Search papers, labs, and topics across Lattice.
Huazhong University of Science and Technology, China
3
1
6
3
Achieving high-fidelity 3D generation with just 1.5% of the training data could revolutionize resource allocation in 3D modeling.
Unbounded interaction horizons and real-time responsiveness redefine the possibilities for immersive AI-driven environments.
MLLMs can gain surprisingly strong 3D spatial reasoning abilities simply by tapping into the latent knowledge already present in video generation models.
