Search papers, labs, and topics across Lattice.
4
0
9
0
Frontis-MA1 achieves a remarkable 71.21% Medal Average on MLE-Bench Lite, outperforming leading models and showcasing the potential of AI systems to recursively improve their own engineering processes.
AI coding agents excel at translating scientific tasks into familiar formats but struggle to achieve true scientific discovery, with only 17.8% surpassing state-of-the-art benchmarks.
AutoMine outperforms existing methods in scenario mining, achieving a HOTA-Temporal score of 36.38 in a competitive setting.
Stop treating domain as an afterthought: DCG bakes domain directly into knowledge graph relations, resolving ambiguities and enabling context-aware reasoning.
