Related papers: EDGI: Equivariant Diffusion for Planning with Embo…

Recent advances in diffusion models hold significant potential in robotics, enabling the generation of diverse and smooth trajectories directly from raw representations of the environment. Despite this promise, applying diffusion models to…

This paper proposes a supervised training algorithm for learning stochastic resource allocation policies with generative diffusion models (GDMs). We formulate the allocation problem as the maximization of an ergodic utility function subject…

3D Euclidean symmetry equivariant neural networks have demonstrated notable success in modeling complex physical systems. We introduce a framework for relaxed $E(3)$ graph equivariant neural networks that can learn and represent symmetry…

Imitation learning powered by generative models has proven effective for modeling complex single-agent behaviors. However, teaching multi-agent systems, like multiple arms or vehicles, to coordinate through imitation learning is hindered by…

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does…

Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…

Robust coordination is critical for effective decision-making in multi-agent systems, especially under partial observability. A central question in Multi-Agent Reinforcement Learning (MARL) is whether to engineer communication protocols or…

Language models are exhibiting increasing capability in knowledge utilization and reasoning. However, when applied as agents in embodied environments, they often suffer from misalignment between their intrinsic knowledge and environmental…

Embodied decision-making enables agents to translate high-level goals into executable actions through continuous interactions within the physical world, forming a cornerstone of general-purpose embodied intelligence. Large language models…

Multimodal large language models are evolving toward multimodal agents capable of proactively executing tasks. Most agent research focuses on GUI or embodied scenarios, which correspond to agents interacting with 2D virtual worlds or 3D…

Imitation learning is a class of promising policy learning algorithms that is free from many practical issues with reinforcement learning, such as the reward design issue and the exploration hardness. However, the current imitation…

Despite remarkable progress in autoregressive language models, alternative generative paradigms beyond left-to-right generation are still being actively explored. Discrete diffusion models, with the capacity for parallel generation, have…

Embodied agents can benefit from skills that guide object search, action execution, and state changes across diverse environments. Since embodied environments vary across layouts, object states, and other execution factors, these skills…

This paper introduces EmbodiedAgent, a hierarchical framework for heterogeneous multi-robot control. EmbodiedAgent addresses critical limitations of hallucination in impractical tasks. Our approach integrates a next-action prediction…

Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to classical trajectory optimizers. While conceptually simple,…

Guidance techniques are commonly used in diffusion and flow models to improve image quality and input consistency for conditional generative tasks such as class-conditional and text-to-image generation. In particular, classifier-free…

Embodied agents, in the form of virtual agents or social robots, are rapidly becoming more widespread. In human-human interactions, humans use nonverbal behaviours to convey their attitudes, feelings, and intentions. Therefore, this…

Failure is inevitable for embodied navigation in complex environments. To enhance the resilience, replanning (RP) is a viable option, where the robot is allowed to fail, but is capable of adjusting plan until success. However, existing RP…

Continuous Conditional Diffusion Model (CCDM) is a diffusion-based framework designed to generate high-quality images conditioned on continuous regression labels. Although CCDM has demonstrated clear advantages over prior approaches across…

Training energy-based models (EBMs) on high-dimensional data can be both challenging and time-consuming, and there exists a noticeable gap in sample quality between EBMs and other generative frameworks like GANs and diffusion models. To…