Linjun Shou

Microsoft (United States) — United States

Computer Science · Physical Sciences

22h-index4.8kcitations103works0.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(89), Natural Language Processing Techniques(75), Multimodal Machine Learning Applications(43), Domain Adaptation and Few-Shot Learning(10), Advanced Graph Neural Networks(9)

Publications103 total

Mixture of Rationale: Multi-modal Reasoning Mixture for Visual Question Answering
Communications in computer and information science·2025
Hypertext Entity Extraction in Webpage
SSRN Electronic Journal·2025· 1 citedOpen Access
Mixture of Rationale: Multi-Modal Reasoning Mixture for Visual Question Answering
arXiv (Cornell University)·2024Open Access
Hypertext Entity Extraction in Webpage
arXiv (Cornell University)·2024Open Access
ControlMath: Controllable Data Generation Promotes Math Generalist Models
2024· 2 citedOpen Access
Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers
arXiv (Cornell University)·2023· 1 citedOpen Access
Typos-aware Bottlenecked Pre-Training for Robust Dense Retrieval
2023· 2 cited
TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs
Intelligent Computing·2023· 84 citedOpen Access
Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency
arXiv (Cornell University)·2023Open Access
Instructed Language Models with Retrievers Are Powerful Entity Linkers
arXiv (Cornell University)·2023Open Access
Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations
arXiv (Cornell University)·2023Open Access
RUEL: Retrieval-Augmented User Representation with Edge Browser Logs for Sequential Recommendation
2023Open Access
Augmenting Passage Representations with Query Generation for Enhanced Cross-Lingual Dense Retrieval
2023· 6 citedOpen Access
A Graph Fusion Approach for Cross-Lingual Machine Reading Comprehension
Proceedings of the AAAI Conference on Artificial Intelligence·2023· 2 citedOpen Access
WIERT: Web Information Extraction via Render Tree
Proceedings of the AAAI Conference on Artificial Intelligence·2023· 6 citedOpen Access
Alleviating Over-smoothing for Unsupervised Sentence Representation
arXiv (Cornell University)·2023Open Access
Typos-aware Bottlenecked Pre-Training for Robust Dense Retrieval
arXiv (Cornell University)·2023Open Access
TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs
arXiv (Cornell University)·2023· 9 citedOpen Access
Large Language Models are Diverse Role-Players for Summarization Evaluation
arXiv (Cornell University)·2023· 2 citedOpen Access
Lexicon-Enhanced Self-Supervised Training for Multilingual Dense Retrieval
arXiv (Cornell University)·2023Open Access
page 1 of 6Next →

Frequent Co-authors

Ming Gong(40), Daxin Jiang(40), Nan Duan(21), Ming Zhou(12), Jian Pei(12), Duyu Tang(10), Yaobo Liang(8), Daya Guo(7), Ming Gong(7), Guihong Cao(5), Shining Liang(5), Michael Zeng(5), Yeyun Gong(4), Weizhen Qi(4), Ruofei Zhang(4), Winnie Wu(4), Wutao Lin(4), Ze Yang(4), Junwei Liao(4), Yu Shi(4)