AI Paper Atlas

Research map / Video / Video generation

Phantom-Data: Towards a General Subject-Consistent Video Generation Dataset

Zhuowei Chen, Bingchuan Li, Tianxiang Ma, Lijie Liu, Mingcong Liu, Yunsheng Jiang, Gen Li, Xinghui Li, Liyang Chen, SiYu Zhou, Qian HE, Xinglong Wu

ICLR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion

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
train on Phantom-Data cross-pair instead of in-pairPhantom-wan 1.3B · Subject-to-video test suite (100 cases)Reward-TA: 2.074 -> 3.827Improved
train on Phantom-Data cross-pair instead of in-pairPhantom-wan 1.3B · Subject-to-video test suite (100 cases)GPT-4o subject score: 2.481 -> 3.041Improved
train on Phantom-Data cross-pair instead of in-pairPhantom-wan 1.3B · Subject-to-video test suite (100 cases)DINO: 0.478 -> 0.416Hurt
train on Phantom-Data cross-pair instead of in-pairPhantom-wan 1.3B · Subject-to-video test suite (100 cases)VBench IQ: 0.725 -> 0.739Improved
use general-subject cross-pair instead of face-only cross-pairPhantom-wan 1.3B · Subject-to-video test suite (100 cases)DINO: 0.354 -> 0.416Improved
add data augmentation to in-pair trainingPhantom-wan 1.3B · Subject-to-video test suite (100 cases)Reward-TA: 2.074 -> 2.427Improved
add data augmentation to in-pair trainingPhantom-wan 1.3B · Subject-to-video test suite (100 cases)DINO: 0.478 -> 0.473No clear effect
enrich training set with diverse subject types (humans, animals, products, multi-subject) (ablation)Phantom-wan 1.3B · Subject-to-video test suite (100 cases)subject consistency and prompt followingImproved
increase training set from 100k to 1 million samples (ablation)Phantom-wan 1.3B · Subject-to-video test suite (100 cases)all metricsImproved
sample reference frames at minute-level instead of second-level intervals (ablation)Phantom-Data pipeline · reference diversityvisual diversityImproved
add LAION image retrieval to the video-only bank (ablation)Phantom-Data pipeline · retrievalrecall and candidate diversityImproved
add prior filtering and VLM identity verification (ablation)Phantom-Data pipeline · pair qualityfalse positivesImproved

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