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 (11)

Learning To Reason And Navigate: Parameter Efficient Action Planning With Large Language Models2025 · 1 citesImplicit Geometry Representations for Vision-and-Language Navigation from Web Videos2026Trajectory-Diversity-Driven Robust Vision-and-Language Navigation2026Global Commander and Local Operative: A Dual-Agent Framework for Scene Navigation2026DV-VLN: Dual Verification for Reliable LLM-Based Vision-and-Language Navigation2026Landmark-Guided Knowledge for Vision-and-Language Navigation2025Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale2025CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation2025Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation2025FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Tasks2025RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation2024