Research map / Video / Video generation
LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
Jiazheng Xing, Fei Du, Hangjie Yuan, Pengwei Liu, Hongbin Xu, Hai Ci, Ruigang Niu, Weihua Chen, Fan Wang, Yong Liu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add R2PE (ablation) | LumosX baseline · Subject-consistent ablation (300K, 240p) | ArcSim: 0.316 -> 0.363 | Improved |
| add R2PE (ablation) | LumosX baseline · Subject-consistent ablation (300K, 240p) | CLIP-T: 0.184 -> 0.178 | Hurt |
| add CSAM (ablation) | LumosX + R2PE · Subject-consistent ablation (300K, 240p) | CLIP-T: 0.178 -> 0.182 | Improved |
| add CSAM (ablation) | LumosX + R2PE · Subject-consistent ablation (300K, 240p) | ArcSim: 0.363 -> 0.363 | No clear effect |
| add MCAM with r=0.1 (ablation) | LumosX + R2PE + CSAM · Subject-consistent ablation (300K, 240p) | ArcSim: 0.363 -> 0.364 | No clear effect |
| add MCAM with r=0.5 (ablation) | LumosX + R2PE + CSAM · Subject-consistent ablation (300K, 240p) | ArcSim: 0.363 -> 0.429 | Improved |
| add MCAM with r=0.5 (ablation) | LumosX + R2PE + CSAM · Subject-consistent ablation (300K, 240p) | CLIP-T: 0.182 -> 0.186 | Improved |
| increase MCAM r from 0.5 to 1.0 (ablation) | LumosX + R2PE + CSAM + MCAM · Subject-consistent ablation (300K, 240p) | ArcSim: 0.429 -> 0.384 | Hurt |
| increase MCAM r from 0.5 to 1.0 (ablation) | LumosX + R2PE + CSAM + MCAM · Subject-consistent ablation (300K, 240p) | CLIP-T: 0.186 -> 0.187 | Improved |
| replace Phantom with LumosX | Phantom · Subject-consistent (500 videos) | ArcSim: 0.444 -> 0.454 | Improved |
| replace SkyReels-A2 with LumosX | SkyReels-A2 · Subject-consistent (500 videos) | ViCLIP-V: 0.839 -> 0.932 | Improved |
| replace Phantom with LumosX | Phantom · Identity-consistent by face count | ArcSim: 0.602 -> 0.542 | Mixed |
Closest papers by meaning
- Multi-subject Open-set Personalization in Video Generation (CVPR 2025 · similarity 0.87)
- VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models (CVPR 2025 · similarity 0.86)
- FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation (NeurIPS 2026 · similarity 0.86)
- MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation (AAAI 2026 · similarity 0.86)
- PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement (NeurIPS 2025 · similarity 0.86)
- DynASyn: Multi-Subject Personalization Enabling Dynamic Action Synthesis (AAAI 2025 · similarity 0.85)
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.
