Picture for Wenxiao Zhang

Wenxiao Zhang

CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework

Add code
Mar 05, 2025
Viaarxiv icon

SafeEmbodAI: a Safety Framework for Mobile Robots in Embodied AI Systems

Add code
Sep 03, 2024
Viaarxiv icon

A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems

Add code
Aug 07, 2024
Figure 1 for A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems
Figure 2 for A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems
Figure 3 for A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems
Figure 4 for A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems
Viaarxiv icon

OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents

Add code
Aug 06, 2024
Figure 1 for OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents
Figure 2 for OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents
Figure 3 for OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents
Figure 4 for OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents
Viaarxiv icon

Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion

Add code
Jul 03, 2024
Figure 1 for Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion
Figure 2 for Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion
Figure 3 for Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion
Figure 4 for Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion
Viaarxiv icon

Embodied AI in Mobile Robots: Coverage Path Planning with Large Language Models

Add code
Jul 02, 2024
Figure 1 for Embodied AI in Mobile Robots: Coverage Path Planning with Large Language Models
Figure 2 for Embodied AI in Mobile Robots: Coverage Path Planning with Large Language Models
Figure 3 for Embodied AI in Mobile Robots: Coverage Path Planning with Large Language Models
Figure 4 for Embodied AI in Mobile Robots: Coverage Path Planning with Large Language Models
Viaarxiv icon

Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models

Add code
Jun 05, 2024
Figure 1 for Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models
Figure 2 for Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models
Figure 3 for Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models
Figure 4 for Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models
Viaarxiv icon

Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning

Add code
Mar 15, 2024
Figure 1 for Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning
Figure 2 for Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning
Figure 3 for Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning
Figure 4 for Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning
Viaarxiv icon

SparseDC: Depth Completion from sparse and non-uniform inputs

Add code
Nov 30, 2023
Viaarxiv icon

DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation

Add code
Apr 21, 2022
Figure 1 for DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation
Figure 2 for DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation
Figure 3 for DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation
Figure 4 for DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation
Viaarxiv icon