Blogs

Technical deep-dives into verification tools, ONNX infrastructure, and neural network research.

January 2026

PropDAG: A Template Framework for Bound Propagation on Neural Network DAGs

A reusable template framework for bound propagation on directed acyclic graphs, separating algorithm logic from graph traversal infrastructure.

Bound PropagationGraph TraversalTemplate Framework
January 2026

ShapeONNX: Solving ONNX's Dynamic Shape Problem

A dual-track shape inference tool that resolves ONNX's dynamic shapes to concrete static values for neural network verification workflows.

ONNXShape InferenceStatic Analysis
January 2026

SlimONNX: A Story of Optimizing Neural Networks for Verification

A pure Python toolkit for optimizing ONNX models specifically for verification workflows, achieving 100% optimization success across VNN-COMP 2024 benchmarks.

ONNX OptimizationGraph SimplificationVerification
January 2026

TorchONNX: A Compiler for ONNX-to-PyTorch Conversion

A pure Python compiler that converts ONNX models to native PyTorch code through a 6-stage pipeline, achieving 100% success on VNN-COMP 2024 benchmarks.

ONNXPyTorchCompiler DesignModel Conversion
January 2026

TorchVNNLIB: A Story of Fast VNN-LIB Property Loading

A tool for converting VNN-LIB verification properties to binary formats, achieving 10-100x faster loading with a two-tier processing architecture.

Neural Network VerificationVNN-LIBPerformance Optimization
January 2026

Wraact: Polytope Approximation for Sound Neural Network Verification

A unified framework for tight convex hull approximation of neural network activation functions, supporting 7 core activation types with sub-millisecond performance.

Polytope ApproximationConvex HullActivation Functions