2 papers
cs.LG2026
Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits
Elena Dumitrescu, Gert Lek, Lydia Y. Chen +1
Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mechanisms remain poorly understoo…
cs.LG2026
Detecting Diffusion-Generated Time Series Under Generator Shift
Zhi Wen Soi, Aditya Shankar, Gert Lek +4
The boundary between real and diffusion-generated time series is becoming increasingly difficult to draw, yet detection in this domain remains underexplored, especially when the ge…