Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
3
0
4
Identity drift in generative agents reveals that anti-self-deception is a dominant modification behavior, challenging assumptions about agent fidelity under pressure.
By tuning step sizes based on the spectral properties of gradients, SpecMuon offers a more stable and faster alternative to Adam and Muon for training physics-informed neural networks.
Neural-POD lets you build resolution-invariant, nonlinear basis functions for complex spatiotemporal systems, outperforming classical POD and bridging the gap between traditional ROM and operator learning.