Search papers, labs, and topics across Lattice.
Affiliation:
3
0
3
Over 95% of LLM tutoring responses provide high levels of assistance, raising questions about the effectiveness of such support in student learning outcomes.
Persona conditioning in LLMs can be reliably assessed, revealing that semantically similar personas can yield meaningful response variations that enhance survey accuracy.
Compress 2D flame simulations by over 100,000x using a convolutional autoencoder and neural ODE, achieving <2% error in predicting transient behavior.