Autonomous AI research team: write a plan.md, spawn agents, train, verify, and deliver a clean ML repo.

Real-time TUI for monitoring cloud GPU training instances

C++/Python microstructure research engine for event-driven limit order book prediction and reproducible quantitative experiments.

Selected LLM, NLP, retrieval and vision-language research-engineering projects.

Open ML systems platform for training, profiling, evaluating, and serving AI models.

Automates hermetic environments (macOS/HPC) to eliminate drift. Provisions offline RAG (Gemma 2), compiles LaTeX manuscripts, and indexes local knowledge. Unifies infrastructure, writing, and inference into a single, audit-ready artifact.

Controlled mini-benchmark for context visibility, shortcut regimes, and composition in tiny causal transformers.

A jekyll site for the Feast and Fast exhibition at the Fitz

Reproducible evaluation suite for LLM behavior research: epistemic pathology, delegated introspection, and temporal consciousness diagnostics

Research-engineering lab for LLM post-training, behavior evaluation, regression detection, and reliability reporting.

GitHub profile README for Nicholas Kashani Motlagh

A follow along of “Build a Large Language Model (From Scratch)” by Sebastian Raschka, which is explained with an insightful YouTube series “Building LLM from Scratch” by Dr. Raj Dandekar (MIT PhD).

Adnane Arharbi

Portfolio landing page for compact AI evaluation artifacts.

PyTorch benchmark for CTM-style adaptive computation, sparse-retrieval failure analysis, adaptive halting, and attention-supervised recovery.

ChronosLOB: Research platform for limit order book representation learning, calibration and execution-aware validation.

Research-grade MLE repo for structured CNN pruning under explicit accuracy guard rails, with deployment-aware evaluation across parameter reduction, MACs, latency, and pruning overhead.

Profile README and portfolio landing page for LLM post-training, model evaluation and reliable production ML.