AI & ML interests

None defined yet.

Recent Activity

hcWang942  updated a dataset 1 day ago
eth-algopt/AuXSpec
hcWang942  updated a model 1 day ago
eth-algopt/AuXSpec-9B-RL
hcWang942  updated a model 1 day ago
eth-algopt/AuXSpec-27B-RL
View all activity

Organization Card

Algorithms and Optimization Group @ Institute of Theoretical Computer Science, ETH Zurich. Led by Rasmus Kyng and Maximilian Probst Gutenberg. More at kyng.inf.ethz.ch.

Latest release

AuXSpec: Learning to Autoformalize Program Specifications via Executable Postconditions

AuXSpec pairs Lean specifications with executable counterparts, so test cases can check generated specifications by execution, which unlocks an execution-based reward for RL on formal specification tasks. Trained with this reward, AuXSpec-27B-RL improves SpecGen pass@4 on AuXSpec-Test 14.3% → 84.3%, outperforms all frontier models and surpasses the open-source state of the art on Verina.

Paper · Website · AuXSpec-27B-RL · AuXSpec-9B-RL · Dataset