Search papers, labs, and topics across Lattice.
4
0
4
Active reconstruction in memory-augmented LLMs can boost reasoning performance by over 20% while cutting down on resource consumption.
SkillComposer enables language models to self-evolve skills in real-time, achieving up to +4.5 improvements on agent tasks compared to larger models.
EvoNote outperforms human-generated health notes 89.6% of the time while slashing correction production time from hours to minutes.
FineVerify boosts GPT-5-mini's accuracy by 8.2 points with just four sampled trajectories, outperforming standard scaling methods.
