GraphCodeBERT
PulseAugur coverage of GraphCodeBERT — every cluster mentioning GraphCodeBERT across labs, papers, and developer communities, ranked by signal.
-
New benchmarks released for LLM-based Java and Rust vulnerability detection
Two new benchmarks, JavaVulBench and RustMizan, have been released to evaluate the capabilities of large language models in detecting software vulnerabilities. JavaVulBench focuses on Java methods and includes over 1,74…
-
XSearch framework introduces explainable semantic code search
Researchers have developed XSearch, a novel framework for explainable semantic code search that addresses limitations in current methods. Unlike existing approaches that rely solely on embedding similarity, XSearch refo…
-
XSearch framework offers explainable code search via concept alignment
Researchers have developed XSearch, a novel framework for explainable code search that moves beyond simple semantic similarity. By explicitly aligning functional concepts within a query to corresponding code statements,…
-
Archaeology team fine-tunes code models for AI-generated code detection
Researchers from the team Archaeology have developed a system for detecting AI-generated code, participating in SemEval-2026 Task 13. Their approach involves fine-tuning several pre-trained code models, including CodeBE…