Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
Paper • 2610.15782 • Published • 25
Gengze Zhou
ZGZzz
AI & ML interests
Embodied Ai, Vision-and-Language Navigation, Computer vision, Multimodality Learning, LLM
Recent Activity
authored a paper 19 days ago
Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping authored a paper 19 days ago
NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime authored a paper 19 days ago
TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM WorkflowsOrganizations
authored 6
papers 19 days ago
NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime
Paper • 2610.10787 • Published • 5
TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
Paper • 2610.02959 • Published • 3
Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation
Paper • 2606.03175 • Published
VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation agents
Paper • 2512.24851 • Published
NavHarness: Towards Lifelong Embodied Navigation
Paper • 2609.34276 • Published • 4
upvoted a paper 19 days ago
submitted a
paper to Daily Papers 19 days ago
updated 2
models 22 days ago
updated a
dataset 22 days ago
published 2
models 27 days ago
liked a
dataset 27 days ago
published a
dataset 27 days ago
upvoted 5
papers 28 days ago
NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models
Paper • 2305.16986 • Published • 1
WebVLN: Vision-and-Language Navigation on Websites
Paper • 2312.15820 • Published • 1
NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
Paper • 2402.15852 • Published • 1
Embodied Navigation Foundation Model
Paper • 2509.12129 • Published • 1
Learning Goal-Oriented Language-Guided Navigation with Self-Improving Demonstrations at Scale
Paper • 2509.24910 • Published • 5