AI Paper Atlas

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

Interpretable Prompts made Edit-Friendly: Token-to-Token Similarity Reduction in dLLMs for Edit-Friendly Hard Prompt Inversion

Naresh Kumar Devulapally, Shruti Agarwal, Vishal Asnani, Vishnu Suresh Lokhande

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation

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
add CLIP steering to plain dLLM decoder (ablation)dLLM prompt inversion · MS COCO (32 tokens)CLIP image similarity: 0.62 -> 0.68Improved
add CLIP steering to plain dLLM decoder (ablation)dLLM prompt inversion · MS COCO (32 tokens)perplexity: 36.91 -> 28.84Improved
add token-token similarity reduction on top of CLIP guidance (ablation)dLLM + CLIP Guide · MS COCO (32 tokens)CLIP image similarity: 0.68 -> 0.71Improved
add token-token similarity reduction on top of CLIP guidance (ablation)dLLM + CLIP Guide · MS COCO (32 tokens)perplexity: 28.84 -> 33.16Hurt
add token-token similarity reduction on top of CLIP guidance (ablation)dLLM + CLIP Guide · MS COCO (32 tokens)TIFA: 0.81 -> 0.89Improved
add token-token similarity reduction on top of CLIP guidance (ablation)dLLM + CLIP Guide · MS COCO (32 tokens)inference time (s): 3.42 -> 5.60Hurt
token similarity reduction without CLIP guidance (ablation)dLLM prompt inversion · MS COCO (32 tokens)TIFA: TIFA 0.74 -> 0.92 but PPL 36.91 -> 45.93Mixed
replace autoregressive beam search with CLIP-guided dLLM decodinghard prompt inversion · Inversion time (77 tokens)time (s): 104.20 -> 10.50 (VGD vs Ours)Improved
use dLLM + CLIP + similarity steering instead of VGDhard prompt inversion · MS COCO (16 tokens)perplexity: 100.17 -> 54.68Improved
use our method instead of VGD on JourneyDB (CLIP text and F1)hard prompt inversion · JourneyDB (32 tokens)CLIP text similarity: 0.48 -> 0.48No clear effect
increase token budget for inversionOurs · MS COCOperplexity: 54.68 -> 17.10Improved

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