Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models
Department of Computer Science, Technion – Israel Institute of Technology(技术学院计算机科学系,以色列技术学院);INSIGHT Lab, School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Israel(内斯坦实验室,贝内-加隆大学内加尔分校,以色列);Computer Science Department, University of Haifa, Haifa, Israel(海法大学计算机科学系,海法,以色列)
Eliron Rahimi, Elad Hirshel, Rom Himelstein, Amit LeVi, Avi Mendelson, Chaim Baskin
Diffusion language models (DLMs) have recently emerged as a competitive alternative to autoregressive (AR) models, offering parallel decoding, competitive generation quality, and initial evidence of improved jailbreak robustness. Despite this progress, the role of sampling mechanisms in shaping refusal behavior remains poorly understood. To address this gap, we present a comprehensive study of step-wise refusal dynamics. We show that diffusion remasking can promote recovery from harmful intermediate generations, provide evidence that this behavior is tied to the sampling mechanism, and demonstrate that switching from AR to diffusion sampling improves jailbreak robustness, including under fixed model weights. To capture generation dynamics not observable at the text level, we propose the Step-Wise Refusal Internal Dynamics (SRI) signal. Consistent with our text-level findings, SRI shows that recovery fails primarily under AR sampling, with these failures often appearing anomalous relative to harmless generations in the SRI space. Based on this observation, we show that SRI enables a simple jailbreak detector that does not modify inference and generalizes to unseen attacks by training only on benign SRI signals. Our evaluation shows that this detector matches or outperforms existing jailbreak detection baselines while adding negligible overhead.
Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generation
Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);Department of Data Science, City University of Hong Kong(香港城市大学数据科学系);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系)
SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences(智能信息处理重点实验室,计算技术研究所,中国科学院);State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(人工智能安全国家重点实验室,计算技术研究所,中国科学院);University of Chinese Academy of Sciences, Beijing, China(中国科学院大学,北京,中国)
Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models
Graduate School of Data Science, Seoul National University(首尔国立大学数据科学研究生院);Department of Biosystems & Biomaterials Science and Engineering, Seoul National University(首尔国立大学生物系统与生物材料科学与工程系)
Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models
Probabilistic Prediction of Neural Dynamics via Autoregressive Flow Matching
Department of Machine Learning and Neural Computing, Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, the Netherlands(荷兰奈梅亨拉德堡德大学唐德斯脑、认知与行为研究所机器学习和神经计算系);Department of Cognitive Neuroscience, Maastricht University, Maastricht, the Netherlands(荷兰马斯特里赫特大学认知神经科学系);Maastricht Brain Imaging Center, Maastricht University, Maastricht, the Netherlands(荷兰马斯特里赫特大学马斯特里赫特脑成像中心)