🧑‍🔬 Si-Qing Chen

🏛️ Affiliations

🏢MicrosoftRedmond · United States2023–2026 · 13 paperscurrent🎓The University of MelbourneMelbourne · Australia2008–2026 · 8 papersEmployment since 2008 · Senior Lecturer, Architecture, Building and Planningcurrent🤝Chinese Academy of Fishery SciencesBeijing · China2007–2024 · 25 papers🔬Yellow Sea Fisheries Research InstituteShandong · China2007–2024 · 25 papers🎓Harbin Engineering UniversityHarbin · China2019–2023 · 11 papers🔬Qingdao National Laboratory for Marine Science and TechnologyQingdao · China2018–2022 · 9 papers🏛️Chinese Academy of SciencesBeijing · China2003–2004 · 7 papers🔬Institute of Geographic Sciences and Natural Resources ResearchBeijing · China2004 · 6 papers🎓Nanjing University of Chinese MedicineNanjing · China2023–2025 · 5 papers🎓Taiyuan University of TechnologyTaiyuan · China2023–2024 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 21 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation (2023 · 103 citations)
   Autoregressive (AR) decoding produces one token per step. This leaves GPUs underused and makes Transformer inference slow and costly. The authors revisit the draft-then-verify paradigm, borrowing the concept of speculative execution from computer architecture. A drafter proposes several future tokens cheaply, and the…
2. LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval (2026)
   The paper tackles agentic document editing: an AI agent applies localized changes to long, structured documents from high-level instructions.

All works

5 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. In-context Autoencoder for Context Compression in a Large Language Model ↗arXiv:2307.06945 · no summary yetTao Ge et al.2023 · 114 citations
2. Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq GenerationFindings of the Association for Computational LinguisticsHeming Xia, Tao Ge, Peiyi Wang, et al.2023 · 103 citations
3. Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models ↗arXiv:2402.13064 · no summary yetHaoran Li et al.2024 · 65 citations
4. LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph RetrievalFindings of the Association for Computational LinguisticsHang Wang, Utkarsh Garg, Reza Davari, et al.2026
5. A User-Centered Evaluation of Spanish Text Simplification ↗arXiv:2308.07556 · no summary yetAdrian de Wynter, Anthony Hevia, Si-Qing Chen2023

🤝 Co-authors here

8 co-authors with a page, the most papers together first.

• Tao Ge ×2
• Baolin Peng
• Furu Wei
• Hang Wang
• Hao Cheng
• Heming Xia
• Peiyi Wang
• Zhifang Sui

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026, Findings of the Association for Computational Linguistics 2023

🔗 Cited by

Papers of our library cite their works 229 times (of the 149,439 papers whose bibliographies we read); 55 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/si-qing-chen/