Search papers, labs, and topics across Lattice.
3
0
4
2
Achieve tighter neural network verification bounds without sacrificing scalability by strategically applying multi-neuron relaxation to only the most critical neurons.
Forget massive models: fine-tuning a small 4B parameter model on carefully curated data can match or even approach the performance of 100B+ parameter LLMs in program verification tasks.
Neural network verification gets a speed boost: reusing learned conflicts across related queries cuts down redundant exploration and speeds up verification by up to 1.9x.
