热点
"BVPO" 相关文章
From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
cs.AI updates on arXiv.org 2025-10-07T04:18:14.000000Z
From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
cs.AI updates on arXiv.org 2025-10-07T04:18:14.000000Z