---
title: "Paul Pu Liang — all works — Elamur Research"
description: "All 49 works of Paul Pu Liang in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/paul-pu-liang/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/paul-pu-liang/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Paul Pu Liang](https://md.research.elamur.ai/free/en/authors/paul-pu-liang/) / all works

# Paul Pu Liang — all works

49 works · [← Paul Pu Liang](https://md.research.elamur.ai/free/en/authors/paul-pu-liang/)

1. **[Multimodal Transformer for Unaligned Multimodal Language Sequences](https://md.research.elamur.ai/free/en/papers/tsai-2019-multimodal-transformer-unaligned-multimodal-language/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, et al.*2019 · 2,193 citations*
2. **[Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph](https://md.research.elamur.ai/free/en/papers/zadeh-2018-multimodal-language-analysis-wild-cmu/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**AmirAli Bagher Zadeh, Paul Pu Liang, Soujanya Poria, et al.*2018 · 1,522 citations*
3. **[Efficient Low-rank Multimodal Fusion With Modality-Specific Factors](https://md.research.elamur.ai/free/en/papers/liu-2018-efficient-low-rank-multimodal-fusion/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Zhun Liu, Ying Shen, Varun Bharadhwaj Lakshminarasimhan, et al.*2018 · 1,188 citations*
4. **[Found in Translation: Learning Robust Joint Representations by Cyclic Translations between Modalities ↗](https://doi.org/10.1609/aaai.v33i01.33016892) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Hai Pham et al.*2019 · 533 citations*
5. **[Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors ↗](https://doi.org/10.1609/aaai.v33i01.33017216) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Yansen Wang et al.*2019 · 513 citations*
6. **[Learning Factorized Multimodal Representations ↗](https://arxiv.org/abs/1806.06176) arXiv (Cornell University) · no summary yet**Yao-Hung Hubert Tsai et al.*2018 · 286 citations*
7. [**Towards Understanding and Mitigating Social Biases in Language Models arXiv:2106.13219**Paul Pu Liang, Chiyu Wu, Louis-Philippe Morency, et al.*2021 · 271 citations*](https://md.research.elamur.ai/free/en/papers/liang-2021-towards-understanding-mitigating-social-biases/)
8. **[Towards Debiasing Sentence Representations](https://md.research.elamur.ai/free/en/papers/liang-2020-debiasing-sentence-representations/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Paul Pu Liang, Irene Mengze Li, Emily Zheng, et al.*2020 · 262 citations*
9. **[Multimodal Language Analysis with Recurrent Multistage Fusion ↗](https://aclanthology.org/D18-1014/) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yet**Paul Pu Liang et al.*2018 · 248 citations*
10. **[Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning ↗](https://doi.org/10.1109/cvpr52688.2022.00982) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Liangqiong Qu et al.*2022 · 202 citations*
11. **[Think Locally, Act Globally: Federated Learning with Local and Global Representations ↗](https://arxiv.org/abs/2001.01523) arXiv (Cornell University) · no summary yet**Paul Pu Liang et al.*2020 · 140 citations*
12. **[Social-IQ: A Question Answering Benchmark for Artificial Social Intelligence ↗](https://doi.org/10.1109/cvpr.2019.00901) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Amir Zadeh et al.*2019 · 133 citations*
13. **[Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization ↗](https://aclanthology.org/P19-1152/) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · no summary yet**Paul Pu Liang et al.*2019 · 109 citations*
14. **[Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis ↗](https://aclanthology.org/2022.findings-emnlp.538/) Findings of the Association for Computational Linguistics: EMNLP 2022 · no summary yet**Yuxin Xiao et al.*2022 · 79 citations*
15. [**OS-ATLAS: A Foundation Action Model for Generalist GUI Agents arXiv:2410.23218**Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, et al.*2024 · 67 citations*](https://md.research.elamur.ai/free/en/papers/wu-2024-os-atlas-foundation-action-model/)
16. **[StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer ↗](https://aclanthology.org/2021.naacl-main.171/) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Yiwei Lyu et al.*2021 · 50 citations*
17. **[Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities](https://md.research.elamur.ai/free/en/papers/wilf-2024-think-twice-perspective-taking-improves/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Alex Wilf, Sihyun Lee, Paul Pu Liang, et al.*2024 · 48 citations*
18. **[DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations ↗](https://doi.org/10.1145/3514094.3534148) Proceedings of the AAAI/ACM Conference on AI Ethics and Society · no summary yet**Yiwei Lyu et al.*2022 · 42 citations*
19. **[MultiBench: Multiscale Benchmarks for Multimodal Representation Learning ↗](https://arxiv.org/abs/2107.07502) PubMed · no summary yet**Paul Pu Liang et al.*2021 · 42 citations*
20. **[Deep Gamblers: Learning to Abstain with Portfolio Theory ↗](https://arxiv.org/abs/1907.00208) arXiv (Cornell University) · no summary yet**Liu Ziyin et al.*2019 · 41 citations*
21. **[Strong and Simple Baselines for Multimodal Utterance Embeddings ↗](https://aclanthology.org/N19-1267/) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · no summary yet**Paul Pu Liang et al.*2019 · 36 citations*
22. **[Factorized Contrastive Learning: Going Beyond Multi-view Redundancy ↗](https://doi.org/10.52202/075280-1430) neural information processing systems · no summary yet**Paul Pu Liang et al.*2023 · 32 citations*
23. **[Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment ↗](https://doi.org/10.1145/3474085.3475247) ACM International Conference on Multimedia (ACM MM) · no summary yet**Paul Pu Liang et al.*2021 · 25 citations*
24. **[MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts ↗](https://aclanthology.org/2024.emnlp-main.558/) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · no summary yet**Haofei Yu et al.*2024 · 22 citations*
25. **[MultiViz: Towards Visualizing and Understanding Multimodal Models ↗](https://arxiv.org/abs/2207.00056) arXiv (Cornell University) · no summary yet**Paul Pu Liang et al.*2022 · 21 citations*
26. **[Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals ↗](https://doi.org/10.52202/075280-0048) neural information processing systems · no summary yet**Yue Wu et al.*2023 · 20 citations*
27. **[Learning Not to Learn in the Presence of Noisy Labels ↗](https://arxiv.org/abs/2002.06541) arXiv (Cornell University) · no summary yet**Liu Ziyin et al.*2020 · 18 citations*
28. **[PACS: A Dataset for Physical Audiovisual CommonSense Reasoning ↗](https://doi.org/10.1007/978-3-031-19836-6_17) Lecture notes in computer science · no summary yet**Samuel Yu et al.*2022 · 17 citations*
29. **[Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning ↗](https://arxiv.org/abs/2106.02866) arXiv (Cornell University) · no summary yet**Martin Q. Ma et al.*2021 · 14 citations*
30. **[High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning ↗](https://arxiv.org/abs/2203.01311) arXiv (Cornell University) · no summary yet**Paul Pu Liang et al.*2022 · 13 citations*
31. **[VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues](https://md.research.elamur.ai/free/en/papers/zhang-2025-vlm2-bench-closer-look-how/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jianshu Zhang, Dongyu Yao, Renjie Pi, et al.*2025 · 12 citations*
32. **[Learning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data ↗](https://aclanthology.org/2021.acl-long.322/) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yet**Paul Pu Liang et al.*2021 · 12 citations*
33. **[Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment ↗](https://aclanthology.org/2023.acl-long.298/) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Rohan Pandey et al.*2023 · 11 citations*
34. **[CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery ↗](https://arxiv.org/abs/2604.01658) arXiv:2604.01658 · no summary yet**Ao Qu et al.*2026 · 9 citations*
35. **[Multimodal Fusion Interactions: A Study of Human and Automatic Quantification ↗](https://doi.org/10.1145/3577190.3614151) INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · no summary yet**Paul Pu Liang et al.*2023 · 9 citations*
36. **[HEMM: Holistic Evaluation of Multimodal Foundation Models ↗](https://doi.org/10.52202/079017-1358) neural information processing systems · no summary yet**Paul Pu Liang et al.*2024 · 8 citations*
37. **[On Emergent Communication in Competitive Multi-Agent Teams ↗](https://doi.org/10.65109/ghof1719) Adaptive Agents and Multi-Agents Systems · no summary yet**Paul Pu Liang et al.*2020 · 7 citations*
38. **[Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks ↗](https://arxiv.org/abs/2101.08919) arXiv (Cornell University) · no summary yet**Peter Wu et al.*2021 · 6 citations*
39. **[Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control ↗](https://aclanthology.org/2023.findings-acl.758/) Findings of the Association for Computational Linguistics: ACL 2023 · no summary yet**Xiang Fan et al.*2023 · 5 citations*
40. **[Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications ↗](https://arxiv.org/abs/2306.04539) arXiv (Cornell University) · no summary yet**Paul Pu Liang et al.*2023 · 4 citations*
41. **[Semantically Corrected Amharic Automatic Speech Recognition](https://md.research.elamur.ai/free/en/papers/adnew-2024-semantically-corrected-amharic-automatic-speech/) [Communications in computer and information science](https://md.research.elamur.ai/free/en/venues/communications-in-computer-and-information-science/)**Samuael Adnew, Paul Pu Liang*2024 · 3 citations*
42. **[MultiViz: Towards User-Centric Visualizations and Interpretations of Multimodal Models ↗](https://doi.org/10.1145/3544549.3585604) Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA) · no summary yet**Paul Pu Liang et al.*2023 · 3 citations*
43. **[A Simple Approach to the Noisy Label Problem Through the Gambler's Loss ↗](https://openalex.org/W3005119220) no summary yet**Liu Ziyin et al.*2019 · 3 citations*
44. **[MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning ↗](https://arxiv.org/abs/2306.16413) arXiv (Cornell University) · no summary yet**Paul Pu Liang et al.*2023 · 1 citation*
45. **[RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis](https://md.research.elamur.ai/free/en/papers/rani-2026-radar-reasoning-guided-attribution-framework/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Anku Rani, Aparna Garimella, Apoorv Saxena, et al.*2026*
46. **[SPADE: Self-Play in Adaptive Synthetic Executable Environments ↗](https://arxiv.org/abs/2608.19197) arXiv (Cornell University) · no summary yet**Bo Liu et al.*2026*
47. **[Act2See: Emergent Active Visual Perception for Video Reasoning ↗](https://arxiv.org/abs/2605.01657) arXiv (Cornell University) · no summary yet**Martin Q. Ma et al.*2026*
48. **[Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models ↗](https://arxiv.org/abs/2605.01662) arXiv (Cornell University) · no summary yet**Martin Q. Ma et al.*2026*
49. **[Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models ↗](https://aclanthology.org/2026.findings-acl.588/) Findings of the Association for Computational Linguistics: ACL 2026 · no summary yet**Hanqi Yan et al.*2026*