EvolvingLMMs-Lab/ MGPO
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
by LMMs-Lab 0 forks Created May 2025 View on GitHub
- Stars
- 56
- <1% of EvolvingLMMs-Lab's stars
- Rank
- #765,236
- of 849,475 repos, top 91%
Among 849,475 repos
40–63 stars: 142,499 repos, including MGPO
top 50%top 10%top 1%top 0.1%
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #755,126
- Next milestone
- +1 star to reach the top 90%
- Yearly average
- 38 stars a year since May 2025