Vision-and-Language Navigation Comparison Hub

Reference Surfaces

Top Papers

• Trajectory-Diversity-Driven Robust Vision-and-Language Navigation(8.0)

  NavGRPO is a robust reinforcement learning framework for goal-directed navigation in photo-realistic environments using natural language instructions.

• Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos(7.0)

  A framework for Vision-and-Language Navigation that leverages web videos to enhance spatial reasoning and navigation capabilities.

• DecoVLN: Decoupling Observation, Reasoning, and Correction for Vision-and-Language Navigation(7.0)

  DecoVLN enhances Vision-and-Language Navigation by optimizing long-term memory and correcting errors in real-time.

• CMMR-VLN: Vision-and-Language Navigation via Continual Multimodal Memory Retrieval(3.0)

  CMMR-VLN improves LLM-based vision-and-language navigation by introducing a structured multimodal memory system.