Generative Models
PulseAugur coverage of Generative Models — every cluster mentioning Generative Models across labs, papers, and developer communities, ranked by signal.
- 2026-05-19 research_milestone A new paper proposes Lipschitz-guided design of interpolation schedules for generative models. 来源
1 天有情绪数据
-
New GORMPO algorithm improves offline RL with generative density modeling
Researchers have developed a new offline reinforcement learning algorithm called Generative OOD-regularized Model-based Policy Optimization (GORMPO). This method integrates generative models to explicitly model density …
-
AI在成像中的幻觉与逆问题极限相关
研究人员开发了一个理论框架，用于理解和量化用于逆问题（如医学成像）的AI模型中的“幻觉”。研究表明，这些逼真但错误的细节可能源于问题本身固有的病态性质，而不仅仅是特定模型。新方法提供了幻觉幅度的可计算界限以及评估重建忠实度的算法，证明了其在各种成像任务和现代生成模型中的广泛适用性。
-
Generative models learn rules across two distinct training timescales
Researchers have identified two distinct timescales in generative model training: the point at which generations become rule-valid ($\tau_{\mathrm{rule}}$) and the point at which models begin reproducing training sample…
-
AI models can avoid output collapse with diverse reward functions
A new theoretical study explores how generative models can avoid collapsing into narrow output ranges during recursive retraining. Researchers propose that using multiple, diverse reward functions for data curation, rat…