Andrew Bond

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.

AI-powered WCAG 2.1 AA document accessibility checker and fixer, built on pandoc + Claude — designed for CSU faculty accessibility compliance

Geometric deep learning for content moderation — hyperbolic policy embeddings, manifold decision boundaries, and distributional fairness

Observation Theory — registration-first claim ledger, prediction registry, experiments, and the foundational paper (Book XIV of the Geometric Series).

Essays and draft papers examining logic, mathematics, theism, and Christian apologetics from a critical, textual-analytical perspective

ErisML is a modeling language for governed, foundation-model-enabled agents operating in pervasive computing environments