Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
Up to 78 percentage points of reported machine unlearning success can be reversed with just 10 unlabeled images and zero weight updates, exposing widely cited forgetting benchmarks as mere BatchNorm illusions.
LLMs hit a hard wall in algebraic reasoning, choking on problems with just 20-30 parallel branches regardless of model size, suggesting an architectural bottleneck, not just a capacity issue.
