5 papers
Learning Lean Feedback for Efficient Proof-Candidate Evaluation on GPUs
Lazar Milikic, Etienne Bamas, Emmanuel Abbe +1
Training language models for formal theorem proving requires large numbers of verifier calls. Slow checks and timeouts often leave GPUs waiting and withhold rewards from potentiall…
LeanFlow: A Case Study in Workflow-Driven Lean Autoformalization
Lazar Milikic, Simon Guilloud, Khanh Nguyen +1
We present and evaluate LeanFlow, an LLM agent system specialized for translating mathematical papers into buildable Lean projects. Recent verifier-in-the-loop systems show that la…
VLD: Visual Language Goal Distance for Reinforcement Learning Navigation
Lazar Milikic, Manthan Patel, Jonas Frey
Training end-to-end policies from image data to directly predict navigation actions for robotic systems has proven inherently difficult. Existing approaches often suffer from eithe…
Exploring Defeasibility in Causal Reasoning
Shaobo Cui, Lazar Milikic, Yiyang Feng +4
Defeasibility in causal reasoning implies that the causal relationship between cause and effect can be strengthened or weakened. Namely, the causal strength between cause and effec…
A Static Analysis Framework for Data Science Notebooks
Pavle Subotić, Lazar Milikić, Milan Stojić
Notebooks provide an interactive environment for programmers to develop code, analyse data and inject interleaved visualizations in a single environment. Despite their flexibility,…