OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling

arXiv:2609.23753 · cs.CV, cs.LG · Submitted 2026-09-20 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-09-20

Updated: 2026-09-20

Comments: 23 pages, 9 figures. Project page: https://onlinewm.github.io/

Project page: https://onlinewm.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• World Model — 50× in this paper · explained in 7 episodes
• Fine-Tuning — 11× in this paper · explained in 5 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Active Online Learning — 9× in this paper
• Generalization — 8× in this paper · explained in 13 episodes
• Causality-Aware Fine-Tuning — 6× in this paper
• Fidelity — 5× in this paper · explained in 2 episodes
• Grounding — 5× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Action Space — 2× in this paper · explained in 1 episode
• Action-Conditioned Dynamics — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Latent Representation — 2× in this paper · explained in 2 episodes
• 3D Gaussian Splatting — 1× in this paper · explained in 2 episodes
• Action Primitives — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Gaussian Splatting — 1× in this paper · explained in 4 episodes
• Joint Attention — 1× in this paper · explained in 2 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes

Sources

• Cosmos World Foundation Model Platform for Physical AI
• MineStudio: A Streamlined Package for Minecraft AI Agent Development
• MineRL: A Large-Scale Dataset of Minecraft Demonstrations
• World Models
• Matrix-game 2.0: An open-source, real-time, and streaming interactive world model
• RELIC: Interactive Video World Model with Long-Horizon Memory
• Open-Endedness is Essential for Artificial Superhuman Intelligence
• Auto-Encoding Variational Bayes
• Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
• Cameras as Relative Positional Encoding
• Open-Sora Plan: Open-Source Large Video Generation Model
• Depth Anything 3: Recovering the Visual Space from Any Views
• Flow Matching for Generative Modeling
• Muon is Scalable for LLM Training
• WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
• Yume-1.5: A Text-Controlled Interactive World Generation Model
• WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation
• SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
• HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning
• WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models