每日Paper进步屋
  文章分类
Anti-Spoofing 7 Domain Adaptation 15 Few-Shot 18 I2I Translation 11 Vision Transformer 13 对抗攻击 9 LLM 31 强化学习 17 视频理解 10 检测/分割/跟踪 22 Face Swapping 6 Diffusion Models 29 NeRF 4 GAN 15 Speech 16 人脸相关 8 医学影像/息肉检测分割 4 无监督/半监督/对比学习 15 Open-Set 9 元宇宙/虚拟人 6 场景文本检测识别 9 MMT 2 Human reconstruction 6 NeRF/3DGS 23 医学影像/Breast Ultrasound 2 图像生成 25 点云相关 11 视频生成 19
LLM LLM
2024-08-27 更新Latent Space Disentanglement in Diffusion Transformers Enables Zero-shot Fine-grained Semantic EditingAut
2024-08-27 LLM
LLM
LLM LLM
2024-08-26 更新Penny-Wise and Pound-Foolish in Deepfake DetectionAuthors:Yabin Wang, Zhiwu Huang, Su Zhou, Adam Prugel-Ben
2024-08-26 LLM
LLM
LLM LLM
2024-08-16 更新Img-Diff: Contrastive Data Synthesis for Multimodal Large Language ModelsAuthors:Qirui Jiao, Daoyuan Chen
2024-08-16 LLM
LLM
LLM LLM
2024-08-15 更新VisMin: Visual Minimal-Change UnderstandingAuthors:Rabiul Awal, Saba Ahmadi, Le Zhang, Aishwarya Agrawal
2024-08-15 LLM
LLM
LLM LLM
2024-05-14 更新MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image GenerationAuthors:Kua
2024-05-14 LLM
LLM
LLM LLM
2024-04-19 更新Efficiently Adversarial Examples Generation for Visual-Language Models under Targeted Transfer Scenarios
2024-04-19 LLM
LLM
LLM LLM
2024-04-18 更新in2IN: Leveraging individual Information to Generate Human INteractionsAuthors:Pablo Ruiz Ponce, German Bar
2024-04-18 LLM
LLM
LLM LLM
2024-04-17 更新DreamScape: 3D Scene Creation via Gaussian Splatting joint Correlation ModelingAuthors:Xuening Yuan, Hong
2024-04-17 LLM
LLM
LLM LLM
2024-04-16 更新Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case StudyAuthor
2024-04-16 LLM
LLM
2 / 4