Lean 4 Programming Language
PulseAugur coverage of Lean 4 Programming Language — every cluster mentioning Lean 4 Programming Language across labs, papers, and developer communities, ranked by signal.
16 day(s) with sentiment data
-
Tencent Hunyuan AI solves 50-year-old math problem, recruits for AI4S
Tencent's Hunyuan AI has achieved a significant breakthrough by solving a mathematical problem that had remained open for approximately 50 years. The AI agent, named Hyra and powered by the Hy3 model, not only found a s…
-
Graph Neural Network explanations lack canonicality due to input symmetries
A new research paper explores a fundamental issue in explaining Graph Neural Networks (GNNs), specifically how their explanations can be non-canonical due to input symmetries. The study highlights that gradient-based GN…
-
New calculus for programming language translations focuses on answer trustworthiness
Researchers have developed a new calculus for analyzing translations between programming languages, focusing on the trustworthiness of answers derived from these translations. This system models translations as a graph …
-
AI-generated proofs verify 3D mesh intersection code
A developer has created a formally verified implementation of a 3D constructive solid geometry (CSG) mesh intersection operation using the Lean 4 Programming Language. This implementation prioritizes minimizing human re…
-
New theory explores depth vs. precision in quantized neural computation
A new research paper explores the theoretical limits of quantized neural computation, investigating when increased model depth can compensate for reduced numerical precision. The study models quantized residual systems …
-
Learned Interventions Enhance Lean 4 Theorem Proving
Researchers have developed a method to integrate learned interventions into the Lean 4 theorem prover's \grind{} tactic. This approach invokes learned heuristics only after standard \grind{} fails, ensuring that proofs …
-
Verified floating-point types for ARCH HDL generated by LLMs
Researchers have developed and verified floating-point data types for the ARCH hardware description language, designed for generation by language models. The system ensures consistency across synthesizable SystemVerilog…
-
Debate arises over trusting AI-generated formal proofs in Lean 4
The reliability of AI-generated formal proofs in the Lean 4 programming language is being questioned. A discussion on Math Stack Exchange explores whether these proofs can be trusted, highlighting potential concerns abo…
-
AI advances formal proof systems with new tools and benchmarks · 4 sources tracked
Researchers have developed new tools and benchmarks for formal theorem proving, an area increasingly relevant to AI. One paper details an interactive sequent prover for Event-B, encoded in Prolog, which offers advantage…
-
New research explores infinite-dimensional null spaces in neural networks
A new arXiv paper by Sho Sonoda explores the existence, structure, and role of infinite-dimensional null spaces within continuous-width depth-two fully connected neural networks. The research introduces a direct method …
-
New AI system MathCoPilot aids mathematicians in formal proof generation
Researchers have introduced MathCoPilot, an interactive system designed to facilitate a symbiotic relationship between mathematicians and AI agents for mathematical research. This system allows mathematicians to guide t…
-
Apple ML Research unveils fast interactive proofs for large data
Apple Machine Learning Research has published a paper detailing "Doubly Sub-linear Interactive Proofs of Proximity" (dsIPPs). These proofs allow for ultra-fast generation by reading only a small portion of a large input…
-
New theory links JEPA world models to Active Inference via SIGReg objective
A new theoretical paper proposes that the SIGReg objective, when used as an anti-collapse regularizer in Joint-Embedding Predictive Architectures (JEPAs), can serve as a valid Active Inference (AIF) variational free ene…
-
AI system 'Starfleet' uses Lean 4 to solve math problems
A new AI system named 'Starfleet' has been developed to tackle complex mathematical problems, including those posed by Erdős. The system utilizes the Lean 4 programming language and is described humorously as a desktop …
-
AI-assisted formalization of Vlasov equation published on arXiv
Researchers have formalized the mean-field derivation of the Vlasov equation using an AI system directed by a mathematician within the Lean 4 proof assistant. This process, framed as a strategy game, involved transformi…
-
Lean-QIT formalizes quantum information theory with Lean 4 library · 2 sources tracked
Researchers have developed Lean-QIT, a new library for the Lean 4 Programming Language, designed to create a formal infrastructure for Quantum Information Theory (QIT). This library provides a machine-checked framework …
-
Lean-Quantum library formalizes quantum information theory with AI assistance
Researchers have developed a new Lean 4 library called Lean-Quantum, designed to aid in the formalization of quantum information theory. This library provides a robust, basis-independent framework for finite-dimensional…
-
New statistical method enhances classification accuracy over QDA and GAMs
A new research paper introduces a closed-form fractional radial link for elliptical Mahalanobis discriminant analysis, aiming to improve binary classification accuracy. The proposed method derives a Bayes radial-link fa…
-
AI agents tackle complex math problems, setting new research benchmarks · 8 sources tracked
Researchers are developing advanced AI agents capable of tackling complex mathematical problems, pushing the boundaries of automated reasoning. Systems like ProofCouncil and OpenProver are demonstrating significant capa…
-
LLMs show routing failures on verified math structures, study finds
A new study investigates routing failures in large language models (LLMs) when processing formally verified algebraic structures. The research found that GPT-OSS 120B achieved 80.3% template accuracy and Llama 3.3-70B a…