3 citations · 6 across the 12 of their papers we have counts for
7 papers · 1 filter
DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
Shigui Li, Delu Zeng
The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact esti…
Implicit Variational Rejection Sampling
Jian Xu, Shigui Li, Wei Chen +6
Variational Inference (VI) is a fundamental inference technique in Bayesian machine learning for approximating complex posterior distributions. Traditional VI often relies on the m…
Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilization
Shigui Li, Delu Zeng
A fundamental tension exists in the large-step inference of diffusion models via their deterministic probability flow ordinary differential equation (PF-ODE) trajectories, which we…
A Minimum Variance Path Principle for Accurate and Stable Score-Based Density Ratio Estimation
Wei Chen, Jiacheng Li, Shigui Li +4
Score-based methods are powerful across machine learning, but they face a paradox: theoretically path-independent, yet practically path-dependent. We resolve this by proving that p…
Dequantified Diffusion-Schr{ö}dinger Bridge for Density Ratio Estimation
Wei Chen, Shigui Li, Jiacheng Li +3
Density ratio estimation is fundamental to tasks involving -divergences, yet existing methods often fail under significantly different distributions or inadequately overlapping…
Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling
Jian Xu, Zhiqi Lin, Shigui Li +4
Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models. However,…
Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Models
Wei Chen, Shian Du, Shigui Li +2
Normalizing Flows (NFs) are widely used in deep generative models for their exact likelihood estimation and efficient sampling. However, they require substantial memory since the l…