Search papers, labs, and topics across Lattice.
3
0
6
6
Unlearning sensitive information in LLMs can be achieved without sacrificing performance, with ADU preserving up to 98% of model utility while effectively forgetting.
Only 5.4% of coding agent attempts successfully complete a migration while preserving behavioral correctness, exposing a critical gap in current AI capabilities for software evolution.
Agents struggle to significantly improve training algorithms, with the best only achieving 25% of the potential optimization gap.
