Juncheng Wan

I am a Machine Learning System Engineerer at Bytedance Seed. In the past, I received my M.Eng. and B.S. (with honors) from School of Computer Science and Engineering at Shanghai Jiao Tong University, advised by Prof. Weinan Zhang and Prof. Yong Yu in APEX Lab. I am also a member of Zhiyuan's Honors Program of Engineering.

Email: jorgenwan [at] gmail.com

Google Scholar  /   Github  /   CV   

Nested Named Entity Recognition with Span-level Graphs
Juncheng Wan,  Dongyu Ru,  Weinan Zhang,  Yong Yu 
Association for Computational Linguistics (ACL), 2022.
Nested NER; span-based method; graph neural networks.

Phrase-level Adversarial Example Generation for Neural Machine Translation
Juncheng Wan*,  Jian Yang*,  Shuming Ma,  Dongdong Zhang,  Weinan Zhang,  Yong Yu,  Zhoujun Li 
International Conference on Computational Linguistics (COLING), 2022. Oral Presentation.
Neural machine translation; adversarial example generation; phrase-level model.

Learning to Select Relevant Knowledge for Neural Machine Translation
Jian Yang*,  Juncheng Wan*,  Shuming Ma,  Haoyang Huang,  Dongdong Zhang,  Yong Yu,  Zhoujun Li,  Furu Wei 
International Conference on Natural Language Processing and Chinese Computing (NLPCC), 2022. 
Neural machine translation; selective translation memory.

Forgetting Fast in Recommender Systems
Wenyan Liu*,  Juncheng Wan*,  Xiaoling Wang,  Weinan Zhang,  Dell Zhang,  Hang Li, 
ArXiv, 2022. 
Machine unlearning; recommender system.

Triple-to-Text: Converting RDF Triples into High-Quality Natural Languages via Optimizing an Inverse KL Divergence
Yaoming Zhu,  Juncheng Wan,  Zhiming Zhou,  Liheng Chen,  Lin Qiu,  Weinan Zhang,  Xin Jiang,  Yong Yu 
Special Interest Group in Information Retrieval (SIGIR), 2019. 
Natural language generation; sequence-to-sequence generation; knowledge bases.

Smart-Start Decoding for Neural Machine Translation
Jian Yang,  Shuming Ma,  Dongdong Zhang,  Juncheng Wan,  Zhoujun Li,  Ming Zhou 
North American Chapter of the Association for Computational Linguistics (NAACL), 2021. 
Neural machine translation; non-monotonic decoding.

Employment 

• Machine Learning System, ByteDance Seed, 2025 - Now.  
• Recommendation System, ByteDance TikTok, 2023 - 2025.  

Internships 

• Recommendation System, Alibaba Taobao, Hangzhou, 2022.  
• Machine Unlearning, ByteDance AI-Lab, Shanghai, 2021 - 2022.  
• Machine Translation, Microsoft Research Asia, Beijing, 2019 - 2020.  

Researches 

• Text Generation, School of Computer Science and Engineering, APEX Lab, SJTU, 2019 - 2023.  
• Graph Theory, School of Mathematical Sciences, SJTU, 2018 - 2020.  

Writings 

• A Survey of Applications of Algebraic Geometry.
• A Survey of Lie Groups in Machine Learning.
• A Survey on Graphs Decomposable into Induced Matchings.
• Representation Theory of Lie Algebra.
• Representation Theory of Symmetric Groups.
• A Note of Differential Geometry Learning.
• Cop Robber Game.
• Erdős-Gallai Conjecture.
• Gale's Lemma.

Workout 

• PL.