Yongxin Chen

Compositional Diffusion with Guided search for Long-Horizon Planning

Proximal Diffusion Neural Sampler

Compositional Visual Planning via Inference-Time Diffusion Scaling

Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond

LapFlow: Laplacian Multi-scale Flow Matching for Generative Modeling

Empirical Robustness of Pixel Diffusion Undermines Adversarial Perturbation as Protection against Diffusion-based Mimicry

Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding

Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization

Adjoint Schrödinger Bridge Sampler

MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling

Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling

Improving Neural Optimal Transport via Displacement Interpolation

Non-equilibrium Annealed Adjoint Sampler

Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms

Rethinking Adversarial Attacks as Protection Against Diffusion-based Mimicry

Plug-and-Play Controllable Generation for Discrete Masked Models