AI RESEARCH
Activation Steering for Masked Diffusion Language Models
arXiv CS.CL
•
ArXi:2512.24143v3 Announce Type: replace Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs from autoregressive LLMs. Yet, efficient representation-level mechanisms for inference-time control in MDLMs remain largely unexplored. To address this gap, we