SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation

arXiv:2604.27620 · cs.CV · Submitted 2026-04-30 · Read on arXiv

cs.CV

Submitted: 2026-04-30

Updated: 2026-10-17

Comments: Accepted by ACM-MM 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 2× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Curriculum Learning — 1× in this paper · explained in 2 episodes
• Long-horizon reasoning — 1× in this paper · explained in 2 episodes
• Vision-and-Language Navigation — 1× in this paper

Sources

• GPT-4 Technical Report
• 1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)
• Qwen Technical Report
• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Matterport3D: Learning from RGB-D Data in Indoor Environments
• NaVILA: Legged Robot Vision-Language-Action Model for Navigation
• ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
• MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots
• Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
• Causal World Modeling for Robot Control
• Think before Go: Hierarchical Reasoning for Image-goal Navigation
• NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction
• SPAN-Nav: Generalized Spatial Awareness for Versatile Embodied Navigation
• Nav-R1: Reasoning and Navigation in Embodied Scenes
• InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment
• DeepSeek-VL: Towards Real-World Vision-Language Understanding
• HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System
• Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
• VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning

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