Related papers: Decoupled Action Expert: Confining Task Knowledge …

A unified video and action model holds significant promise for robotics, where videos provide rich scene information for action prediction, and actions provide dynamics information for video prediction. However, effectively combining video…

Diffusion policies have demonstrated strong performance in generative modeling, making them promising for robotic manipulation guided by natural language instructions. However, generalizing language-conditioned diffusion policies to…

We introduce FLEX (FLow EXpert), a backbone architecture for generative modeling of spatio-temporal physical systems using diffusion models. FLEX operates in the residual space rather than on raw data, a modeling choice that we motivate…

The rapid evolution of Embodied AI has enabled Vision-Language-Action (VLA) models to excel in multimodal perception and task execution. However, applying Reinforcement Learning (RL) to these massive models in large-scale distributed…

Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse attention - enhance inference speed but typically rely on a…

Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to supervising VLAs with latent actions are fragmented and…

Moving beyond the traditional paradigm of adapting internet-pretrained models to physical tasks, we present DM0, an Embodied-Native Vision-Language-Action (VLA) framework designed for Physical AI. Unlike approaches that treat physical…

Training an agent to achieve particular goals or perform desired behaviors is often accomplished through reinforcement learning, especially in the absence of expert demonstrations. However, supporting novel goals or behaviors through…

Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate…

Multi-modal distribution in robotic manipulation action sequences poses critical challenges for imitation learning. To this end, existing approaches often model the action space as either a discrete set of tokens or a continuous,…

Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge to downstream robot control. Yet current diffusion-based…

Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model…

Multi-domain learning (MDL) aims to train a model with minimal average risk across multiple overlapping but non-identical domains. To tackle the challenges of dataset bias and domain domination, numerous MDL approaches have been proposed…

Visuomotor imitation learning policies enable robots to efficiently acquire manipulation skills from visual demonstrations. However, as scene complexity and visual distractions increase, policies that perform well in simple settings often…

Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios. We identify a critical pathology in current training paradigms where…

Humanoid loco-manipulation requires coordinated high-level motion plans with stable, low-level whole-body execution under complex robot-environment dynamics and long-horizon tasks. While diffusion policies (DPs) show promise for learning…

We present a diffusion-based approach to quadrupedal locomotion that simultaneously addresses the limitations of learning and interpolating between multiple skills and of (modes) offline adapting to new locomotion behaviours after training.…

With the rise of large-scale foundation models, efficiently adapting them to downstream tasks remains a central challenge. Linear probing, which freezes the backbone and trains a lightweight head, is computationally efficient but often…

Deep reinforcement learning (RL) algorithms typically parameterize the policy as a deep network that outputs either a deterministic action or a stochastic one modeled as a Gaussian distribution, hence restricting learning to a single…

Current approaches to multi-agent cooperation rely heavily on centralized mechanisms or explicit communication protocols to ensure convergence. This paper studies the problem of distributed multi-agent learning without resorting to…