MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper
•
2504.00999
•
Published
•
69
Juanxi Tian
Juanxi
AI & ML interests
MLLM｜Optimization ｜Visual Generation
Recent Activity
commented on
a paper
3 days ago
MergeVQ: A Unified Framework for Visual Generation and Representation
with Disentangled Token Merging and Quantization
Organizations
Juanxi's activity
authored
a
paper
3 days ago
upvoted
a
paper
3 days ago
commented
a
paper
3 days ago
updated
a
dataset
10 days ago
Add task category and tags
1
#2 opened 18 days ago
by
nielsr
liked
a
dataset
19 days ago
authored
a
paper
19 days ago
upvoted
a
paper
19 days ago
liked
a
model
4 months ago
liked
a
Space
4 months ago
upvoted
a
paper
6 months ago
authored
5
papers
6 months ago
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Paper
•
2406.06007
•
Published
•
2
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Paper
•
2410.06373
•
Published
•
33
Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis
Paper
•
2410.07155
•
Published
•
11
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Paper
•
2402.09240
•
Published
•
3
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Paper
•
2209.04851
•
Published
•
2