Paul Pu Liang

7.7k citations
48 papers · 3.5k indexed · 6 hit papers · h-index 20
Topics
Topic Modeling (20 papers)Multimodal Machine Learning Applications (15 papers)Natural Language Processing Techniques (8 papers)

In The Last Decade

Paul Pu Liang

43 papers receiving 3.4k citations

Hit Papers

Multimodal Language Analysis in the Wild: CMU-MOSEI Datas...201820262020202320182018201820192019200400600

Peers

Paul Pu Liang
Comparison fields: 5 of 122
  • Artificial Intelligence 2.7k
  • Experimental and Cognitive Psychology 1.1k
  • Computer Vision and Pattern Recognition 928
  • Signal Processing 597
  • Social Psychology 191
Replace Dawei Song with:
Dawei Song China
Helen Meng Hong Kong
Navonil Majumder Singapore
Dawen Liang United States
Shervin Minaee United States
Anis Yazidi Norway
Yi‐Hsuan Yang Taiwan
Michael Auli United States
Quanzeng You United States
Shaoxiong Ji Finland
Paul Pu Liang relative to Dawei Song China Dawei Song's profile →
Citations per field
00.5×1.5×2.3×
Dawei Song · 1×
Citations per year

Countries citing papers authored by Paul Pu Liang

Since Specialization
Citations

This map shows the geographic impact of Paul Pu Liang's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Paul Pu Liang with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Paul Pu Liang more than expected).

Fields of papers citing papers by Paul Pu Liang

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Paul Pu Liang. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Paul Pu Liang. The network helps show where Paul Pu Liang may publish in the future.

Co-authorship network of co-authors of Paul Pu Liang

This figure shows the co-authorship network connecting the top 25 collaborators of Paul Pu Liang. A scholar is included among the top collaborators of Paul Pu Liang based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Paul Pu Liang. Paul Pu Liang is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
#WorkIndexed citations
1 0
2 2
3 1
4 2
5 5
6 7
7 3
8 3
9 2
10 3
11 1
12 13
13 26
14 24
15 84
16
Variational Auto-Decoder: Neural Generative Modeling from Partial Data
1
17
Deep Gamblers: Learning to Abstain with Portfolio Theory
3
18 38
19
Learning Factorized Multimodal Representations
28
20
Efficient Low-rank Multimodal Fusion With Modality-Specific Factorsbreakdown →
614

About Paul Pu Liang

Paul Pu Liang is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Human-Computer Interaction, having authored 48 papers that have together received 3.5k indexed citations. Recurring topics across this work include Topic Modeling (20 papers), Multimodal Machine Learning Applications (15 papers) and Natural Language Processing Techniques (8 papers). The work is most often cited by research in Artificial Intelligence (2.7k citations), Experimental and Cognitive Psychology (1.1k citations) and Signal Processing (597 citations). Paul Pu Liang has collaborated with scholars based in United States, Singapore and China. Frequent co-authors include Louis–Philippe Morency, AmirAli Bagher Zadeh, Soujanya Poria, Erik Cambria, Amir Zadeh, Zhun Liu, Ying Shen, Thomas Manzini, Hai Pham and Barnabás Póczos. Their work appears in journals such as ACM Computing Surveys, IEEE Transactions on Vehicular Technology and Information Fusion.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026