Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-Training
cs.RO
Submitted: 2026-10-14
Updated: 2026-10-14
Comments: CoRL 2026
Project page: https://meta-gensim.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets
- RT-1: Robotics Transformer for Real-World Control at Scale
- Eurekaverse: Environment Curriculum Generation via Large Language Models
- GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation
- MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
- DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning
- NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptors
- HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning
- PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies
- From Imitation to Refinement -- Residual RL for Precise Assembly
- Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels
- Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation
- AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent
- Efficient Data Collection for Robotic Manipulation via Compositional Generalization
- Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation
- DataMIL: Selecting Data for Robot Imitation Learning with Datamodels
- CUPID: Curating Data your Robot Loves with Influence Functions
- Curating Demonstrations using Online Experience
- STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning
- Edify 3D: Scalable High-Quality 3D Asset Generation
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies