Search papers, labs, and topics across Lattice.
2
3
6
0
LLM safety can be significantly bolstered against harmful fine-tuning attacks by strategically projecting models back into safe parameter space using a relevance- and diversity-aware curated dataset.
Point-VLMs can learn to see the world as it really is: targeted reward assignment and cross-modal verification nearly close the reality gap in 3D reasoning.
