Researchers presented an articulated humanoid robot head with 21 DoF, realistic silicone skin, and advanced face recognition and natural language processing capabilities.

A single robot platform, Handroid, is introduced that can function as both a dexterous hand and a humanoid robot, with interchangeable control and learning frameworks.

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

Development of a compliant full-body telepresence control stack for miniature humanoids, enabling tele-locomotion and manipulation.

This paper proposes a compact, explicit interface for humanoid robots that enables diverse manipulation skills and demonstrates its feasibility through natural-language-driven task roll-outs.

The paper presents CONTACTMIMIC, a learning framework that tracks explicit part-level binary contact commands alongside keypoint trajectories for object interaction tasks.

The paper introduces using frozen, generalist value functions as differentiable surrogates to efficiently optimize and analyze new multi-embodiment robot designs without requiring repeated reinforceme…

This paper proposes a human-likeness index based on time laws of human movement to evaluate the comfort of robot movements.

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-…

This paper introduces FurnitureVLA, a systematic study of real-scale bimanual furniture assembly using Vision-Language-Action models, improving simulation success from 48% to 80% and reducing errors.

This paper proposes coupled egocentric control, a body-following teleoperation approach for whole-body robot control, improving efficiency, reducing effort, and increasing ease of use.

This paper introduces Adversarial Dynamics Priors (ADP) for perturbation-resilient humanoid locomotion control, which uses dynamics features for adversarial regularization and encourages policy rollou…

The paper introduces RoboTrustBench, a comprehensive benchmark that evaluates the trustworthiness of video world models for robotic manipulation across challenging scenarios, finding that current mode…

The paper introduces RoboJailBench, the first standardized evaluation framework for assessing adversarial jailbreak attacks and defenses in embodied AI systems like robots.

GSAM introduces a generalizable and safe robotic framework for articulated object manipulation, significantly improving success rates and reducing variability across diverse tasks by integrating commo…

This paper derives puppetry principles for robot design, complementing prior insights from animation, theater, and dance.