Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
David Bensaïd, Noam Rotstein, Roy Velich +2 authors
SingLoRA, a reformulated low-rank adaptation method, enhances parameter-efficient fine-tuning by learning a single low-rank matrix and its transpose, ensuring stable optimization and reducing parameter count.
Lihe Yang, Bingyi Kang, Zilong Huang +4 authors
Depth Anything V2 improves monocular depth estimation through synthetic images, larger teacher models, and pseudo-labeled real images, achieving better efficiency and accuracy than Stable Diffusion models.
Advait Gupta, NandaKiran Velaga, Dang Nguyen +1 authors
A three-stage approach, CoSTA*, combines LLMs and A* search to efficiently find cost-effective tool paths for multi-turn text-to-image editing, outperforming state-of-the-art models in cost and quality.
Chenyang Si, Ziqi Huang, Yuming Jiang +1 authors
A method called FreeU improves diffusion U-Net models' generation quality by re-weighting skip connections and backbone features without additional training.
Yuwei Guo, Ceyuan Yang, Anyi Rao +4 authors
A framework inserts a motion model into existing text-to-image models to enable animation, using video clips to learn motion priors while preserving model domain and diversity.
Eyal Segalis, Dani Valevski, Danny Lumen +2 authors
Relabeling a text-to-image dataset with a specialized automatic captioning model improves image quality and semantic alignment in diffusion models.
Jinbin Bai, Tian Ye, Wei Chow +6 authors
Meissonic, a non-autoregressive masked image model, achieves high-quality image generation by incorporating advanced techniques and outperforms existing models like SDXL.
Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi
SHIC leverages foundation computer vision models to learn canonical surface maps without manual supervision, achieving superior results by simulating the annotation process using image-to-image correspondences and enhanced template views.
Yang Sui, Yanyu Li, Anil Kag +7 authors
A weight quantization method reduces the size of diffusion-based image generation models while improving generation quality.
Cheng-Yu Hsieh, Si-An Chen, Chun-Liang Li +5 authors
LLMs can effectively use tool documentation instead of demonstrations to perform complex tasks, achieving performance comparable or superior to few-shot learning on both vision and language benchmarks.
Huizhuo Yuan, Zixiang Chen, Kaixuan Ji +1 authors
Self-play fine-tuning improves diffusion models' performance and alignment with human preferences using competition between model versions, outperforming supervised and RL-based methods with less data.
Xingchao Liu, Xiwen Zhang, Jianzhu Ma +2 authors
Rectified Flow is used to develop an ultra-fast one-step text-to-image generator named InstaFlow, achieving high image quality with significantly reduced inference time compared to existing methods.
Aliasghar Khani, Saeid Asgari Taghanaki, Aditya Sanghi +2 authors
SLiMe segments images at desired granularity using Stable Diffusion with minimal annotations and outperforms existing one-shot and few-shot segmentation methods.
Ke Chen, Yusong Wu, Haohe Liu +3 authors
A text-to-music model named MusicLDM, based on Stable Diffusion and AudioLDM, overcomes limitations in music data and plagiarism with beat tracking and mixup strategies, enhancing music quality, novelty, and text correspondence.
Renrui Zhang, Zhengkai Jiang, Ziyu Guo +5 authors
A training-free and fine-tuning variant of the Segment Anything Model (SAM), PerSAM and PerSAM-F, achieves personalized image and video segmentation using a single reference image and minimal fine-tuning, improving performance on personalized and dreambooth applications.
Yuchao Gu, Xintao Wang, Jay Zhangjie Wu +10 authors
Mix-of-Show addresses challenges in decentralized multi-concept customization for text-to-image diffusion models using embedding-decomposed LoRA, gradient fusion, and regionally controllable sampling.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号