Elevator performs the first fully static, heuristic-free whole-program binary translation from x86-64 to AArch64 by exhaustively interpreting every byte and composing ISA-derived code tiles.
Lerner, Matthew Flower, Dan Grossman, and Craig Chambers
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Ablation experiment in Shplait finds that detailed type error messages improve AI agents' type-error repair rates over minimal messages or dynamic errors, with type systems adding further benefit.
MOA deploys LLM agents to detect recurring memory anti-patterns via profiling, synthesize static analyzers, and apply patches, reporting 42% heap and 11% binary-size reductions on OpenHarmony after finding over 10,000 issues.
citing papers explorer
-
Deterministic Fully-Static Whole-Binary Translation without Heuristics
Elevator performs the first fully static, heuristic-free whole-program binary translation from x86-64 to AArch64 by exhaustively interpreting every byte and composing ISA-derived code tiles.
-
Type-Error Ablation and AI Coding Agents
Ablation experiment in Shplait finds that detailed type error messages improve AI agents' type-error repair rates over minimal messages or dynamic errors, with type systems adding further benefit.
-
MOA: A Profiling-Guided LLM Framework for Memory-Optimization Automation at Codebase Scale
MOA deploys LLM agents to detect recurring memory anti-patterns via profiling, synthesize static analyzers, and apply patches, reporting 42% heap and 11% binary-size reductions on OpenHarmony after finding over 10,000 issues.