Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
Paper
•
2508.13755
•
Published
•
14
Yinhong Liu
yinhongliu
AI & ML interests
NLP, NLG
Recent Activity
upvoted
a
paper
about 2 months ago
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with
Adaptive Exploration
upvoted
a
paper
5 months ago
Visual Planning: Let's Think Only with Images
authored
a paper
about 1 year ago
Instruct-SCTG: Guiding Sequential Controlled Text Generation through
Instructions
Organizations
