Roozbeh Mottaghi

PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks ICLR 2025 Controllable Human-Object Interaction Synthesis ECCV 2024 GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation CVPR 2024 Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation ECCV 2024 From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos NIPS 2024 GOAT: GO to Any Thing RSS 2024 Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots ICLR 2024 Situated Instruction Following ECCV 2024 Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-per-Second CVPR 2023 Navigating to Objects Specified by Images ICCV 2023 UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks ICLR 2023 Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics ICLR 2023 Neural Priming for Sample-Efficient Adaptation NIPS 2023 Neural Radiance Field Codebooks ICLR 2023 HomeRobot: Open-Vocabulary Mobile Manipulation CORL 2023 ENTL: Embodied Navigation Trajectory Learner ICCV 2023 Simple but Effective: CLIP Embeddings for Embodied AI CVPR 2022 🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural Generation NIPS 2022 Ask4Help: Learning to Leverage an Expert for Embodied Tasks NIPS 2022 Multi-Modal Answer Validation for Knowledge-Based VQA AAAI 2022 What Do Navigation Agents Learn About Their Environment? CVPR 2022 Interactron: Embodied Adaptive Object Detection CVPR 2022 Continuous Scene Representations for Embodied AI CVPR 2022 A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge ECCV 2022 Object Manipulation via Visual Target Localization ECCV 2022 Visual Room Rearrangement CVPR 2021 PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World ACL 2021 PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World IJCNLP 2021 Container: Context Aggregation Networks NIPS 2021 Contrasting Contrastive Self-Supervised Representation Learning Pipelines ICCV 2021 RobustNav: Towards Benchmarking Robustness in Embodied Navigation ICCV 2021 Factorizing Perception and Policy for Interactive Instruction Following ICCV 2021 What Can You Learn From Your Muscles? Learning Visual Representation from Human Interactions ICLR 2021 Learning Generalizable Visual Representations via Interactive Gameplay ICLR 2021 ManipulaTHOR: A Framework for Visual Object Manipulation CVPR 2021 Pushing It Out of the Way: Interactive Visual Navigation CVPR 2021 ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks CVPR 2020 VisualCOMET: Reasoning about the Dynamic Context of a Still Image ECCV 2020 Visual Reaction: Learning to Play Catch With Your Drone CVPR 2020 Learning About Objects by Learning to Interact with Them NIPS 2020 RoboTHOR: An Open Simulation-to-Real Embodied AI Platform CVPR 2020 OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge CVPR 2019 Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning CVPR 2019 Visual Semantic Navigation using Scene Priors ICLR 2019 Who Let the Dogs Out? Modeling Dog Behavior From Visual Data CVPR 2018 SeGAN: Segmenting and Generating the Invisible CVPR 2018 Visual Semantic Planning Using Deep Successor Representations ICCV 2017 See the Glass Half Full: Reasoning About Liquid Containers, Their Volume and Content ICCV 2017 A Task-Oriented Approach for Cost-Sensitive Recognition CVPR 2016 Complexity of Representation and Inference in Compositional Models with Part Sharing JMLR 2016 Newtonian Scene Understanding: Unfolding the Dynamics of Objects in Static Images CVPR 2016 A Coarse-to-Fine Model for 3D Pose Estimation and Sub-Category Recognition CVPR 2015 The Role of Context for Object Detection and Semantic Segmentation in the Wild CVPR 2014 Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts CVPR 2014 Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs CVPR 2013 Bottom-Up Segmentation for Top-Down Detection CVPR 2013