Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training
Paper • 2603.16139 • Published • 32
SII-Pandalin
pandalin98
AI & ML interests
Time Series, Multi Modal
Recent Activity
upvoted a paper about 1 month ago
Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training upvoted a paper 5 months ago
Thinking with Video: Video Generation as a Promising Multimodal
Reasoning Paradigm new activity 8 months ago
pandalin98/ITFormer-7B:模型使用咨询Organizations
None yet