80%Highly rated
?Highly ratedVote to see the score
All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models
GRPO causes vision-language models to collapse into narrow reasoning paths, and proposed Multi-Group Policy Optimization restores diverse reasoning and improves benchmark scalability.
Published Apr 1, 2026 · 0 citations · ▲ 65 on Hugging Face · Code ★ 149
– ReadersNo votes yet
12/20 AI panelreviewers recommend it
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in to vote.
AI panel: 12 of 20 reviewers recommend it
lenient 4/5
medium 7/10
strict 1/5