P. Liang

Shinji Watanabe, Ruslan Salakhutdinov, Louis-Philippe Morency, 2021, 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Face-to-Face Contrastive Learning for Social Intelligence Question-Answering

Paul Pu Liang, Qianli Ma, Louis-Philippe Morency, 2022, 2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG).

Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities pdf

Barnabás Póczos, Louis-Philippe Morency, Paul Pu Liang, 2018, AAAI.

Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors

Louis-Philippe Morency, Ying Shen, Amir Zadeh, 2018, AAAI.

Learning Factorized Multimodal Representations pdf

Ruslan Salakhutdinov, Louis-Philippe Morency, Amir Zadeh, 2018, ICLR.

Multimodal Language Analysis with Recurrent Multistage Fusion

Louis-Philippe Morency, Amir Zadeh, Paul Pu Liang, 2018, EMNLP.

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

D. Rubin, L. Fei-Fei, Yingda Xia, 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

High Throughput Phenotyping with 3 D CNNs in Ladder Networks

Paul Pu Liang, Hanqi Sun, Yuehua Niu, 2018 .

Think Locally, Act Globally: Federated Learning with Local and Global Representations pdf

Ruslan Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang, 2020, ArXiv.

Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment

Paul Pu Liang, R. Salakhutdinov, Louis-Philippe Morency, 2022, ArXiv.

HighMMT: Towards Modality and Task Generalization for High-Modality Representation Learning

R. Salakhutdinov, Dani Yogatama, Louis-Philippe Morency, 2022, ArXiv.

Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment pdf

Ruslan Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang, 2020, ACM Multimedia.

Deep Gamblers: Learning to Abstain with Portfolio Theory

Ruslan Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang, 2019, NeurIPS.

Factorized Multimodal Transformer for Multimodal Sequential Learning

Louis-Philippe Morency, Soujanya Poria, Amir Zadeh, 2019, ArXiv.

DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations

R. Salakhutdinov, Louis-Philippe Morency, Yiwei Lyu, 2022, AIES.

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

Tom Michael Mitchell, Yuan-Fang Li, Yewen Fan, 2023, ArXiv.

MultiBench: Multiscale Benchmarks for Multimodal Representation Learning

Paul Pu Liang, Michelle A. Lee, R. Salakhutdinov, 2021, NeurIPS Datasets and Benchmarks.

Multi-attention Recurrent Network for Human Communication Comprehension

Erik Cambria, Louis-Philippe Morency, Amir Zadeh, 2018, AAAI.

Towards Debiasing Sentence Representations

Ruslan Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang, 2020, ACL.

Memory Fusion Network for Multi-view Sequential Learning pdf

Erik Cambria, Louis-Philippe Morency, Amir Zadeh, 2018, AAAI.

Diverse and Admissible Trajectory Forecasting through Multimodal Context Understanding pdf

Louis-Philippe Morency, Seong Hyeon Park, Paul Pu Liang, 2020, ECCV.

StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer pdf

Eduard Hovy, Ruslan Salakhutdinov, Louis-Philippe Morency, 2021, NAACL.

Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control

R. Salakhutdinov, Louis-Philippe Morency, Yiwei Lyu, 2022, ArXiv.

A Simple Approach to the Noisy Label Problem Through the Gambler's Loss

Ruslan Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang, 2019 .

An Investigation of how Label Smoothing Affects Generalization pdf

Paul Pu Liang, Blair Chen, Ziyin Liu, 2020, ArXiv.

Multimodal sentiment analysis with word-level fusion and reinforcement learning

Sen Wang, Louis-Philippe Morency, Amir Zadeh, 2017, ICMI.

Brainish: Formalizing A Multimodal Language for Intelligence and Consciousness

Paul Pu Liang, P. Liang, 2022, ArXiv.

Deep Neural Network for Robust Modulation Classification Under Uncertain Noise Conditions

Yiyang Pei, Ying-Chang Liang, Paul Pu Liang, 2020, IEEE Transactions on Vehicular Technology.

Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization

Ruslan Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang, 2019, ACL.

MultiViz: Towards Visualizing and Understanding Multimodal Models

Paul Pu Liang, R. Salakhutdinov, Louis-Philippe Morency, 2022, ICLR.

MultiViz: An Analysis Benchmark for Visualizing and Understanding Multimodal Models

Paul Pu Liang, R. Salakhutdinov, Louis-Philippe Morency, 2022, ArXiv.

Learning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data pdf

Michal Muszynski, Ruslan Salakhutdinov, Louis-Philippe Morency, 2021, ACL.

MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning

R. Salakhutdinov, Louis-Philippe Morency, Yiwei Lyu, 2023, ArXiv.

High-Modality Multimodal Transformer: Quantifying Modality&Interaction Heterogeneity for High-Modality Representation Learning

R. Salakhutdinov, Dani Yogatama, Louis-Philippe Morency, 2022, 2203.01311.

Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis

R. Salakhutdinov, Louis-Philippe Morency, W. Neiswanger, 2022, EMNLP.

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction

Drew F. K. Williamson, Richard J. Chen, Faisal Mahmood, 2023, ArXiv.

Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies

Yuan Wang, Amr Ahmed, Paul Pu Liang, 2020, ICLR.

Anchor & Transform: Learning Sparse Representations of Discrete Objects pdf

Yuan Wang, Amr Ahmed, Paul Pu Liang, 2019, ArXiv.

HighMMT: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning

Paul Pu Liang, R. Salakhutdinov, Dani Yogatama, 2022 .

Difference-Masking: Choosing What to Mask in Continued Pretraining

Syeda Nahida Akter, Louis-Philippe Morency, Louis-Philippe Morency, 2023, ArXiv.

Strong and Simple Baselines for Multimodal Utterance Embeddings

Ruslan Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang, 2019, NAACL.

Label-Assisted Transmission for Short Packet Communications: A Machine Learning Approach

Yiyang Pei, Ying-Chang Liang, Paul Pu Liang, 2018, IEEE Transactions on Vehicular Technology.

Learning Not to Learn in the Presence of Noisy Labels pdf

Ruslan Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang, 2020, ArXiv.

PACS: A Dataset for Physical Audiovisual CommonSense Reasoning

Paul Pu Liang, R. Salakhutdinov, Louis-Philippe Morency, 2022, ECCV.

Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment

R. Salakhutdinov, Louis-Philippe Morency, Rulin Shao, 2022, ACL.

Computational Modeling of Human Multimodal Language : The MOSEI Dataset and Interpretable Dynamic Fusion

Paul Pu Liang, R. Salakhutdinov, P. Liang, 2018 .

Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions

Louis-Philippe Morency, Praneetha Vaddamanu, Atishay Jain, 2023, ACL.

Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications

Chun Kai Ling, R. Salakhutdinov, Louis-Philippe Morency, 2023, ArXiv.

Robust Modulation Classification under Uncertain Noise Condition Using Recurrent Neural Network

Yiyang Pei, Ying-Chang Liang, Paul Pu Liang, 2018, 2018 IEEE Global Communications Conference (GLOBECOM).

Multimodal Local-Global Ranking Fusion for Emotion Recognition

Louis-Philippe Morency, Amir Zadeh, Paul Pu Liang, 2018, ICMI.

An Empirical Evaluation of Sketched SVD and its Application to Leverage Score Ordering

Paul Pu Liang, Hui Han Chin, P. Liang, 2018, ACML.

Quantifying & Modeling Feature Interactions: An Information Decomposition Framework

Chun Kai Ling, Richard J. Chen, R. Salakhutdinov, 2023, ArXiv.

Demystify the Gravity Well in the Optimization Landscape (Student Abstract)

Yanfu Zhang, R. Bao, Haiyi Mao, 2023, AAAI.

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

Martin Q. Ma, James Y. Zou, R. Salakhutdinov, 2023, ArXiv.

Multimodal Fusion Interactions: A Study of Human and Automatic Quantification

R. Salakhutdinov, Louis-Philippe Morency, Yun Cheng, 2023, 2306.04125.

Tutorial on Multimodal Machine Learning

Paul Pu Liang, Louis-Philippe Morency, Amir Zadeh, 2022, NAACL.

Quantifying&Modeling Multimodal Interactions: An Information Decomposition Framework

Chun Kai Ling, Richard J. Chen, R. Salakhutdinov, 2023, 2302.12247.

A Machine Learning Approach to MIMO Communications

Ying-Chang Liang, Paul Pu Liang, Qianqian Zhang, 2018, 2018 IEEE International Conference on Communications (ICC).

Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP

Aryaman Arora, Rohan Pandey, P. Liang, 2023, 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW).

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

Martin Q. Ma, James Y. Zou, R. Salakhutdinov, 2023, NeurIPS.

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

Tom Michael Mitchell, Yuan-Fang Li, Yewen Fan, 2023, ArXiv.

High-Modality Multimodal Transformer: Quantifying Modality&Interaction Heterogeneity for High-Modality Representation Learning

R. Salakhutdinov, Dani Yogatama, Louis-Philippe Morency, 2022, 2203.01311.

MultiBench: Multiscale Benchmarks for Multimodal Representation Learning pdf

Yuke Zhu, Ruslan Salakhutdinov, Louis-Philippe Morency, 2021, NeurIPS Datasets and Benchmarks.

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Ronan Le Bras, Stuart M. Shieber, Vinay Uday Prabhu, 2022, ArXiv.

MultiViz: Towards User-Centric Visualizations and Interpretations of Multimodal Models

R. Salakhutdinov, Louis-Philippe Morency, Gunjan Chhablani, 2023, CHI Extended Abstracts.

Comparative Knowledge Distillation

Louis-Philippe Morency, Alex Wilf, P. Liang, 2023, ArXiv.

HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer

Hae Won Park, C. Breazeal, Sharifa Alghowinem, 2023, ICMI.

Modeling Spatiotemporal Multimodal Language with Recurrent Multistage Fusion

Louis-Philippe Morency, Amir Zadeh, Paul Pu Liang, 2018 .

Hierarchical Seq 2 Seq : Learning Representations of Online Spoken Speech

Louis-Philippe Morency, Amir Zadeh, Irene Li, 2019 .

MFM Neural Architecture MFM Generative Network ( b ) MFM Inference Network Inference Network Generative Network

Paul Pu Liang, Yao-Hung Hubert Tsai, R. Salakhutdinov, 2018 .

Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities

Paul Pu Liang, B. Póczos, Louis-Philippe Morency, 2018 .

Learning Robust Joint Representations for Multimodal Sentiment Analysis

Barnabás Póczos, Louis-Philippe Morency, Paul Pu Liang, 2018 .

Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities

Louis-Philippe Morency, Alex Wilf, P. Liang, 2023, ArXiv.

T ailor : Generating and Perturbing Text with Semantic Controls

Ankur P. Parikh, Amrith Rajagopal Setlur, Yinhan Liu, 2021 .

Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions

Louis-Philippe Morency, P. Liang, Leena Mathur, 2024, ArXiv.

Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control

R. Salakhutdinov, Louis-Philippe Morency, Yiwei Lyu, 2022, ACL.

Tutorial on Multimodal Machine Learning: Principles, Challenges, and Open Questions

Louis-Philippe Morency, P. Liang, 2023, ICMI Companion.

Relational Attention Networks via Fully-Connected Conditional Random Fields

Paul Pu Liang, Ziyin Liu, Junxiang Chen, 2018 .

BACN: Bi-direction Attention Capsule-based Network for Multimodal Sentiment Analysis

Soujanya Poria, Prateek Vij, P. Liang, 2021 .

Graph-based Fine-grained Multimodal Attention Mechanism for Sentiment Analysis

Louis-Philippe Morency, G. Monfardini, Soujanya Poria, 2021 .

Incongruity-Aware Hierarchical Crossmodal Transformer with Dynamic Modality Gating: A Study on Affect Recognition

Louis-Philippe Morency, Yuanchao Li, P. Liang, 2022 .

IoT-LM: Large Multisensory Language Models for the Internet of Things

Louis-Philippe Morency, P. Liang, Shentong Mo, 2024, 2407.09801.

HEMM: Holistic Evaluation of Multimodal Foundation Models

R. Salakhutdinov, Louis-Philippe Morency, Akshay Goindani, 2024, 2407.03418.

MMOE: Mixture of Multimodal Interaction Experts

R. Salakhutdinov, Louis-Philippe Morency, P. Liang, 2023, ArXiv.

MultiIoT: Benchmarking Machine Learning for the Internet of Things

Louis-Philippe Morency, Shentong Mo, P. Liang, 2023, 2311.06217.

Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework

Chun Kai Ling, Richard J. Chen, R. Salakhutdinov, 2023, NeurIPS.