Stars
PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
CVPR 2025: VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction
"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training" official implementation.
[AAAI 2026] SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries
SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model
DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data
DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
[AAAI 2026] OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)
[CVPR 2025] Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction
OmniNWM: Omniscient Navigation World Models for Autonomous Driving
Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"
Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling
Native Multimodal Models are World Learners
Marco Search Agent for Realistic and Challenging Agentic Search
[ICCV 2025] ALOcc: Adaptive Lifting-based 3D Semantic Occupancy and Cost Volume-based Flow Prediction
Official implementation of "From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction"
Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).
Fast and Universal 3D reconstruction model for versatile tasks
ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
[ICCV 2023 Oral] Game-theoretic modeling and learning of Transformer-based interactive prediction and planning