Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
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.
Preference-based refinement with DPO can dramatically improve recall in polarization detection without requiring additional human annotation.
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.
