Search papers, labs, and topics across Lattice.
3
15
6
5
A single verification prompt is insufficient; learning a reliability score from multiple, complementary perspectives unlocks robust self-verification for VLMs.
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.
