Search papers, labs, and topics across Lattice.
3
0
5
4
Existing SFT reweighting methods fail to reverse harmful learned features; a new entropy-guided approach enables precise suppression, reversal, and extrapolation of pretrained knowledge.
LoRA-GA$^2$ closes the performance gap with full fine-tuning by leveraging multi-step gradient dynamics without sacrificing efficiency.
Achieving trillion-parameter performance with just 35 billion parameters by scaling agent horizons reveals a new frontier in model efficiency.
