Search papers, labs, and topics across Lattice.
2
0
4
LLMs struggle to reliably predict numerical materials properties, even after fine-tuning, and their performance fluctuates wildly over time, casting doubt on their use in high-stakes scientific applications.
By aligning a generative flow network with physics-based stability proxies via reinforcement learning, PackFlow drastically improves the efficiency of molecular crystal structure prediction, offering a practical route to circumvent the costly relax-and-rank bottleneck.
