Skip to content
Atlas profile

Aditya Ray

@AddyCuberVerified GitHub profile

AI-Atlas score

Advanced
0100
Strongest
Computer Vision
64.9/100 domain score
Rank
18th=
of 86
India
3rd=
of 12
  • IndiaLocation
  • 15 Nov 2026Mapped
  • 17 / 31AI projects
01Skills matrix

AI Skills Matrix

AI Skills Matrix scores, 0 to 100
Machine Learning63
Computer Vision65
Data Science63
NLP & LLMs64
AI Agents59
MLOps20

Each node is one domain, scored only from evidence in these public repositories. Select one to see why.

Substantial implementations with real depth.

02Evaluated projects6 of 17

31 public repositories → 17 with AI work, evaluated. The other 14 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected

Ranked by contribution

Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.

01
53.8

Implementation

15% of Atlas Score

ML Application· Jupyter Notebook

The repository provides an end-to-end application for analyzing pulsar timing residuals using time series models (ARIMA, ARIMAX, Prophet) with glitch events as exogenous variables. It includes data processing, model training, a REST API, and a web dashboard for visualization and forecasting.

Machine Learning0.90Data Science0.80MLOps0.20
02
54.1

Implementation

15% of Atlas Score

Educational Implementation· Python

chart

The repository implements a naive LLM generation loop (without KV cache) and sampling utilities for the Qwen2.5-0.5B-Instruct model, using Hugging Face for the forward pass. It includes benchmarking, testing, and plotting to demonstrate the performance impact of prompt length on generation speed.

NLP & LLMs0.90Machine Learning0.80Data Science0.20
03
64.1

Advanced

11% of Atlas Score

ML Application· Python

Diagram-autograder is a computer vision system that grades hand-drawn diagrams by detecting shapes, connections, and comparing structure to a reference key, providing a web interface and educational documentation.

Computer Vision0.90
04
56.0

Implementation

10% of Atlas Score

Dataset / Data Pipeline· Python

The repository implements an automated data pipeline that discovers recently funded startups hiring in tech roles by ingesting RSS feeds, enriching articles with an LLM, resolving company domains, detecting hiring signals via ATS platforms, storing results in SQLite, and publishing to Google Sheets with Telegram alerts.

Data Science0.90NLP & LLMs0.60
05
56.0

Implementation

9% of Atlas Score

Agent System· Python

The repository provides an end-to-end pipeline for generating faceless short videos using text-to-speech, automated B-roll retrieval, video editing, and auto-upload to social media platforms.

AI Agents0.90NLP & LLMs0.20
06
41.4

Implementation

9% of Atlas Score

ML Application· Python

Multi-Image Inference Grid

This repository provides a trained ResNet-18 model and inference scripts for classifying six types of steel surface defects. It showcases the use of the RailCompute autonomous training platform to identify and correct a data leakage issue in the NEU-DET dataset.

Computer Vision0.80Machine Learning0.70AI Agents0.60Data Science0.50