Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
Jade Zou, Tao Huang, Weijie Kong +7
Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying o…
cs.LG2025
JANUS: A Dual-Constraint Generative Framework for Stealthy Node Injection Attacks
Jiahao Zhang, Xiaobing Pei, Zhaokun Zhong +2
Graph Neural Networks (GNNs) have demonstrated remarkable performance across various applications, yet they are vulnerable to sophisticated adversarial attacks, particularly node i…