Zhang Maoqi's picture

3

Zhang Maoqi

maoseven

AI & ML interests

None yet

Recent Activity

upvoted a paper 11 days ago

VideoRoPE: What Makes for Good Video Rotary Position Embedding?

upvoted a paper 11 days ago

Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models

upvoted a paper 11 days ago

QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation

View all activity

Organizations

None yet

maoseven's activity

upvoted 3 papers 11 days ago

VideoRoPE: What Makes for Good Video Rotary Position Embedding?

Paper • 2502.05173 • Published 13 days ago • 60

Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models

Paper • 2502.04404 • Published 15 days ago • 19

QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation

Paper • 2502.05178 • Published 13 days ago • 10