Search papers, labs, and topics across Lattice.
2
0
6
7
Forget coarse sequence-level hacks: LenVM lets you precisely dial in token generation length, boosting a 7B model's length accuracy from 30.9 to 64.8 and crushing closed-source rivals.
Realistic user simulation is now possible: Pare offers a framework that moves beyond flat tool-calling APIs to model stateful user interactions, enabling better evaluation of proactive agents.
