MétaCan
Menu
Back to cohort
Record W4410427888 · doi:10.1109/dapic66097.2025.00006

MicroEBM: Scale Composition for Single-Image Energy-Based Models

2025· article· en· W4410427888 on OpenAlexaff
Di He

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldPhysics and Astronomy
TopicNuclear Physics and Applications
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsScale (ratio)Composition (language)Computer scienceImage (mathematics)Energy (signal processing)Computer visionArtificial intelligenceStatisticsMathematicsCartographyGeographyArt

Abstract

fetched live from OpenAlex

Typical generative models are trained on relatively large datasets, ranging from thousands to even millions of images. Training on such large datasets is often expensive and has raised concerns from regulators and gathered scrutiny from rights-holders of images used in such datasets. Previous works have shown that, with appropriate architectural constraints, it is possible to train generative models on datasets as small as a single image, which can be used in a variety of image manipulation tasks, such as image harmonization and style transfer. However, such models often require choosing an input scale in which to operate, which constrains the manipulations that can be performed by the end-users. This paper presents MicroEBM, a novel flexible architecture that exploits the unique compositional properties of energy-based models to train a single-image generative model. MicroEBM can operate on all scales of the image simultaneously, instead of just one scale. We have demonstrated the effectiveness of our method via extensive visual examples.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.971
Threshold uncertainty score0.292

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.009
GPT teacher head0.239
Teacher spread0.230 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicNuclear Physics and ApplicationsFrench-language works237,207