Related papers: STAR: Learning Diverse Robot Skill Abstractions th…
Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself,…
As comprehensive large model evaluation becomes prohibitively expensive, predicting model performance from limited observations has become essential. However, existing statistical methods struggle with pattern shifts, data sparsity, and…
Autonomous skill discovery aims to enable robots to acquire diverse behaviors without explicit supervision. Learning such behaviors directly on physical hardware remains challenging due to safety and data efficiency constraints. Existing…
Cross-task generalization is a core challenge in open-world robotic manipulation, and the key lies in extracting transferable manipulation knowledge from seen tasks. Recent in-context learning approaches leverage seen task demonstrations to…
Vision-Language-Action (VLA) models leverage powerful perceptual priors from web-scale Vision-Language Model (VLM) pre-training, yet they remain surprisingly brittle in practice, frequently failing at simple robotic tasks. To mitigate this,…
Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than solely relying on verbal reasoning. However, existing AI benchmarks primarily assess verbal reasoning, neglecting the…
A novel skill learning approach is proposed that allows a robot to acquire human-like visuospatial skills for object manipulation tasks. Visuospatial skills are attained by observing spatial relationships among objects through…
We present a framework for robot skill acquisition, which 1) efficiently scale up data generation of language-labelled robot data and 2) effectively distills this data down into a robust multi-task language-conditioned visuo-motor policy.…
The complexity of the real world demands robotic systems that can intelligently adapt to unseen situations. We present STEER, a robot learning framework that bridges high-level, commonsense reasoning with precise, flexible low-level…
Advances in robot learning have enabled robots to generate skills for a variety of tasks. Yet, robot learning is typically sample inefficient, struggles to learn from data sources exhibiting varied behaviors, and does not naturally…
Developing robotic systems capable of robustly executing long-horizon manipulation tasks with human-level dexterity is challenging, as such tasks require both physical dexterity and seamless sequencing of manipulation skills while robustly…
Defining reward functions for skill learning has been a long-standing challenge in robotics. Recently, vision-language models (VLMs) have shown promise in defining reward signals for teaching robots manipulation skills. However, existing…
Equivariant representation learning aims to capture variations induced by input transformations in the representation space, whereas invariant representation learning encodes semantic information by disregarding such transformations. Recent…
Effective planning of long-horizon deformable object manipulation requires suitable abstractions at both the spatial and temporal levels. Previous methods typically either focus on short-horizon tasks or make strong assumptions that…
Learning structured representations of visual scenes is currently a major bottleneck to bridging perception with reasoning. While there has been exciting progress with slot-based models, which learn to segment scenes into sets of objects,…
We observe that current state-of-the-art (SOTA) methods suffer from the performance imbalance issue when performing multi-task reinforcement learning (MTRL) tasks. While these methods may achieve impressive performance on average, they…
Evaluating policies using off-policy data is crucial for applying reinforcement learning to real-world problems such as healthcare and autonomous driving. Previous methods for off-policy evaluation (OPE) generally suffer from high variance…
Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: performance often peaks at a certain iteration depth and then collapses with further recurrence.…
Robots operating in open, unstructured real-world environments must rely on onboard visual perception while autonomously moving across different locations. Continuous changes in onboard camera viewpoints cause significant visual scale…
To assist with everyday human activities, robots must solve complex long-horizon tasks and generalize to new settings. Recent deep reinforcement learning (RL) methods show promise in fully autonomous learning, but they struggle to reach…