mlsanityData to 14 Oct 2026

Concat-ID: Towards Universal Identity-Preserving Video Synthesis

arXiv 2503.14151 ↗First posted 18 Mar 2025cs.CV cs.AIcited by 28

Not on the map. Why?

Abstract (arXiv)

We present Concat-ID, a unified framework for identity-preserving video generation. Concat-ID employs variational autoencoders to extract image features, which are then concatenated with video latents along the sequence dimension. It relies exclusively on inherent 3D self-attention mechanisms to incorporate them, eliminating the need for additional parameters or modules. A novel cross-video pairing strategy and a multi-stage training regimen are introduced to balance identity consistency and facial editability while enhancing video naturalness. Extensive experiments demonstrate Concat-ID's superiority over existing methods in both single and multi-identity generation, as well as its seamless scalability to multi-subject scenarios, including virtual try-on and background-controllable generation. Concat-ID establishes a new benchmark for identity-preserving video synthesis, providing a versatile and scalable solution for a wide range of applications.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 29 of its 34 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

29 of 34 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  5. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  6. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  7. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  8. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  9. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  10. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  11. 2024Movie Gen: A Cast of Media Foundation Modelscited by 644
  12. 2024LTX-Video: Realtime Video Latent Diffusioncited by 581
17 more
  1. 2023InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generationcited by 497
  2. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 366
  3. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 321
  4. 2024Identity-Preserving Text-to-Video Generation by Frequency Decompositioncited by 158
  5. 2024PuLID: Pure and Lightning ID Customization via Contrastive Alignmentcited by 144
  6. 2024ID-Animator: Zero-Shot Identity-Preserving Human Video Generationcited by 124
  7. 2024Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detectioncited by 122
  8. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 89
  9. 2025ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuningcited by 68
  10. 2025RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformerscited by 66
  11. 2024Magic-Me: Identity-Specific Video Customized Diffusioncited by 59
  12. 2025MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformerscited by 34
  13. 2024Imagine yourself: Tuning-Free Personalized Image Generationcited by 30
  14. 2024VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Modelscited by 16
  15. 2025Ingredients: Blending Custom Photos with Video Diffusion Transformerscited by 13
  16. 2024PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Controlcited by 10
  17. 2024Toffee: Efficient Million-Scale Dataset Construction for Subject-Driven Text-to-Image Generationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 15; 2026: 13.

28 papers.

Sort:

By area:

  1. 2025OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generationcited by 73
  2. 2026Helios: Real Real-Time Long Video Generation Modelcited by 65
  3. 2025Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generationcited by 28
  4. 2025MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglementcited by 23
  5. 2025DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformerscited by 22
  6. 2026DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generationcited by 20
  7. 2025Phantom-Data : Towards a General Subject-Consistent Video Generation Datasetcited by 17
  8. 2025Frame In-N-Out: Unbounded Controllable Image-to-Video Generationcited by 10
  9. 2026RefAlign: Representation Alignment for Reference-to-Video Generationcited by 10
  10. 2026RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulationcited by 7
  11. 2026ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generationcited by 7
  12. 2025Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Routercited by 6
16 more
  1. 2025Proteus-ID: ID-Consistent and Motion-Coherent Video Customizationcited by 6
  2. 2025ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generationcited by 6
  3. 2026LumosX: Relate Any Identities with Their Attributes for Personalized Video Generationcited by 6
  4. 2026Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generationcited by 6
  5. 2026EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generationcited by 6
  6. 2025ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generationcited by 5
  7. 2025Temporal In-Context Fine-Tuning with Temporal Reasoning for Versatile Control of Video Diffusion Modelscited by 4
  8. 2025Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representationscited by 4
  9. 2025LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creationcited by 3
  10. 2025Active Intelligence in Video Avatars via Closed-loop World Modelingcited by 3
  11. 2026TIDE: Task-Isolated Diffusion for Unified Video Editing and Generationcited by 2
  12. 2026Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignmentcited by 2
  13. 2025Collaborative Face Experts Fusion in Video Generation: Boosting Identity Consistency Across Large Face Posescited by 0
  14. 2026Keyframe-Anchored Identity Preservation for Sequential-Action Video Generationcited by 0
  15. 2026GroupVideo: Multi-Identity Customized Text-to-Video Generationcited by 0
  16. 2026KeyID: Decoupled Drafting and Keyframe Editing for Identity-Preserving Video Generationcited by 0