Search papers, labs, and topics across Lattice.
2
0
5
Collapsing pre-, mid-, and post-training into a single fully synthetic run matches open-weight model performance while slashing required training tokens by up to 140×.
The shutdown of Perspective API exposes a critical vulnerability in NLP research: over-reliance on opaque, proprietary tools for toxicity measurement, threatening the validity and reproducibility of past and future work.
