5 papers
Data-regularized Reinforcement Learning for Diffusion Models at Scale
Haotian Ye, Kaiwen Zheng, Jiashu Xu +15
Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hac…
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
NVIDIA, :, Alisson Azzolini +51
Physical AI systems need to perceive, understand, and perform complex actions in the physical world. In this paper, we present the Cosmos-Reason1 models that can understand the phy…
Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
Kaiwen Zheng, Yongxin Chen, Huayu Chen +4
While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimatio…
Exploratory Diffusion Model for Unsupervised Reinforcement Learning
Chengyang Ying, Huayu Chen, Xinning Zhou +3
Unsupervised reinforcement learning (URL) aims to pre-train agents by exploring diverse states or skills in reward-free environments, facilitating efficient adaptation to downstrea…
Visual Generation Without Guidance
Huayu Chen, Kai Jiang, Kaiwen Zheng +3
Classifier-Free Guidance (CFG) has been a default technique in various visual generative models, yet it requires inference from both conditional and unconditional models during sam…