HM-3D-OVON

The 'HM-3D-OVON' dataset/benchmark contains 3D environments and is used to evaluate the performance of Vision-Language Navigation agents in their ability to follow instructions and navigate efficiently.

Papers using HM-3D-OVON (6)

LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation2026SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning2026DRIVE-Nav: Directional Reasoning, Inspection, and Verification for Efficient Open-Vocabulary Navigation2026D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation2025AstraNav-Memory: Contexts Compression for Long Memory2025FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning2025