cd /news/machine-learning/probing-diffusion-denoising-dynamics… · home topics machine-learning article
[ARTICLE · art-56854] src=arxiv.org ↗ pub= topic=machine-learning verified=true sentiment=↑ positive

Probing Diffusion Denoising Dynamics for Contrastive Representation Learning

Researchers introduced D³CL, a parameter-efficient framework that adapts pretrained text-to-image diffusion models for discriminative representation learning by coupling contrastive objectives with denoising reconstruction. On ImageNet-1K, D³CL achieved 80.1% linear-probing accuracy and an FID of 5.56 for unconditional generation, demonstrating that noise-level contrastive learning can enhance discriminative tasks while preserving generative performance.

read1 min views1 publishedJul 13, 2026

arXiv:2607.09067v1 Announce Type: new Abstract: Text-to-image diffusion models exhibit unprecedented generative capability and contain rich intermediate representations that can be useful for discriminative vision tasks. Motivated by this observation, we study a focused question: how can the denoising dynamics of a pretrained diffusion model be adapted to support discriminative representation learning while preserving its generative behavior under parameter-efficient updates? We present D$^3$CL as an investigation of this question. Our key observation is that noisy latents at different diffusion timesteps can be interpreted as stochastic views of the same underlying image, enabling a contrastive objective to be coupled with the standard denoising reconstruction loss. This formulation provides a simple way to probe the interaction between generative denoising and discriminative representation learning without training from scratch. To keep the adaptation lightweight, we apply LoRA updates to a pretrained Stable Diffusion backbone while freezing the original model parameters. D$^3$CL provides strong empirical evidence that reconstruction and noise-level contrastive objectives can be complementary: on ImageNet-1K, it obtains 80.1% linear-probing accuracy and an FID of 5.56 for $256 \times 256$ unconditional generation. Additional ablations on the design space suggest that the usefulness of diffusion features depends on where and how denoising states are sampled. These results establish D$^3$CL as a parameter-efficient adaptation framework for pretrained diffusion models, showing that noise-level contrastive learning can structure denoising representations for discriminative tasks while maintaining generative performance.

── more in #machine-learning 4 stories · sorted by recency
── more on @d³cl 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/probing-diffusion-de…] indexed:0 read:1min 2026-07-13 ·