Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
Jiaming Han
csuhan
AI & ML interests
Computer Vision
Recent Activity
authored
a paper
1 day ago
Vision as a Dialect: Unifying Visual Understanding and Generation via
Text-Aligned Representations
updated
a collection
2 days ago
Tar
Organizations
None yet
Collections
2
models
9
csuhan/OneLLM-7B-x-text
Updated
csuhan/OneLLM-7B-image-text
Updated
csuhan/OneLLM-7B
Updated
•
4
csuhan/OneLLM-7B-hf-v1.1
Updated
•
2
csuhan/OneLLM-7B-hf
Updated
csuhan/OneLLM-7B-backup
Updated
•
3
csuhan/blip2_opt2.7b
Feature Extraction
•
Updated
•
16
csuhan/knn
Updated
csuhan/llama_storage
Updated
•
6