Search papers, labs, and topics across Lattice.
3
1
5
6
It is suggested that safety does not automatically scale with reasoning capability, especially under long-context inference, as context length increases and safety alignment consistently degrades.
Pruning redundant reasoning in teacher traces can boost recommendation model performance while streamlining output length.
VLMs are surprisingly bad at visually matching objects unless they can name them, revealing a critical reliance on textual anchors that overshadows their visual processing capabilities.
