An integrated workflow for contextual functional evaluation of real-world AI applications.

A benchmark for evaluating continual learning and optimization in AI agents.

A method for extracting symbolic, human-readable rules from RL agents.

A process-supervision method for multi-turn search reasoning in LLM agents.

An agentic framework for discovering ODE models of biological systems.

A framework for evaluating and probing negation in audio-language embedding models.

A guideline-based structured reasoning framework for human-factor event diagnosis.

A benchmark for measuring prospective memory capabilities in LLM agents using a simulated seven-day week.

Source code for a traffic forecasting model comparing spatial attention with uniform mixing.

A multi-subject model for brain-wide cortical dynamics modeling using atlas-aligned spatiotemporal tokenization.

A unified performance tracking platform for agentic portfolio management and financial-agent evaluation.

A high-performance tar parser and writer for JavaScript without external dependencies.

Shared memory layer for AI and team collaboration.

An Excel-compatible runtime for agents and humans

An AI agent framework for creating autonomous, task-oriented behaviors.

A framework for generating synthetic tabular data while preserving statistical properties.

A coreset selection framework with ensemble aggregation for image classification.

Integration of LLMs and GCNs for semi-supervised image classification.

Docker image to run Adobe DNG Converter headlessly on Linux via Wine.

An offline CLI for turning life goals into quests.