collaborators

11 papers

cs.CV2026

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.…

cs.LG2026

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…

stat.ML2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…