 CTRL-O: Language-Controllable Object-Centric Visual Representation LearningComputer Vision and Pattern Recognition (CVPR), 2025 |
 Learning the meanings of function words from grounded language using a
visual question answering modelCognitive Sciences (CogSci), 2023 |
 Embodied Concept Learner: Self-supervised Learning of Concepts and
Mapping through Instruction FollowingConference on Robot Learning (CoRL), 2023 |
 3D Concept Grounding on Neural FieldsNeural Information Processing Systems (NeurIPS), 2022 |
 Voxel-informed Language GroundingAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 FILM: Following Instructions in Language with Modular MethodsInternational Conference on Learning Representations (ICLR), 2021 |
