CurveRL: 用于LLM推理的基于分布感知的上下文重加权原则

GeMPO：在线扩散强化学习的广义度量匹配

GeMPO: Generalized Measure Matching for Online Diffusion Reinforcement Learning

提出GeMPO框架，通过将扩散RL中的重加权从softmax推广到一般单调函数，并引入负重加权机制，以解决过贪策略和负样本利用不足的问题。

不要浪费错误：通过置信度重加权利用负强化学习组

Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting

本文提出LENS方法，通过置信度重加权为错误响应分配非零奖励，利用负RL组提升GRPO效率，在MATH基准上显著优于基线。

Model Agnostic Sample Reweighting for Out-of-Distribution Learning

Distributionally robust optimization (DRO) and invariant risk minimization (IRM) are two popular methods proposed to improve out-of-distribution (OOD) generalization performance of machine learning models. While effective for small models, it has been observed that these methods can be vulnerable to overfitting with large overparameterized models. This work proposes a principled method, \textbf{M}odel \textbf{A}gnostic sam\textbf{PL}e r\textbf{E}weighting (\textbf{MAPLE}), to effectively address OOD problem, especially in overparameterized scenarios. Our key idea is to find an effective reweig…

Sharpness-Aware Minimization with Dynamic Reweighting

Deep neural networks are often overparameterized and may not easily achieve model generalization. Adversarial training has shown effectiveness in improving generalization by regularizing the change of loss on top of adversarially chosen perturbations. The recently proposed sharpness-aware minimization (SAM) algorithm conducts adversarial weight perturbation, encouraging the model to converge to a flat minima. SAM finds a common adversarial weight perturbation per-batch. Although per-instance adversarial weight perturbations are stronger adversaries and can potentially lead to better generaliza…

通过后验重加权理解多模态上下文越狱

Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting

本文提出后验重加权框架，将多模态大模型上下文越狱建模为证据累积过程，导出缩放定律，并据此设计后验感知推理时防御，在固定干预预算下显著提升鲁棒性-效用权衡。

基于比率方差正则化的策略优化用于高效的LLM微调

Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning

R²VPO通过正则化策略比率的方差，提升LLM微调的稳定性和数据效率。