DreamFormer: Dream Imitation with a Transformer World Model for Language-Conditioned Robotic Manipulation
cs.RO
Submitted: 2026-10-03
Updated: 2026-10-03
Comments: submitted to IEEE Transactions on Cognitive and Developmental Systems (TCDS)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- DITTO: Offline Imitation Learning with World Models
- TransDreamer: Reinforcement Learning with Transformer World Models
- OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
- DINOv3
- DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
- DINOv2: Learning Robust Visual Features without Supervision
- Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- RT-1: Robotics Transformer for Real-World Control at Scale
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