Baoxiong Jia

papers

1,339

total citations

papers (20)

Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance

CVPR 2024arXiv

citations

ARNOLD: A Benchmark for Language-Grounded Task Learning with Continuous States in Realistic 3D Scenes

ICCV 2023arXiv

citations

LEMMA: A Multi-view Dataset for LEarning Multi-agent Multi-task Activities

ECCV 2020arXiv

citations

ACRE: Abstract Causal REasoning Beyond Covariation

CVPR 2021arXiv

citations

Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning

ECCV 2022arXiv

citations

Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting

ICLR 2025arXiv

citations

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

ICCV 2025arXiv

citations

Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis

CVPR 2025arXiv

citations

METASCENES: Towards Automated Replica Creation for Real-world 3D Scans

CVPR 2025arXiv

citations

GWM: Towards Scalable Gaussian World Models for Robotic Manipulation

ICCV 2025arXiv

citations

SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent

NEURIPS 2025arXiv

citations

MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes

CVPR 2025arXiv

citations

Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding

CVPR 2025arXiv

citations

ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab

NEURIPS 2023arXiv

citations

X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events

ICCV 2023arXiv

citations

Baoxiong Jia

papers (20)

An Embodied Generalist Agent in 3D World

Diffusion-Based Generation, Optimization, and Planning in 3D Scenes

EgoTaskQA: Understanding Human Tasks in Egocentric Videos

PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI

Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution

Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance

ARNOLD: A Benchmark for Language-Grounded Task Learning with Continuous States in Realistic 3D Scenes

LEMMA: A Multi-view Dataset for LEarning Multi-agent Multi-task Activities

ACRE: Abstract Causal REasoning Beyond Covariation

Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning

Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis

METASCENES: Towards Automated Replica Creation for Real-world 3D Scans

GWM: Towards Scalable Gaussian World Models for Robotic Manipulation

SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent

MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes

Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding

ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab

X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events

papers (20)

An Embodied Generalist Agent in 3D World

Diffusion-Based Generation, Optimization, and Planning in 3D Scenes

EgoTaskQA: Understanding Human Tasks in Egocentric Videos

PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI

Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution

Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance

ARNOLD: A Benchmark for Language-Grounded Task Learning with Continuous States in Realistic 3D Scenes

LEMMA: A Multi-view Dataset for LEarning Multi-agent Multi-task Activities

ACRE: Abstract Causal REasoning Beyond Covariation

Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning

Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis

METASCENES: Towards Automated Replica Creation for Real-world 3D Scans

GWM: Towards Scalable Gaussian World Models for Robotic Manipulation

SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent

MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes

Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding

ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab

X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events