Zizhuo Lin — accepted AI-conference papers

2026

Part-X-MLLM: Part-aware 3D Multimodal Large Language Model

Chunshi Wang, Junliang Ye, Yunhan Yang, YANG LI, Zizhuo Lin, Jun Zhu +3

ICLR 2026poster

We introduce Part-X-MLLM, a native 3D multimodal large language model that unifies diverse 3D tasks by formulating them as programs in a structured, executable grammar. Given an RGB point cloud and a natural language prompt, our model autoregressively generates a single, coherent token sequence enco…

Cited by 4 Source ↗code ↗Scholar ↗

2026

ParticleGS: Learning Neural Gaussian Particle Dynamics from Videos for Prior-free Physical Motion Extrapolation

Jinsheng Quan, Qiaowei Miao, Yichao Xu, Zizhuo Lin, Ying Li, Wei Yang +2

CVPR 2026

The ability to extrapolate dynamic 3D scenes beyond the observed timeframe is fundamental to advancing physical world understanding and predictive modeling. Existing dynamic 3D reconstruction methods have achieved high-fidelity rendering of temporal interpolation, but typically lack physical consist

Cited by 0 Source ↗Scholar ↗