Picture for Xiaoyu Tian

Xiaoyu Tian

DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models

Add code
Feb 25, 2024
Figure 1 for DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
Figure 2 for DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
Figure 3 for DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
Figure 4 for DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
Viaarxiv icon

From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models

Add code
Jan 05, 2024
Viaarxiv icon

DUMA: a Dual-Mind Conversational Agent with Fast and Slow Thinking

Add code
Oct 30, 2023
Viaarxiv icon

GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training

Add code
May 15, 2023
Viaarxiv icon

Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving

Add code
Apr 27, 2023
Figure 1 for Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving
Figure 2 for Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving
Figure 3 for Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving
Figure 4 for Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving
Viaarxiv icon

VectorFlow: Combining Images and Vectors for Traffic Occupancy and Flow Prediction

Add code
Aug 09, 2022
Figure 1 for VectorFlow: Combining Images and Vectors for Traffic Occupancy and Flow Prediction
Figure 2 for VectorFlow: Combining Images and Vectors for Traffic Occupancy and Flow Prediction
Figure 3 for VectorFlow: Combining Images and Vectors for Traffic Occupancy and Flow Prediction
Viaarxiv icon

Unsupervised Learning of 3D Scene Flow from Monocular Camera

Add code
Jun 08, 2022
Figure 1 for Unsupervised Learning of 3D Scene Flow from Monocular Camera
Figure 2 for Unsupervised Learning of 3D Scene Flow from Monocular Camera
Figure 3 for Unsupervised Learning of 3D Scene Flow from Monocular Camera
Figure 4 for Unsupervised Learning of 3D Scene Flow from Monocular Camera
Viaarxiv icon