Search papers, labs, and topics across Lattice.
Email:
2
0
4
Decoy activations fail to protect split-LLM training because zero-valued backward gradients unmask private frames with 100% accuracy, rendering forward-only privacy audits dangerously deceptive.
Democratized LLM pre-training is now a reality: Covenant-72B proves you can train a competitive 72B model with untrusted peers over the internet, opening the door to broader participation and reduced costs.
