3 papers
cs.CL2026
Commitment Before Realization: When Classifier-Free Guidance Becomes Unnecessary in Masked Diffusion Language Models
Fan Zhou, Weitian Wang, Tim Van de Cruys
Classifier-free guidance (CFG) is usually kept on throughout masked diffusion language model decoding, although its benefit varies across prompts and over time. We study when CFG i…
cs.CL2025
Controllable Stylistic Text Generation with Train-Time Attribute-Regularized Diffusion
Fan Zhou, Chang Tian, Tim Van de Cruys
Generating stylistic text with specific attributes is a key problem in controllable text generation. Recently, diffusion models have emerged as a powerful paradigm for both visual…
cs.CV2024
From Geometric Mimicry to Comprehensive Generation: A Context-Informed Multimodal Diffusion Model for Urban Morphology Synthesis
Fangshuo Zhou, Huaxia Li, Liuchang Xu +5
Urban morphology is fundamental to determining urban functionality and vitality. Prevailing simulation methods, however, often oversimplify morphological generation as a geometric…