Neuro-symbolic IC3+LLM framework finds inductive invariants for 29 distributed protocols in TLA+ and proves them inductive via TLAPS.
Baghsorkhi, Nalini Vasudevan, and Youfeng Wu
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
LeetProof achieves higher rates of fully certified program synthesis from natural language by using a multi-modal verifier in Lean to validate specifications via randomized testing and delegate proofs to AI tools, outperforming single-mode baselines on benchmarks while uncovering defects in prior参考.
AutoVecCoder combines VecPrompt for automated intrinsic knowledge synthesis and VecRL for efficiency-aligned RL to train an 8B LLM that achieves SOTA on SimdBench SSE/AVX subsets and sometimes exceeds -O3 compiler results.
CodeXGLUE supplies a standardized collection of 10 code-related tasks, 14 datasets, an evaluation platform, and BERT-, GPT-, and encoder-decoder-style baselines.
Ranger is a bidirectional refinement type system for integer range types, implemented in the Licorne language, that integrates inference and flow analysis to verify bounds properties with low annotation overhead compared to Java, Scala, Checker Framework, and Liquid Java.
citing papers explorer
-
Synthesizing Inductive Invariants for Distributed Protocols via IC3 and Large Language Models
Neuro-symbolic IC3+LLM framework finds inductive invariants for 29 distributed protocols in TLA+ and proves them inductive via TLAPS.
-
Certified Program Synthesis with a Multi-Modal Verifier
LeetProof achieves higher rates of fully certified program synthesis from natural language by using a multi-modal verifier in Lean to validate specifications via randomized testing and delegate proofs to AI tools, outperforming single-mode baselines on benchmarks while uncovering defects in prior参考.
-
AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code
AutoVecCoder combines VecPrompt for automated intrinsic knowledge synthesis and VecRL for efficiency-aligned RL to train an 8B LLM that achieves SOTA on SimdBench SSE/AVX subsets and sometimes exceeds -O3 compiler results.
-
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
CodeXGLUE supplies a standardized collection of 10 code-related tasks, 14 datasets, an evaluation platform, and BERT-, GPT-, and encoder-decoder-style baselines.
-
Practical Range Refinement Types with Inference
Ranger is a bidirectional refinement type system for integer range types, implemented in the Licorne language, that integrates inference and flow analysis to verify bounds properties with low annotation overhead compared to Java, Scala, Checker Framework, and Liquid Java.