1

Abstract We introduce InteractVLM, a novel method to estimate 3D contact points on human bodies and objects from single in-the-wild images, enabling accurate human-object joint reconstruction in 3D. This is challenging due to occlusions, depth ambiguities, and widely varying object shapes.

Abstract Benchmarks are essential for tracking rapid LLM progress—but today’s models exceed 90% on tasks like MMLU, saturating existing exams. We introduce Humanity’s Last Exam (HLE), a multi-modal, closed-ended benchmark spanning 2,500 questions across 100+ subjects at the frontier of human knowledge.

Abstract Acquiring physically plausible motor skills across diverse and unconventional morphologies—from humanoids to ants—is crucial for robotics and simulation. We introduce No-data Imitation Learning (NIL), which: Generates a reference video with a pretrained video diffusion model from a single simulation frame + text prompt.

Abstract We present HaPTIC, an approach that infers coherent 4D hand trajectories from monocular videos. Current video-based hand pose reconstruction methods primarily focus on improving frame-wise 3D pose using adjacent frames rather than studying consistent 4D hand trajectories in space.

Abstract Synthesizing accurate hand–object interactions (HOI) is critical for AR/VR and vision tasks. Existing dense–correspondence methods improve contact fidelity but lack full differentiability or generality. We propose CHOIR, a versatile, fully differentiable interaction field:

Abstract Synthesizing 3D whole bodies that realistically grasp objects is crucial for animation, mixed reality, and robotics. Key challenges include natural coordination between hand, body, and environment, and the scarcity of training data.

Abstract Generating realistic human motion is crucial for many computer vision and graphics applications. The rich diversity of human body shapes and sizes significantly influences how people move. However, existing motion models typically overlook these differences, using a normalized, average body instead.

Abstract Synthesizing natural human motions that enable a 3D human avatar to walk and reach for arbitrary goals in 3D space remains an unsolved problem with many applications. Existing methods (data-driven or using reinforcement learning) are limited in terms of generalization and motion naturalness.

Abstract Hands are dexterous and highly versatile manipulators that are central to how humans interact with objects and their environment. Consequently, modeling realistic hand-object interactions, including the subtle motion of individual fingers, is critical for applications in computer graphics, computer vision, and mixed reality.

Abstract Humans intuitively understand that inanimate objects do not move by themselves, but that state changes are typically caused by human manipulation (e.g., the opening of a book). This is not yet the case for machines.