Search papers, labs, and topics across Lattice.
2
0
4
1
Subtracting the mean from activations unlocks stable FP4 training for LLMs, closing the performance gap with BF16 without complex spectral methods.
Forget catastrophic forgetting: this imitation learning framework remembers up to 65% more while improving AUC by 10-17 points on the LIBERO benchmark.
