collaborators

5 papers

cs.LG2026

Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment

Haozhe Jia, Pengyu Yin, Wenshuo Chen +6

Physics-informed diffusion models typically enforce PDE constraints only on final outputs, leaving intermediate representations unconstrained and prone to shortcut learning under s…

cs.CV2026

Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models

Haosen Li, Wenshuo Chen, Lei Wang +4

Diffusion models have achieved remarkable success in synthesizing complex static and temporal visuals, a breakthrough largely driven by Classifier-Free Guidance (CFG). However, des…

cs.CV2025

POLARIS: Projection-Orthogonal Least Squares for Robust and Adaptive Inversion in Diffusion Models

Wenshuo Chen, Haosen Li, Shaofeng Liang +6

The Inversion-Denoising Paradigm, which is based on diffusion models, excels in diverse image editing and restoration tasks. We revisit its mechanism and reveal a critical, overloo…

cs.CV2025

LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model

Haozhe Jia, Wenshuo Chen, Yuqi Lin +8

While current diffusion-based models, typically built on U-Net architectures, have shown promising results on the text-to-motion generation task, they still suffer from semantic mi…

cs.CV2025

ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model

Wenshuo Chen, Kuimou Yu, Haozhe Jia +8

While diffusion models advance text-to-motion generation, their static semantic conditioning ignores temporal-frequency demands: early denoising requires structural semantics for m…