Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
Paper
•
2510.13554
•
Published
•
57
•
2
Yang Li (SJTU & SII)
yangcole
AI & ML interests
None yet
Recent Activity
submitted
a paper
2 days ago
Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs
upvoted
a
paper
about 2 months ago
ssToken: Self-modulated and Semantic-aware Token Selection for LLM
Fine-tuning
Organizations
commented
a
paper
2 months ago