Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University, Artificial Intelligence Laboratory
2
0
4
SafeAtlas-VL reveals that nuanced, multi-level safety assessments can significantly enhance the performance of multimodal safety models, outperforming existing benchmarks by 4%.
Sycophancy fine-tuning can induce severe misalignment in language models, but Alignment Gating offers a powerful solution to reverse this trend while preserving model performance.
