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。
RadixArk, Tom Chen, Mao Cheng +10 authors
Miles is an open-source, production-ready system for large-scale reinforcement learning and post-training that supports diverse backends, weight synchronization, LoRA, distillation, and diffusion models.
Yu Lu, Yuanzhi Liang, Linchao Zhu +1 authors
FreeLong enhances long video generation by balancing global and local video features during denoising, improving quality and consistency.
Cong Wei, Zheyang Xiong, Weiming Ren +3 authors
An omnipotent image editor trained on multisource supervision, importance sampling, and a versatile architecture excels in multiple tasks with diverse aspect ratios and high data quality.
Bram Wallace, Meihua Dang, Rafael Rafailov +7 authors
A method called Diffusion-DPO aligns text-to-image diffusion models to human preferences using direct optimization on comparison data, improving visual appeal and prompt alignment.
Junsong Chen, Yue Wu, Simian Luo +5 authors
PIXART-{\delta} integrates Latent Consistency Model (LCM) and ControlNet into PIXART-{\alpha} for accelerated, high-quality text-to-image synthesis with efficient training and inference.
Zeyu Lu, Zidong Wang, Di Huang +4 authors
The Flexible Vision Transformer adapts to varied image resolutions and aspect ratios through dynamic tokenization and extrapolation techniques, outperforming traditional methods.
Fu-Yun Wang, Zhaoyang Huang, Alexander William Bergman +9 authors
The Phased Consistency Model (PCM) addresses limitations in Latent Consistency Models (LCM) and outperforms them in high-resolution, text-conditioned image and few-step text-to-video generation.
Yanwu Xu, Yang Zhao, Zhisheng Xiao +1 authors
UFOGen, a hybrid diffusion-GAN model, achieves efficient one-step text-to-image synthesis at high quality.
Jiatao Gu, Shuangfei Zhai, Yizhe Zhang +2 authors
Matryoshka Diffusion Models use a NestedUNet architecture for joint denoising at multiple resolutions, enabling efficient high-resolution image and video synthesis.
Xiwei Hu, Rui Wang, Yixiao Fang +3 authors
ELLA, an Efficient Large Language Model Adapter, enhances text-to-image diffusion models by integrating powerful Large Language Models through a Timestep-Aware Semantic Connector, improving dense prompt comprehension and generation quality.
Jooyoung Choi, Chaehun Shin, Yeongtak Oh +2 authors
The Style-friendly SNR sampler modifies the noise level distribution during fine-tuning to improve style alignment in diffusion models, enabling better capture of unique artistic styles.
Donghyun Lee, Jitesh Chavan, Duy Nguyen +5 authors
OrbitQuant enables efficient post-training quantization for diffusion transformers by using a normalized rotated basis that eliminates the need for recalibration across different timesteps and modalities.
Chong Mou, Xintao Wang, Jiechong Song +2 authors
DragonDiffusion, a novel image editing method, enables precise manipulation of generated or real images using classifier guidance and multi-scale attention mechanisms without requiring fine-tuning.
Dongzhi Jiang, Guanglu Song, Xiaoshi Wu +5 authors
CoMat, an end-to-end diffusion model fine-tuning strategy with an image-to-text concept matching mechanism, improves text-to-image alignment in SDXL without additional data.
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.
Shiwei Zhang, Jiayu Wang, Yingya Zhang +6 authors
The cascaded I2VGen-XL approach uses hierarchical encoders and text-image pairs to improve the semantic accuracy, continuity, and clarity of generated videos.
Zehua Chen, Guande He, Kaiwen Zheng +2 authors
Bridge-TTS introduces a novel text-to-speech system using a clean deterministic prior in diffusion models, significantly improving synthesis quality and sampling efficiency over existing methods.
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.
Linoy Tsaban, Apolinário Passos
LEDITS combines Edit Friendly DDPM inversion and Semantic Guidance to enable versatile and efficient real-image editing using text prompts.
Tero Karras, Miika Aittala, Jaakko Lehtinen +3 authors
Modifications to network layers in the ADM diffusion model architecture improve training stability and synthesis quality, reducing FID from 2.41 to 1.81, and a novel method for post-hoc EMA parameter tuning is introduced.
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