Kaiyou Song
- Papers
- 5
Cite
Notes
Only stored in your browser.
5papers
Authored papers
5Ming-Omni: A Unified Multimodal Model for Perception and Generation
arXiv 2025
M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance
arXiv 2025
DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
droppos-pre-training-vision-transformers-by
Bootstrap Masked Visual Modeling via Hard Patches Mining
arXiv 2023
Semantic-Aware Autoregressive Image Modeling for Visual Representation Learning
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 5 papers