TorchLean formalizes neural networks in Lean 4, from autograd to CUDA verification

srush_nlp · x · 2026-09-16

A Caltech-led team released TorchLean, a Lean 4 codebase for specifying, executing, and verifying neural networks, selected as an ICML 2026 AI4Math Workshop Spotlight. Sasha Rush also referenced the earlier Lean Verified Transformers project, which proved a set of Transformer invariants from scratch in Lean.

Original post →

More from Research

Research channel →