Skip to content
View adityaravi9034's full-sized avatar
๐ŸŽฏ
Focusing
๐ŸŽฏ
Focusing

Block or report adityaravi9034

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
adityaravi9034/README.md

๐Ÿง  Aditya Ravi

Dynamic Title

B.Sc. Artificial Intelligence | Universitร  degli Studi di Pavia
๐Ÿ“ Pavia, Italy | ๐ŸŽ“ Expected Graduation: February 2026

LinkedIn Email GitHub


About Me

I am a final-year AI undergraduate with four research internships spanning diverse domains from temporal graph neural networks for financial prediction to multimodal deep learning for cancer immunotherapy. My research journey reflects a deliberate exploration toward understanding principled machine learning methods that bridge theoretical foundations with real-world impact.

Currently focused on computational biology and healthcare AI, I'm particularly interested in deep generative models, multimodal data integration, and uncertainty quantification in high-dimensional biological systems.

"Each project was a step toward understanding not just how to apply machine learning, but what fundamental principles govern effective learning from complex data."


๐Ÿ”ฌ Research Connection Map

flowchart TD
    subgraph Theory[" ๐Ÿงฎ THEORETICAL FOUNDATIONS "]
        DM[Diffusion Models<br/>Statistical Physics & ML<br/>Prof. Gherardi - UniMi]
    end
    
    subgraph Methods[" โš™๏ธ METHOD DEVELOPMENT "]
        TGCN[Temporal Graph Networks<br/>Financial Prediction<br/>Prof. Zignani - UniMi]
        CGM[CGM Validation<br/>Pediatric Obesity Study<br/>Prof. Aiello - UniPV]
    end
    
    subgraph Application[" ๐ŸŽฏ CLINICAL APPLICATION "]
        MMIO[Multimodal Immunotherapy<br/>NSCLC Prediction<br/>Dr. Miskovic - PoliMi]
    end
    
    subgraph Synthesis[" ๐Ÿ’ก RESEARCH SYNTHESIS "]
        PHD[ Research Vision<br/>Principled ML for<br/>Computational Sciences ]
    end

    DM -->|Training dynamics| MMIO
    TGCN -->|Structured data| MMIO
    CGM -->|Biomedical knowledge| MMIO
    
    DM -->|Theory| PHD
    TGCN -->|Graphs| PHD
    CGM -->|Clinical| PHD
    MMIO -->|Multimodal| PHD
Loading
๐Ÿ“Š How My Research Connects (Click to Expand)
Research Area Key Learning Connection to Academic Goals
Temporal GNNs (Finance) Structured data, multi-relational graphs, distribution shift Foundation for biological graph representations
CGM Validation (Healthcare) Clinical validation, inter-individual variability, real-world data challenges Domain expertise in healthcare AI
Diffusion Models (Theory) Training dynamics, noise schedules, closed-loop learning Theoretical understanding of generative models
Multimodal Cancer ML (Application) Cross-modal fusion, uncertainty propagation, interpretability Integration of all previous learnings

๐ŸŽ“ Current Research Positions

๐Ÿงฌ AI-ON-LAB, Politecnico Milano

Research Intern | Nov 2025 - Present
Supervisor: Dr. Vanja Miskovic

Developing multimodal ML approaches for predicting immunotherapy efficacy in Non-Small Cell Lung Cancer:

  • Transformer-based fusion architectures
  • Contrastive alignment for clinical + genomic + imaging data
  • SHAP-based interpretability analysis

โš›๏ธ Statistical Physics & ML Group, UniMi

Research Intern | Oct 2025 - Present
Supervisor: Prof. Marco Gherardi

Investigating closed-loop learning dynamics in diffusion-based generative models:

  • PyTorch implementation of diffusion models
  • Analysis of noise schedules and coupling parameters
  • Statistical physics perspective on ML theory

๐Ÿฉบ ICDS Lab, University of Pavia

Research Intern | May 2025 - Nov 2025
Supervisor: Prof. Eleonora Maria Aiello

CGM validation study in pediatric obesity:

  • Temporal alignment of CGM vs plasma glucose
  • MARD, Bland-Altman, and Error Grid analysis
  • Clinical classification impact assessment

๐Ÿ“ˆ University of Milan, CS Dept

Research Intern | Oct 2024 - May 2025
Supervisor: Prof. Matteo Zignani

Temporal Graph Neural Networks for NASDAQ prediction:

  • Relational TGCN implementation
  • Multi-relational edge construction
  • Hyperparameter optimization & ranking systems

๐Ÿ“ Academic Presentations & Output

Conference-Style Presentations

  • ๐ŸŽค "A Vision-Language Foundation Model for Precision Oncology" (Nature, 2025) - AI-ON-LAB weekly meeting
  • ๐ŸŽค "Heat Death of Generative Models in Closed-Loop Learning" - Gherardi Group seminar
  • ๐ŸŽค "Predicting Changes in Glycemic Control from Wearable Device Data" - Medical Applications course

Publications & Manuscripts

  • ๐Ÿ“„ CGM vs OGTT Comparative Analysis - Expected submission Spring 2026
  • ๐Ÿ“„ Bachelor's Thesis: Glucose Response Patterns Based on Macronutrient Composition

๐Ÿ› ๏ธ Technical Stack

Core Languages & ML Frameworks

Python PyTorch R SQL

ML & Data Science

Scikit Learn NumPy Pandas PyTorch Geometric

Visualization & Tools

Matplotlib Git LaTeX Jupyter

Specialized Skills

๐Ÿง  Deep Learning: CNNs, Transformers, VAEs, Diffusion Models, Graph Neural Networks
๐Ÿ“Š Statistical Methods: Bayesian Inference, Survival Analysis, Clinical Validation Metrics
๐Ÿ”ฌ Domains: Computational Biology, Healthcare AI, Quantitative Finance

๐ŸŽฏ Research Interests & Focus

flowchart LR
    subgraph CB[" ๐Ÿงฌ Computational Biology "]
        CB1[Single-cell Analysis]
        CB2[Spatial Omics]
        CB3[Perturbation Prediction]
    end
    
    subgraph DGM[" ๐ŸŽฒ Deep Generative Models "]
        DGM1[Diffusion Models]
        DGM2[VAEs]
        DGM3[Flow Matching]
    end
    
    subgraph ML[" ๐Ÿ”€ Multimodal Learning "]
        ML1[Cross-modal Fusion]
        ML2[Uncertainty Propagation]
        ML3[Modality Weighting]
    end
    
    subgraph PML[" ๐Ÿ“ Probabilistic ML "]
        PML1[Causal Discovery]
        PML2[Uncertainty Quantification]
        PML3[Bayesian Methods]
    end
    
    CENTER((Research<br/>Vision))
    
    CB --- CENTER
    DGM --- CENTER
    ML --- CENTER
    PML --- CENTER
Loading

Core Questions I'm Pursuing:

  • How should we weight different modalities when they provide conflicting signals?
  • What inductive biases are appropriate for cross-modal representation learning?
  • How do we rigorously quantify uncertainty when integrating heterogeneous biological data?

๐Ÿ“ซ Let's Connect

I'm actively looking to work in Machine Learning, Computational Biology, and AI for Healthcare.

Open to discussing research collaborations, opportunities, and innovative applications of ML in biology and medicine.

Email: adityaravu@gmail.com
LinkedIn: linkedin.com/in/aditya-ravi-a3aab11b6
Location: Pavia, Italy ๐Ÿ‡ฎ๐Ÿ‡น


Profile Views

"Bridging theoretical ML research with principled applications in computational biology"

Pinned Loading

  1. Machine-Learning-for-Physical-Systems Machine-Learning-for-Physical-Systems Public

    Laboratory of Machine Learning Applied to Physical Systems

    Jupyter Notebook

  2. Lab-of-Machine-Learning Lab-of-Machine-Learning Public

    A comprehensive collection of machine learning laboratories covering audio processing, computer vision, sequence modeling, and generative models

    Jupyter Notebook

  3. Labs-of-Medical-Applications-Healthcare Labs-of-Medical-Applications-Healthcare Public

    Laboratory of Machine Learning

  4. portfolio-optimizer portfolio-optimizer Public

    Python

  5. snake-rl-qlearning snake-rl-qlearning Public

    JavaScript

  6. trustlens trustlens Public

    TypeScript