Search papers, labs, and topics across Lattice.
4
0
7
Environmental illusions can degrade lane detection accuracy by over 7%, posing serious safety risks for autonomous vehicles.
KD can significantly enhance model performance in low-data settings, but its effectiveness hinges on the quality of the teacher model.
LLM-generated stories exhibit surprising character diversity, yet they often lack the depth and complexity found in human-written narratives.
Misfired alignment in LLMs can lead to a 18.9% failure rate in reasoning about stereotypes, revealing a critical flaw in current safety-oriented training methods.
