VGAS: Variance-Reduced Guidance and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion proposes a new inference-time framework that improves steering of frozen masked discrete diffusion models. By reducing the variance of guidance estimates, applying reward tilting to clean-token logits, and adapting the selection temperature at each step, VGAS addresses three default choices in existing pipelines. Experiments on regulatory DNA, protein, and small-molecule benchmarks show that VGAS achieves the best training-free reward performance and matches or surpasses reward-fine-tuned generators.
By Kwanyoung Kim
The paper introduces GRAS, a method that improves training‑free reward alignment for discrete diffusion models by reducing variance in guided proposals and adapting the resampling temperature during search. It achieves this without adding denoiser cost, using Rao‑Blackwellized estimates for differentiable rewards and a leave‑one‑out baseline for non‑differentiable ones. Experiments on regulatory DNA and protein design show GRAS outperforms existing training‑free techniques and rivals reward‑fine‑tuned models.
By Kwanyoung Kim
Spectral Feedback is a new algorithm for aligning discrete diffusion models at test time by iteratively revisiting and editing token positions rather than only steering the reverse process. It selects edit-sets—groups of token positions to re-mask and re-sample—using sparse Fourier representations of edit-set value functions, enabling efficient optimization of which tokens to revisit. The method is model-agnostic and improves alignment performance across pretrained, test‑time aligned, and fine‑tuned diffusion models, achieving significant gains in protein stability for inverse folding tasks.
By Shai Dickman, Mert Cemri, Landon Butler, Kannan Ramchandran
arXiv:2609.31882v2 Announce Type: replace-cross
Abstract: Reward-based diffusion fine-tuning faces practical challenges when desirable outcomes are rare or conditioning corrections are costly to esti...
By Zhengyi Guo, Jiayuan Sheng, Wenpin Tang, David D. Yao
The paper introduces RefineMix, a framework for training discrete diffusion models when data is scarce, common in scientific settings. RefineMix strategically incorporates out‑of‑distribution data at specific diffusion times to enhance generalization without distorting the sampling distribution. Experiments across five domain‑shift scenarios show that RefineMix matches or surpasses in‑domain fine‑tuning, and in protein sequence generation it nearly doubles the proportion of novel, foldable, in‑family proteins produced from just 197 in‑domain examples.
By Julian Kleutgens, Mauricio Tec, Claudio Battiloro, Francesca Dominici, Giannis Daras
arXiv:2607. 02834v1 Announce Type: new Abstract: Molecular optimization often starts from a pretrained generative model that captures a broad prior over valid molecular structures.
By Trevor Chen, Ariel Dai, Jason Yang, Riccardo De Santi, Daniel Khalil, Wenda Chu, Nate Gruver, Pranav Murugan, Alexander F. G. Goldberg, Maruan Al-Shedivat, Yisong Yue
arXiv:2601. 08379v2 Announce Type: replace-cross Abstract: Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data.
By Matina Mahdizadeh Sani, Nima Jamali, Mohammad Jalali, Farzan Farnia
arXiv:2606. 06303v1 Announce Type: new Abstract: Controllable generation with discrete diffusion models is often hindered by high computational overhead or the need for retraining.
By Hongkun Dou, Zike Chen, Fengji Li, Hongjue Li, Yue Deng
arXiv:2608. 03929v1 Announce Type: new Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process.
By Yuanshen Guan, Zipeng Feng, Zhiwei Xiong, Peiqin Sun
arXiv:2604. 26985v2 Announce Type: replace-cross Abstract: Masked diffusion models (MDMs) generate discrete sequences by iterative denoising under an absorbing masking process.
By Michael Cardei, Huu Binh Ta, Ferdinando Fioretto
arXiv:2511. 09173v3 Announce Type: replace-cross Abstract: External trajectories can improve offline decision-sequence learning, but dynamics shift may make some source subsequences inconsistent with the target environment.
By Guojian Wang, Quinson Hon, Xuyang Chen, Lin Zhao
The paper introduces Noise Policy Optimization (NPO), a method for aligning few-step generative models with black-box reward signals. NPO learns an amortized flow policy that transforms initial Gaussian noise into a reward-tilted distribution, allowing the pretrained generator to produce higher-reward outputs without fine-tuning. The approach achieves superior reward-quality trade-offs across image, language, and protein generation tasks while drastically reducing inference cost compared to test-time search methods.
By Woocheol Shin, Taeyoung Yun, Jiwon Sung, Hyeongyu Kang, Jeongmin Park, Jaewoo Lee, Kyuil Sim, Dohyun Kim, Yutong He, Jinkyoo Park