Search papers, labs, and topics across Lattice.
4
0
3
1
LEGO-RL boosts coding agent performance by up to 8.4% while ensuring robust training signals and execution reliability.
Multi-item users can face significantly more powerful poisoning attacks, but a new method achieves robust estimation without sacrificing performance.
TrajSpec transforms vague bug reports into actionable specifications, boosting APR success rates by over 18% through structured evidence gathering.
Agentic code review can transform AI-generated pull requests into high-quality solutions, outperforming traditional methods in both accuracy and usefulness.
