MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper • 2504.00999 • Published • 96
Luyuan Zhang
LuyuanZhang01
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
The Trinity of Consistency as a Defining Principle for General World Models upvoted a paper 5 months ago
Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights upvoted a paper 9 months ago
Rep-MTL: Unleashing the Power of Representation-level Task Saliency for
Multi-Task LearningOrganizations
None yet
authored a
paper about 1 year ago