α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Roozbeh Mottaghi
Roozbeh Mottaghi
28
papers
3,671
total citations
papers (28)
ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
CVPR 2020
arXiv
959
citations
A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge
ECCV 2022
arXiv
792
citations
🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural Generation
NEURIPS 2022
arXiv
394
citations
RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
CVPR 2020
arXiv
289
citations
Simple but Effective: CLIP Embeddings for Embodied AI
CVPR 2022
arXiv
268
citations
ManipulaTHOR: A Framework for Visual Object Manipulation
CVPR 2021
arXiv
154
citations
Visual Room Rearrangement
CVPR 2021
arXiv
149
citations
Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation
ECCV 2024
arXiv
77
citations
GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation
CVPR 2024
arXiv
72
citations
RobustNav: Towards Benchmarking Robustness in Embodied Navigation
ICCV 2021
arXiv
68
citations
Navigating to Objects Specified by Images
ICCV 2023
arXiv
61
citations
Continuous Scene Representations for Embodied AI
CVPR 2022
arXiv
53
citations
PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks
ICLR 2025
arXiv
50
citations
Contrasting Contrastive Self-Supervised Representation Learning Pipelines
ICCV 2021
arXiv
48
citations
Interactron: Embodied Adaptive Object Detection
CVPR 2022
arXiv
37
citations
Factorizing Perception and Policy for Interactive Instruction Following
ICCV 2021
arXiv
37
citations
Pushing It Out of the Way: Interactive Visual Navigation
CVPR 2021
arXiv
34
citations
Ask4Help: Learning to Leverage an Expert for Embodied Tasks
NEURIPS 2022
arXiv
29
citations
Neural Priming for Sample-Efficient Adaptation
NEURIPS 2023
arXiv
19
citations
Learning About Objects by Learning to Interact with Them
NEURIPS 2020
arXiv
18
citations
Visual Reaction: Learning to Play Catch With Your Drone
CVPR 2020
arXiv
14
citations
What Do Navigation Agents Learn About Their Environment?
CVPR 2022
arXiv
13
citations
ENTL: Embodied Navigation Trajectory Learner
ICCV 2023
arXiv
12
citations
Object Manipulation via Visual Target Localization
ECCV 2022
arXiv
9
citations
Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-per-Second
CVPR 2023
arXiv
7
citations
VisualCOMET: Reasoning about the Dynamic Context of a Still Image
ECCV 2020
arXiv
6
citations
ADAPT: Actively Discovering and Adapting to Preferences for any Task
COLM 2025
arXiv
2
citations
Container: Context Aggregation Networks
NEURIPS 2021
0
citations
