Search papers, labs, and topics across Lattice.
2
0
6
1
Forget Claude and GPT: KARL, a reinforcement-learning-trained enterprise search agent, achieves Pareto-optimal performance on a diverse suite of search tasks, even outperforming closed models with sufficient compute.
Train models on half the memory: FlashOptim slashes optimizer memory requirements by over 50% without sacrificing accuracy, even when fine-tuning Llama-3.1-8B.
