# **Sen Yang's Personal Website**

## About Me
- **Computer Vision & MLLM Researcher**
- Research Interests
  - Multimodal Large Language Models for Understanding
  - Autonomous Driving with Map construction and VLMs
  - 2D & 3D Human Pose Estimation

## Education
- **Ph.D.**: Southeast University (2019.5-2023.3)
- Master: Southeast University (2017.9-2019.1)
- Bachelor: Jilin University (2013.9-2017.7)

## Work Experience
- **Baidu VIS Senior R&D Engineer** (2023.7-Present)
- Tencent TPG Intern (2021.12-2022.8)
- Megvii Intern (2021.1-2021.10)

## Research Publications
- **Autonomous Driving**
  - TopoSD
  - MGMapNet
  - HisTrackMap
- **Multimodal Large Models**
  - Vision Remember
  - MomentSeg
  - EM-KD
- **Human Pose Estimation**
  - TransPose
  - SimCC
  - TokenPose
  - Capturing the 3D motion of every joint
  - Detecting and grouping keypoints

## Technical Stack
- **Multimodal Large Models**
  - Visual Grounding & Referring Segmentation
  - Video Understanding & Temporal Reasoning
  - Post-Training: CoT, cold-start SFT, RL
  - Efficient Token Compression
- **Autonomous Driving Perception**
  - BEV Mapping & Temporal Fusion
  - Vision-Map Multimodal Fusion
  - Topology Prediction & Probabilistic Planning
- **Engineering & Systems**
  - Large-scale Distributed Training
  - GPU / Ascend NPU Heterogeneous Computing
  - Model Optimization & Deployment

## Contact Information
- Email: yangsenius@gmail.com
- Blog: senyang-ml.github.io
- Google Scholar Profile