16 citations · 24 across the 11 of their papers we have counts for
13 papers
WorldOracle: Benchmarking Action-Conditioned World Models against Real-World Executions
Haoyi Duan, Liliang Chen, Nan Wang +13
We introduce WorldOracle, a benchmark specifically designed to evaluate action-conditioned world models (ACWMs) against paired real-world executions. Given the same initial observa…
Grounded in Time: A Multi-Source Dataset and Benchmark for Temporal Grounding in Robotic Manipulation
Yi Wang, Yang Yang, Guangqi Xu +9
Robotic manipulation often requires inferring task-relevant states from past interactions when the current observation alone is insufficient to determine the appropriate action. De…
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing
Kaizhi Zheng, Xiaotong Chen, Xuehai He +7
Given the steep learning curve of professional 3D software and the time-consuming process of managing large 3D assets, language-guided 3D scene editing has significant potential in…
Tabletop Transparent Scene Reconstruction via Epipolar-Guided Optical Flow with Monocular Depth Completion Prior
Xiaotong Chen, Zheming Zhou, Zhuo Deng +4
Reconstructing transparent objects using affordable RGB-D cameras is a persistent challenge in robotic perception due to inconsistent appearances across views in the RGB domain and…
TransNet: Transparent Object Manipulation Through Category-Level Pose Estimation
Huijie Zhang, Anthony Opipari, Xiaotong Chen +3
Transparent objects present multiple distinct challenges to visual perception systems. First, their lack of distinguishing visual features makes transparent objects harder to detec…
TransNet: Category-Level Transparent Object Pose Estimation
Huijie Zhang, Anthony Opipari, Xiaotong Chen +3
Transparent objects present multiple distinct challenges to visual perception systems. First, their lack of distinguishing visual features makes transparent objects harder to detec…
VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation
Kaizhi Zheng, Xiaotong Chen, Odest Chadwicke Jenkins +1
Benefiting from language flexibility and compositionality, humans naturally intend to use language to command an embodied agent for complex tasks such as navigation and object mani…
ClearPose: Large-scale Transparent Object Dataset and Benchmark
Xiaotong Chen, Huijie Zhang, Zeren Yu +2
Transparent objects are ubiquitous in household settings and pose distinct challenges for visual sensing and perception systems. The optical properties of transparent objects leave…
ProgressLabeller: Visual Data Stream Annotation for Training Object-Centric 3D Perception
Xiaotong Chen, Huijie Zhang, Zeren Yu +2
Visual perception tasks often require vast amounts of labelled data, including 3D poses and image space segmentation masks. The process of creating such training data sets can prov…
Manipulation-Oriented Object Perception in Clutter through Affordance Coordinate Frames
Xiaotong Chen, Kaizhi Zheng, Zhen Zeng +5
In order to enable robust operation in unstructured environments, robots should be able to generalize manipulation actions to novel object instances. For example, to pour and serve…
LIT: Light-field Inference of Transparency for Refractive Object Localization
Zheming Zhou, Xiaotong Chen, Odest Chadwicke Jenkins
Translucency is prevalent in everyday scenes. As such, perception of transparent objects is essential for robots to perform manipulation. Compared with texture-rich or texture-less…
GRIP: Generative Robust Inference and Perception for Semantic Robot Manipulation in Adversarial Environments
Xiaotong Chen, Rui Chen, Zhiqiang Sui +4
Recent advancements have led to a proliferation of machine learning systems used to assist humans in a wide range of tasks. However, we are still far from accurate, reliable, and r…