Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915327513722880 |
|---|---|
| author | Jia, Ziqi Wang, Anmin Qu, Xiaoyang Yang, Xiaowen Wang, Jianzong |
| author_facet | Jia, Ziqi Wang, Anmin Qu, Xiaoyang Yang, Xiaowen Wang, Jianzong |
| contents | Previous continual learning setups for embodied intelligence focused on executing low-level actions based on human commands, neglecting the ability to learn high-level planning and multi-level knowledge. To address these issues, we propose the Hierarchical Embodied Continual Learning Setups (HEC) that divide the agent's continual learning process into two layers: high-level instructions and low-level actions, and define five embodied continual learning sub-setups. Building on these setups, we introduce the Task-aware Mixture of Incremental LoRA Experts (Task-aware MoILE) method. This approach achieves task recognition by clustering visual-text embeddings and uses both a task-level router and a token-level router to select the appropriate LoRA experts. To effectively address the issue of catastrophic forgetting, we apply Singular Value Decomposition (SVD) to the LoRA parameters obtained from prior tasks, preserving key components while orthogonally training the remaining parts. The experimental results show that our method stands out in reducing the forgetting of old tasks compared to other methods, effectively supporting agents in retaining prior knowledge while continuously learning new tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04595 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning Jia, Ziqi Wang, Anmin Qu, Xiaoyang Yang, Xiaowen Wang, Jianzong Computer Vision and Pattern Recognition Previous continual learning setups for embodied intelligence focused on executing low-level actions based on human commands, neglecting the ability to learn high-level planning and multi-level knowledge. To address these issues, we propose the Hierarchical Embodied Continual Learning Setups (HEC) that divide the agent's continual learning process into two layers: high-level instructions and low-level actions, and define five embodied continual learning sub-setups. Building on these setups, we introduce the Task-aware Mixture of Incremental LoRA Experts (Task-aware MoILE) method. This approach achieves task recognition by clustering visual-text embeddings and uses both a task-level router and a token-level router to select the appropriate LoRA experts. To effectively address the issue of catastrophic forgetting, we apply Singular Value Decomposition (SVD) to the LoRA parameters obtained from prior tasks, preserving key components while orthogonally training the remaining parts. The experimental results show that our method stands out in reducing the forgetting of old tasks compared to other methods, effectively supporting agents in retaining prior knowledge while continuously learning new tasks. |
| title | Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.04595 |