conftrace_

importance ratio

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

text prompt alignment (1) gradient reweighting (1) reward overoptimization (1) entropy regularization (1) maximum likelihood estimation (1) label shift (1) flow matching (1) distributed learning (1) reinforcement learning (1)

Papers

GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping CVPR 2026 Addressing Label Shift in Distributed Learning via Entropy Regularization ICLR 2025