Search papers, labs, and topics across Lattice.
3
0
6
4
SkillSynth's skill graph approach lets you explicitly control the diversity of execution trajectories during terminal task synthesis, leading to more effective agent training.
On-policy data generation closes the training distribution gap and unlocks +2.54 performance gains at 128K context lengths, proving that LLMs learn best from data that evolves with their capabilities.
Open-source LLMs can now rival proprietary models in text-to-CAD generation, thanks to a novel reinforcement learning framework that teaches them to expertly wield CAD tools.
