Xiaoxi Liang — accepted AI-conference papers

2026

Video Spatial Reasoning with Object-Centric 3D Rollout

Haoran Tang, Meng Cao, Ruyang Liu, Xiaoxi Liang, Linglong Li, Ge Li +1

AAAI 2026technical

Recent advances in Multi-modal Large Language Models (MLLMs) have showcased remarkable capabilities in vision-language understanding. However, enabling robust video spatial reasoning—the ability to comprehend object locations, orientations, and inter-object relationships in dynamic 3D scenes—remains

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

DGTalker: Disentangled Generative Latent Space Learning for Audio-Driven Gaussian Talking Heads

Xiaoxi Liang, Yanbo Fan, Qiya Yang, Xuan Wang, Wei Gao, Ge Li

ICCV 2025poster

In this work, we investigate the generation of high-fidelity, audio-driven 3D Gaussian talking heads from monocular videos. We present DGTalker, an innovative framework designed for real-time, high-fidelity, and 3D-aware talking head synthesis. By leveraging Gaussian generative priors and treating t…

Cited by 0 Source ↗PDF ↗Scholar ↗