Unified Embodied Reasoning through Agentic Data-Model Co-Evolution
AI & ML interests
Computer Vision; Multi-modality; Generative Models; Structure from Motion; Multi-view Stereo; Localization and Mapping; Argument Reality; Virtual Reality.
Recent Activity
Papers
Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction
GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation