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
Paul Pu Liang — most-cited papers & profile · Multimodal
← authors
·
overview
Paul Pu Liang
13
papers ·
350
citations ·
34
h-index
Moscow Institute of Thermal Technology · Human Media · Massachusetts Institute of Technology
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Learning Factorized Multimodal Representations
2018 · 197 citations
Localized Symbolic Knowledge Distillation for Visual Commonsense Models
2023 · 1 citations
Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
2024 · 1 citations
MINT: Multimodal Instruction Tuning With Multimodal Interaction Grouping
2025
Benchmarking Vision, Language, & Action Models In Procedurally Generated, Open Ended Action Environments
2025
VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues
2025
Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment
2022
Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP
2023
Top co-authors
Harshvardhan Sikka
· 2
Pranav Guruprasad
· 2
Rohan Pandey
· 2
Ruslan Salakhutdinov
· 2
Yangyue Wang
· 2
Ali Farhadi
· 1
Amir Zadeh
· 1
Aryaman Arora
· 1
Dongyu Yao
· 1
Haofei Yu
· 1
Jack Hessel
· 1
Jae Sung Park
· 1
Topics
Vision-Language Models
Video-Language
Benchmarks
Visual QA & Reasoning
Instruction Tuning
Embodied & Agents
Audio-Visual