mlsanityData to 14 Oct 2026

SAGE: Semantic-Aware Shared Sampling for Efficient Diffusion

arXiv 2509.15865 ↗First posted 19 Sep 2025cs.LGcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models manifest evident benefits across diverse domains, yet their high sampling cost, requiring dozens of sequential model evaluations, remains a major limitation. Prior efforts mainly accelerate sampling via optimized solvers or distillation, which treat each query independently. In contrast, we reduce total number of steps by sharing early-stage sampling across semantically similar queries. To enable such efficiency gains without sacrificing quality, we propose SAGE, a semantic-aware shared sampling framework that integrates a shared sampling scheme for efficiency and a tailored training strategy for quality preservation. Extensive experiments show that SAGE reduces sampling cost by 25.5%, while improving generation quality with 5.0% lower FID, 5.4% higher CLIP, and 160% higher diversity over baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 19 of its 22 references that are in the map. First posted on arXiv 19 Sep 2025.

Builds on

19 of 22 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity24 May
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  3. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  4. 2023Parallel Sampling of Diffusion Models25 May
  5. 2022On Distillation of Guided Diffusion Models6 Oct
  6. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  8. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  11. 2020Denoising Diffusion Implicit Models6 Oct
  12. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 7

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  6. 2023Reinforcement Learning With LLMs Interaction For Distributed Diffusion Model Servicescited by 7
  7. 2025Brick-Diffusion: Generating Long Videos with Brick-to-Wall Denoisingcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Tale of Two Temperatures: Simple, Efficient, and Diverse Sampling from Diffusion Language Models
  2. 2025Diffusion Language Models are Provably Optimal Parallel Samplers
  3. 2025Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language Models
  4. 2025Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models
  5. 2026Less Uniform Discrete Diffusion is More Powerful and Scalable
  6. 2026Simple Diffusion Language Models Are More Effective Few-Step Generators Than Reported
  7. 2025Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model
  8. 2026Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation