arXiv AI September 30, 2026 By Hua (Edward), Xu, Dongxin Li, Gwen Yidou-Weng, Guy Van den Broeck, Wei Wang, Anji Liu

Grab a Coffee: Future-Aware Guidance for Discrete Diffusion with Compiled Objectives

COFFEE is a plug‑and‑play framework that enables future‑aware guidance for discrete diffusion models by separating sequence dependence from the objective. It uses a target‑free carrier to absorb marginal token distributions and a compiled finite‑state model to capture how token combinations affect sequence‑level preferences, allowing global preferences to be transferred to unresolved positions without retraining the diffusion model. The framework supports both hard constraints and learned soft objectives and demonstrates strong control results across symbolic, language, and biological benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Aug 7

Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models

Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences.

diffusion reinforcement-learning efficiency safety

arXiv Machine Learning

Aug 28

GRAS: Guided Reduced-Variance Proposals and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion

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

diffusion fine-tuning safety

arXiv Machine Learning

Jun 5

Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction

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

diffusion fine-tuning benchmarks

arXiv AI

Aug 3

RAPiD: Reward-Guided Consistency Distillation of Diffusion Planners for Real-Time Autonomous Driving

arXiv:2602. 07339v2 Announce Type: replace Abstract: Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck for real-time closed-loop deployment.

By Ruturaj Reddy, Hrishav Bakul Barua, Junn Yong Loo, Thanh Thi Nguyen, Ganesh Krishnasamy

agents diffusion reinforcement-learning robotics efficiency multimodal safety

arXiv Machine Learning

2d ago

FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models

arXiv:2609.36202v1 Announce Type: cross Abstract: Gradient-based reward guidance provides a flexible way to use downstream reward models to control masked diffusion language models at inference time....

By Darshan Thaker, Lachlan Ewen MacDonald, Ren\'e Vidal

llms diffusion reinforcement-learning benchmarks

arXiv AI

Jul 9

Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF

arXiv:2607. 07693v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models with human preferences.

By Eric Zhu, Abhinav Shrivastava, Soumik Mukhopadhyay

diffusion reinforcement-learning

One email a morning, machine-written

Related stories

Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models

GRAS: Guided Reduced-Variance Proposals and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion

Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction

RAPiD: Reward-Guided Consistency Distillation of Diffusion Planners for Real-Time Autonomous Driving

FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models

Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF