Baoxiong Jia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Baoxiong Jia has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Siyuan Huang
Beijing Institute for General Artificial Intelligence (BIGAI)
9 shared publications - Yixin Zhu
Peking University
6 shared publications - Song-Chun Zhu
Peking University
5 shared publications - Yixin Chen
BIGAI
5 shared publications - Chi Zhang
School of Intelligence Science and Technology, Peking University, Beijing, China and State Key Lab of General AI, Beijing, China
4 shared publications - Feng Gao
University of California Los Angeles
2 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14924-14931
OmniTrack: General Motion Tracking via Physics-Consistent Reference
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14924-14931
OmniTrack: General Motion Tracking via Physics-Consistent Reference
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3853-3862
ARFlow: Real-time Human Action-Reaction Synthesis with Reprojection Guidance
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3853-3862
Open AccessARFlow: Real-time Human Action-Reaction Synthesis with Reprojection Guidance
- 22 October 2024
- Published by Springer Nature
- p. 270-288
SlotLifter: Slot-Guided Feature Lifting for Learning Object-Centric Radiance Fields
- 22 October 2024
- Published by Springer Nature
- p. 270-288
SlotLifter: Slot-Guided Feature Lifting for Learning Object-Centric Radiance Fields
- Top Cited Papers
- 22 October 2024
- Published by Springer Nature
- p. 289-310
SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
- 22 October 2024
- Published by Springer Nature
- p. 289-310
Top Cited PapersSceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
- 30 September 2024
- Published by Springer Nature
- p. 188-206
Unifying 3D Vision-Language Understanding via Promptable Queries
- 30 September 2024
- Published by Springer Nature
- p. 188-206
Unifying 3D Vision-Language Understanding via Promptable Queries
- Open Access
SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields
The ability to distill object-centric abstractions from intricate visual scenes underpins human-level generalization. Despite the significant progress in object-centric learning methods, learning object-centric representations in the 3D physical world remains a crucial challenge. In this work, we propose SlotLifter, a novel object-centric radiance model addressing scene reconstruction and decomposition jointly via slot-guided feature lifting. Such a design unites object-centric learning representations and image-based rendering methods, offering state-of-the-art performance in scene decomposition and novel-view synthesis on four challenging synthetic and four complex real-world datasets, outperforming existing 3D object-centric learning methods by a large margin. Through extensive ablative studies, we showcase the efficacy of designs in SlotLifter, revealing key insights for potential future directions.
Open AccessSlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields
The ability to distill object-centric abstractions from intricate visual scenes underpins human-level generalization. Despite the significant progress in object-centric learning methods, learning object-centric representations in the 3D physical world remains a crucial challenge. In this work, we propose SlotLifter, a novel object-centric radiance model addressing scene reconstruction and decomposition jointly via slot-guided feature lifting. Such a design unites object-centric learning representations and image-based rendering methods, offering state-of-the-art performance in scene decomposition and novel-view synthesis on four challenging synthetic and four complex real-world datasets, outperforming existing 3D object-centric learning methods by a large margin. Through extensive ablative studies, we showcase the efficacy of designs in SlotLifter, revealing key insights for potential future directions.
- Open Access
- 19 April 2024
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 10 (16) , eadg2488
Human-level few-shot concept induction through minimax entropy learning
Humans learn concepts both from labeled supervision and by unsupervised observation of patterns, a process machines are being taught to mimic by training on large annotated datasets—a method quite different from the human pathway, wherein few examples with no supervision suffice to induce an unfamiliar relational concept. We introduce a computational model designed to emulate human inductive reasoning on abstract reasoning tasks, such as those in IQ tests, using a minimax entropy approach. This method combines identifying the most effective constraints on data via minimum entropy with determining the best combination of them via maximum entropy. Our model, which applies this unsupervised technique, induces concepts from just one instance, reaching human-level performance on tasks of Raven’s Progressive Matrices (RPM), Machine Number Sense (MNS), and Odd-One-Out (O 3 ). These results demonstrate the potential of minimax entropy learning for enabling machines to learn relational concepts efficiently with minimal input.
- 19 April 2024
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 10 (16) , eadg2488
Open AccessHuman-level few-shot concept induction through minimax entropy learning
Humans learn concepts both from labeled supervision and by unsupervised observation of patterns, a process machines are being taught to mimic by training on large annotated datasets—a method quite different from the human pathway, wherein few examples with no supervision suffice to induce an unfamiliar relational concept. We introduce a computational model designed to emulate human inductive reasoning on abstract reasoning tasks, such as those in IQ tests, using a minimax entropy approach. This method combines identifying the most effective constraints on data via minimum entropy with determining the best combination of them via maximum entropy. Our model, which applies this unsupervised technique, induces concepts from just one instance, reaching human-level performance on tasks of Raven’s Progressive Matrices (RPM), Machine Number Sense (MNS), and Odd-One-Out (O 3 ). These results demonstrate the potential of minimax entropy learning for enabling machines to learn relational concepts efficiently with minimal input.
- Open Access
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3969-3979
X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events
Intuitive physics is pivotal for human understanding of the physical world, enabling prediction and interpretation of events even in infancy. Nonetheless, replicating this level of intuitive physics in artificial intelligence (AI) remains a formidable challenge. This study introduces X-VoE, a comprehensive benchmark dataset, to assess AI agents’ grasp of intuitive physics. Built on the developmental psychology-rooted Violation of Expectation (VoE) paradigm, X-VoE establishes a higher bar for the explanatory capacities of intuitive physics models. Each VoE scenario within X-VoE encompasses three distinct settings, probing models’ comprehension of events and their underlying explanations. Beyond model evaluation, we present an explanation-based learning system that captures physics dynamics and infers occluded object states solely from visual sequences, without explicit occlusion labels. Experimental outcomes highlight our model’s alignment with human commonsense when tested against X-VoE. A remarkable feature is our model’s ability to visually expound VoE events by reconstructing concealed scenes. Concluding, we discuss the findings’ implications and outline future research directions. Through X-VoE, we catalyze the advancement of AI endowed with human-like intuitive physics capabilities.
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3969-3979
Open AccessX-VoE: Measuring eXplanatory Violation of Expectation in Physical Events
Intuitive physics is pivotal for human understanding of the physical world, enabling prediction and interpretation of events even in infancy. Nonetheless, replicating this level of intuitive physics in artificial intelligence (AI) remains a formidable challenge. This study introduces X-VoE, a comprehensive benchmark dataset, to assess AI agents’ grasp of intuitive physics. Built on the developmental psychology-rooted Violation of Expectation (VoE) paradigm, X-VoE establishes a higher bar for the explanatory capacities of intuitive physics models. Each VoE scenario within X-VoE encompasses three distinct settings, probing models’ comprehension of events and their underlying explanations. Beyond model evaluation, we present an explanation-based learning system that captures physics dynamics and infers occluded object states solely from visual sequences, without explicit occlusion labels. Experimental outcomes highlight our model’s alignment with human commonsense when tested against X-VoE. A remarkable feature is our model’s ability to visually expound VoE events by reconstructing concealed scenes. Concluding, we discuss the findings’ implications and outline future research directions. Through X-VoE, we catalyze the advancement of AI endowed with human-like intuitive physics capabilities.
- Open Access
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 20426-20438
ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes
Understanding the continuous states of objects is essential for task learning and planning in the real world. However, most existing task learning benchmarks assume discrete (e.g., binary) object goal states, which poses challenges for the learning of complex tasks and transferring learned policy from simulated environments to the real world. Furthermore, state discretization limits a robot’s ability to follow human instructions based on the grounding of actions and states. To tackle these challenges, we present ARNOLD, a benchmark that evaluates language-grounded task learning with continuous states in realistic 3D scenes. ARNOLD is comprised of 8 language-conditioned tasks that involve understanding object states and learning policies for continuous goals. To promote language-instructed learning, we provide expert demonstrations with template-generated language descriptions. We assess task performance by utilizing the latest language-conditioned policy learning models. Our results indicate that current models for language-conditioned manipulations continue to experience significant challenges in novel goal-state generalizations, scene generalizations, and object generalizations. These findings highlight the need to develop new algorithms that address this gap and underscore the potential for further research in this area. Project website: https://arnold-benchmark.github.io.
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 20426-20438
Open AccessARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes
Understanding the continuous states of objects is essential for task learning and planning in the real world. However, most existing task learning benchmarks assume discrete (e.g., binary) object goal states, which poses challenges for the learning of complex tasks and transferring learned policy from simulated environments to the real world. Furthermore, state discretization limits a robot’s ability to follow human instructions based on the grounding of actions and states. To tackle these challenges, we present ARNOLD, a benchmark that evaluates language-grounded task learning with continuous states in realistic 3D scenes. ARNOLD is comprised of 8 language-conditioned tasks that involve understanding object states and learning policies for continuous goals. To promote language-instructed learning, we provide expert demonstrations with template-generated language descriptions. We assess task performance by utilizing the latest language-conditioned policy learning models. Our results indicate that current models for language-conditioned manipulations continue to experience significant challenges in novel goal-state generalizations, scene generalizations, and object generalizations. These findings highlight the need to develop new algorithms that address this gap and underscore the potential for further research in this area. Project website: https://arnold-benchmark.github.io.
- 23 October 2022
- Published by Springer Nature
- p. 692-709
Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning
- 23 October 2022
- Published by Springer Nature
- p. 692-709
Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning