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
8
papers
66
total citations
papers (8)
Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms
ICLR 2025
arXiv
43
citations
From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
CVPR 2025
arXiv
23
citations
UINavBench: A Framework for Comprehensive Evaluation of Interactive Digital Agents
ICCV 2025
0
citations
The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation
ICCV 2021
arXiv
0
citations
Contrast and Classify: Training Robust VQA Models
ICCV 2021
arXiv
0
citations
Spatially Aware Multimodal Transformers for TextVQA
ECCV 2020
0
citations
Housekeep: Tidying Virtual Households Using Commonsense Reasoning
ECCV 2022
0
citations
SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation
NeurIPS 2021
arXiv
0
citations