Related papers: FFHFlow: Diverse and Uncertainty-Aware Dexterous G…
Unbounded 3D world generation is emerging as a foundational task for scene modeling in computer vision, graphics, and robotics. In this work, we present WorldFlow3D, a novel method capable of generating unbounded 3D worlds. Building upon a…
Deep generative modeling has seen impressive advances in recent years, to the point where it is now commonplace to see simulated samples (e.g., images) that closely resemble real-world data. However, generation quality is generally…
Recent 4D shape representations model continuous temporal evolution of implicit shapes by (1) learning query flows without leveraging shape and articulation priors or (2) decoding shape occupancies separately for each time value. Thus, they…
Despite advances in hand-object interaction modeling, generating realistic dexterous manipulation data for robotic hands remains a challenge. Retargeting methods often suffer from low accuracy and fail to account for hand-object…
Flow Matching (FM) has recently emerged as a leading approach for high-fidelity visual generation, offering a robust continuous-time alternative to ordinary differential equation (ODE) based models. However, despite their success, FM models…
We propose to learn to generate grasping motion for manipulation with a dexterous hand using implicit functions. With continuous time inputs, the model can generate a continuous and smooth grasping plan. We name the proposed model…
We present a generative modeling framework for synthesizing physically feasible two-dimensional incompressible flows under arbitrary obstacle geometries and boundary conditions. Whereas existing diffusion-based flow generators either ignore…
Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks. Yet, most existing approaches remain limited in handling multiple types of…
Teaching a multi-fingered dexterous robot to grasp objects in the real world has been a challenging problem due to its high dimensional state and action space. We propose a robot-learning system that can take a small number of human…
Efficient sampling of complex data distributions can be achieved using trained invertible flows (IF), where the model distribution is generated by pushing a simple base distribution through multiple non-linear bijective transformations.…
In this paper, we propose Continuous Graph Flow, a generative continuous flow based method that aims to model complex distributions of graph-structured data. Once learned, the model can be applied to an arbitrary graph, defining a…
Future motion representations, such as optical flow, offer immense value for control and generative tasks. However, forecasting generalizable spatially dense motion representations remains a key challenge, and learning such forecasting from…
Many density estimation techniques for 3D human motion prediction require a significant amount of inference time, often exceeding the duration of the predicted time horizon. To address the need for faster density estimation for 3D human…
Generating human grasping poses that accurately reflect both object geometry and user-specified interaction semantics is essential for natural hand-object interactions in AR/VR and embodied AI. However, existing semantic grasping approaches…
Recent advancements in prosthetic technology have increasingly focused on enhancing dexterity and autonomy through intelligent control systems. Vision-based approaches offer promising results for enabling prosthetic hands to interact more…
Flow Matching has limited ability in achieving one-step generation due to its reliance on learned curved trajectories. Previous studies have attempted to address this limitation by either modifying the coupling distribution to prevent…
Generative flows are promising tractable models for density modeling that define probabilistic distributions with invertible transformations. However, tractability imposes architectural constraints on generative flows, making them less…
Dexterous grasping remains a central challenge in robotics due to the complexity of its high-dimensional state and action space. We introduce T(R,O) Grasp, a diffusion-based framework that efficiently generates accurate and diverse grasps…
This work presents mixed variational flows (MixFlows), a new variational family that consists of a mixture of repeated applications of a map to an initial reference distribution. First, we provide efficient algorithms for i.i.d. sampling,…
Tactile sensation is essential for contact-rich manipulation tasks. It provides direct feedback on object geometry, surface properties, and interaction forces, enhancing perception and enabling fine-grained control. An inherent limitation…