Shengyuan Liu

Data Scientist

https://talent.gravityer.com/shengyuan-liu

Stay Hungry, Stay Foolish

CUHK

Key Strengths

Extensive experience in medical image analysis and vision-language models, highly relevant for a Data Scientist role in specialized domains.
Strong publication record indicated by multiple projects referencing NeurIPS, ICRA, MICCAI, and CVPR, suggesting research capabilities.
Proficiency in Python, Jupyter Notebook, and Shell scripting, essential tools for data science and machine learning.
Demonstrated ability to work on complex, multi-modal data challenges as seen in projects like OmniBrainBench and MedPruner.

Cultural & Operational Fit

Cultural Fit Analysis

The candidate's projects are heavily concentrated in medical imaging and vision-language models, indicating a strong research-oriented profile. While this depth is valuable, the lack of diversity in project domains outside of medical AI might suggest a narrower scope of interest or experience, potentially impacting cultural fit in a broader data science team without a specific medical focus. The single listed experience as 'Data Scientist' at CUHK aligns with the target role.

Soft Skills & Operational Fit

Insufficient data to assess soft skills or operational fit. No psychometric test results or interview feedback provided.

AI is analyzing your overall score…

Identifying your key strengths…

Evaluating your skill match against the job requirements…

Assessing your cultural and operational fit

Projects

MedPruner

June 14, 2026 – Present

[MICCAI 2026] MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models

View Project

NeuroClaw

March 25, 2026 – Present

NeuroClaw — GitHub repository

View Project

MedSAM-Agent

February 3, 2026 – Present

MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning

View Project

OmniBrainBench

October 31, 2025 – Present

[CVPR 2026] OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks

View Project

medical-llm-reasoning-survey

August 3, 2025 – October 17, 2025

A curated list of medical reasoning research on large language models, organized by modality, technique, application, and benchmark.

View Project

saint-lsy.github.io

July 24, 2025 – Present

saint-lsy.github.io — GitHub repository

View Project

Med-VLM-Bench-Summary

June 10, 2025 – Present

A Curated Benchmark Repository for Medical Vision-Language Models

View Project

EndoBench

May 11, 2025 – Present

[NeurIPS'25] EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis

View Project

SE-Guidance

November 8, 2024 – November 8, 2024

SE-Guidance — GitHub repository

View Project

Polyp-Gen

September 12, 2024 – Present

[ICRA 2025] Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion

View Project

Key Strengths

Extensive experience in medical image analysis and vision-language models, highly relevant for a Data Scientist role in specialized domains.
Strong publication record indicated by multiple projects referencing NeurIPS, ICRA, MICCAI, and CVPR, suggesting research capabilities.
Proficiency in Python, Jupyter Notebook, and Shell scripting, essential tools for data science and machine learning.
Demonstrated ability to work on complex, multi-modal data challenges as seen in projects like OmniBrainBench and MedPruner.

Cultural & Operational Fit

Cultural Fit Analysis

Soft Skills & Operational Fit

Insufficient data to assess soft skills or operational fit. No psychometric test results or interview feedback provided.

Shengyuan Liu

Key Strengths

Cultural & Operational Fit

Top Skills

Skills

Experience

Projects

Key Strengths

Cultural & Operational Fit