method · first seen 9 Oct 2026
few-step diffusion sampling
Also: few-step sampling, accelerated sampling, few-step diffusion models, few-step generative models
Techniques that reduce the number of model evaluations needed to generate samples from diffusion or flow generative models.
Few-step diffusion sampling covers methods that cut the number of network evaluations needed to draw samples from diffusion and flow models, through distillation, better solvers, or interval-average velocity models such as MeanFlow. The sources show steady incremental work rather than a new idea. Papers correct endpoint errors after training (TraceSampler), separate prediction horizons from state updates in MeanFlow, and extend few-step sampling to masked diffusion language models such as LLaDA-8B. Several groups, including one with Jong Chul Ye, adapt reward alignment and reinforcement learning to few-step generators. Code releases cover velocity adversarial distillation and RL fine-tuning on SD-3.5.
Sampling cost has been a central diffusion research problem since DDIM, consistency models and progressive distillation, so this activity reflects an established area rather than a new trend. The newer threads worth tracking are RL and reward alignment for few-step models and few-step sampling for masked diffusion language models.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 49 on 14 Nov 2026 · 6 mentions in 28 days · 6 independent groups · papers → code · first seen 5 weeks ago · acceleration +2.02
Earliest sources
- TraceSampler: Making Sampling Errors Predictable and Correctable for Accelerated Generative SamplingPapers · 9 Oct 2026 · George Matthew, Guoqiang Zhang, Kenta Niwa
- Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlowPapers · 14 Oct 2026 · Tinglan Wang, Haixu Liu, Shaobo Chen, Nuo Qian, Qi Gao, Kai Wen, Yu Yao
- Domino: Joint Unmasking via First-order Markov Chain for Few-Step Masked DiffusionPapers · 14 Oct 2026 · Mansoor Ahmed, Lilia Chebbah, Jenny Dinh, Murray Patterson, Hemanth Venkateswara
- Noise-Space Reward Alignment for Few-Step Generative ModelsPapers · 15 Oct 2026 · Woocheol Shin, Taeyoung Yun, Jiwon Sung, Hyeongyu Kang, Jeongmin Park, Jaewoo Le…
- PRIMFLOW: Learning Trajectory Primitives for Few-Step DistillationPapers · 19 Oct 2026 · Hongyi Fang, Benjia Zhou
- Train the Sampler You Run: Few-Step Masked Diffusion Language Models via Mixture-Likelihood Fine-TuningPapers · 2 Nov 2026 · Amin Najafgholizadeh
Latest sources
- EDAPINENUT/fewsteprl-sd35Code · 5 Nov 2026 · EDAPINENUT · 34 stars
- FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement LearningPapers · 5 Nov 2026 · Haitao Lin, Minsi Ren, Yang Li, Xingtong Ge, Zheyuan Hu, Peiyan Hu, Tailin Wu
- Luo-Yihong/VA-TDMCode · 4 Nov 2026 · Luo-Yihong · 32 stars
- Learning Noise Optimization for Reward Alignment in Few-Step Generative ModelsPapers · 4 Nov 2026 · Hongeun Kim, Jeongsol Kim, Jong Chul Ye
- Train the Sampler You Run: Few-Step Masked Diffusion Language Models via Mixture-Likelihood Fine-TuningPapers · 2 Nov 2026 · Amin Najafgholizadeh
- PRIMFLOW: Learning Trajectory Primitives for Few-Step DistillationPapers · 19 Oct 2026 · Hongyi Fang, Benjia Zhou
- Noise-Space Reward Alignment for Few-Step Generative ModelsPapers · 15 Oct 2026 · Woocheol Shin, Taeyoung Yun, Jiwon Sung, Hyeongyu Kang, Jeongmin Park, Jaewoo Le…
- Domino: Joint Unmasking via First-order Markov Chain for Few-Step Masked DiffusionPapers · 14 Oct 2026 · Mansoor Ahmed, Lilia Chebbah, Jenny Dinh, Murray Patterson, Hemanth Venkateswara
- Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlowPapers · 14 Oct 2026 · Tinglan Wang, Haixu Liu, Shaobo Chen, Nuo Qian, Qi Gao, Kai Wen, Yu Yao
- TraceSampler: Making Sampling Errors Predictable and Correctable for Accelerated Generative SamplingPapers · 9 Oct 2026 · George Matthew, Guoqiang Zhang, Kenta Niwa