Picture for Bin Dai

Bin Dai

DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving

May 07, 2024
Viaarxiv icon

Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level

Apr 08, 2024
Figure 1 for Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level
Figure 2 for Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level
Figure 3 for Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level
Figure 4 for Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level
Viaarxiv icon

AgentAvatar: Disentangling Planning, Driving and Rendering for Photorealistic Avatar Agents

Add code
Dec 04, 2023
Viaarxiv icon

Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM

Add code
Sep 15, 2023
Figure 1 for Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM
Figure 2 for Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM
Figure 3 for Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM
Figure 4 for Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM
Viaarxiv icon

UniWorld: Autonomous Driving Pre-training via World Models

Add code
Aug 14, 2023
Figure 1 for UniWorld: Autonomous Driving Pre-training via World Models
Figure 2 for UniWorld: Autonomous Driving Pre-training via World Models
Figure 3 for UniWorld: Autonomous Driving Pre-training via World Models
Figure 4 for UniWorld: Autonomous Driving Pre-training via World Models
Viaarxiv icon

Controlling Character Motions without Observable Driving Source

Aug 11, 2023
Figure 1 for Controlling Character Motions without Observable Driving Source
Figure 2 for Controlling Character Motions without Observable Driving Source
Figure 3 for Controlling Character Motions without Observable Driving Source
Figure 4 for Controlling Character Motions without Observable Driving Source
Viaarxiv icon

Contrastive Label Disambiguation for Self-Supervised Terrain Traversability Learning in Off-Road Environments

Jul 06, 2023
Figure 1 for Contrastive Label Disambiguation for Self-Supervised Terrain Traversability Learning in Off-Road Environments
Figure 2 for Contrastive Label Disambiguation for Self-Supervised Terrain Traversability Learning in Off-Road Environments
Figure 3 for Contrastive Label Disambiguation for Self-Supervised Terrain Traversability Learning in Off-Road Environments
Figure 4 for Contrastive Label Disambiguation for Self-Supervised Terrain Traversability Learning in Off-Road Environments
Viaarxiv icon

Traversability Analysis for Autonomous Driving in Complex Environment: A LiDAR-based Terrain Modeling Approach

Jul 05, 2023
Figure 1 for Traversability Analysis for Autonomous Driving in Complex Environment: A LiDAR-based Terrain Modeling Approach
Figure 2 for Traversability Analysis for Autonomous Driving in Complex Environment: A LiDAR-based Terrain Modeling Approach
Figure 3 for Traversability Analysis for Autonomous Driving in Complex Environment: A LiDAR-based Terrain Modeling Approach
Figure 4 for Traversability Analysis for Autonomous Driving in Complex Environment: A LiDAR-based Terrain Modeling Approach
Viaarxiv icon

PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm

Jun 11, 2023
Figure 1 for PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm
Figure 2 for PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm
Figure 3 for PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm
Figure 4 for PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm
Viaarxiv icon

Occ-BEV: Multi-Camera Unified Pre-training via 3D Scene Reconstruction

Add code
Jun 07, 2023
Figure 1 for Occ-BEV: Multi-Camera Unified Pre-training via 3D Scene Reconstruction
Figure 2 for Occ-BEV: Multi-Camera Unified Pre-training via 3D Scene Reconstruction
Figure 3 for Occ-BEV: Multi-Camera Unified Pre-training via 3D Scene Reconstruction
Figure 4 for Occ-BEV: Multi-Camera Unified Pre-training via 3D Scene Reconstruction
Viaarxiv icon