Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
Paper
•
2506.09040
•
Published
•
36
Mingzhe Zheng
Dunge0nMaster
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
29 days ago
Autoregressive Semantic Visual Reconstruction Helps VLMs Understand
Better
new activity
about 2 months ago
songdj/CML-Bench:pull request
new activity
about 2 months ago
songdj/CML-Bench:sync latest database
Organizations
None yet
upvoted
a
paper
29 days ago
upvoted
4
papers
7 months ago
Large Motion Video Autoencoding with Cross-modal Video VAE
Paper
•
2412.17805
•
Published
•
24
Identity-Preserving Text-to-Video Generation by Frequency Decomposition
Paper
•
2411.17440
•
Published
•
38
OmniCreator: Self-Supervised Unified Generation with Universal Editing
Paper
•
2412.02114
•
Published
•
14
VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation
Paper
•
2412.02259
•
Published
•
60
upvoted
a
paper
over 1 year ago