Search papers, labs, and topics across Lattice.
TU Wien
4
0
6
LRAT-Catcher enables the seamless integration of SAT solver outputs into Lean 4, pushing the boundaries of theorem proving in combinatorial mathematics.
LLMs can automatically discover constraints that dramatically accelerate Answer Set Programming solvers, achieving up to 5x speedups on standard benchmarks.
Human-AI collaboration using LLMs and symbolic solvers just cracked a notoriously hard problem in combinatorial design theory, finding a tight lower bound on Latin square imbalance.
LLM self-explanations are more sensitive to semantic framing than actual task performance, suggesting they reflect semantic expectations rather than true internal states.
