SOTAVerified

Vision and Language Navigation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 223 papers

TitleStatusHype
WebLINX: Real-World Website Navigation with Multi-Turn DialogueCode5
NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language ModelsCode3
Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation ModelsCode3
Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language NavigationCode2
BEVBert: Multimodal Map Pre-training for Language-guided NavigationCode2
Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language NavigationCode2
NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLMCode2
Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human InteractionsCode2
1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)Code2
NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous EnvironmentsCode2
Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language NavigationCode2
Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future DirectionsCode2
Vision-and-Language Navigation via Causal LearningCode2
FLAME: Learning to Navigate with Multimodal LLM in Urban EnvironmentsCode2
Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language NavigationCode2
CityNav: Language-Goal Aerial Navigation Dataset with Geographic InformationCode2
FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language ModelsCode2
General Scene Adaptation for Vision-and-Language NavigationCode2
Scaling Data Generation in Vision-and-Language NavigationCode2
NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled ReasoningCode2
AerialVLN: Vision-and-Language Navigation for UAVsCode2
NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language ModelsCode2
Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor AreasCode1
Airbert: In-domain Pretraining for Vision-and-Language NavigationCode1
A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language NavigationCode1
Show:102550
← PrevPage 1 of 9Next →
All datasetsVLN ChallengeTouchdown DatasetRxRmap2seqRoom2Roomrobo-vln

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1humansuccess0.86—Unverified
2Lilysuccess0.79—Unverified
3Airbertsuccess0.78—Unverified
4Global Normalizationsuccess0.74—Unverified
5explore@40 beam-searchsuccess0.74—Unverified
6BEVBertsuccess0.73—Unverified
7GMapsuccess0.73—Unverified
8VLN-Bertsuccess0.73—Unverified
9Gloabl Normalization pre-exploresuccess0.73—Unverified
10FOAM-Beam Searchsuccess0.72—Unverified
#ModelMetricClaimedVerifiedStatus
1FLAMETask Completion (TC)40.2—Unverified
2ORAR + junction type + heading deltaTask Completion (TC)29.1—Unverified
3ORARTask Completion (TC)24.2—Unverified
4ARC + L2STOPTask Completion (TC)16.68—Unverified
5VLN Transformer +M-50 +styleTask Completion (TC)16.2—Unverified
6VLN TransformerTask Completion (TC)14.9—Unverified
7ARCTask Completion (TC)14.13—Unverified
8Retouch-RConcatTask Completion (TC)12.8—Unverified
9Gated Attention (GA)Task Completion (TC)11.9—Unverified
10RConcatTask Completion (TC)11.8—Unverified
#ModelMetricClaimedVerifiedStatus
1MARVALndtw66.76—Unverified
2EnvEdit-PTndtw64.61—Unverified
3HAMTndtw59.94—Unverified
4CLEAR-CLIPndtw53.69—Unverified
5Monolingual Baselinendtw41.05—Unverified
6Multilingual Baselinendtw36.81—Unverified
#ModelMetricClaimedVerifiedStatus
1FLAMETask Completion (TC)52.44—Unverified
2ORAR + junction type + heading deltaTask Completion (TC)46.7—Unverified
3ORARTask Completion (TC)45.1—Unverified
4Gated AttentionTask Completion (TC)17—Unverified
5RconcatTask Completion (TC)14.7—Unverified
#ModelMetricClaimedVerifiedStatus
1R2R+EnvDropspl0.61—Unverified
2RCM + SILspl0.59—Unverified
3Tactical Rewind - shortspl0.41—Unverified
#ModelMetricClaimedVerifiedStatus
1Hierarchical Cross-Modal AgentSPL (Sucess Weighted by Path Length)0.4—Unverified