Xuweiyi Chen

Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentation

Frame In-N-Out: Unbounded Controllable Image-to-Video Generation

Bootstrapping Visual Assistant Modeling with Situated Interaction Simulation

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination