Awesome Multimodal
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
James Glass — most-cited papers & profile · Multimodal
← authors
·
overview
James Glass
26
papers ·
89
citations ·
66
h-index
Moscow Institute of Thermal Technology · IIT@MIT · Artificial Intelligence in Medicine (Canada) · Massachusetts Institute of Technology
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks
2025
Teaching VLMs to Localize Specific Objects from In-context Examples
2024
Top co-authors
Assaf Arbelle
· 1
Eli Schwartz
· 1
Hilde Kuehne
· 1
Hongyin Luo
· 1
Leonid Karlinsky
· 1
M. Jehanzeb Mirza
· 1
Nimrod Shabtay
· 1
Ondrej Biza
· 1
Philip Schroeder
· 1
Raja Giryes
· 1
Rogerio Feris
· 1
Shimon Ullman
· 1
Topics
Vision-Language Models
Benchmarks
Video-Language
Embodied & Agents
Visual QA & Reasoning
Instruction Tuning