Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
5
Restricting LLM fine-tuning to the bottom singular subspace nearly eliminates catastrophic forgetting, even when protecting 99% of weights, while maintaining strong target-task performance.
Overparameterization doesn't just add parameters; it warps the loss landscape geometry itself, making well-conditioned minima easier to find.
Models are substantially better at pairwise self-verification than independent scoring, unlocking a more efficient and accurate approach to test-time scaling for complex reasoning.