Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning
Hongjun Wang, Wei Liu, Weibo Gu +2
Regulating the importance ratio is critical for the training stability of Group Relative Policy Optimization (GRPO) based frameworks. However, prevailing ratio control methods, suc…
cs.LG2026
Mask Is What DLLM Needs: A Masked Data Training Paradigm for Diffusion LLMs
Linrui Ma, Yufei Cui, Kai Han +1
Discrete diffusion models offer global context awareness and flexible parallel generation. However, uniform random noise schedulers in standard DLLM training overlook the highly no…