Related papers: Trajectory balance: Improved credit assignment in …

Traditional reinforcement learning often struggles to generate diverse, high-reward solutions, especially in domains like drug design and black-box function optimization. Markov Chain Monte Carlo (MCMC) methods provide an alternative method…

Generative Flow Networks (GFlowNets) have recently emerged as a suitable framework for generating diverse and high-quality molecular structures by learning from rewards treated as unnormalized distributions. Previous works in this framework…

Achieving chemical accuracy in quantum simulations is often constrained by the measurement bottleneck: estimating operators requires a large number of shots, which remains costly even on fault-tolerant devices and is further exacerbated on…

Optical flow estimation is a fundamental task in computer vision. Recent direct-regression methods using deep neural networks achieve remarkable performance improvement. However, they do not explicitly capture long-term motion…

In recent years, generative models have shown remarkable capabilities across diverse fields, including images, videos, language, and decision-making. By applying powerful generative models such as flow-based models to reinforcement…

With the rapid growth of traffic sensors deployed, a massive amount of traffic flow data are collected, revealing the long-term evolution of traffic flows and the gradual expansion of traffic networks. How to accurately forecasting these…

Graph Neural Networks (GNNs) play a crucial role in various fields. However, most existing deep graph learning frameworks assume pre-stored static graphs and do not support training on graph streams. In contrast, many real-world graphs are…

Flow-based text-to-image models follow deterministic trajectories, making it costly to explore diverse modes under limited sampling budgets. Existing approaches to improving diversity often rely on retraining or degrade image fidelity. To…

Generative Adversarial Networks have been shown to be powerful in generating content. To this end, they have been studied intensively in the last few years. Nonetheless, training these networks requires solving a saddle point problem that…

Generating molecular graphs is crucial in drug design and discovery but remains challenging due to the complex interdependencies between nodes and edges. While diffusion models have demonstrated their potentiality in molecular graph design,…

In many real-world settings, agents must learn from an offline dataset gathered by some prior behavior policy. Such a setting naturally leads to distribution shift between the behavior policy and the target policy being trained - requiring…

Recent years have witnessed the significant success of applying graph neural networks (GNNs) in learning effective node representations for classification. However, current GNNs are mostly built under the balanced data-splitting, which is…

Generative modeling has recently shown remarkable promise for visuomotor policy learning, enabling flexible and expressive control across diverse embodied AI tasks. However, existing generative policies often struggle with data…

Generative Flow Networks (GFlowNets), a class of generative models over discrete and structured sample spaces, have been previously applied to the problem of inferring the marginal posterior distribution over the directed acyclic graph…

Predicting the future trajectories of pedestrians on the road is an important task for autonomous driving. The pedestrian trajectory prediction is affected by scene paths, pedestrian's intentions and decision-making, which is a multi-modal…

Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference time, for example in diffusion and…

The availability of data is limited in some fields, especially for object detection tasks, where it is necessary to have correctly labeled bounding boxes around each object. A notable example of such data scarcity is found in the domain of…

Trajectory prediction, as a critical component of autonomous driving systems, has attracted the attention of many researchers. Existing prediction algorithms focus on extracting more detailed scene features or selecting more reasonable…

Generative policies based on expressive model classes, such as diffusion and flow matching, are well-suited to complex control problems with highly multimodal action distributions. Their expressivity, however, comes at a significant…

Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated…