热点
"KL散度损失" 相关文章
Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization
cs.AI updates on arXiv.org 2025-10-03T04:15:24.000000Z
Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization
cs.AI updates on arXiv.org 2025-10-03T04:15:24.000000Z