This paper organizes embodied data sources for multimodal foundation models into a pyramid, focusing on real-robot, UMI-style, egocentric and exocentric, simulation, and general vision-language data.

This paper provides a systematic survey of ROS 2 middleware and identifies architectural limits through three dimensions: Space, Time, and State.

The paper proposes an automated data-collection scheme for contact-rich tasks using offline deep reinforcement learning, achieving high success rates and generalization.

RoboDream introduces an embodiment-centric world model that synthesizes photorealistic, physically feasible robot demonstrations by decoupling motion generation from environment synthesis, significant…

This paper introduces Retriever, an asynchronous decision model and runtime system for building long-horizon robot agents with explicit clock and input-consumption semantics.

This paper proposes ASMR, a framework for automatically generating compact and informative schemas from historical ship maintenance reports using two specialized agents.

ASPIRE is a continual learning system that autonomously writes and refines robot control programs in a code-as-policy paradigm, discovering transferable skills and surpassing prior methods on various…

This paper presents GRAIL, a digital generation pipeline that synthesizes human-object interactions for humanoid robots.

The study compares agentic data retrieval using unstructured web data versus structured, semantically-annotated datasets, concluding that semantic metadata remains essential for high-precision, reliab…

The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.

This paper presents a new modular architecture for NeoSLAM using modern frameworks, achieving real-time execution and minimal data discarding. It also compares NeoSLAM and RatSLAM across three dataset…

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

This paper presents ABot-C0, a motion-control system for quadruped robots, which includes a scalable multi-source motion-data pipeline, robust policy learning, and a unified deployment stack for real-…

The paper proposes a method for constructing scene graphs to represent and characterize assembly relationships between components using a Faster R-CNN model, transformer architecture, adjacency matrix…

The paper presents AutoDex, a system that automatically collects real-world data for robust dexterous grasping, achieving a 4.8x throughput improvement over teleoperation and higher success rate than…