Related papers: Mimicking-Bench: A Benchmark for Generalizable Hum…
How (dis)similar are the learning trajectories of vision-language models and children? Recent modeling work has attempted to understand the gap between models' and humans' data efficiency by constructing models trained on less data,…
With the rapid evolution of 3D generation algorithms, the cost of producing 3D humanoid character models has plummeted, yet the field is impeded by the lack of a comprehensive dataset for automatic rigging, which is a pivotal step in…
Learning from human demonstrations has exhibited remarkable achievements in robot manipulation. However, the challenge remains to develop a robot system that matches human capabilities and data efficiency in learning and generalizability,…
Reasoning about dynamic spatial relationships is essential, as both observers and objects often move simultaneously. Although vision-language models (VLMs) and visual expertise models excel in 2D tasks and static scenarios, their ability to…
We propose a new 3D holistic++ scene understanding problem, which jointly tackles two tasks from a single-view image: (i) holistic scene parsing and reconstruction---3D estimations of object bounding boxes, camera pose, and room layout, and…
As robots are increasingly deployed in real-world scenarios, a key question is how to best transfer knowledge learned in one environment to another, where shifting constraints and human preferences render adaptation challenging. A central…
The comic domain is rapidly advancing with the development of single-page analysis and synthesis models. However, evaluation metrics and datasets lag behind, often limited to small-scale or single-style test sets. We introduce a novel…
Animating realistic character interactions with the surrounding environment is important for autonomous agents in gaming, AR/VR, and robotics. However, current methods for human motion reconstruction struggle with accurately placing humans…
Recent advancements in implicit 3D reconstruction methods, e.g., neural rendering fields and Gaussian splatting, have primarily focused on novel view synthesis of static or dynamic objects with continuous motion states. However, these…
Human-robot interaction (HRI) has long studied how agents and people coordinate to achieve shared goals. In this work, we formalize and benchmark the non-intrusive assistance as an independent paradigm of HRI, where a robot proactively…
Understanding action correspondence between humans and robots is essential for evaluating alignment in decision-making, particularly in human-robot collaboration and imitation learning within unstructured environments. We propose a…
This paper introduces a framework, called EMOTION, for generating expressive motion sequences in humanoid robots, enhancing their ability to engage in humanlike non-verbal communication. Non-verbal cues such as facial expressions, gestures,…
Previous humanoid robot research works treat the robot as a bipedal mobile manipulation platform, where only the feet and hands contact the environment. However, we humans use all body parts to interact with the world, e.g., we sit in…
Video generation models have significantly advanced embodied intelligence, unlocking new possibilities for generating diverse robot data that capture perception, reasoning, and action in the physical world. However, synthesizing…
We introduce DreamGen, a simple yet highly effective 4-stage pipeline for training robot policies that generalize across behaviors and environments through neural trajectories - synthetic robot data generated from video world models.…
This paper presents GenH2R, a framework for learning generalizable vision-based human-to-robot (H2R) handover skills. The goal is to equip robots with the ability to reliably receive objects with unseen geometry handed over by humans in…
Creating machines capable of understanding the world in 3D is essential in assisting designers that build and edit 3D environments and robots navigating and interacting within a three-dimensional space. Inspired by advances in language and…
This paper presents a new large multiview dataset called HUMBI for human body expressions with natural clothing. The goal of HUMBI is to facilitate modeling view-specific appearance and geometry of five primary body signals including gaze,…
Humanoid robots have shown success in locomotion and manipulation. Despite these basic abilities, humanoids are still required to quickly understand human instructions and react based on human interaction signals to become valuable…
Recent advances in humanoid locomotion have enabled dynamic behaviors such as dancing, martial arts, and parkour, yet these capabilities are predominantly demonstrated in open, flat, and obstacle-free settings. In contrast, real-world…