Cheng-Fu Yang, Yao-Hung Hubert Tsai, Wan-Cyuan Fan, Ruslan Salakhutdinov, Louis-Philippe Morency, Yu-Chiang, Frank Wang. Paraphrasing Is All You Need for Novel Object Captioning. NeurIPS 2022
Links: PDFPaul Pu Liang, Yiwei Lyu, Xiang Fan, Jeffrey Tsaw, Yudong Liu, Dani Yogatama, Louis-Philippe Morency, Ruslan Salakhutdinov. High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning. TMLR 2022
Links: PDF Demo & CodePaul Pu Liang, Yiwei Lyu, Xiang Fan, Arav Agarwal, Yun Cheng, Louis-Philippe Morency, Ruslan Salakhutdinov. MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning. JMLR Open Source Software 2022
Links: PDF Demo & CodeYuxin Xiao, Paul Pu Liang, Umang Bhatt, Willie Neiswanger, Ruslan Salakhutdinov, Louis-Philippe Morency. Uncertainty Quantification with Pre-trained Language Models: A Large-scale Empirical Analysis. EMNLP Findings 2022
Links: PDF Demo & CodeT. Wörtwein, L. B. Sheeber, N. B. Allen, J. F. Cohn, L.-P. Morency. Beyond Additive Fusion: Learning Non-Additive Multimodal Interactions. Findings of the Association for Computational Linguistics: EMNLP 2022 (F-EMNLP ’22).
Links: PDF Demo & CodeSamuel Yu, Peter Wu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency. PACS: A Dataset for Physical Audiovisual Commonsense Reasoning. ECCV 2022
Links: PDF Demo & CodeYiwei Lyu, Paul Pu Liang, Zihao Deng, Ruslan Salakhutdinov, Louis-Philippe Morency. DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations. AIES 2022
Links: PDF Demo & CodeArish Alreja, Michael James Ward, Qianli Ma, Mark Richardson, Brian Russ, Stephan Bickel, Nelleke Van Wouwe, Jorge A González-Martínez, Lisa S Parker, Joseph Neimat, Charles Schroeder, Louis-Phillipe Morency, Avniel Singh Ghuman. A Multimodal Approach to Investigate the Neural Mechanisms of Real World Social Vision. bioRxiv (2021).
Links: PDFYao-Hung Hubert Tsai, Tianqin Li, Weixin Liu, Peiyuan Liao, Ruslan Salakhutdinov, Louis-Philippe Morency. Learning Weakly-supervised Contrastive Representations. ICLR 2022
Links: PDFTsai, Y. H. H., Li, T., Ma, M. Q., Zhao, H., Zhang, K., Morency, L. P., & Salakhutdinov, R. Conditional Contrastive Learning with Kernel. International Conference on Learning Representations 2022.
Links: PDF