Semantic Code Refactorer
AI / Full-Stack Application
May 2025 – June 2025
Goal & Impact

automate intelligent, context-aware code improvements beyond syntax checking. analyzes abstract semantics to suggest and execute complex transformations — renaming, restructuring, simplification — vastly improving code quality and maintainability.

Architecture
  • Frontend: React interface for inputting code, selecting refactoring types, and reviewing changes.
  • Backend: FastAPI service handling concurrent requests with PostgreSQL for data persistence.
  • AI Core: Gemini API with advanced prompt engineering for context-aware pattern detection and semantic transformation.
Gemini API FastAPI React PostgreSQL
View on GitHub →
Multi-modal Cancer Grading Framework
Deep Learning / Medical Vision Research
May 2025 – June 2025
Goal & Impact

improved accuracy and reliability of cancer grading by integrating multiple data modalities, grounded in the principles of the "IHC Matters" research paper, developed under MMVL Lab.

Methodology
  • Model: Attention-based Multiple Instance Learning (MIL) for whole-slide imaging data.
  • Innovation: Two-stage pipeline with feature fusion and generative models for enhanced representation learning.
  • Scale: Trained and validated on a dataset of over 5,000 medical images.
PyTorch Computer Vision Multi-modal AI Generative Models
View MMVL Lab →
TSPN PyTorch Implementation
Research Module / Transformers
November 2025
Goal & Impact

high-fidelity, from-scratch implementation of the Transformer-based Set Prediction Network as a foundational and flexible module for set prediction in research-focused deep learning pipelines.

Implementation Details
  • Core: Built from fundamental PyTorch components with no high-level wrappers, ensuring maximum control over layer implementation, optimization, and debugging.
  • Application: Designed as a replaceable module within complex research architectures with emphasis on clear structure and performance on scientific datasets.
PyTorch Transformers Deep Learning NumPy
View on GitHub →
Rust Text Editor
Rust / Low-level Systems
May 2025
Goal & Impact

high-performance, from-scratch text editor in Rust focusing on low-level systems programming principles — efficiency, safety, extensibility. first major Rust project; AI assistance used for code generation and debugging.

Implementation Details
  • Core: Entire editor built from fundamental Rust components, prioritizing low-level control with no external runtime dependencies.
  • Application: Extensible editor suitable for programming and writing tasks with robust terminal rendering via crossterm.
Rust Low-level Systems crossterm
View on GitHub →
Diffused CIFAR
Diffusion Model / Deep Learning
July 2025
Goal & Impact

diffusion model built from scratch in PyTorch and trained on CIFAR, exploring core generative modeling principles at the implementation level.

Implementation Details
  • Core: Full diffusion pipeline from fundamental components — forward process, noise schedule, U-Net denoiser — no high-level wrappers.
  • Application: Serves as a flexible base for experimenting with image generation and score-based generative models.
PyTorch Deep Learning Generative Models
View on GitHub →
ZK-SNARK
Zero-Knowledge Proof / Cryptography
August 2025
Goal & Impact

basic ZK-SNARK protocol implemented in Rust using ArkWorks, primarily as a Rust learning exercise in cryptographic systems. AI assistance used for code generation and debugging.

Implementation Details
  • Core: End-to-end ZK-SNARK circuit setup, proving, and verification using the ArkWorks library.
  • Application: Usable as a base for more complex cryptographic tasks and zero-knowledge applications.
Rust ArkWorks Cryptography ZK Proofs
View on GitHub →