Yixuan Pan's Blog

09-08

旋转

09-08

Pixel2Mesh

08-28

Survey: Open Vocabulary 3D Scene Understanding

08-28

Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models

08-27

BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs

08-10

Review of Large Vision Models and Visual Prompt Engineering

08-08

CoWs on PASTURE: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation

08-08

Prior Exploration

08-07

USA-Net: Unified Semantic and Affordance Representations for Robot Memory

08-07

BEVBert: Multimodal Map Pre-training for Language-guided Navigation