Open source

Artifacts & GitHub repos

Recruiters and collaborators often want to see reproducibility at a glance. Each repo lists what you can run, the datasets you can download, and how it ties back to the paper above.

calibration

GitHub

Evaluation harness for multimodal MT, selective LLM routing, and visual-text calibration experiments.

  • Run imagery-aware contrastive probes against WMT-style checkpoints.
  • Benchmark LLM reject-option heads on held-out OOD prompts.
  • Log structured reports (HTML/Markdown) for rapid model comparisons.
  • Used to benchmark LLM reject-option heads and multimodal MT models for AFRL and academic deployments.

Supports:  Assessing the Role of Imagery in Multimodal Machine Translation , Selective LLM Training with Reject Options

Construction-Site-Satellite-Imagery

GitHub

Semi-automatic satellite data ingestion plus labeling UI for monitoring changing regions.

  • Generate OpenStreetMap-guided scrape manifests for temporal imagery.
  • Label construction phases with the included lightweight annotation app.
  • Export train/val/test splits for change-detection baselines.
  • Demonstrates end-to-end dataset design, labeling tooling, and export pipelines for remote sensing change detection.

Supports:  A Framework for Semi-automatic Collection of Temporal Satellite Imagery for Analysis of Dynamic Regions

learning-idk

GitHub

PyTorch toolkit for per-class reject-option training with binomial threshold search, dashboards, and CLI.

  • Tune per-class thresholds on ImageNet, iNat, or custom datasets with one command.
  • Export coverage/accuracy curves and selective accuracy plots for reports.
  • Integrate abstention policies into existing Torch models via lightweight hooks.
  • Production-ready toolkit that underpins selective prediction guardrails across multiple domains (vision, text, and 2-D data).

Supports:  Learning When to Say "I Don't Know" , Naturally Constrained Reject Option Classification