Yixuan Pan's Blog

08-07

Scaling Data Generation in Vision-and-Language Navigation

08-07

Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation

07-31

Visual Language Maps for Robot Navigation

07-29

ConceptFusion: Open-set Multimodal 3D Mapping

07-29

CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory

07-28

Open-vocabulary Queryable Scene Representations for Real World Planning

07-25

3D-LLM: Injecting the 3D World into Large Language Models

07-25

Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts

07-24

PROTO-CLIP: Vision-Language Prototypical Network for Few-Shot Learning

07-23

Navigating to Objects in the Real World