Search papers, labs, and topics across Lattice.
FIZ Karlsruhe
3
0
4
23
A surprising representation mismatch between syntax and semantics in scientific formulae can be effectively bridged through contrastive learning, enhancing retrieval performance.
LLMs alone can't capture the nuances of mathematical research, but injecting aspect-aware information into a heterogeneous GNN unlocks surprisingly effective paper recommendations.
TCP and QUIC can achieve NAT traversal success rates statistically indistinguishable from UDP, overturning long-held beliefs about P2P networking.
