ICLR 2026 Paper: Ctrl-World

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)

SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking

[NeurIPS 2025] Video World Models with Long-term Spatial Memory

[ICRA 2025] WeatherGS: 3D Scene Reconstruction in Adverse Weather Conditions via Gaussian Splatting

[CVPR 2026] VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving

[CVPR 2026] LoST: Level of Semantics Tokenization for 3D Shapes

Real-Time Physical Action-Conditioned Video Generation

Code of SelfE (CVPR 2026)

🚀🚀🚀Official Repository of Intelligent Remote Sensing Agents: A Survey

Inference, evaluation and analysis code for STEVO-Bench

[SIGGRAPH Asia 2025] FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion

Official implementation of 'MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors'

Geometry-grounded Point Transformer (CVPR 2026)

Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"

Animate Any Character in Any World

Monocular whole-body 3D human pose estimation using the SOMA body model

High-Fidelity 3D Shape Generation via Scalable Geometric Refinement

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

Official implementation of Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data

[ICLR 25, TPAMI 26, CVPR 26] Track-On: Online Point Tracking with Memory