ML Research Wiki / Benchmarks / Visual Navigation / R2R

R2R

Visual Navigation Benchmark

Performance Over Time

📊 Showing 11 results | 📏 Metric: spl

Top Performing Models

Rank Model Paper spl Date Code
1 SUSA Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation 0.64 2024-12-09 📦 HCI-LMC/VLN-SUSA
2 Meta-Explore Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding 0.61 2023-03-07 -
3 BEV-BERT BEVBert: Multimodal Map Pre-training for Language-guided Navigation 0.60 2022-12-08 📦 marsaki/vln-bevbert
4 NaviLLM Towards Learning a Generalist Model for Embodied Navigation 0.60 2023-12-04 📦 zd11024/NaviLLM 📦 lavi-lab/navillm
5 HOP HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation 0.59 2022-03-22 📦 yanyuanqiao/hop-vln
6 VLN-PETL VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation 0.58 2023-08-20 📦 yanyuanqiao/vln-petl
7 DUET Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation 0.58 2022-02-23 📦 cshizhe/vln-duet
8 VLN-BERT A Recurrent Vision-and-Language BERT for Navigation 0.57 2020-11-26 📦 YicongHong/Recurrent-VLN-BERT
9 Prevalent Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training 0.51 2020-02-25 📦 weituo12321/PREVALENT
10 RCM+SIL(no early exploration) Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation 0.38 2018-11-25 -

All Papers (11)

HCI-LMC/VLN-SUSA
marsaki/vln-bevbert
zd11024/NaviLLM lavi-lab/navillm
yanyuanqiao/hop-vln
yanyuanqiao/vln-petl
cshizhe/vln-duet
YicongHong/Recurrent-VLN-BERT
weituo12321/PREVALENT
peteanderson80/Matterport3DSimulator YicongHong/Recurrent-VLN-BERT