Latent diffusion models (LDM) have revolutionized text-to-image generation, leading to the proliferation of various advanced models and diverse downstream applications. However, despite these significant advancements, current diffusion models still suffer from several limitations, including inferior visual quality, inadequate aesthetic appeal, and inefficient inference, without a comprehensive solution in sight. To address these challenges, we present UniFL, a unified framework that leverages feedback learning to enhance diffusion models comprehensively. UniFL stands out as a universal, effective, and generalizable solution applicable to various diffusion models, such as SD1.5 and SDXL. Notably, UniFL consists of three key components: perceptual feedback learning, which enhances visual quality; decoupled feedback learning, which improves aesthetic appeal; and adversarial feedback learning, which accelerates inference. In-depth experiments and extensive user studies validate the superior performance of our method in enhancing generation quality and inference acceleration. For instance, UniFL surpasses ImageReward by 17% user preference in terms of generation quality and outperforms LCM and SDXL Turbo by 57% and 20% general preference with 4-step inference.
Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
University of Amsterdam(阿姆斯特丹大学);Mohamed Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Inception Institute of Artificial Intelligence(起源人工智能研究院)
HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedback
Northwest A&F University(西北农林科技大学);Tencent AI Lab(腾讯AI实验室);The University of Melbourne(墨尔本大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Video Generation Models Are Good Latent Reward Models
University of Chinese Academy of Sciences(中国科学院大学);Tencent Hunyuan(腾讯文元);Huazhong University of Science and Technology(华中科技大学);Peking University(北京大学);Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学);Nanjing University(南京大学)
A Markovian View of Iterative-Feedback Loops in Image Generative Models: Neural Resonance and Model Collapse
Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA(印第安纳大学信息学、计算与工程学院);Department of Computer Science, Stonehill College, Easton, MA, USA(石溪学院计算机科学系)
Closed-Loop Unsupervised Representation Disentanglement with $β$-VAE Distillation and Diffusion Probabilistic Feedback
Ningbo Institute of Digital Twin, Eastern Institute of Technology(宁波数字孪生研究所、东部技术研究所);Shanghai Jiao Tong University(上海交通大学);Xi’an Jiaotong University(西安交通大学)
Token-Disentangled Latent Test-Time Scaling for Vision-Language Reasoning
Qwen Business Unit of Alibaba(阿里巴巴通义千问事业部);School of Artificial Intelligence, Nanjing University(南京大学人工智能学院);National Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术全国重点实验室);Zhejiang University(浙江大学);University of Waterloo(滑铁卢大学);Chinese Academy of Sciences(中国科学院);The Hong Kong University of Science and Technology(香港科技大学);Frontier Robotics(前沿机器人)