Search papers, labs, and topics across Lattice.
College of Computing and Data Science, Nanyang Technological University, Singapore
2
46
4
5
Self-repair mechanisms in transformers can obscure critical components, but Conditional Co-Ablation reveals hidden backups that are essential for understanding model behavior.
RealSafe-R1 achieves safety alignment of DeepSeek-R1 without sacrificing reasoning performance, a common trade-off in prior safety alignment efforts.
