AI Paper Atlas

Research map / Video / Video generation

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

Zhengyang Sun, Yu Chen, Xin Zhou, Xiaofan Li, Xiwu Chen, Dingkang Liang, Xiang Bai

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models · 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
add NUMINA layout guidanceWan2.1-1.3B · CountBenchCountAcc (%): 42.3 -> 49.7Improved
add NUMINA layout guidanceWan2.1-14B · CountBenchCountAcc (%): 53.6 -> 59.1Improved
add seed search of 5 seeds instead of NUMINAWan2.1-1.3B · CountBenchCountAcc (%): 42.3 -> 45.5Improved
add prompt enhancementWan2.1-1.3B · CountBenchCountAcc (%): 42.3 -> 47.2Improved
add attention-derived layout instead of GroundingDINO layout (ablation)NUMINA · CountBenchCountAcc (%): 47.5 -> 49.7Improved
add temporal cost C_t to overlap cost (ablation)NUMINA layout refinement · CountBenchCountAcc (%): 45.1 -> 48.9Improved
add center cost C_c to overlap cost (ablation)NUMINA layout refinement · CountBenchCountAcc (%): 45.1 -> 46.9Improved
select Top-1 head instead of averaging all heads (ablation)NUMINA head selection · CountBenchCountAcc (%): 43.0 -> 49.7Improved
select Top-1 head instead of random head (ablation)NUMINA head selection · CountBenchCountAcc (%): 44.1 -> 49.7Improved
add object addition alongside removal (ablation)NUMINA · CountBenchCountAcc (%): 43.8 -> 49.7Improved
add object removal alongside addition (ablation)NUMINA · CountBenchCountAcc (%): 47.7 -> 49.7Improved
add EasyCache accelerationNUMINA · CountBenchwall-clock time (s): 431 -> 355Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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