arXiv (All)
open access
Data-Free Continual Learning for World Action Model with Rectified Generative Replay
World action models (WAMs) built on pretrained video generation models adapt quickly to new robotic tasks, but they forget previously learned tasks under sequential fine-tuning. Experience replay (ER) mitigates such forgetting by rehearsing data of previous tasks, yet this data is often unavailable
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- SPARS: A Stability-Plasticity-Aware Region Selection Framework for Continual Learning#1354558
- Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation#1122473
- Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision#1034609
- Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision#978453
- RM-WAM: Reliable Memory-Augmented World Action Models for Long-Horizon Robot Manipulation#1326555
Record · ID 1354232
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive