoRA-512

Image-to-Image • Updated Jan 7 • 15 • 1

VisualCloze/VisualClozePipeline-LoRA-384

Image-to-Image • Updated Jan 7 • 10 • 4

VisualCloze/VisualClozePipeline-512

Image-to-Image • 12B • Updated Jan 7 • 36 • 1

VisualCloze/VisualClozePipeline-384

Image-to-Image • 12B • Updated Jan 7 • 71 • 8

liked a Space over 1 year ago

VisualCloze

Generate images based on uploaded examples and prompts

liked a dataset over 1 year ago

VisualCloze/Graph200K

Viewer • Updated Jan 7 • 183k • 244 • 18

liked a model over 1 year ago

VisualCloze/VisualCloze

Image-to-Image • Updated Jan 7 • 14