Ruyi Yang

Multimodal AI

Favela 4D: Deep Learning for Slum Expansion Analysis • Utilized deep learning approaches to analyze satellite imagery data, monitoring the three-dimensional expansion of favelas in Rio de Janeiro. • Spearheaded outward expansion analysis by benchmarking semantic segmentation models (Unet/ResUnet/Segformer) on satellite imagery, achieving 79% IoU accuracy (benchmark: ~75%). Testing deep learning, unsupervised, and generative AI methods . • Developed an LSTM-based time series prediction model using 20-year favela boundary data (1999-2019) to predict expansion trends, enabling data-driven urban planning decisions. • Collaborated with Lidar members to develop 3D expansion segmentation through satellite-point cloud fusion. Metabolic Walking: Computer Vision for Pedestrian Behavior Analysis Under Varying Weather Conditions • Trained a shadow detection segmentation model with 95% accuracy, enabling precise classification of shaded areas in urban environments. • Developed an automated pedestrian tracking model to extract movement patterns (walking speed, presence in shaded areas, demographic attributes), providing quantitative insights on pedestrian behavior in relation to shade. • Analyzed pedestrian response to shading infrastructure under varying weather conditions, supporting adaptive urban design and mobility policy.

• Developed comprehensive ROI analysis frameworks for TikTok Shop (US, UK, SEA markets), processing data from 100M+ DAUs to optimize $50 million budget allocations, significantly improving ROI measurement accuracy through advanced SQL and Python implementations. • Designed and implemented advanced machine learning models (including PSM & LightGBM) to quantify user tier-upgrade impacts, achieving 90% prediction accuracy, and developed a multi-dimensional measurement to estimate customer lifetime value (LTV), supporting long-term ROI optimization and financial forecasting. • Spearheaded the development of automated ROI tracking dashboards for SEA markets, enabling real-time monitoring of key metrics and facilitating data-driven strategy optimization that led to a ~10%increase in GMV and a 12% reduction in CAC.

MIT Media Lab, City Science Group • Developed front-end interfaces for a carbon footprint tracking DApp Green Commute using React Native, applied Redux for store management and Resso for smooth animated interactions. • Refined time-series input, feature engineering, and loss function configuration for LSTM models to segment and classify user transportation patterns, achieving 70% accuracy on labeled trajectory datasets. • Engaged in user carbon footprint analysis research and devised strategies for efficient sensor data collection pathways.

AI Industry Landscape Analysis • Analyzed active user churn and growth of AI apps using App Annie data to understand market dynamics. • Tracked investments in AI startups on Crunchbase to identify key business models, highlighting ongoing interest in model/infrastructure layers. • Monitored industry-leading advancements in AI, particularly from OpenAI (GPTs), Anthropic, Stability AI and tech giants. Cross-border E-commerce Opportunities Analysis • Analyzed economic and cross-border e-commerce opportunities in Spain, Poland and Indonesia based on 50,000+ data records from multiple sources including Euromonitor and Trademap. • Identified key features including import/export, marketing channels, product categories, brand concentration and changes. • Utilized Jaccard similarity and matrix in Python for brand similarity analysis across 5 major European countries.

AC215 LLMLOps, AILOps

Multimodal AI Advance NLP Deep Learning Algorithms AI, Decision Making and Society

Tongji Academic Star Award (Top 0.05%) Shanghai Outstanding Graduates (Top 0.1%) National Scholarship (Top 1%) AI related courses: Data Engineering, Machine Learning, Intelligent Robotics, Integrated Design, Quantitative Reasoning, Artificial Intelligence Programming Framework, Virtual Reality, Visualization, Introduction to IoT

Leveraged deep learning and computer vision to tackle urban challenges. The first undergraduate visiting student/researcher at MIT Senseable City Lab

First Prize in Olympics Physics Competition