REVERIE

Dataset Card for REVERIE Dataset Details Dataset Type: REVERIE is the first large-scale visual instruction-tuning dataset with ReflEctiVE RatIonalE annotations. REVERIE comprises 115k machine-generated reasoning instructions, each meticulously annotated with a corresponding pair of correct and confusing responses, alon

Papers using REVERIE (20)

ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigation2026Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos2026Trajectory-Diversity-Driven Robust Vision-and-Language Navigation2026Beyond Textual Knowledge-Leveraging Multimodal Knowledge Bases for Enhancing Vision-and-Language Navigation2026Enhancing Vision-Language Navigation with Multimodal Event Knowledge from Real-World Indoor Tour Videos2026Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale2025Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation2025A Recurrent Vision-and-Language BERT for Navigation2020 · 40 citesVision-and-Language Navigation via Causal Learning2024 · 28 citesHistory Aware Multimodal Transformer for Vision-and-Language Navigation2021 · 21 citesThe Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation2021 · 12 citesHOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation2022 · 8 citesCLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation2022 · 8 citesVisual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration2022VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation2023Prompt-based Context- and Domain-aware Pretraining for Vision and Language Navigation2023DAP: Domain-aware Prompt Learning for Vision-and-Language Navigation2023Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigation2024Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts2024Seeing is Believing? Enhancing Vision-Language Navigation using Visual Perturbations2024