Research map / Continual learning / Online and replay-based
Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments
Jinwoo Jang, Daniel Rho, Sihyung Yoon, Hyunsuk Cho, Honguk Woo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add meta-router (two-stage routing) (ablation) | multi-scale world model mixture · EB-Habitat | success rate avg (%): 32.22 -> 40.44 | Improved |
| add scale alignment loss L_S(1) (ablation) | multi-scale world model mixture · EB-Habitat | success rate avg (%): 37.78 -> 40.44 | Improved |
| add scale alignment loss L_S(1) (ablation) | multi-scale world model mixture · HAZARD Flood | rescued value: 45.38 -> 49.83 | Improved |
| add variance regularizer L_S(2) (ablation) | multi-scale world model mixture · EB-Habitat | success rate avg (%): 35.56 -> 40.44 | Improved |
| add variance regularizer L_S(2) (ablation) | multi-scale world model mixture · HAZARD Fire | rescued value: 44.89 -> 43.71 | Hurt |
| add magnitude regularizer L_S(3) (ablation) | multi-scale world model mixture · EB-Habitat | success rate avg (%): 38.89 -> 40.44 | Improved |
| add magnitude regularizer L_S(3) (ablation) | multi-scale world model mixture · HAZARD Fire | rescued value: 44.52 -> 43.71 | Hurt |
| add scale-dependent forgetting (intra-scale) (ablation) | multi-scale world model mixture · EB-Habitat | success rate avg (%): 38.89 -> 40.44 | Improved |
| add scale-dependent forgetting (intra-scale) (ablation) | multi-scale world model mixture · HAZARD Fire | rescued value: 39.84 -> 43.71 | Improved |
| add gated cross-scale transfer (inter-scale) (ablation) | multi-scale world model mixture · EB-Habitat | success rate avg (%): 37.78 -> 40.44 | Improved |
| add gated cross-scale transfer (inter-scale) (ablation) | multi-scale world model mixture · HAZARD Fire | rescued value: 41.67 -> 43.71 | Improved |
| use 3D instead of 1D scale space (ablation) | meta-router · EB-Habitat | success rate avg (%): 38.89 -> 40.44 | Improved |
Closest papers by meaning
- World Model Implanting for Test-time Adaptation of Embodied Agents (ICML 2025 · similarity 0.88)
- From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents (ICLR 2026 · similarity 0.87)
- COMBO: Compositional World Models for Embodied Multi-Agent Cooperation (ICLR 2025 · similarity 0.87)
- ModularAgent: A Task-Aware Modular Framework for Joint Optimization of Multimodal Large Language Models and World Models (CVPR 2026 · similarity 0.86)
- Scaling Laws for Pre-training Agents and World Models (ICML 2025 · similarity 0.86)
- Learning 3D Persistent Embodied World Models (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
