Ever since the Turing Test was proposed in the 1950s, humans have explored the mastering
of language intelligence by machine. Language is essentially a complex, intricate system of …

Large language models (LLMs) have shown promise in proving formal theorems using proof
assistants such as Lean. However, existing methods are difficult to reproduce or build on …

Autoformalization is the process of automatically translating from natural language
mathematics to formal specifications and proofs. A successful autoformalization system …

Logical reasoning, ie, deductively inferring the truth value of a conclusion from a set of
premises, is an important task for artificial intelligence with wide potential impacts on …

We propose SDFDiff, a novel approach for image-based shape optimization using
differentiable rendering of 3D shapes represented by signed distance functions (SDFs) …

Despite the success of large language models (LLMs), the task of theorem proving still
remains one of the hardest reasoning tasks that is far from being fully solved. Prior methods …

We introduce ProofNet, a benchmark for autoformalization and formal proving of
undergraduate-level mathematics. The ProofNet benchmarks consists of 371 examples …

Labeled data for imitation learning of theorem proving in large libraries of formalized
mathematics is scarce as such libraries require years of concentrated effort by human …

We study the generalization abilities of language models when translating natural language
into formal specifications with complex semantics. In particular, we fine-tune language …

Automated theorem provers and formal proof assistants are general reasoning systems that
are in theory capable of proving arbitrarily hard theorems, thus solving arbitrary problems …