MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper
•
2504.00999
•
Published
•
83
Utopia
Wutopia
AI & ML interests
None yet
Recent Activity
liked
a Space
15 days ago
Qwen/Qwen2.5-VL-72B-Instruct
upvoted
a
paper
19 days ago
Improved Visual-Spatial Reasoning via R1-Zero-Like Training
Organizations
None yet
Wutopia's activity
upvoted
2
papers
19 days ago