Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
AdenPredictor: accurate prediction of the adenylation domain specificity of nonribosomal peptide biosynthetic gene clusters in microbial genomes
Published in Bioinformatics, 2023
Recommended citation: Mihir Mongia, Romel Baral, Abhinav Adduri, Donghui Yan, Yudong Liu, Yuying Bian, Paul Kim, Bahar Behsaz, Hosein Mohimani. AdenPredictor: accurate prediction of the adenylation domain specificity of nonribosomal peptide biosyn- thetic gene clusters in microbial genomes. Bioinformatics, 2023, 39, i40-i46. DOI:10.1093/bioinformatics/btad235 https://academic.oup.com/bioinformatics/article/39/Supplement_1/i40/7210450
Fast Mass Spectrometry Search and Clustering of Untargeted Metabolomics Data
Published in Nature Biotechnology, 2024
Recommended citation: Mihir Mongia*, Tyler M. Yasaka*, Yudong Liu*, Mustafa Guler, Liang Lu, Aditya Bhagwat, Bahar Behsaz, Mingxun Wang, Pieter C. Dorrestein, Hosein Mohimani. Fast Mass Spectrometry Search and Clustering of Untargeted Metabolomics Data. Nature Biotechnology (2024). DOI:10.1038/s41587-023-01985-4 https://www.nature.com/articles/s41587-023-01985-4
Quantifying Interactions in Semi-supervised Multimodal Learning: Guarantees and Applications
Published in ICLR, 1900
Recommended citation: Paul Pu Liang, Chun Kai Ling, Yun Cheng, Alexander Obolenskiy, Yudong Liu, Rohan Pandey, Alex Wilf, Louis- Philippe Morency, Russ Salakhutdinov. Quantifying Interactions in Semi-supervised Multimodal Learning: Guarantees and Applications. Submitted to The Twelfth International Conference on Learning Representations (In review) https://openreview.net/pdf?id=BrjLHbqiYs
High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning
Published in Transactions on Machine Learning Research, 2023
Recommended citation: Paul Pu Liang, Yiwei Lyu, Xiang Fan, Jeffrey Tsaw, Yudong Liu, Shentong Mo, Dani Yogatama, Louis-Philippe Morency, Ruslan Salakhutdinov. High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning. Transactions on Machine Learning Research (05/2023). DOI:10.48550/arXiv.2203.01311 https://arxiv.org/abs/2203.01311
talks
Presentation on Multimodal Coreference Resolution
Published:
Provided a poster presentation on a attention-based model for coreference resolution in interactive shopping, providing the results of our exploration such as tracking objects over turns, predicting object counts, and contrasting conversations to tackle prediction errors by existing models and optimizing performances Our model exceeded State of Art Performance (Max F1 score 69.5) on Situated Interactive Multimodal Conversation (SIMMC) 2.0 dataset
Presentation on Video Dense Captioning with Knowledge Distillation
Published:
Provided a poster presentation on a Multimodal Dense Video Captioning pipleline. Presented our intuition of using knowledge distillation to expand pretrained LSTM vocabulary embedding space to a pretrained GPT-2 model with few-shot adaptation, raising performance on the baseline model.
Presentation on DynPartition
Published:
Presented a novel rein-forcement learning-based scheduler that performs dynamic partitioning of computation workload across multiple heterogeneous GPUs for large neural network inference tasks. Formated our results and contributions as a technical report and provided a slide presentation.
teaching
Teaching Assistant
Undergrad level course, 15-213/513 Introduction to Computer Systems, 2023
Teaching Assistant
Ph.D. level course, 10-701 Introduction to Machine Learning (Ph.D.), 2023
Teaching Assistant
Graduate level course, 15-712 Advanced Operating Systems and Distributed Systems, 2023