Results 1 to 10 of about 24,691,873 (342)
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning [PDF]
Neural Information Processing Systems, 2023 Diffusion models have demonstrated highly-expressive generative capabilities in vision and NLP. Recent studies in reinforcement learning (RL) have shown that diffusion models are also powerful in modeling complex policies or trajectories in offline ...
Haoran He +7 more
openalex +3 more sources
CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis [PDF]
International Conference on Medical Image Computing and Computer-Assisted Intervention, 2023 MRI synthesis promises to mitigate the challenge of missing MRI modality in clinical practice. Diffusion model has emerged as an effective technique for image synthesis by modelling complex and variable data distributions.
Lan Jiang +4 more
openalex +3 more sources
Human Motion Diffusion Model [PDF]
International Conference on Learning Representations, 2022 Natural and expressive human motion generation is the holy grail of computer animation. It is a challenging task, due to the diversity of possible motion, human perceptual sensitivity to it, and the difficulty of accurately describing it.
Guy Tevet +5 more
semanticscholar +1 more source
Diffusion Model Alignment Using Direct Preference Optimization [PDF]
Computer Vision and Pattern Recognition, 2023 Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has not been widely
Bram Wallace +9 more
semanticscholar +1 more source
ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting [PDF]
Neural Information Processing Systems, 2023 Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps.
Zongsheng Yue +2 more
semanticscholar +1 more source
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model [PDF]
Computer Vision and Pattern Recognition, 2023 This paper studies the human image animation task, which aims to generate a video of a certain reference iden-tity following a particular motion sequence.
Zhongcong Xu +7 more
semanticscholar +1 more source
SE(3) diffusion model with application to protein backbone generation [PDF]
International Conference on Machine Learning, 2023 The design of novel protein structures remains a challenge in protein engineering for applications across biomedicine and chemistry. In this line of work, a diffusion model over rigid bodies in 3D (referred to as frames) has shown success in generating ...
Jason Yim +6 more
semanticscholar +1 more source
Your Diffusion Model is Secretly a Zero-Shot Classifier [PDF]
IEEE International Conference on Computer Vision, 2023 The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a staggering variety of prompts and exhibit impressive compositional ...
Alexander C. Li +4 more
semanticscholar +1 more source
MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 Human motion modeling is important for many modern graphics applications, which typically require professional skills. In order to remove the skill barriers for laymen, recent motion generation methods can directly generate human motions conditioned on ...
Mingyuan Zhang +6 more
semanticscholar +1 more source
FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model [PDF]
IEEE International Conference on Computer Vision, 2023 Recently, conditional diffusion models have gained popularity in numerous applications due to their exceptional generation ability. However, many existing methods are training-required.
Jiwen Yu +4 more
semanticscholar +1 more source