Search papers, labs, and topics across Lattice.
Université Paris-Cité
3
0
5
LLMs can now tackle complex TCS proof generation with a benchmark that achieves over 90% accuracy in verification against human experts.
A novel auditing framework reveals that synthetic data can leak private information without model access, challenging assumptions about data privacy in generative AI.
Surprisingly, using only a single inner loop update in data mixing can lead to failure, and the optimal number of inner loop steps scales logarithmically with the parameter update budget.
