reliable-ai

A curated list of awesome responsible machine learning resources.

Open-source framework for uncertainty and deep learning models in PyTorch 🌱

Archived. Earlier Bonnard product. Current: bonnard.dev / @bonnard/mcp-charts

Analyzing and scoring reasoning traces of LLMs

Archived. Earlier Bonnard product. Current: bonnard.dev / @bonnard/mcp-charts

TRIAGE: Characterizing and auditing training data for improved regression (NeurIPS 2023)

Open Symbolic AI Core Repository

🌍 Agentic geopolitical risk analyzer — discovers second-order asset exposures through historical evidence, not LLM hallucination. Agent proposes, deterministic layer verifies. LangGraph + ChromaDB + FastAPI.

Official code for AAAI2025 paper "Mining In-distribution Attributes in Outliers for Out-of-distribution Detection"

Repository for the Reliable and Trustworthy AI course offered in Fall 2022 at ETH Zürich: implementation of DeepPoly, Robustness Analyzer for Deep Neural Networks

AICO explores long-term memory and longitudinal alignment for AI that evolves with people, context, topics, and strategy.

Reliable and Trustworthy Intelligence AI notebooks from ETH Zurich course taught by Prof. Dr. Martin Vechev

Studying Minimum Sufficient Inference: when objective execution evidence can stop LLM inference without sacrificing reliability.

Reliable medical QA with Mistral-7B, QLoRA, selective prediction, and learned abstention via warm-start SFT + DPO.

Implementation of a custom DeepPoly abstract domain transformer for Sigmoid Parabola-Unit activation function using PyTorch

SNGP for uncertainty-aware biomedical image classification and OOD detection.

Bilingual LLM-as-a-judge benchmark and dashboard for measuring agreement, robustness, coverage, and when AI evaluators should abstain.

A control plane for reliable and autonomous AI agents

Reliability-constrained visual-token budgeting for energy-efficient vision-language model inference.