Visual Navigation on R2R
Metric: spl (higher is better)
Metric: spl (higher is better)
| # | Model↕ | spl▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | SUSA | 0.6383 | No | Agent Journey Beyond RGB: Unveiling Hybrid Seman... | 2024-12-09 | Code |
| 2 | Meta-Explore | 0.61 | No | Meta-Explore: Exploratory Hierarchical Vision-an... | 2023-03-07 | - |
| 3 | BEV-BERT | 0.6 | No | BEVBert: Multimodal Map Pre-training for Languag... | 2022-12-08 | Code |
| 4 | NaviLLM | 0.6 | No | Towards Learning a Generalist Model for Embodied... | 2023-12-04 | Code |
| 5 | HOP | 0.59 | No | HOP: History-and-Order Aware Pre-training for Vi... | 2022-03-22 | Code |
| 6 | VLN-PETL | 0.58 | No | VLN-PETL: Parameter-Efficient Transfer Learning ... | 2023-08-20 | Code |
| 7 | DUET | 0.58 | No | Think Global, Act Local: Dual-scale Graph Transf... | 2022-02-23 | Code |
| 8 | VLN-BERT | 0.57 | No | A Recurrent Vision-and-Language BERT for Navigat... | 2020-11-26 | Code |
| 9 | Prevalent | 0.51 | No | Towards Learning a Generic Agent for Vision-and-... | 2020-02-25 | Code |
| 10 | RCM+SIL(no early exploration) | 0.38 | No | Reinforced Cross-Modal Matching and Self-Supervi... | 2018-11-25 | - |
| 11 | Seq2Seq baseline | 0.18 | No | Vision-and-Language Navigation: Interpreting vis... | 2017-11-20 | Code |