7 papers
MARS: Enabling Autoregressive Models Multi-Token Generation
Ziqi Jin, Lei Wang, Ziwei Luo +1
Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreS…
Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models
Ziwei Luo, Ziqi Jin, Lei Wang +2
This work presents self-rewarding sequential Monte Carlo (SMC), an inference-time scaling algorithm enabling effective sampling of masked diffusion language models (MDLMs). Our alg…
Taming Diffusion Models for Image Restoration: A Review
Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao +2
Diffusion models have achieved remarkable progress in generative modelling, particularly in enhancing image quality to conform to human preferences. Recently, these models have als…
Efficient Image Restoration with State-Dependent Forward Diffusion
Ziwei Luo, Fredrik K. Gustafsson, Jens Sjölund +3
This paper proposes to perform image restoration through a state-dependent mean-reverting forward diffusion (FoD) process. In contrast to traditional diffusion-based approaches tha…
Real-Time Diffusion Policies for Games: Enhancing Consistency Policies with Q-Ensembles
Ruoqi Zhang, Ziwei Luo, Jens Sjölund +3
Diffusion models have shown impressive performance in capturing complex and multi-modal action distributions for game agents, but their slow inference speed prevents practical depl…
Conditional sampling within generative diffusion models
Zheng Zhao, Ziwei Luo, Jens Sjölund +1
Generative diffusions are a powerful class of Monte Carlo samplers that leverage bridging Markov processes to approximate complex, high-dimensional distributions, such as those fou…