6 papers · 1 filter
One-Step Generative Modeling via Wasserstein Gradient Flows
Jiaqi Han, Puheng Li, Qiushan Guo +3
Diffusion models and flow-based methods have shown impressive generative capability, especially for images, but their sampling is expensive because it requires many iterative updat…
Structured Scaling of AI Discovery Across Diverse Scientific Domains
Haotian Ye, Haowei Lin, Jingyi Tang +30
Scientific discovery often requires many cycles of proposing, testing, and refining candidate solutions. Language models can increasingly participate in these loops, but simply gen…
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…
CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers
Jiaqi Han, Haotian Ye, Puheng Li +3
Diffusion-based generative models have become dominant generators of high-fidelity images and videos but remain limited by their computationally expensive inference procedures. Exi…
On the Generalization Properties of Diffusion Models
Puheng Li, Zhong Li, Huishuai Zhang +1
Diffusion models are a class of generative models that serve to establish a stochastic transport map between an empirically observed, yet unknown, target distribution and a known p…
Exploring Neural Network Landscapes: Star-Shaped and Geodesic Connectivity
Zhanran Lin, Puheng Li, Lei Wu
One of the most intriguing findings in the structure of neural network landscape is the phenomenon of mode connectivity: For two typical global minima, there exists a path connecti…