papers

Publications (31)

cs.CV2023

Shape Guided Gradient Voting for Domain Generalization

Jiaqi Xu, Yuwang Wang, Xuejin Chen

Domain generalization aims to address the domain shift between training and testing data. To learn the domain invariant representations, the model is usually trained on multiple do…

cs.CV2024

Context-aware Talking Face Video Generation

Meidai Xuanyuan, Yuwang Wang, Honglei Guo +1

In this paper, we consider a novel and practical case for talking face video generation. Specifically, we focus on the scenarios involving multi-people interactions, where the talk…

cs.AI2026

Abstract representational geometry supports inference in large language models

Yunan Zeng, Yuwang Wang

A defining feature of human intelligence is the ability to adapt to changing environments by inferring latent task structure from sparse observations. Neuroscientific research indi…

cs.CV2021

S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation

Xiaotian Chen, Yuwang Wang, Xuejin Chen +1

Human can infer the 3D geometry of a scene from a sketch instead of a realistic image, which indicates that the spatial structure plays a fundamental role in understanding the dept…

cs.CV2023

DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models

Tao Yang, Yuwang Wang, Yan Lv +1

Targeting to understand the underlying explainable factors behind observations and modeling the conditional generation process on these factors, we connect disentangled representat…

cs.CV2025

Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects

Shuohan Tao, Boyao Zhou, Hanzhang Tu +2

3D Gaussian Splatting (GS) enables highly photorealistic scene reconstruction from posed image sequences but struggles with viewpoint extrapolation due to its anisotropic nature, l…