Search papers, labs, and topics across Lattice.
Affiliation:
2
15
4
5
Confidence estimates from LLMs can be misleading when evaluating many candidates, but a new framework ensures high-probability agreement with human judgments.
Gradient spikes in LLM training can be 1000x larger than normal, but a new optimizer, SPAM, tames them with momentum reset and spike-aware clipping, boosting performance and memory efficiency.
