arxiv:2508.19652
Haitao Mi
haitaominlp
AI & ML interests
Large Language Models
Recent Activity
upvoted
a
paper
3 days ago
Every Question Has Its Own Value: Reinforcement Learning with Explicit
Human Values
upvoted
a
paper
24 days ago
VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal
Reasoning
upvoted
a
paper
24 days ago
CLUE: Non-parametric Verification from Experience via Hidden-State
Clustering