Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
LLM reasoning can be significantly improved by penalizing token probabilities that drift under semifactual interventions, even without model retraining.
On-demand safety interventions can significantly improve the performance of vision-language models without sacrificing their multimodal reasoning capabilities.
SafeCap boosts LVLM safety by up to 19 points through innovative caption-mediated reinforcement learning, outpacing traditional alignment methods.
