Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
Paper
•
2506.02867
•
Published
•
2
shenqi
shenqiorient
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 months ago
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative
Textual Feedback
liked
a dataset
6 months ago
Foreshhh/vlsbench
Organizations
None yet