About me
I am a PhD candidate at UC San Diego, advised by Prof. Nuno Vasconcelos. Prior to joining UCSD, I received the BEng in Electronic Engineering at the Chinese University of Hong Kong in 2017. I have interned at MIT-IBM Watson AI Lab and Intel AI Lab.
My research centers around building reliable machine learning & vision systems under various forms of dataset and model bias. Specifically, I work on developing bias mitigation techniques for data and models, applying them to challenging vision problems such as temporal video understanding and multimodal learning from visual, text and audio modalities.
I am graduating in 2024 and seeking full-time research & postdoctoral positions. Please contact me for relevant opportunities.
News
<06/2023> Attended CVPR 2023 Doctoral Consortium, mentored by Prof. Kate Saenko
<05/2023> Named as CVPR 2023 Outstanding Reviewer
<03/2023> Paper on sparse video transformers (SViTT) accepted to CVPR 2023
Selected Research
Visit my Google Scholar for full publications.
SViTT: Temporal Learning of Sparse Video-Text Transformers
Yi Li, Kyle Min, Subarna Tripathi, Nuno Vasconcelos ⋅ CVPR 2023
VALHALLA: Visual Hallucination for Machine Translation
Yi Li, Rameswar Panda, Yoon Kim, Chun-Fu Chen, Rogerio Feris, David Cox, Nuno Vasconcelos ⋅ CVPR 2022
Improving Video Model Transfer with Dynamic Representation Learning
Yi Li, Nuno Vasconcelos ⋅ CVPR 2022
Learning Representations from Audio-Visual Spatial Alignment
Pedro Morgado*, Yi Li*, Nuno Vasconcelos ⋅ NeurIPS 2020