AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration

Xiefan Guo, Xinzhu Ma, Haiyu Zhang, Di Huang

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
naively align cross-attention maps of all tokens across timesteps (ablation)SD 2.1 + GORS · T2I-CompBench++ Color (B-VQA)score: 0.6426 -> 0.6286Hurt
restrict alignment to noun-token attention maps (ablation)CTCAL · T2I-CompBench++ Color (B-VQA)score: 0.6286 -> 0.6897Improved
add pixel-semantic joint optimization (ablation)CTCAL · T2I-CompBench++ Color (B-VQA)score: 0.6897 -> 0.6992Improved
add subject response alignment regularization (ablation)CTCAL · T2I-CompBench++ Color (B-VQA)score: 0.6992 -> 0.7148Improved
add timestep-aware adaptive weighting (ablation)CTCAL · T2I-CompBench++ Color (B-VQA)score: 0.7148 -> 0.7233Improved
add timestep-aware adaptive weighting (ablation)CTCAL · T2I-CompBench++ 2D-Spatial (UniDet)score: 0.2095 -> 0.2142Improved
fix teacher timestep t_tea=0 rather than random sampling (ablation)CTCAL on SD 2.1 · T2I-CompBench++ Color (B-VQA)score: 0.7028 -> 0.7233Improved
also align adjective tokens (ablation)CTCAL on SD 2.1 · T2I-CompBench++ Texture (B-VQA)score: 0.6754 -> 0.6877Improved
apply CTCAL fine-tuning to SD 3 (2B)SD 3 (2B) · GenEval Overallscore: 0.62 -> 0.69Improved
apply CTCAL fine-tuning to SD 3 (2B)SD 3 (2B) · T2I-CompBench++ Shape (B-VQA)score: 0.5885 -> 0.5968Improved
apply CTCAL fine-tuning to SD 2.1 vs GORSSD 2.1 · T2I-CompBench++ Complex (3-in-1)score: 0.3386 -> 0.3403No clear effect
apply CTCAL fine-tuningSD 2.1 · Diversity (Mean LPIPS, Color)Mean LPIPS: 0.637 -> 0.634No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy