I am a Nanyang Associate Professor at the School of Computer Science and Engineering, Nanyang Technological University, Singapore. My research interests lie mainly in Computational Narrative Intelligence, Multi-modal Learning, and Machine Learning.
Story is a powerful tool for communication, an exhibit of creativity, and a timeless form of entertainment. Computational Narrative Intelligence (CNI) aims to create intelligent machines that can understand and create stories, manage interactive narratives, and respond appropriately to stories told to them. I have made contributions to all major areas of CNI, ranging from story generation and interactive narratives to human cognition, from learning story knowledge to story understanding.
CNI is obviously a hard problem, requiring semantic understanding and powerful learning algorithms. Therefore, I am also interested in methods that learn grounded, multimodal semantics and strong machine learning algorithms. In particular, I am excited by techniques that adopt a system view of intelligence, which considers the interaction of multiple specialized components.
Jun Chen, Han Guo, Kai Yi, Boyang Li, and Mohamed Elhoseiny. VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022.
TL;DR: We developed a data-efficient method to adapt large-scale pretrained language models for image captioning and achieved SOTA results on X-ray image captioning.Paper Code bibtex
Yinan Zhang, Boyang Li, Yong Liu, Hao Wang, Chunyan Miao. Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD). 2021.
TL;DR: If neural recommenders performed poorly (e.g., worse than well-tuned k-nearest-neighbors), it is probably because they did not use this data-dependent, manifold-informed initialization.Paper Video Code bibtex
Xu Guo, Boyang Li, Han Yu, and Chunyan Miao. Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection. The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT). 2021.
TL;DR: Sarcasm detection is an ideal problem for transfer learning. We identify the competition between losses in adversarial transfer learning and propose a modified optimization technique to solve the problem, which achieves the SOTA result on the iSarcasm dataset.Paper Code bibtex
Chang Liu, Han Yu, Boyang Li, Zhiqi Shen, Zhanning Gao, Peiran Ren, Xuansong Xie, Lizhen Cui, and Chunyan Miao. Noise-resistant Deep Metric Learning with Ranking-based Instance Selection. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021.
TL;DR: We introduce a simple, efficient, and (we believe) the first technique for deep metric learning under noisy training data; the method outperforms 12 baseline methods under both synthetic and natural noise.Paper Supplemental Video 视频 Code bibtex
Yuanyuan Chen, Boyang Li, Han Yu, Pengcheng Wu, and Chunyan Miao. HyDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks. The AAAI Conference on Artificial Intelligence (AAAI). 2021.
TL;DR: We provide an approximate hypergradient method for estimating how training data contribute to individual network predictions and a theoretical bound on the approximation error.Paper Supplemental Code bibtex
Jianan Wang, Boyang Li, Xiangyu Fan, Jing Lin, and Yanwei Fu. Data-efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions. The IEEE Winter Conference on Applications of Computer Vision (WACV). 2021.
TL;DR: We present several tricks that improve data efficiency of the NeuMATCH network, which aligns video and textual sequences.Paper Supplemental Video Code & Data bibtex
Adam Noack, Isaac Ahern, Dejing Dou, and Boyang Li. An Empirical Study on the Relation between Network Interpretability and Adversarial Robustness Springer Nature Computer Science. 2020.
TL;DR: Does the interpretability of neural networks imply robustness against adversarial attack? We provide some positive empirical evidence.Paper Code bibtex
Hannah Kim, Denys Katerenchuk, Daniel Billet, Jun Huan, Haesun Park, and Boyang Li. Understanding Actors and Evaluating Personae with Gaussian Embeddings. The AAAI Conference on Artificial Intelligence (AAAI). 2019.
TL;DR: We computationally model movie casting decisions and actors' versatility.Paper Code & Data bibtex
Pelin Dogan, Boyang Li, Leonid Sigal, Markus Gross. A Neural Multi-sequence Alignment TeCHnique (NeuMATCH). The Conference on Computer Vision and Pattern Recognition (CVPR). 2018.
TL;DR: We propose the first end-to-end optimizable network for aligning video and text sequences.Paper Data bibtex
Ng Annalyn, Maarten Bos, Leonid Sigal, Boyang Li. Predicting Personality from Book Preferences with User-Generated Content Labels. IEEE Transaction on Affective Computing. 2018.
TL;DR: We can infer your personality from the books you read.Paper bibtex
I have multiple open positions for Ph.D. students, postdocs, and research engineers. Please send me your CV.
- July-Sep 2022: Serving as Area Chair for AAAI 2022.
- May 2022: At ACL 2022.
- May 2022: Gave a talk about recent work on machine learning at Microsoft Research Cambridge.
- Mar 2022: Multiple paper acceptance. One to CVPR 2021, one to the ACM Transactions on Intelligent Systems and Technology, and one to the 4th workshop on NLP for ConvAI.
- Sep 2021: Presented recent work to world-renowned scientists at the WLF Young Scientist Forum. [Slides]
- Sep 2021: Reviewing papers for WACV 2022 and AAAI 2022.
- Jun-Oct 2021: Serving as an area chair for Narrative Systems at ICIDS 2021, a leading conference for AI and narratives.
- Jul 2021: One paper accepted at ICCV 2021 (acceptance rate = 25.9%).
- Jun 2021: Reviewing papers for ICCV 2021.
- May 2021: One paper accepted to KDD 2021 (acceptance rate = 15.4%).
- Mar 2021: One long paper accepted to NAACL 2021.
- Mar 2021: Received the NRF Fellowship award with funding of 3M SGD.
- Feb 2021: One paper accepted to CVPR 2021. (acceptance rate = 23.7%)