Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
Paper
•
2506.09040
•
Published
•
34
Wei Song (SII)
Songweii
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
19 days ago
TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
upvoted
a
paper
about 1 month ago
GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization
upvoted
a
paper
2 months ago
UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image
Generation
Organizations
authored
a
paper
7 months ago
authored
4
papers
9 months ago
M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark
Paper
•
2406.05343
•
Published
Baichuan-Omni Technical Report
Paper
•
2410.08565
•
Published
•
87
Baichuan-Omni-1.5 Technical Report
Paper
•
2501.15368
•
Published
•
60
DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies
Paper
•
2503.14324
•
Published
•
2