VLN-CE

The 'VLN-CE' dataset/benchmark contains language instructions paired with visual observations for evaluating embodied navigation tasks that require translating these inputs into spatial actions for robots.

Papers using VLN-CE (11)

Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation2026GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigation2026Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation2026SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation2026SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation2026EmergeNav: Structured Embodied Inference for Zero-Shot Vision-and-Language Navigation in Continuous Environments2026CLASH: Collaborative Large-Small Hierarchical Framework for Continuous Vision-and-Language Navigation2025Beyond Pixels: Introducing Geometric-Semantic World Priors for Video-based Embodied Models via Spatio-temporal Alignment2025DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigation2025Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale2025VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning2025