activity
20242026
collaborators

5 papers

cs.LG2026

PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training

Senmiao Wang, Tiantian Fang, Haoran Zhang +4

We propose a preconditioning (PC) layer, a weight parameterization via polynomial preconditioner that ensures stable weight conditioning throughout LLM training. The PC module resh…

cs.CV2025

Bridging Diffusion Models and 3D Representations: A 3D Consistent Super-Resolution Framework

Yi-Ting Chen, Ting-Hsuan Liao, Pengsheng Guo +2

We propose 3D Super Resolution (3DSR), a novel 3D Gaussian-splatting-based super-resolution framework that leverages off-the-shelf diffusion-based 2D super-resolution models. 3DSR…

cs.CV2025

CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

Chen Chen, Pengsheng Guo, Liangchen Song +7

Conditional generative modeling aims to learn a conditional data distribution from samples containing data-condition pairs. For this, diffusion and flow-based methods have attained…

cs.LG2025

Variational Rectified Flow Matching

Pengsheng Guo, Alexander G. Schwing

We study Variational Rectified Flow Matching, a framework that enhances classic rectified flow matching by modeling multi-modal velocity vector-fields. At inference time, classic r…

cs.CV2024

On Inductive Biases That Enable Generalization of Diffusion Transformers

Jie An, De Wang, Pengsheng Guo +2

Recent work studying the generalization of diffusion models with UNet-based denoisers reveals inductive biases that can be expressed via geometry-adaptive harmonic bases. However,…