11 papers
DVD: Discrete Voxel Diffusion for 3D Generation and Editing
Zhengrui Xiang, Jiaqi Wu, Fupeng Sun +2
We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) based 3D generative pipelines.…
Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score
Mariya Pavlova, Harrison Bo Hua Zhu, Lidia Vitanova +2
We introduce the Trajectory-based Quantization Sensitivity Score (TQS), a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability. By…
Free energy Estimation on Any State Space
Jiajun He, Zijing Ou, Francisco Vargas +4
Free energy estimation is a fundamental yet challenging problem, from physics to statistics. Classical approaches rely on thermodynamic transformations, ranging from direct estimat…
Spectral Transformer Neural Processes
Xianhe Chen, Hao Chen, Yingzhen Li
Time series, spatial data, and images are natural applications of Neural Processes. However, when such data exhibit strong periodicity and quasi-periodicity, existing methods often…
Structured Coupling for Flow Matching
Xavier Sumba, Carles Balsells-Rodas, Yingzhen Li
Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models…
Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design
Zijing Ou, Chinmay Pani, Yingzhen Li
Discrete diffusion models have become highly effective across various domains. However, real-world applications often require the generative process to adhere to certain constraint…