Search papers, labs, and topics across Lattice.
University of Texas
3
0
6
Recirculation enables foundation models to achieve a 23% reduction in perplexity and a 21% increase in accuracy without any added generation latency.
Human-inspired context sensitivity boosts visual reasoning in machines, closing the gap between AI and human perception.
"Machine unlearning" research is actually tackling two distinct problems鈥攔emoving the influence of specific data points versus removing the influence of entire data distributions鈥攁nd conflating them is holding the field back.