This AI fact-checking system, built with LangGraph, dissects text into verifiable claims, cross-referencing them with real-world evidence via web searches. It then generates detailed accuracy reports, ideal for combating misinformation in LLM outputs, news, or any text.

chromaVive turns grayscale images into vibrant, colorized versions using advanced deep learning inspired by Richard Zhang's research at UC Berkeley. Powered by models from the ECCV16 and SIGGRAPH17 papers, chromaVive advances the art of image colorization.

This is a Research Paper implementation of Levi-Hessaner Age-Gender Classification model which has re-implemented and trained on Indian faces.

From-scratch, paper-faithful PyTorch implementation of DeepSeek-V4 core architecture for transparent study, testing, ablation, and mini-scale training.

Data structures & algorithms project for implementing the Hilbert R Tree data structure as present in the original research paper, focusing on the adding of elements and searching of elements along with a pre-order traversal of the tree.

End-to-End Python implementation of CompactPrompt (Choi et al., 2025): a unified pipeline for LLM prompt and data compression. Features modular compression pipeline with dependency-driven phrase pruning, reversible n-gram encoding, K-means quantization, and embedding-based exemplar selection. Achieves 2-4x token reduction while preserving accuracy.

Implement the DeepSeek-V4 architecture from scratch using PyTorch for efficient research, controlled ablations, and study of sparse MoE and long-context mechanisms.

From-scratch PyTorch implementation of the Gated Attention mechanism for transformer architectures, focusing on efficient sequence modeling and attention optimization.

QueensGambit is a Python-based chess engine using the Minimax algorithm with alpha-beta pruning to make optimal moves. It incorporates piece values inspired by AlphaZero and an entropy-based evaluation for dynamic gameplay. The engine supports both human-AI and AI-AI matches.

End-to-End Python implementation of Semantic Divergence Metrics (SDM) for LLM hallucination detection. Uses ensemble paraphrasing, joint embedding clustering, and information-theoretic measures (JSD, KL divergence, Wasserstein distance) to quantify prompt-response semantic consistency. Based on Halperin (2025).

Production implementation of OPRO (Wei et al., 2023) — gradient-free prompt optimization via LLM-as-optimizer. Implements p* = argmax f(p) over discrete natural language space. Built from the paper, no prompt libraries. arXiv:2309.03409

This project is my PyTorch reproduction of PaliGemma, a compact 3B vision–language model that integrates SigLIP vision features with a Gemma decoder. I implemented the full multimodal pipeline from vision encoding to autoregressive text generation to study modern VLM architectures from a research perspective.

📈 Analyze how rumors affect investment decisions using a qualitative reasoning engine for better outcomes and informed choices.

End-to-End Python implementation of Mancilla et al.'s (2026) methodology for solving the direct indexing portfolio selection problem as quantum combinatorial optimization. Enforces cardinality constraints via subspace confinement. Benchmarks PennyLane quantum circuits against D-Wave simulated annealing & HRP baselines with walk-forward backtesting.

C++ tool for linear code analysis using Gröbner bases. Computes leader codewords, tests code equivalence, and analyzes automorphism groups based on recent coding theory research.

Hands-on study of Srinivas et al. AI-Augmented SOC research (MDPI Informatics 2025). Original implementation by Abdul Bari — attribution preserved per Apache 2.0.

End-to-End Python implementation of a bankruptcy prediction method which adapts Altman's Z-Score to Compositional Data Analysis (Keivani et al., 2026). Benefits: Uses the Aitchison simplex to eliminate outliers & asymmetry in financial ratios. Pipeline: log-ratio EM imputation, pairwise log-ratios, ML classifiers (Logit/k-NN/RF), validation.

noisOut is a DDPM-based implementation for generating high-quality images, inspired by Dhariwal & Nichol (2021) and Ho et al. (2020). Using a UNet architecture with Sinusoidal Position Embeddings, the model learns to reverse a diffusion process, progressively removing noise from images.

This project is a clean, from-scratch implementation of a GPT-2 style autoregressive transformer built using PyTorch. Unlike character-level toy models, this implementation operates on tokenized text (via tiktoken) and supports modern training features.

Graph-informed U-Net with GCN fusion for floor plan generation — implementation of arXiv:2407.10121