Publications

P. P. Liang, Y. Lyu, X. Fan, Z. Wu, Y. Cheng, J. Wu, L. Chen, P. Wu, M. Lee, Y. Zhu, R. Salakhutdinov, L.-P. Morency. MultiBench: Multiscale Benchmarks for Multimodal Representation Learning. NeurIPS 2021 Datasets and Benchmarks Track

Y.-H. H. Tsai*, M. Q. Ma*, M. Yang, H. Zhao, L.-P. Morency, R. Salakhutdinov. Self-supervised Representation Learning with Relative Predictive Coding. International Conference on Learning Representations (ICLR) 2021.

Y.-H. H. Tsai, Y. Wu, R. Salakhutdinov, L.-P. Morency. Self-supervised Learning from a Multi-view Perspective. International Conference on Learning Representations (ICLR) 2021

P. Wu, P. P. Liang, J. Shi, R. Salakhutdinov, S. Watanabe, L.-P. Morency. Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks. Asia Pacific Signal and Information Processing Association Annual Summit and Conference 2021

P. P. Liang, C. Wu, L.-P. Morency, R. Salakhutdinov. Towards Understanding and Mitigating Social Biases in Language Models. ICML 2021

P. P. Liang*, T. Liu*, A. Cai, M. Muszynski, R. Ishii, N. Allen, R. Auerbach, D. Brent, R. Salakhutdinov, L.-P. Morency. Learning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data. ACL 2021

T. Wörtwein, L. B. Sheeber, N. B. Allen, J. F. Cohn, L.-P. Morency. Human-Guided Modality Informativeness for Affective States. In Proceedings of the 2021 International Conference on Multimodal Interaction (ICMI ’21).

J. Girard*, A. Vail*, E. Liebenthal, K. Brown, C. Kilciksiz, L. Pennant, E. Liebson, D. Öngür, L.-P. Morency, J. Baker. Computational Analysis of Spoken Language in Acute Psychosis and Mania. Schizophrenia Research, 2021. (*equal contribution)

Lee, D. W., Ahuja, C., Morency, L. P. Crossmodal clustered contrastive learning: Grounding of spoken language to gestures. ICMI 2021 Generation and Evaluation of Non-verbal Behaviour for Embodied Agents Workshop

Tsai, Y. H. H., Ma, M. Q., Zhao, H., Zhang, K., Morency, L. P., & Salakhutdinov, R. Conditional contrastive learning: Removing undesirable information in self-supervised representations. arXiv preprint arXiv:2106.02866.