α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Harsh Agrawal
Harsh Agrawal
2
Affiliations
Affiliations
Apple
Georgia Institute of Technology
9
papers
482
total citations
papers (9)
Large Language Models as Generalizable Policies for Embodied Tasks
ICLR 2024
arXiv
105
citations
Spatially Aware Multimodal Transformers for TextVQA
ECCV 2020
arXiv
95
citations
Housekeep: Tidying Virtual Households Using Commonsense Reasoning
ECCV 2022
arXiv
85
citations
SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation
NEURIPS 2021
arXiv
73
citations
The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation
ICCV 2021
arXiv
50
citations
Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms
ICLR 2025
arXiv
45
citations
From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
CVPR 2025
arXiv
24
citations
Contrast and Classify: Training Robust VQA Models
ICCV 2021
arXiv
5
citations
UINavBench: A Framework for Comprehensive Evaluation of Interactive Digital Agents
ICCV 2025
0
citations