Related papers: RMD: A Simple Baseline for More General Human Moti…

Diffusion models (DMs) have recently demonstrated remarkable generation capability. However, their training generally requires huge computational resources and large-scale datasets. To solve these, recent studies empower DMs with the…

Generating the motion of orchestral conductors from a given piece of symphony music is a challenging task since it requires a model to learn semantic music features and capture the underlying distribution of real conducting motion. Prior…

Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, standard DLM training uses a static, single-step masked prediction…

Many of today's data is time-series data originating from various sources, such as sensors, transaction systems, or production systems. Major challenges with such data include privacy and business sensitivity. Generative time-series models…

Magnetic Resonance Imaging (MRI) is a powerful medical imaging modality, but unfortunately suffers from long scan times which, aside from increasing operational costs, can lead to image artifacts due to patient motion. Motion during the…

We propose a novel mechanism for real-time (human-in-the-loop) feedback focused on false positive reduction to enhance anomaly detection models. It was designed for the lightweight deployment of a behavioral network anomaly detection model.…

Learning physical dynamics from data is a fundamental challenge in machine learning and scientific modeling. Real-world observational data are inherently incomplete and irregularly sampled, posing significant challenges for existing…

Data augmentation plays a crucial role in deep learning, enhancing the generalization and robustness of learning-based models. Standard approaches involve simple transformations like rotations and flips for generating extra data. However,…

Recently, a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks. In these techniques, two or more randomly selected natural images are mixed together to generate an…

In the real world, trajectory data is often sparse and incomplete due to low collection frequencies or limited device coverage. Trajectory recovery aims to recover these missing trajectory points, making the trajectories denser and more…

While Masked Diffusion Language Models (MDLMs) relying on token masking and unmasking have shown promise in language modeling, their computational efficiency and generation flexibility remain constrained by the masking paradigm. In this…

Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support tasks required for 3D understanding, such as view-consistent 3D…

This paper tackles the problem of human motion prediction, consisting in forecasting future body poses from historically observed sequences. State-of-the-art approaches provide good results, however, they rely on deep learning architectures…

Real-world databases are predominantly relational, comprising multiple interlinked tables that contain complex structural and statistical dependencies. Learning generative models on relational data has shown great promise in generating…

Vision-based motion capture solutions often struggle with occlusions, which result in the loss of critical joint information and hinder accurate 3D motion reconstruction. Other wearable alternatives also suffer from noisy or unstable data,…

Diffusion models, a powerful and universal generative AI technology, have achieved tremendous success in computer vision, audio, reinforcement learning, and computational biology. In these applications, diffusion models provide flexible…

Safe and effective motion planning is crucial for autonomous robots. Diffusion models excel at capturing complex agent interactions, a fundamental aspect of decision-making in dynamic environments. Recent studies have successfully applied…

Time series generation is a crucial research topic in the area of decision-making systems, which can be particularly important in domains like autonomous driving, healthcare, and, notably, robotics. Recent approaches focus on learning in…

Generating realistic and controllable human motions, particularly those involving rich multi-character interactions, remains a significant challenge due to data scarcity and the complexities of modeling inter-personal dynamics. To address…

The paper demonstrate that simple adjustments of the fine-tuning recipes of multimodal large language models (MLLM) are sufficient to mitigate catastrophic forgetting. On visual question answering, we design a 2x2 experimental framework to…