AI Paper Atlas

Research map / Benchmarks / R2R

R2R leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on R2R. Best SPL: 62.2 (NaviLLM+RT3DAction, CVPR 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

R2R · SPL

10 papers, each with its best reported number for its own method; higher is better.

#SPL ↑MethodPaperTopic
162.2NaviLLM+RT3DAction
NaviLLM
RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation
CVPR 2025 · Table 1
Video-language understanding
262CoNavCoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
TPAMI 2026 · Table 1
Multimodal LLMs
361.9PanoGen
DUET-CLIP
PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation
NeurIPS 2023 · Table 1
Robot action and navigation
460NaviLLM
Vicuna-7B-v0
Towards Learning a Generalist Model for Embodied Navigation
CVPR 2024 · Table 1
Human-AI and goal-conditioned
560VLN-SIG
HAMT
Improving Vision-and-Language Navigation by Generating Future-View Image Semantics
CVPR 2023 · Table 1
Human-AI and goal-conditioned
659MTVM
PREVALENT init
Multimodal Transformer with Variable-Length Memory for Vision-and-Language Navigation
ECCV 2022 · Table 1
Robot action and navigation
759RCM + SIL (unseen)
RCM
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
CVPR 2019 · Test Set table
Robot action and navigation
852ORISTThe Road To Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
ICCV 2021 · Table 3
Robot action and navigation
942EGP*Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
NeurIPS 2020 · R2R comparison table
Robot action and navigation
1040.9RCM + augaps
RCM
Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler
ECCV 2020 · Table 1
Robot action and navigation

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.