Jiayuan Mao

Discovering Hybrid World Representations with Co-Evolving Foundation Models AAAI 2026 SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models CVPR 2026 Agent Workflow Memory ICML 2025 Foundation Models Meet Embodied Agents NAACL 2025 Generating Fine Details of Entity Interactions EMNLP 2025 Infer Human’s Intentions Before Following Natural Language Instructions AAAI 2025 Learning Language through Grounding NAACL 2025 What Makes a Maze Look Like a Maze? ICLR 2025 Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making NeurIPS 2024 Grounding Language Plans in Demonstrations Through Counterfactual Perturbations ICLR 2024 Learning Compositional Behaviors from Demonstration and Language CoRL 2024 Learning Grounded Action Abstractions from Language ICLR 2024 Learning Iterative Reasoning through Energy Diffusion ICML 2024 Learning Planning Abstractions from Language ICLR 2024 Learning to Act from Actionless Videos through Dense Correspondences ICLR 2024 Set It Up!: Functional Object Arrangement with Compositional Generative Models RSS 2024 Composable Part-Based Manipulation CoRL 2023 Compositional Diffusion-Based Continuous Constraint Solvers CoRL 2023 Learning Rational Subgoals from Demonstrations and Instructions AAAI 2023 Learning Reusable Manipulation Strategies CoRL 2023 NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations CVPR 2023 Programmatically Grounded, Compositionally Generalizable Robotic Manipulation ICLR 2023 What Planning Problems Can A Relational Neural Network Solve? NeurIPS 2023 What’s Left? Concept Grounding with Logic-Enhanced Foundation Models NeurIPS 2023 CLEVRER-Humans: Describing Physical and Causal Events the Human Way NeurIPS 2022 FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations ICLR 2022 HandMeThat: Human-Robot Communication in Physical and Social Environments NeurIPS 2022 IKEA-Manual: Seeing Shape Assembly Step by Step NeurIPS 2022 PDSketch: Integrated Domain Programming, Learning, and Planning NeurIPS 2022 Programmatic Concept Learning for Human Motion Description and Synthesis CVPR 2022 Translating a Visual LEGO Manual to a Machine-Executable Plan ECCV 2022 Grammar-Based Grounded Lexicon Learning NeurIPS 2021 Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning ICLR 2021 Hierarchical Motion Understanding via Motion Programs CVPR 2021 Language-Mediated, Object-Centric Representation Learning ACL 2021 Temporal and Object Quantification Networks IJCAI 2021 Multi-Plane Program Induction with 3D Box Priors NeurIPS 2020 Perspective Plane Program Induction From a Single Image CVPR 2020 Neural Logic Machines ICLR 2019 Neurally-Guided Structure Inference ICML 2019 Program-Guided Image Manipulators ICCV 2019 The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision ICLR 2019 Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning Representations CVPR 2019 Visual Concept-Metaconcept Learning NeurIPS 2019 Visually Grounded Neural Syntax Acquisition ACL 2019 Acquisition of Localization Confidence for Accurate Object Detection ECCV 2018 Learning Visually-Grounded Semantics from Contrastive Adversarial Samples COLING 2018 Universal Agent for Disentangling Environments and Tasks ICLR 2018 What Can Help Pedestrian Detection? CVPR 2017