Related papers: Active Tabular Augmentation via Policy-Guided Diff…

Intelligent access point (AP) deployment remains challenging in next-generation wireless networks due to complex indoor geometries and signal propagation. We firstly benchmark general-purpose large language models (LLMs) as agentic…

Diffusion Policies (DPs) have attracted attention for their ability to achieve significant accuracy improvements in various imitation learning tasks. However, DPs depend on Diffusion Models, which require multiple noise removal steps to…

This paper studies stable learning methods for generative models that enable high-quality data generation. Noise injection is commonly used to stabilize learning. However, selecting a suitable noise distribution is challenging.…

The recently introduced Theory of the Adjacent Possible (TAP) is a model of combinatorial innovation aiming to explain the "hockey-stick" upward trend of human technological evolution, where an explosion in the number of produced items with…

Diffusion-based planning has shown promising results in long-horizon, sparse-reward tasks by training trajectory diffusion models and conditioning the sampled trajectories using auxiliary guidance functions. However, due to their nature as…

Out-of-distribution generalization in reinforcement learning is hard to diagnose when benchmark shifts mix dynamics, observations, goals, and rewards. We address this with Tape, a controlled benchmark that isolates latent rule-shift in…

Missing value imputation in machine learning is the task of estimating the missing values in the dataset accurately using available information. In this task, several deep generative modeling methods have been proposed and demonstrated…

Learning performance data describe correct and incorrect answers or problem-solving attempts in adaptive learning, such as in intelligent tutoring systems (ITSs). Learning performance data tend to be highly sparse (80\%\(\sim\)90\% missing…

Data augmentation is a critical contributing factor to the success of deep learning but heavily relies on prior domain knowledge which is not always available. Recent works on automatic data augmentation learn a policy to form a sequence of…

Data augmentation has long been a cornerstone for reducing overfitting in vision models, with methods like AutoAugment automating the design of task-specific augmentations. Recent advances in generative models, such as conditional diffusion…

Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert…

Image and multimodal machine learning tasks are very challenging to solve in the case of poorly distributed data. In particular, data availability and privacy restrictions exacerbate these hurdles in the medical domain. The state of the art…

This paper presents Dual Action Policy (DAP), a novel approach to address the dynamics mismatch inherent in the sim-to-real gap of reinforcement learning. DAP uses a single policy to predict two sets of actions: one for maximizing task…

Data collection is often difficult in critical fields such as medicine, physics, and chemistry. As a result, classification methods usually perform poorly with these small datasets, leading to weak predictive performance. Increasing the…

Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space. Contrastive learning has witnessed…

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…

Data augmentation is crucial for pixel-wise annotation tasks like semantic segmentation, where labeling requires significant effort and intensive labor. Traditional methods, involving simple transformations such as rotations and flips,…

Recently, Vision-Language-Action models (VLA) have advanced robot imitation learning, but high data collection costs and limited demonstrations hinder generalization and current imitation learning methods struggle in out-of-distribution…

Tabular data is one of the most ubiquitous modalities, yet the literature on tabular generative foundation models is lagging far behind its text and vision counterparts. Creating such a model is hard, due to the heterogeneous feature spaces…

In robotic visuomotor policy learning, diffusion-based models have achieved significant success in improving the accuracy of action trajectory generation compared to traditional autoregressive models. However, they suffer from inefficiency…