Related papers: Long-Horizon Manipulation via Trace-Conditioned VL…

Foundation models like Vision-Language Models (VLMs) excel at common sense vision and language tasks such as visual question answering. However, they cannot yet directly solve complex, long-horizon robot manipulation problems requiring…

Vision-language-action (VLA) reasoning tasks require agents to interpret multimodal instructions, perform long-horizon planning, and act adaptively in dynamic environments. Existing approaches typically train VLA models in an end-to-end…

Bimanual robotic manipulation provides significant versatility, but also presents an inherent challenge due to the complexity involved in the spatial and temporal coordination between two hands. Existing works predominantly focus on…

Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. We introduce Context-Folding, a framework that empowers agents to actively manage their working context. An agent can procedurally…

Equipping embodied agents with the ability to reason about tasks, foresee physical outcomes, and generate precise actions is essential for general-purpose manipulation. While recent Vision-Language-Action (VLA) models have leveraged…

Sequential decision-making in high-dimensional continuous action spaces, particularly in stochastic environments, faces significant computational challenges. We explore this challenge in the traditional offline RL setting, where an agent…

In contrast to single-skill tasks, long-horizon tasks play a crucial role in our daily life, e.g., a pouring task requires a proper concatenation of reaching, grasping and pouring subtasks. As an efficient solution for transferring human…

Robotic manipulation in open-world environments requires reasoning across semantics, geometry, and long-horizon action dynamics. Existing hierarchical Vision-Language-Action (VLA) frameworks typically use 2D representations to connect…

We introduce Being-H0, a dexterous Vision-Language-Action model (VLA) trained on large-scale human videos. Existing VLAs struggle with complex manipulation tasks requiring high dexterity and generalize poorly to novel scenarios and tasks,…

Offline goal-conditioned reinforcement learning remains challenging for long-horizon tasks. While hierarchical approaches mitigate this issue by decomposing tasks, most existing methods rely on separate high- and low-level networks and…

Perceptive locomotion for legged robots requires anticipating and adapting to complex, dynamic environments. Model Predictive Control (MPC) serves as a strong baseline, providing interpretable motion planning with constraint enforcement,…

Enabling robots to flexibly schedule and compose learned skills for novel long-horizon manipulation under diverse perturbations remains a core challenge. Early explorations with end-to-end VLA models show limited success, as these models…

Robot swarms promise scalable assistance in complex and hazardous environments. Task planning lies at the core of human-swarm collaboration, translating the operator's intent into coordinated swarm actions and helping determine when…

Enabling humanoid robots to reliably execute complex multi-step manipulation tasks is crucial for their effective deployment in industrial and household environments. This paper presents a hierarchical planning and control framework…

VLA models have shown promising potential in embodied navigation by unifying perception and planning while inheriting the strong generalization abilities of large VLMs. However, most existing VLA models rely on reactive mappings directly…

General vision-language models increasingly support unified spatiotemporal reasoning over long video streams, yet deploying such capabilities on robots remains constrained by the prohibitive latency of processing long-horizon histories and…

We introduce LHM-Humanoid, a benchmark and learning framework for long-horizon whole-body humanoid loco-manipulation in diverse, cluttered scenes. In our setting, multiple objects are displaced from their intended locations and may obstruct…

Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing…

We present GR-RL, a robotic learning framework that turns a generalist vision-language-action (VLA) policy into a highly capable specialist for long-horizon dexterous manipulation. Assuming the optimality of human demonstrations is core to…

Recent high-capacity vision-language-action (VLA) models have demonstrated impressive performance on a range of robotic manipulation tasks by imitating human demonstrations. However, exploiting offline data with limited visited states will…