Search papers, labs, and topics across Lattice.
4
0
9
3
Optimizing conversational timing as a standalone objective can lead to more natural interactions without compromising reasoning abilities in dialogue systems.
Evolving Meta-Skills enables automatic Multi-Agent Systems to achieve superior performance without sacrificing experience retention or scalability.
Certainty preservation in lab notes is the key to preventing AI agents from misinterpreting scientific uncertainty as actionable knowledge.
Stop letting SFT ruin your LMMs: PRISM uses on-policy distillation to realign your model *before* RL, boosting performance by up to 6%.
