Hi, my name is Ali Rahimian, and I'm a graduate research assistant at the Charlotte Machine Learning Lab (CharMLab), where I work on sparse attention, efficient Transformer models, and visual representation learning.
Some highlights from my CV:
- 2nd Place — JCAL Programming Contest (May 2018)
- 3rd Place — Sharif ICT Challenge (Aug 2019)
- 4th Place — Sharif Spaghetti Programming Contest (Dec 2019)
- 10th Place — JavaCup Programming Contest (Oct 2019)
- 31st Place — Mobile Programming Marathon (Sep 2019)
- Certificate of Achievement — 17th ACM ICPC (Nov 2019)
- fibottention — Inceptive Visual Representation Learning with Diverse Attention Across Heads
- truthlens — TruthLens: Training-Free Data Verification for Deepfake Images via VQA-style Probing (ICML 2025)
- sparse-attention-benchmarks — A Comprehensive Benchmark of Sparse Attention Mechanisms in Vision Transformers
- attention-is-all-you-need — Attention Is All You Need: A PyTorch Implementation from Scratch
- fine-grained-pruning — Fine-grained Pruning
- linear-quantization-vgg — Linear Quantization
- sparxiv — A Spark-Based Recommender System for arXiv
- 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
- hadoop-mapreduce-wordcount — Hadoop-MapReduce-WordCount
- docker — Flask + Redis with Docker Compose
- docker-containers — Docker Containers
- watershed — 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.)
- ira — Real-time keypoint detection (face, eyes, edges)
- hsfc — Hand segmentation & finger counting with convex hull
- kcnn — CNN for image classification (TensorFlow/Keras, MNIST)
- 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
- competitive-programming — ACM-ICPC problems & algorithm design
- data-processing — Fast transaction data processing with SQLite
- parallel-computation — Blockchain transaction concurrency
Competitive Programming Profiles
- Codeforces: https://codeforces.com/profile/Ali811
- Timus Online Judge: https://acm.timus.ru/author.aspx?id=238630
- alpha-beta-pruning — Optimal decision-making with minimax pruning
- pacman-pathfinding— Pac-Man RL agent with BFS/DFS/A* heuristics
- jina — Genetic & simulated annealing optimization
- tcp-socket — TCP-based messenger
- aes-encryption — AES encryption/decryption