AI Paper Atlas

Research map / Video / Video generation

ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generation

Panwang Pan, Jingjing Zhao, Yuchen Lin, Chenguo Lin, Chenxin Li, Hengyu Liu, Tingting Shen, Yadong Mu

CVPR 2026 · Video › Video generation · approach: Trajectory-guided motion control · 6 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 hierarchical identity-preserving attention (vs plain cross-attention) (ablation)ID-Crafter 1.3B · OpenS2VFaceSim: 51.34% -> 58.12%Improved
add Qwen2.5-VL encoder alongside T5 (ablation)ID-Crafter 1.3B · OpenS2VQ-Align: 0.287 -> 0.351Improved
add curated training data pipeline (ablation)ID-Crafter 1.3B · OpenS2VTotal Score: 48.78% -> 54.33%Improved
add online GRPO post-training instead of SFT only (ablation)ID-Crafter 1.3B · OpenS2VFaceSim: 58.12% -> 66.10%Improved
online GRPO instead of offline DPO (ablation)ID-Crafter 1.3B · OpenS2VFaceSim: 62.35% -> 66.10%Improved
add fidelity reward R_fid (ablation)online GRPO · OpenS2VFaceSim: 45.32% -> 66.10%Improved
add natural reward R_nat (ablation)online GRPO · OpenS2VQ-Align: Q-Align 0.361 -> 0.410; FaceSim 69.30% -> 66.10%Mixed
scale ID-Crafter from 1.3B to 14BID-Crafter · OpenS2VTotal Score: 55.16% -> 57.05%Improved

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