VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
Paper
• 2602.12579 • Published
• 2
Xin-Qiang Cai
caixq
AI & ML interests
RL, RLHF, Learning under Weak Supervision, Diffusion Model
Recent Activity
authored
a paper
5 months ago
PIG-Nav: Key Insights for Pretrained Image Goal Navigation Models authored
a paper
5 months ago
Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect
Verifiers Organizations
None yet