Search papers, labs, and topics across Lattice.
3
0
3
0
Event-centric memory can boost long-video QA accuracy by over 3 points while slashing inference costs by nearly 64%.
High-norm outlier tokens, often preserved by existing methods, are actually redundant and can be pruned without sacrificing performance鈥擲inkPruner proves it with an 89% token reduction while retaining over 96% of model effectiveness.
Users can now have a personal AI that remembers and retrieves daily experiences seamlessly, enhancing everyday assistance like never before.