Search papers, labs, and topics across Lattice.
2
0
5
5
VLMs struggle to understand negation in non-English languages, with standard CLIP performing at or below chance on non-Latin script languages.
LMs can learn to generate multiple plausible answers in a single forward pass, outperforming traditional single-answer models on tasks requiring distributional reasoning and offering a compute-efficient alternative to best-of-k sampling.