Orbis 2: A Hierarchical World Model for Driving
cs.CV, cs.AI, cs.LG, cs.RO
Submitted: 2026-07-17
Updated: 2026-11-14
Project page: https://lmb-freiburg.github.io/orbis2.github.io
Terminology
Sources
- Cosmos World Foundation Model Platform for Physical AI
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- World Models
- Mastering Diverse Domains through World Models
- GAIA-1: A Generative World Model for Autonomous Driving
- DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT
- Hierarchical Latent Action Model
- Auto-Encoding Variational Bayes
- Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
- ImageFolder: Autoregressive Image Generation with Folded Tokens
- Flow Matching for Generative Modeling
- One Million Scenes for Autonomous Driving: ONCE Dataset
- DINOv2: Learning Robust Visual Features without Supervision
- Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models
- Diffusion Models Are Real-Time Game Engines
- GenAD: Generalized Predictive Model for Autonomous Driving
- Hierarchical Planning with Latent World Models
- Diffusion Transformers with Representation Autoencoders
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs