Search papers, labs, and topics across Lattice.
4
0
4
4
AstroPT reveals that galaxy properties emerge in a predictable order during training, offering a new lens to understand concept emergence in LLMs.
Premature verification and flawed assumptions in reasoning traces can lead to dramatic drops in LLM accuracy, but targeted interventions can recover performance by over 70%.
Mechanism recovery in AI-generated hypotheses falters in early reasoning stages, revealing vulnerabilities in scientific validity that could mislead experimental planning.
Graph-native reinforcement learning can boost hypothesis generation in materials science by achieving up to 65% better traceability than traditional models.
