AI News HubLIVE
Original source2 min read

Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers

This study reveals a phenomenon called 'massive activations' in Diffusion Transformers (DiTs): a small subset of hidden-state channels with consistently larger responses. Despite their sparsity, these channels are functionally critical, spatially organized, and transferable, enabling prompt interpolation and subject-driven generation without additional training.

SourcearXiv Computer VisionAuthor: Evelyn Turri, Davide Bucciarelli, Sara Sarto, Lorenzo Baraldi, Marcella Cornia

[2605.13974] Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers

[Submitted on 13 May 2026]

Title:Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers

View a PDF of the paper titled Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers, by Evelyn Turri and 4 other authors

View PDF HTML (experimental)

Abstract:Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood. In this work, we study massive activations: a small subset of hidden-state channels whose responses are consistently much larger than the rest. We show that, despite their sparsity, these few channels effectively draw the whole picture, in three complementary senses. First, they are functionally critical: a controlled disruption probe that zeroes the massive channels causes a sharp collapse in generation quality, while disrupting an equally-sized set of low-statistic channels has marginal effect. Second, they are spatially organized: restricting image-stream tokens to massive channels and clustering them yields coherent partitions that closely align with the main subject and salient regions, exposing a structured spatial code hidden inside an apparently outlier-like subspace. Third, they are transferable: transporting massive activations from one prompt-conditioned trajectory into another, shifts the final image toward the source prompt while preserving substantial content from the target, producing localized semantic interpolation rather than unstructured pixel blending. We exploit this property in two use cases: text-conditioned and image-conditioned semantic transport, where massive activations transport enables prompt interpolation and subject-driven generation without any additional training. Together, these results recast massive activations not as activation anomalies, but as a sparse prompt-conditioned carrier subspace that organizes and controls semantic information in modern DiT models.

Comments: Project page: this https URL

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Multimedia (cs.MM)

Cite as: arXiv:2605.13974 [cs.CV]

(or arXiv:2605.13974v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2605.13974

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Evelyn Turri [view email] [v1] Wed, 13 May 2026 18:00:12 UTC (38,278 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers, by Evelyn Turri and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-05

Change to browse by:

cs cs.AI cs.MM

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)