3 papers
cs.LG2026
x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability
Xin Peng, Ang Gao
Diffusion and flow matching models generate high-quality samples, but their ODE samplers often need tens to hundreds of neural function evaluations (NFEs). This remains a practical…
cs.LG2026
Rethinking Refinement: Correcting Generative Bias without Noise Injection
Xin Peng, Ang Gao
Generative models, including diffusion and flow-based models, often exhibit systematic biases that degrade sample quality, particularly in high-dimensional settings. We revisit ref…
cs.LG2026
Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling
Xin Peng, Ang Gao
The scalability of continuous normalizing flows (CNFs) for unbiased Boltzmann sampling remains limited in high-dimensional systems due to the cost of Jacobian-determinant evaluatio…