Every project below reports a held-out number, not a training-split screenshot. Most of them are also built around an opponent on purpose: a fraudster routing around detection, a paraphraser trained to evade a classifier, a model that hallucinates the moment nobody's checking.
The rest is full-stack work, shipped past the notebook and reachable behind a live URL. Scroll on — each project below is one screen, pinned until the next one covers it.
Fraud, forensics, steering, survival — four systems designed against something actively working against them.
Built to run in production, not just pass code review. Airflow orchestrates ingestion through to a Lambda-served model behind FastAPI, with MLflow tracking every version and Evidently AI watching for drift once it's live. The infrastructure — Terraform, S3, PostgreSQL — is part of the deliverable, not an afterthought.
A machine-generated text detector hardened by its own adversary: an RL-trained paraphraser learns to evade it, round after round, until the detector is retrained against exactly what it learned. Held-out splits withhold entire domains and generators — not a random shuffle — so the numbers measure generalization, not memorization.
A real-time risk probe steers a language model away from hallucination only at the moment it's about to happen, instead of applying a fixed correction to every token like prior activation-steering methods. Written up as a CS762 (UW–Madison) paper formatted for ICML, with ITI and CAA reproduced here as baselines rather than taken on faith.
A creature in a grid world with one energy meter, hazards, and a predator that hunts — every decision point it chooses between a free reflex, a cheap short-horizon plan, or a full-sight route, each costing energy in proportion to the model doing the thinking. The routing policy is learned by RL and compared against fixed baselines and a hand-tuned heuristic, not assumed to win by default.
Full-stack ML, live behind a URL — real backends, real users in mind.
Turns a raw earnings call into an analyst-grade report: 43 deterministic linguistic signals plus four LLM agents that cross-check what was said against the company's own SEC filings and prior calls. An optional calibrated XGBoost + LightGBM overlay is validated walk-forward on 46K calls — built as reading and diligence support, not a trading signal.
Pick any point on a real map — or upload your own aerial photo — and a UNet with an EfficientNet-B0 encoder extracts the roads live, vectorizing them into GeoJSON centerlines with real-world length and coverage stats. The results shown are the model's own output on real neighborhoods, not the dataset's held-out set.
A two-tower recommender for Amazon Fashion: a transformer encodes purchase history, an attention-fused item tower combines text, CLIP image embeddings, and learned IDs. Trained on real Amazon Reviews 2023 data — k-core filtered down to a dense subset from over two million raw users — and served live over FastAPI and FAISS.
Upload a CSV, JSON, Parquet, or Excel file, ask a question in plain English, and get SQL back — generated by Gemini or Groq, checked by an AST-level safety layer before it's allowed to touch data, and executed on Spark. Built so a wrong or destructive query fails before execution, not after.
| Category | Instruments |
|---|---|
| Languages & ML | Python · PyTorch · TensorFlow · scikit-learn · XGBoost / LightGBM |
| Systems & Serving | FastAPI · React · TypeScript · Docker · Streamlit |
| Data & Infra | AWS (Lambda, S3, EC2) · Terraform · PostgreSQL · Apache Spark · Airflow |
| ML Ops & Eval | MLflow · Evidently AI · SHAP · Isotonic Calibration |
Eight projects summarized here; fourteen on record. Source, commit history, and READMEs live in the repository.
→ github.com/Sonith-Bingi