Search papers, labs, and topics across Lattice.
2
0
3
Forget gradient projections – NESS sidesteps catastrophic forgetting by directly exploiting the null space of previous tasks, identified via small singular values, to constrain weight updates.
LoRA fine-tuning just got a memory-efficient upgrade: LoRSum matches or beats standard LoRA performance by reformulating optimization as a proximal problem and using diagonal K-FAC approximations, all without expensive SVD.
