GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
Paper
•
2504.08736
•
Published
•
47
•
2
Tianwei Xiong
YuuTennYi
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
16 days ago
T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image
Generation
upvoted
a
paper
2 months ago
StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context
Modeling
upvoted
a
paper
2 months ago
OmniPart: Part-Aware 3D Generation with Semantic Decoupling and
Structural Cohesion
Organizations
commented
a
paper
5 months ago
commented
a
paper
11 months ago