Yifei (Alvin) Ming
Contact: alvinming [at] cs [dot] wisc [dot] edu
I am a 5th-year Ph.D. student in the Computer Sciences Department at the University of Wisconsin-Madison advised by Prof. Sharon Li. I am broadly interested in reliable machine learning that aligns with human values, especially in the era of multi-modal foundation models. A central theme that continually resonates with me is: How can we foster innovative algorithms and deeper understanding to ensure that our machine learning systems perform reliably in the real world?
News
01/2024 | Our paper Provable Out-of-Distribution Generalization in Hypersphere is accepted by ICLR 2024. |
---|---|
06/2023 | Research intern at Microsoft Research working on spatial and mathematical reasoning for vision-language models. |
01/2023 | Our paper How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection is accepted by ICLR 2023. |
10/2022 | Our paper Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment is accepted by EMNLP Findings 2022. |
09/2022 | Two of our papers Delving into OOD Detection with Vision-Language Representations and SIREN: Shaping Representations for Detecting Out-of-distribution Objects are accepted by NeurIPS 2022. |
Publications
-
ICLRProvable Out-of-Distribution Generalization in HypersphereIn International Conference on Learning Representations (ICLR) 2024
-
CPAL
Oral Domain Generalization via Nuclear Norm RegularizationIn Conference on Parsimony and Learning (CPAL) 2023 -
EMNLPA Critical Analysis of Document Out-of-Distribution DetectionIn Empirical Methods in Natural Language Processing (EMNLP Findings) 2023
-
IJCVHow Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?In International Journal of Computer Vision (IJCV) 2023
-
NeurIPSDomain Generalization with Nuclear Norm RegularizationIn Neural Information Processing Systems (NeurIPS’W) DistShift Workshop 2022
-
ICMLAre Vision Transformers Robust to Spurious Correlations?In International Conference on Machine Learning (ICML’W), SCIS Workshop 2022