VLN-CE

The VLN-CE dataset/benchmark contains a collection of tasks for evaluating Vision-and-Language Navigation models by assessing their ability to navigate in environments using language instructions and spatial representations.

Papers using VLN-CE (11)

PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation2026Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments2026EmergeNav: Structured Embodied Inference for Zero-Shot Vision-and-Language Navigation in Continuous Environments2026Spatial-VLN: Zero-Shot Vision-and-Language Navigation With Explicit Spatial Perception and Exploration2026Beyond 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 Scale2025StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling2025Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation2025VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning2025Cross-modal Map Learning for Vision and Language Navigation2022 · 2 cites