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

The paper proposes SWIM, a novel imitation learning method that can synthesize physically-based swimming motions from a single example, demonstrating superior data efficiency and generalization across…

PhyDrawGen is a neuro-symbolic pipeline that generates physically accurate diagrams from natural language by explicitly enforcing physical laws and geometric constraints, significantly outperforming c…

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…

The paper introduces Archon, a unified, fully pretrained multimodal model that addresses the challenge of generating holistic digital humans by integrating seven modalities (including text, audio, mot…

The paper proposes VERA, a decoupled policy that uses an action-free video world model combined with an embodiment-specific Inverse Dynamics Model (IDM) to achieve generalizable, zero-shot robot contr…

SimuScene introduces a novel compositional 3D reconstruction pipeline that integrates physics simulation directly into the shape and layout estimation process to generate stable, simulation-ready 3D s…

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

The paper introduces BilliardPhys-Bench, a new benchmark that demonstrates that current multimodal LLMs struggle with complex physical reasoning and predicting object dynamics in simulated environment…

The paper introduces Center-of-Pressure (CoP), a physics-grounded tactile representation that enables robust zero-shot sim-to-real transfer for complex, contact-rich manipulation tasks.

The paper introduces NewtPhys, a novel 4D dataset of real-world scenes with dense physical annotations, to systematically evaluate and reveal the limitations of foundation models in low-level Newtonia…

The paper introduces AnyMo, a unified multimodal framework that enables high-quality, scalable conditional human motion generation by leveraging a massive, cross-modal dataset and a masked modeling tr…

The paper introduces TouchSafeBench, a physics-grounded benchmark, to evaluate collision grounding—the ability to predict robot-human collisions—and finds that current Vision-Language Models (VLMs) ar…

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handl…

CubePart is a generative framework that enables the creation of complex 3D meshes by explicitly controlling and generating individual, semantically defined parts based on open-vocabulary text prompts.

The paper proposes a novel render-free framework that conditions video diffusion models directly on compressed 3D human mesh tokens, enabling robust 3D-aware human motion control without relying on re…

T2Mo is a novel framework that generates controllable dynamic 3D object shapes by combining explicit 3D trajectories for spatial guidance with natural language text semantics.

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 presents Mana, a sim-to-real framework for dexterous articulated tool manipulation.