I'm a Computer Science researcher working on neural retriever and reader in NLP and multimodal (vision and language) domains. I am a Research Fellow at Machine Intelligence in Medical Imaging (MI2) lab, Mayo Clinic, AZ, working with Dr. Imon Banerjee and Dr. Bhavik Patel. I was privileged to earn my doctoral degree in 2023 from Arizona State University, Cognition & Intellifent Lab, supervised by Dr. Chitta Baral. Prior to my Ph.D., I obtained my Bachelor's degree in Computer Science from Beijing Forestry University, located in Beijing, China.
My research focuses on developing intelligent models that can search for and leverage external knowledge to improve their comprehension and reasoning skills, with a particular focus on tasks such as question answering. To achieve this goal, I have invented new models (Poly-DPR, VRR) and training objectives (SCONER) that are specifically designed to enhance the ability of these models to retrieve relevant knowledge from a corpus. I also care about the robustness, generalization and efficiency of the models. My research includes contributions to the biomedical field, including the creation of the first biomedical instruction-learning benchmark (BoX).
A Study on the Efficiency and Generalization of Light Hybrid Retrievers Man Luo, Shashank Jain, Anchit Gupta, Arash Einolghozati, Barlas Oguz Debojeet Chatterjee, Xilun Chen, Chitta Baral, Peyman Heidari ACL 2023 [Paper]
Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness Tejas Gokhale*, Swaroop Mishra*, Man Luo*, Bhavdeep Singh Sachdeva, Chitta Baral ACL 2022 Finding [Paper]
Improving Biomedical Information Retrieval with Neural Retrievers Man Luo, Arindam Mitra, Tejas Gokhale, Chitta Baral AAAI 2022 [Paper]
Strong equivalence for LPMLN programs Joohyung Lee and Man Luo ICLP 2019 [Paper]
Can Transformers Reason About Effects of Actions? Pratyay Banerjee, Chitta Baral, Man Luo, Arindam Mitra, Kuntal Pal, Tran C Son, Neeraj Varshney arXiv preprint [Paper]