GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment Paper • 2410.08193 • Published Oct 10, 2024 • 4
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models Paper • 2310.15140 • Published Oct 23, 2023 • 1
Talking Models: Distill Pre-trained Knowledge to Downstream Models via Interactive Communication Paper • 2310.03188 • Published Oct 4, 2023 • 1
More Context, Less Distraction: Visual Classification by Inferring and Conditioning on Contextual Attributes Paper • 2308.01313 • Published Aug 2, 2023 • 8