Methods › Computer Vision › Generative Models › PAG
Perturbed-Attention Guidance
PAG
Introduced by Donghoon Ahn et al. in Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The archive carries no description for this method.
Papers archive 2025-07-28
5 shown of 5, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier 12 Jun 2025 · 0 repositories · arXiv:2506.10406
-
dcFCI: Robust Causal Discovery Under Latent Confounding, Unfaithfulness, and Mixed Data 10 May 2025 · 0 repositories · arXiv:2505.06542
-
Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation 17 Feb 2025 · 1 repository · arXiv:2502.11477
-
Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding 22 Apr 2024 · 1 repository · arXiv:2404.14600Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
-
Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance 26 Mar 2024 · 3 repositories · arXiv:2403.17377Syntology ran 13 of 16 samples · 3 unverified
Tasks archive 2025-07-28
11 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections