2 papers
cs.CV2025
Multimodal Pragmatic Jailbreak on Text-to-image Models
Tong Liu, Zhixin Lai, Jiawen Wang +6
Diffusion models have recently achieved remarkable advancements in terms of image quality and fidelity to textual prompts. Concurrently, the safety of such generative models has be…
cs.CL2024
Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the "right reasons"?
Tong Liu, Iza Å krjanec, Vera Demberg
A wide body of evidence shows that human language processing difficulty is predicted by the information-theoretic measure surprisal, a word's negative log probability in context. H…