6 papers
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…
Flow Matching with Arbitrary Auxiliary Paths
Xin Peng, Ang Gao
We introduce a new generative modeling framework, \textbf{Flow Matching with Arbitrary Auxiliary Paths (AuxPath-FM)}, which generalizes conditional flow matching by incorporating a…
P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference
Xin Peng, Ang Gao
Classifier-Free Guidance (CFG) is essential for high-fidelity conditional generation in flow matching, yet it imposes significant computational overhead by requiring dual forward p…
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…
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…
Flow Perturbation to Accelerate Unbiased Sampling of Boltzmann distribution
Xin Peng, Ang Gao
Flow-based generative models have been employed for sampling the Boltzmann distribution, but their application to high-dimensional systems is hindered by the significant computatio…