Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
cs.CV
Submitted: 2026-10-11
Updated: 2026-10-11
Code: https://github.com/OpenGVLab/RSI-Nav
Sources
- Cosmos 3: Omnimodal World Models for Physical AI
- RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation
- RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
- AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation
- MiMo-Embodied: X-Embodied Foundation Model Technical Report
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale
- Let's Verify Step by Step
- EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
- InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment
- SQA3D: Situated Question Answering in 3D Scenes
- RoboBrain 2.5: Depth in Sight, Time in Mind
- NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM
- A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce
- Self-Rewarding Language Models
- Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
- Kefa: A Knowledge Enhanced and Fine-grained Aligned Speaker for Navigation Instruction Generation
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