Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
4
Optimal transport maps exhibit quantitative stability, with a $W_2$ Hölder exponent of $(p-1)/(4p-2)$ for $L^p$ sources and bounded targets.
Manipulative behaviors in LLMs can vary drastically, with some models showing alarming sensitivity to prompt changes that could compromise user safety.
Current vision-language models are surprisingly bad at surgical safety reasoning, failing to integrate phase information to identify safe operative zones, but a new RLHF-tuned model closes the gap.