Research map / Vision-language and multimodal / Robot action and navigation
All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation
Xudong Wang, Gan Li, Zhiyu Liu, Yao Wang, Lianqing Liu, Zhi Han
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 |
|---|---|---|---|
| use fourth-order tensor (decoupled scene and environment experts) instead of third-order tensor (ablation) | TuKA · AML-VLN 20 simulation tasks | SR | Improved |
| share core tensor G across tasks (ablation) | TuKA · AML-VLN 20 simulation tasks | SR: 55 -> 65 | Improved |
| share encoder U2 across tasks (ablation) | TuKA · AML-VLN 20 simulation tasks | SR: 62 -> 65 | Improved |
| share decoder U1 across tasks (ablation) | TuKA · AML-VLN 20 simulation tasks | SR: 65 -> 65 | No clear effect |
| TuKA with DKIL vs best LoRA baseline SD-LoRA | StreamVLN · AML-VLN (24 tasks) | avg SR: 56 -> 65 | Improved |
| train on 30 tasks instead of 24 (ablation) | AlldayWalker · AML-VLN T1-T24 | SR: T4: 81 -> 70; T24: 72 -> 66; most tasks within 1 | No clear effect |
| use TuKA instead of BranchLoRA / SD-LoRA on unseen scenarios | StreamVLN · Unseen scenarios G1-G6 | avg SR: 40 -> 55 | Improved |
Closest papers by meaning
- DecoVLN: Decoupling Observation, Reasoning, and Correction for Vision-and-Language Navigation (CVPR 2026 · similarity 0.89)
- M$^3$E: Continual Vision-and-Language Navigation via Mixture of Macro and Micro Experts (ICLR 2026 · similarity 0.89)
- Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation (ICML 2026 · similarity 0.89)
- Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method (CVPR 2025 · similarity 0.88)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.88)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.87)
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.
