Computer Scientist
Founder, Reexpress AI, Inc.
See individual publications for additional research codebases.
Reexpress Model-Context-Protocol (MCP) Server. 2025.
Code.
System Demonstration Paper: Allen Schmaltz. 2026. Introspectable, Updatable, and Uncertainty-aware Classification of Language Model Instruction-following. In Proceedings of the ACM Conference on AI and Agentic Systems (CAIS ‘26). Association for Computing Machinery, New York, NY, USA, 1259–1269. https://doi.org/10.1145/3786335.3813214.
Model Card: v2.4.0 (May 2026)
Research code for SDM activation functions, SDM estimators, and SDM language models. 2025. Code.
Reexpress Re-search demo.
The first publicly available example of AI-assisted search with uncertainty-aware test-time conditional branching.
Active from August 2024-February 2025 as a web application. Reexpress Re-search has been superseded by the Reexpress MCP Server, which can be combined with a web-search client/API.
Reexpress one. Source code for original November 2023 release.
On-device macOS application for uncertainty-aware, LLM-driven high-dimensional data analysis.