Search papers, labs, and topics across Lattice.
4
0
6
0
Fine-tuned lightweight LLMs can successfully generate Control Flow Graphs from incomplete or erroneous code, outperforming traditional methods.
Generative recommendation gets a boost: modeling behavior intensity and transitions yields 15-23% gains in prediction accuracy.
Solves the data bottleneck in code smell detection with a semi-automatic dataset generation approach that balances scale and quality.
GLM-5 doesn't just code; it engineers, showcasing unprecedented capability in tackling end-to-end software engineering challenges.
