Search papers, labs, and topics across Lattice.
Zhejiang University, Inclusion AI, Ant Group
3
0
6
5
Synthetic data that looks good can still tank your model's performance – Optimsyn uses influence functions to find the *actually* useful synthetic examples and optimize your generation rubrics.
Forget quadratic attention: FEAT achieves state-of-the-art performance on structured data with linear complexity and 40x faster inference.
LLMs can match SOTA supervised theorem provers without training, if you give them the right structural scaffolding.
