DeepfakeGenome: Toward Next-Generation Deepfake Attribution
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-05
Code: https://github.com/haofanwang/inswapper
Terminology
Sources
- Qwen-Image Technical Report
- LoRAX: LoRA eXpandable Networks for Continual Synthetic Image Attribution
- On Attribution of Deepfakes
- DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis
- Emerging Properties in Unified Multimodal Pretraining
- HunyuanImage 3.0 Technical Report
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
- The DeepFake Detection Challenge (DFDC) Dataset
- Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
- DINOv2: Learning Robust Visual Features without Supervision
- DINOv3
- Auto-Encoding Variational Bayes
- PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Qwen3-VL Technical Report
- FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
- Latent Image Animator: Learning to Animate Images via Latent Space Navigation
- Few-shot Video-to-Video Synthesis
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
- SiT: Self-supervised vIsion Transformer
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs