-
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper • 2504.00999 • Published • 78 -
Multi-Token Attention
Paper • 2504.00927 • Published • 43 -
Scaling Language-Free Visual Representation Learning
Paper • 2504.01017 • Published • 26
Yang Liu
largelymfs
AI & ML interests
None yet
Recent Activity
updated
a collection
13 days ago
worthy_a_read
updated
a collection
13 days ago
worthy_a_read
new activity
28 days ago
Salesforce/blip3-ocr-200m:Extremely low quality of data
Organizations
None yet
Collections
1
models
None public yet
datasets
None public yet