Tianrui Guan
Research Engineer at University of Maryland
College Park, Maryland, United States
Summary
👤
Senior🎓
Top SchoolTianrui Guan is a research engineer with nine years of experience at the intersection of perception, trajectory prediction, and robotic navigation, currently advancing trajectory prediction for autonomous vehicles on Waymo’s Prediction & Planning team. He holds a Ph.D. in Computer Science from the University of Maryland, where he built end-to-end frameworks like TrackNPred and integrated perception algorithms into navigation systems that handle dynamic obstacles. Tianrui has industry experience applying AI to consumer robotics at Amazon Lab126 and multiple research internships at Baidu, demonstrating an ability to translate academic research into product-focused solutions. Known for combining rigorous academic research with hands-on system integration, he brings deep expertise in object detection, tracking, and VLM-driven scene understanding to safety-critical, real-world driving problems.
9 years of coding experience
1 year of employment as a software developer
The University of Maryland, College ParkDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of MarylandShandong Experimental High School
Chinese, English
Github Skills (78)
attention-mechanism10
3d-object-detection10
self-attention10
kitti-dataset10
transformer-architecture10
computer-vision9
transformer-models9
prediction9
spectral9
semantic-segmentation9
point-cloud9
transformer8
object-detection8
theory8
deep-learning8
Programming languages (3)
Github contributions (5)
rayguan97/M3DETR
Apr 2021 - Aug 2022
Code base for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
Contributions:14 commits, 4 PRs, 36 pushes in 1 year 3 months
3d-object-detectiondeep-learningkitti-datasetobject-detectionpoint-cloud
tianyi-lab/HallusionBench
Oct 2023 - Feb 2025
HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models
Contributions:1 PR, 42 pushes, 1 branch in 1 year 4 months
benchmarkbenchmarksgpt-4gpt-4vhallucination
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.