Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
CoverPruner reveals that optimizing for representational coverage can significantly enhance the accuracy of pruned vision-language models, especially when faced with aggressive compression.
Probing for user information can be costly, but RO-PnR shows that strategic questioning can significantly enhance the effectiveness of health misinformation interventions.
Flash-WAM achieves real-time inference for world-action models by reducing latency from 8.1 seconds to 348 milliseconds without sacrificing performance.
