Scholar
Yu Zhang
Google Scholar ID: y3JK-1oAAAAJ
Soochow University
Citations & Impact
Citations
670
H-index
11
i10-index
11
Publications
13
Co-authors
1
list available
Contact
Resume
Academic Achievements
- Publications:
- - Kimi Linear: An Expressive, Efficient Attention Architecture (Preprint)
- - Gated Slot Attention for Efficient Linear-Time Sequence Modeling (NeurIPS 2024)
- - Parallelizing Linear Transformers with the Delta Rule over Sequence Length (NeurIPS 2024)
- - Scalable MatMul-free Language Modeling (Preprint)
- - Non-autoregressive Text Editing with Copy-aware Latent Alignments (EMNLP 2023)
- - Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments (COLING 2022)
- - Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing (COLING 2022, Best Paper Award)
- - Fast and Accurate Neural CRF Constituency Parsing (IJCAI 2020)
- - Efficient Second-Order TreeCRF for Neural Dependency Parsing (ACL 2020)
- - Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing? (NLPCC 2020, Best Paper Award)
- - HLT@SUDA at SemEval-2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing (SemEval 2019)
Research Experience
- 2020-2021: Research Intern at Alibaba DAMO Academy, mentored by Yong Jiang
- 2023-2024: Research Intern at Tencent AI Lab, mentored by Wei Bi
Education
- 2018-2021: M. Eng. from Soochow University
- 2021-Present: Ph.D. student at Soochow University, advised by Prof. Guohong Fu
Background
- Currently a third-year PhD student at Soochow University, focusing on developing efficient text generation models and hardware-efficient linear-time sequence modeling methods. Early research focused on structured prediction tasks, specifically dependency parsing and constituency parsing.
Miscellany
- Projects:
- - FLA: A Triton-Based Library for Hardware-Efficient Implementations of Linear Attention Mechanism
- - SuPar: State-of-the-art syntactic/semantic parsers
