EngineeringAI Lab
Open 3D World Models-Lingjing
We build 3D world models that connect representation, spatial synthesis, interaction dynamics, and decision intelligence for agents in digital worlds.
Who We Are
EngineeringAI Lab was established by AP Huadong Mo at UNSW and Prof. Daoyi Dong at UTS, together with Zhenhong Sun. Zhenhong leads the practical research directions and coordinates the shared 3D World Model agenda.
EngineeringAI Lab is an innovation team focused on 3D World Model research and engineering deployment. We believe truly intelligent systems must understand, model, and interact with the 3D physical world, so we build world models with spatial perception, scene understanding, dynamic simulation, and interaction capabilities, connecting foundational construction, perceptual understanding, and decision-making action.
Open to strong candidates
We are recruiting PhD students or Research Assistants at UNSW and UTS. We welcome candidates with curiosity, passion, and engagement. Send a short introduction, and CV to Huadong Mo and Daoyi Dong. For informal questions, contact Zhenhong Sun.
We Work On
Our research agenda follows the same four directions as LingJing 3D World Model work, turning a research vision into coordinated lab systems.
Compact and controllable 3D asset representations for reconstruction, editing, decomposition, and state prediction.
Agentic generation pipelines and engine-grounded tools for coherent 3D scenes, simulation data, and spatial evaluation.
Expressive avatars, human-scene interaction, and multi-person motion generation for dynamic digital worlds.
LLM-based reasoning, language-guided planning, reinforcement learning, and decision systems for agents in 3D worlds.
Highlights
StoryBlender is the first team-led paper from EngineeringAI Lab accepted to ECCV, marking an important milestone for our 3D World Model program.
We value people who can turn ideas into datasets, simulators, tools, benchmarks, demos, and reproducible research infrastructure.
News
StoryBlender became the first EngineeringAI Lab team-led paper accepted to ECCV.
The invitation reflects the lab's growing engagement with top-tier machine learning research communities.
Latest Posts
Short research notes and project updates from our 3D World Model agenda.
A first team-level acceptance shows how the lab can coordinate research, engineering, writing, and system building around open 3D world models.
3DXTalker connects identity, lip motion, emotion, and head movement to make expressive 3D digital humans more controllable.
We look for people who can think from first principles, implement carefully, communicate clearly, and stay curious across disciplines.