-
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
Paper • 2406.11271 • Published • 21 -
Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
Paper • 2410.13674 • Published • 17 -
Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities
Paper • 2410.11190 • Published • 22
Haonan Zhang
haonanzhang
AI & ML interests
AI & ML, Multi-modal Learning，Agent，LLM, etc.
Recent Activity
authored
a paper
2 days ago
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
liked
a model
about 2 months ago
facebook/VGGT-1B
upvoted
an
article
2 months ago
Why Did MiniMax M2 End Up as a Full Attention Model?
Organizations
-
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
Paper • 2406.11271 • Published • 21 -
Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
Paper • 2410.13674 • Published • 17 -
Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities
Paper • 2410.11190 • Published • 22
