alexdotham Goto Github PK

Embodied Intelligence, Autonomous driving, Multimodal Models, Object Tracking

• P.G. in Software Engineering, 2022-2025 (expected)
  • Xi’an Jiaotong University, advised by Associate Prof. Xing Wei
• B.Eng. in Computer Science and Technology, 2018-2022
  • Xidian University, School of Computing (GPA 3.9/4.0, ranked 2st)

• Intern in Autonomous Driving at the Foundation Model Group of Megvii Technology. 2023.12 --- 2024.05
  • Main Work: The application of 3D perception in multimodal large models for autonomous driving.
• Intern in Embodied Intelligence at the Visual Technology Center of Alibaba DAMO Academy. 2024.05 --- Now
  • Main Work: The application of temporal understanding and task decomposition in multimodal large models for embodied intelligence.

• Is a 3D-Tokenized LLM the Key to Reliable Autonomous Driving?
  • Arxiv
• ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe
  • Accepted by CVPR 2024
• Autoregressive Visual Tracking
  • Accepted by CVPR 2023 Highlight (Top 2.5%)

• School Email: [email protected]
• Personal Email: [email protected]
• WeChat: yfbaiyry1008
• QQ: 826980835