GuidedNav: Shaping Vision-Language Navigation Representations through Pre-action Attention and Spatial Guidance
cs.CV
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/MarSaKi/VLN-BEVBert
Project page: https://jingyu198.github.io/GuidedNav/ABSTRACT
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- 1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)
- Qwen3-VL Technical Report
- NaVILA: Legged Robot Vision-Language-Action Model for Navigation
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping
- GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
- Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments
- Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments
- Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
- Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
- Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
- VGGT: Visual Geometry Grounded Transformer
- Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation
- g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks
- GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation
- Cambrian-S: Towards Spatial Supersensing in Video
- JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation
- Top-down Neural Attention by Excitation Backprop
- NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
- FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models