Hi. My name is Ali Rahimian, and these are some highlights from my CV:
- Honorable Mention – 17th ACM ICPC Asia Tehran Regional Contest (Nov 2019)
- 2nd Place – JCAL Programming Contest (May 2018)
- 3rd Place – Sharif ICT Fintech Hackathon (Aug 2019)
- 4th Place – Sharif Obfuscated C Code Contest (Dec 2019)
- 10th Place – JavaCup Programming Contest (Oct 2019)
Selected Repositories
-
Fibottention – Wythoff/Fibonacci sparse attention cutting ViT self-attention from
$O(N^2)$ to$O(N \log N)$ - TruthLens – Training-free deepfake data verification via VQA-style probing of vision-language models; ICML 2025
- Sparxiv – Spark recommender over 3M+ arXiv papers: Parquet ETL, MLlib TF-IDF, CSR top-k search
- CTRL – Cross-task RL with PPO transfer, Reptile meta-learning, and EWC continual learning
- Jaga – A Java game development framework for Android
Machine Learning and Efficient Transformer Models
- sparse-attention-benchmark-suite – Sparse attention for ViTs at ~2% of dense FLOPs, benchmarked across 10 mechanisms
- vgg-magnitude-pruning – PyTorch implementation of Han et al. magnitude pruning on VGG
- linear-quantization-from-scratch – Linear quantization in PyTorch from first principles, down to int8 multiply + int32 accumulate
- transformer-encoder-from-scratch – Transformer encoder in PyTorch, built up from scaled dot-product attention to a full stack
- accelerated-gradient-methods – Accelerated gradient methods: Momentum, Nesterov, and when theory misbehaves
- gradient-descent-convergence – Gradient descent variants compared across quadratic, nonconvex, and least-squares tasks
- closed-form-ridge-regression – Ridge vs. OLS via normal equations: log-spaced λ sweep with pairwise interaction features
- logistic-regression-naive-bayes – Multiclass logistic regression (GD/IRLS) and Gaussian/Bernoulli Naive Bayes from scratch
- nonlinear-2d-classifier – Two-layer classifier from scratch: manual backprop, gradient checks, nonlinear 2D boundaries
- genetic-simulated-annealing-optimization – Genetic & simulated annealing optimization
Computer Vision & Deep Learning
- watershed-image-segmentation – Image segmentation with Watershed algorithm
- oneshot-openclip-tta – One-Shot Classification with OpenCLIP + Test-Time Prototype Adaptation
- moco-joint-ssl-training – SSL-First Image Classification (MoCo + Joint Optimization)
- vit-transfer-learning-pipeline – Transfer Learning for Maximum Accuracy: ViT Fine-Tuning Pipeline
- mnist-simplenet-pytorch – MNIST SimpleNet with PyTorch
- opencv-tracking-algorithms – Real-time tracking (CAMShift, Lucas-Kanade, KCF, etc.)
- realtime-facial-keypoint-detection – Real-time keypoint detection (face, eyes, edges)
- hand-segmentation-convex-hull – Hand segmentation & finger counting with convex hull
- keras-cnn-classifier – CNN for image classification (TensorFlow/Keras, MNIST)
Deep Reinforcement Learning & Game Theory
- carracing-ppo – CarRacing PPO (Gymnasium + Stable-Baselines3)
- pong-dqn – Pong DQN: Deep Q-Learning on Atari Pong
- frozenlake-qlearning – FrozenLake Q-Learning
- lunarlander-ppo – LunarLander Proximal Policy Optimization
- lunarlander-dqn-per-noise – LunarLander DQN: Prioritized Replay + Parameter Noise
- pacman-pathfinding – Pac-Man RL agent with BFS/DFS/A* heuristics
- alpha-beta-pruning – Optimal decision-making with minimax pruning
Distributed & Cloud Computing
- aws-serverless-data-analytics-pipeline – AWS Serverless Data Analytics Pipeline
- aws-ecommerce-analytics-s3-glue-athena-pipeline – AWS E-Commerce Analytics Pipeline (S3 • Glue • Athena)
- spark-structured-streaming – Ride Sharing Analytics Using Spark Structured Streaming & Spark SQL
- spark-music-streaming-analysis – Music Streaming Analysis Using Spark Structured APIs
- jaccard-mapreduce – Jaccard Similarity with Hadoop MapReduce
Parallel Computing
- cuda-openmp-nbody-simulation – Sequential, OpenMP, and CUDA N-body simulations
- cuda-openmp-nbody-simulation – Parallel N Body Simulation: Sequential, OpenMP, and CUDA Implementations
- cuda-h2d-d2h-bandwidth-study – CUDA H2D/D2H Bandwidth Study
- mergesort-parallelization-study – Merge Sort: Parallelization Study
- prefixsum-openmp-benchmark – Parallel Prefix Sum With OpenMP
- rapid-data-processing – Rapid transaction data processing with SQLite
- blockchain-transaction-concurrency – Blockchain transaction concurrency
Algorithms & Competitive Programming
- competitive-programming – ACM-ICPC problems & algorithm design
- Profiles
- Codeforces: https://codeforces.com/profile/Ali811
- Timus Online Judge: https://acm.timus.ru/author.aspx?id=238630
Software Development
- Jaga – A 2D/3D Android game development framework
- EZpark – Campus parking spot availability app
- tcp-socket-messenger – TCP-based messenger
- aes-encryption – AES encryption/decryption
- tfidf-ngram-search-engine – Local search engine with TF-IDF and n-grams
- infinity-bot – Large-scale Discord community bot with ~300 Python modules across 72 independently loadable extensions




