Pith. sign in

REVIEW

Concept Algebra for (Score-Based) Text-Controlled Generative Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.03693 v6 pith:KO4RXHCD submitted 2023-02-07 cs.CL cs.LGstat.ML

classification cs.CLcs.LGstat.ML
keywords modelsconceptsrepresentationconceptdisentangledgenerativeideamanner
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper concerns the structure of learned representations in text-guided generative models, focusing on score-based models. A key property of such models is that they can compose disparate concepts in a `disentangled' manner. This suggests these models have internal representations that encode concepts in a `disentangled' manner. Here, we focus on the idea that concepts are encoded as subspaces of some representation space. We formalize what this means, show there's a natural choice for the representation, and develop a simple method for identifying the part of the representation corresponding to a given concept. In particular, this allows us to manipulate the concepts expressed by the model through algebraic manipulation of the representation. We demonstrate the idea with examples using Stable Diffusion. Code in https://github.com/zihao12/concept-algebra-code

Discussion (0). Continue with ORCID to comment.

Pith tools