Related papers: Instructed Diffuser with Temporal Condition Guidan…

Trajectory prediction facilitates effective planning and decision-making, while constrained trajectory prediction integrates regulation into prediction. Recent advances in constrained trajectory prediction focus on structured constraints by…

Conditional diffusion models have achieved remarkable success in various generative tasks recently, but their training typically relies on large-scale datasets that inevitably contain imprecise information in conditional inputs. Such…

Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or…

Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning. In these applications, conditional diffusion models incorporate…

Temporal abstraction and efficient planning pose significant challenges in offline reinforcement learning, mainly when dealing with domains that involve temporally extended tasks and delayed sparse rewards. Existing methods typically plan…

Recently, the application of diffusion probabilistic models has advanced speech enhancement through generative approaches. However, existing diffusion-based methods have focused on the generation process in high-dimensional waveform or…

In this paper, a new reinforcement learning (RL) method known as the method of temporal differential is introduced. Compared to the traditional temporal-difference learning method, it plays a crucial role in developing novel RL techniques…

Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio. Due to their adaptiveness in iterative refinement, they provide a strong potential for achieving better non-autoregressive…

Time series generation focuses on modeling the underlying data distribution and resampling to produce authentic time series data. Key components, such as trend and seasonality, drive temporal fluctuations, yet many existing approaches fail…

Diffusion models for continuous data gained widespread adoption owing to their high quality generation and control mechanisms. However, controllable diffusion on discrete data faces challenges given that continuous guidance methods do not…

Generative models have attracted significant interest due to their ability to handle uncertainty by learning the inherent data distributions. However, two prominent generative models, namely Generative Adversarial Networks (GANs) and…

Compositional diffusion planning generates long-horizon trajectories by stitching together overlapping short-horizon segments through score composition. However, when local plan distributions are multimodal, existing compositional methods…

Offline reinforcement learning (RL) enables agents to learn policies from fixed datasets, avoiding costly or unsafe environment interactions. However, its effectiveness is often limited by dataset sparsity and the lack of transition overlap…

Long-horizon contact-rich manipulation has long been a challenging problem, as it requires reasoning over both discrete contact modes and continuous object motion. We introduce Implicit Contact Diffuser (ICD), a diffusion-based model that…

Causal discovery from time series is critical for many real-world applications, such as tracing the root causes of anomalies. Existing approaches typically rely on dataset-specific optimization, making it difficult to transfer their causal…

Data generation is recognized as a potent strategy for unsupervised domain adaptation (UDA) pertaining semantic segmentation in adverse weathers. Nevertheless, these adverse weather scenarios encompass multiple possibilities, and…

While pre-trained visual representations have significantly advanced imitation learning, they are often task-agnostic as they remain frozen during policy learning. In this work, we explore leveraging pre-trained text-to-image diffusion…

Recent deep learning approaches seek to automate CAD creation by representing a model as a sequence of discrete commands and parameters, and then generating them using autoregressive models or continuous diffusion operating in Euclidean…

Federated learning (FL) has become a cornerstone in decentralized learning, where, in many scenarios, the incoming data distribution will change dynamically over time, introducing continuous learning (CL) problems. This continual federated…

Time series generation (TSG) synthesizes realistic sequences and has achieved remarkable success. Among TSG, conditional models generate sequences given observed covariates, however, such models learn observational correlations without…