SIMULATION DATA → FOUNDATION MODEL
[1] RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning, RSS-25
[4] MimicLabs: A Large-Scale Procedural Benchmark for Robotic Manipulation
[7] GraspVLA: A Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data
[10] Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation
[2] InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy
[5] AgentWorld: A Platform for Scalable Data Generation and Sim-to-Real Transfer
[8] GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
[11] GENMANIP: LLM-driven Simulation for Generalizable Instruction-Following Manipulation
[3] RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
[6] Proc4Gem: Foundation Models for Physical Agency through Procedural Generation
[9] Cosmos: World Foundation Model Platform for Physical AI